Skip to main content

2024 | Book

Proceedings of the 6th International Conference on Electrical Engineering and Information Technologies for Rail Transportation (EITRT) 2023

Advanced Information Enabling Technology for Rail Transportation

Editors: Ming Gong, Limin Jia, Yong Qin, Jianwei Yang, Zhigang Liu, Min An

Publisher: Springer Nature Singapore

Book Series : Lecture Notes in Electrical Engineering


About this book

This book reflects the latest research trends, methods, and experimental results in the field of electrical and information technologies for rail transportation, which covers abundant state-of-the-art research theories and ideas. As a vital field of research that is highly relevant to current developments in a number of technological domains, the subjects it covered include intelligent computing, information processing, communication technology, automatic control, etc. The objective of the proceedings is to provide a major interdisciplinary forum for researchers, engineers, academicians, and industrial professionals to present the most innovative research and development in the field of rail transportation electrical and information technologies. Engineers and researchers in academia, industry, and government will also explore an insightful view of the solutions that combine ideas from multiple disciplines in this field. The volumes serve as an excellent reference work for researchers and graduate students working on rail transportation and electrical and information technologies.

Table of Contents

Dynamic Interaction Study on Double-Pantograph and Rigid-Catenary for AC Traction Power Supply System

With the development of urban rail transit and the installation of rigid catenary in low clearance tunnels during electrification renovations, the dynamic coupling of pantograph catenary in AC rigid contact network system has become a new hot topic. This article studies the coupling characteristics of the pantograph catenary under the operating conditions of dual pantographs. Equivalent AC rigid contact network to Euler Bernoulli beam based on beam theory, the pantograph model is established using three mass blocks, and the dual pantograph catenary model is established using penalty functions. The results show that under the operating condition of the AC rigid catenary, the train speed is inversely proportional to the span of the AC rigid catenary; Among the commonly used spans, a span of 8 or 10 m is suitable for train speeds below 80 km/h, while a span of 6 or 8 m is suitable for train speeds of 80–140 km/h.

Qiang Huang, Ying Wang, Xiaoqiang Chen, Yuting Wang, Jianlong Guo
Real-Time Low-Light Image Enhancement Method for Train Driving Scene Based on Improved Zero-DCE

Low-light train driving scenes often suffer from issues such as poor visibility, low contrast, and image noise, which seriously affects the accuracy and safety of train detection. In this paper, we propose a real-time low-light image enhancement method based on an improved Zero-DCE algorithm. We first establish a mathematical model of the light curve based on a high-order polynomial function. Then we use the encoder-decoder architecture to build the parameter estimation network for the illumination curve. To ensure real-time performance, the lightweight MobileNet v3 is utilized as the encoder, and the LR-ASPP module is employed for feature fusion and decoding to guarantee real-time performance. Finally, we design a set of self-supervised losses for model training without reference labels. Our experiments on a self-built train driving dataset show that the proposed method outperforms the original images in terms of image details, color vividness, overall evaluation score, and inference time of only 2.84 ms. Our method has important practical and theoretical significance and is of great value for application in railway transportation.

Zhichao Chen, Jie Yang, Fan Li, Zhicheng Feng
Mathematical Model of Adaptive Optimal Allocation for the Whole Process of Driving Through No. 18 Non-crossing Crossover Considering Special Sections

With the large-scale construction and the requirement of speed increase of high-speed railway in China, non-crossing crossover has been widely used in high-speed railway catenary. In order to satisfy the requirements of smooth operation of the line, a model of No. 18 non-crossing crossover based on the whole running process is proposed. Based on the whole process of driving through No. 18 non-crossing crossover, the operating principle of No. 18 non-crossing crossover is introduced, the whole model of No. 18 non-crossing crossover composed of line center and contact line model is established, the process of driving through two special sections of No. 18 non-crossing crossover initial contact area and contour area is studied, the influence of special section on the model of no-crossing crossover is considered, and the special section model of No. 18 non-crossing crossover is established. Based on the laboratory platform, the software of No. 18 non-crossing crossover is developed, and the model is validated by using the measured data of high-speed field of Ningdong Station from Yinchuan to Zhongwei of Yinlan Passenger Dedicated. The calcu-lation results show that the proposed model has the characteristics of validity, accuracy and real-time, and is suitable to the calculation of No. 18 non-crossing crossover in various situations.

Ganghui Zhao, Ying Wang, Xiaoqiang Chen, Yixuan Wang
Research on Enhancing Speed Measurement Accuracy in Rail Transit Systems Using Curve Fitting Techniques

Urban rail systems depend on speed sensors for velocity measurements, which often face challenges such as noise interference and sampling delay errors, particularly at low speeds. This study delves into the hardware structure, measurement principles, speed calculation methods, and the root causes and impacts of sampling errors on train control. A novel approach employing least squares curve fitting is proposed to tackle these issues. Our research endeavors to augment the efficacy and safety of urban rail systems by augmenting low-speed speed detection's precision and dependability. To authenticate the efficacy of the suggested technique, we conducted rigorous simulation tests. The study's results unveil auspicious strides in fortifying the security and steadfastness of rail operations, thereby accentuating the latent potential harbored within the proposed method to optimize urban rail systems.

Yimin Li
A Fine-Grained Method for Detecting Defects of Track Fasteners Using RGB-D Image

To ensure the safety of railway transportation, it is necessary to promote the defect detection of track fasteners. However, most current inspections focus on coarse-grained detection of defects, while neglecting the potential fine-grained defects, such as looseness and subtle deformation. To solve this problem, this paper proposes a method for fine-grained defect detection of track fasteners using RGB-D images. The proposed method is divided into two stages: coarse-grained detection, which detects defects such as missing or loose elastic strips, and fine-grained detection, which detects potential defects such as loose fasteners. By combining coarse-grained detection and fine-grained detection, more excellent defect detection of track fasteners has been achieved The proposed method achieves 99.6% accuracy of coarse-grained detection and 90.6% accuracy of fine-grained detection at 23.3 FPS.

Xuanyu Ge, Yong Qin, Zhiwei Cao, Yang Gao, Lirong Lian, Jie Bai, Hang Yu
Research on Key Parameter Optimization Method of High-Speed Railway Vehicle-Bridge System Based on Proxy Model

This paper proposes a key parameter optimization method for a high-speed railway vehicle-bridge system using numerical calculations, proxy models, and optimization design. A three-dimensional vehicle-bridge coupled dynamic model is constructed to calculate the vertical acceleration of the vehicle body under different sampling combinations. Based on this, a Kriging proxy model of vehicle body vertical acceleration is constructed to accurately describe the relationship between vehicle axle weight, bridge creep deflection, and vehicle body vertical acceleration. A matching optimization model for vehicle axle weight and bridge creep deflection is proposed, with the objective of minimizing vehicle body vertical acceleration. The cuckoo search algorithm is utilized to obtain the optimal design parameters. The results show that the sensitivity of vehicle body vertical acceleration to creep deflection is much higher than that to vehicle axle weight. The optimal vehicle axle weight for a high-speed railway is 15 t, and the creep deflection limit for the bridge is 3 mm, resulting in a minimum vehicle body vertical acceleration of 0.4909 m/s2. This method provides an important basis for controlling bridge creep deflection and vehicle design from a system-level perspective.

Kexin Zhang, Mingming Wang, Ze Xie, Ning Xu
Reliability Analysis of Metro Vehicles Bogie System Based on Fuzzy Bayesian Network

Metro vehicles bogie system is one of the important components of urban rail train. The performance largely determines the vehicle running stability and safety. Accurately analyzing the reliability of the bogie system in metro vehicles is of great significance for ensuring the stability and security of urban rail trains during operation. In this paper, a Bayesian network model for the metro vehicles bogie system is established. The GeNIE software was used to calculate the posterior probability, probability importance and critical importance of the root nodes for reliability analysis. The results indicate that wheel diameter deviation is too large, excessive wheel diameter deviation, brake shoe wear, height valve leakage blocking and different pressure valve leakage blocking have a significant impact on the performance of the bogie system. These findings are consistent with previous research and actual operational data.

Rui Liu, Ying Zhou, Limin Jia, Yong Qin, Zhipeng Wang
A Lightweight Pedestrian Intrusion Detection Algorithm Based on On-Board Video

In order to enhance the real-time perception of the environment of the train and ensure safety, it is necessary to detect intrusion. Most of the intrusion detection algorithms have large parameters and slow speed, so they cannot be well applied in high-speed trains. Therefore, this paper proposes a lightweight pedestrian intrusion detection algorithm with on-board video. First, the lightweight object detection algorithm is used to realize pedestrian detection in the whole scene. Second, the railway track area is extracted by a lightweight semantic segmentation algorithm. Finally, by judging the coordinate position, the pedestrian intrusion detection in the railway track area is realized. In experiments, the positive detection rate is 94.84%, and the missing detection rate is 0.97%, and the false detection rate is 0.81%, which can effectively detect the pedestrian intrusion in the railway track and further improve the intelligent perception system of railway operation environment, which has practical significance and application value for railway safety.

Yang Gao, Yong Qin, Zhiwei Cao, Lirong Lian, Jie Bai, Xuanyu Ge, Hang Yu
A Railway Similarity Multiple Object Tracking Framework Based on Vehicle Front Video

Real-time awareness of the service status of facilities and equipment in metro tunnels is essential for the safe movement of trains. For low illumination underground tunnel environments where objects have high similarity characteristics and are difficult to distinguish, this paper proposes a framework for tracking high similarity objects along the rail line based on on-board visual perception devices. The framework mainly consists of two stages: object detection and object association. In the first stage, an object detection algorithm is used to detect potentially faulty objects in the video, and this paper takes the continuous occurrence of insulated steel supports on the line as the high similarity research object. In the second stage a matching strategy is used to associate the same object in the video sequence and assign the same ID (identity document). Finally, the proposed framework was tested on metro tunnel video and achieved an accuracy of 95.64 and a detection performance of 25 FPS (frames per second), 82.17 MOTA (multiple object tracking accuracy) and 88.46 MOTP (multiple object tracking precision) tracking performance.

Lirong Lian, Yong Qin, Zhiwei Cao, Yang Gao, Jie Bai, Xuanyu Ge, Hang Yu
A Lightweight Sementic Segmentation Model for Metro Tunnel Scene Based on Vehicle Front Camera

Metro intrusion seriously affects the safety of metro operation. Semantic segmentation is the main content of the research on metro intrusion. Tunnels account for a large proportion of metro lines, by processing the images captured by the vehicle front camera, the state of the elements in the tunnel can be obtained, among which the perception and understanding of the whole scene is an important part of the image processing. For on-board cameras, we propose a lightweight semantic segmentation algorithm for metro to satisfy the real-time requirements. Finally, for a 2048 × 1024 input, the algorithm achieves 75.21% MIoU on the metro tunnel data set with speed of 54FPS (Frames Per Second) on NVIDIA 3090 Ti card.

Jie Bai, Yong Qin, Zhiwei Cao, Lirong Lian, Yang Gao, Xuanyu Ge, Hang Yu
Dynamic Fault Detection Method of Traction Systems in High-Speed Trains Based on Joint Observer

This paper proposes a joint state observer based on deep learning for traction systems in high-speed trains. For actual systems, the signal collected by multiple sensors contains different variables, and each variable will reflect the state of the systems. However, most researchers construct the state estimation strategy without consideration of relations between variables, reducing the accuracy of fault detection. Therefore, how to analyze the correlation of different variables and design the data-driven observer becomes the difficult problem. This paper designs a data-driven joint output observer for traction system of high-speed trains. The joint distribution function is constructed by the marginal distribution of different variables and the resultant weight of the joint model is calculated by Kendall rank correlation coefficient. In the end, the proposed method is verified on a pilot-scale experimental platform and traction systems in high-speed trains.

Chao Cheng, Weijun Wang, Yang Song, Hongtian Chen
Electromagnetic Wind Energy Harvester for Condition Monitoring System of High-Speed Train Bogies

The abundant wind energy around high-speed trains can be used as an energy source for self-powered systems when they are in operation. However, wind energy harvesters installed on trains have been less studied in the past. In this paper, a rotating-mode electromagnetic wind energy harvester is proposed for a wireless condition monitoring in high-speed train bogie. The harvester uses an S-rotor, which is driven by the high-speed wind, and the rotor drives the relative motion between the magnet and the winding coil, and then converting wind energy into electrical energy. Theoretical analysis and experiments were conducted on the harvester. The experimental results show that the electromagnetic wind energy harvester achieves an output power of 39.01 mW at a wind speed of 20 m/s and a load of 400 Ω. It proves that the electromagnetic wind energy harvester has the potential to be an energy supply device for self-powered technology based on the wind energy harvesting mechanism.

Xinyu Mao, Yuan Zhang, Lei Zhu, Xuejun Zhao, Dilong Tu, Ben Yang, Yanping Du
An Exploration of Voltage-Type Rotor Magnetic Field Indirect Vector Control

This study primarily delves into the control system of electric braking in urban rail trains, with a particular focus on the asynchronous motor and its associated mathematical model. The investigation embarks upon an exhaustive exploration of two discerning control methodologies: constant voltage-to-frequency ratio control and the rotor magnetic field-oriented vector control method with voltage feedforward decoupling. The culmination of this analysis, coupled with a profound comprehension of the fundamental principles of coordinate transformation, illuminates the intrinsically nonlinear, multivariable essence, and robust coupling characteristics inherent in the asynchronous motor. Through a comparative examination of the two control methods, the constraints of constant voltage-to-frequency ratio control come to the fore, instigating the proposition of a rotor field-oriented vector control strategy. The study reaches its apex with the development of a simulation model, facilitating a comprehensive juxtaposition of the aforementioned control methods. The simulation substantiates the superiority of the vector control method in the context of electric braking control.

Yimin Li
Method to Detect Arc Across Pantograph-Catenary Structure Atop Train Based on Frequency Features of Entry Current

During a train running at speed, the pantograph-catenary structure atop the train would be influenced by many factors, resulting in disconnections. A timely detection on arcs across this structure helps to guide works on real-time operating and later maintenance, to eliminate latent factors of disconnection. A theory on the generation of arcs is researched, simulated, and verified with practical data. Two features of entry current, in frequency bands at kHz degree and at harmonic-Hz degree, are picked for the detection. Based on the discrepancy on these bands while arcing and normally running, a model of support vector machine (SVM) is constructed. Existing signals on train are processed and rearranged to be datasets for training SVM. After applying it to a practical railway, the results illustrate: the accuracy on arc detections is up to 99.96%. With guidance from results, an on-site investigation was launched, and mark of flaming was found at corresponding location of catenary, which verified the correctness.

Yufei Du, Yang Jiao, Yongzheng Zhu, Jun Chen, Hongbin Li, Qing Chen
A Foreign Object Detection Method for Railway Overhead Lines Based on Few-Shot Learning

It often occurs that foreign objects hang on railway overhead lines especially in windy days, which may lead to the delay of train, and even cause loss of life and property. With the gradual maturity of computer vision, railway foreign object detection has made great progress. This paper focuses on foreign object in railway overhead lines, and proposes a foreign object detection method based on few-shot learning. The proposed method consists of two stages: general training and fine-tuning training. In the first stage, the data-abundant common classes dataset is used to train the entire detector to obtain the underlying model parameters. In the fine-tuning stage, we make a balanced dataset consisting of common classes and enhanced railway classes, and fine-tune the last layer of the detector to accomplish few-shot foreign object detection. Finally, this proposed method is tested on images of overhead lines intrusions taken in actual railway scenario, and achieves 79% mAP in railway classes.

Hang Yu, Yong Qin, Zhiwei Cao, Lirong Lian, Yang Gao, Jie Bai, Xuanyu Ge
Transformer-Aware Graph Convolution Networks for Relation Extraction of Railway Safety Risk

The relation extraction of railway safety risk is important in constructing railway knowledge graph, which drives the development of intelligent transportation system through knowledge. However, existing models always concentrate on extracting relation from the universal text, fail to mine the railway text, especially the Chinese railway text. In this paper, we propose a novel relation extraction model named Transformer-aware Graph Convolution Networks (TGCN), which aims to comprehensively perceive railway semantics and improves the final results. Specifically, we construct a graph structure by the dependency tree to capture syntax features of input sentence, which can deep exploit the features contained in the sentence without introducing extra knowledge. In addition, we integrate these syntax features with contextual feature captured by the transformer mechanism. To better aggregate the railway semantic features, we use GCN to further encode the features confused by syntax and contextual features. Finally, a softmax classifier is used to identify the relation types. Extensive experiments on two real-world datasets show that, the proposed TGCN model achieves the state-of-the-art results. The TGCN provides a novel view to operate the railway safety risk management.

Youwei Wang, Xiwang Li, Yuying Wu, Wei She, Yangdong Ye
A Comprehensive Study on Train Operation Dynamics and Passenger Comfort Optimization

As global economic expansion fuels urban population growth and an increase in motor vehicles, the significance of urban rail trains is rising. These systems offer substantial benefits, including high capacity and speed. With the elevation in living standards, the focus has transitioned from mere transport capacity to the safety and comfort of train travel. This research utilizes a dynamic model of train operation to analyze the forces involved in the process, deriving an equation of motion on the motor side. It proposes a method for controlling the deceleration impulse rate to enhance passenger comfort. On this foundation, a load model for the train is designed and simulated. This study contributes to the field of train operation, introducing methods and models that can improve train travel, ultimately aiding in the establishment of a more sustainable, efficient, and comfortable urban transportation system.

Yimin Li, Ruini Zhu
Model-Driven Study of Intelligent Passenger Information System for Urban Rail Transit

The passenger information system (PIS) of urban rail transit consists of three major functions: Public Address (PA), Closed Circuit Television (CCTV) and Passenger Information Display (PID). Their functions are independent of each other, with low integration and development efficiency. To solve these problems, the three functional modules of PIS were modularized, and the Model-based Systems Engineering (MBSE) concept was adopted to model the PIS, proposing the Intelligent Passenger Information System (IPIS). Based on the characteristics of classic MBSE and IPIS, a new modeling IPIS method is proposed in this paper, which will complete the design of complex systems after considering stakeholders, relevant requirements, and use case scenarios. A performance metamodel, functional metamodel, and system requirement metamodel of the IPIS system have been established to meet the modeling process of IPIS, which will improve the reuse rate of the model and shorten the design cycle. The performance metamodel, functional metamodel, and system requirements metamodel of the IPIS system have been established to meet the modeling process of IPIS, which will improve the reuse rate of the model and shorten the design cycle.

Tingli Huang, Baomin Wang, Ningguo Qiao, Haifang Wang, Jiahao Zhao, Qingyong Wang
Research on Positioning of Permanent Magnet Maglev Trains Based on Weighted Adaptive Kalman Information Fusion

In this paper, an improved adaptive Kalman fusion method is proposed to solve the problems of low accuracy, poor interference immunity and stability when using a single sensor to localize a suspended permanent magnetic levitation train in a practical situation. The measurement data from three sensors are fused in the first layer by weighted adaptive Kalman filtering (WKF). Then, the measurements and the positioning data from the Global Navigation Satellite System (GNSS) are fused in the second layer using recursive weighted least squares (RW) to achieve highly accurate positioning of the levitated permanent magnet maglev train. The experimental results of WKF-RW algorithm improve the positioning accuracy by 51.79% and 32.5% compared with the conventional Kalman (KF) and WKF, respectively, which effectively improves the positioning accuracy and robustness of the permanent magnetically levitated trains and can be better applied to the real environment.

Yiwei Xu, Kuangang Fan, Qian Hu
Analysis of Dynamic Characteristics of Dropper in Catenary System

A finite element method is used to simulate the catenary, in which rod elements were used to simulate the dropper. The vibration amplitude and dropper-force when the pantograph passes at a constant speed are calculated. The results indicate that the coupling effect between the pantograph and the contact wire causes the amplitude of the dropper to exceed 5 mm at least 8 times. The first and sixth dropper s have the highest vibration amplitude, but their compression and dropper-force are the smallest. The fifth dropper has the highest dropper-force and compression, indicating that this dropper is the most susceptible to damage.

Yongming Yao, Jing Wang, Bin Wang, Meijun Mu, Yan Xu
A Power Flow Optimization Method for Urban Rail Flexible Traction Power Supply System Considering Train Dwell Time

The introduction of flexible traction power supply system can promote the mass utilization ratio of train regenerative braking energy, but the utilization is still insufficient. The unused part will be sent back to the urban distribution network through the converter in main substation, thus affecting its power supply quality. To solve them, this paper propones a power flow optimization tactic for urban rail transit flexible traction power supply system considering train dwell time. Firstly, the principle and law of regenerative braking energy utilization in flexible system are introduced, and the feasibility and necessity of further using this part of energy are analyzed. Secondly, the energy-economizing optimal model of urban rail multiple trains is established, and the system power flow optimization scheme considering train dwell time is designed based on PSO algorithm. Finally, based on real data of a domestic subway line, the validness of the scheme is supported by simulation. The simulation results indicate that the total energy expenditure of the optimized power supply system is reduced by 1.91%, and the energy saving efficiency is high, which has great practical value.

Zishi Ni, Gang Zhang, Hong Yu, Renyu Wang, Zhaofeng Gong
A Mechanism and Data-Driven Hybrid Mechanical Model of Rotary Arm Positioning Rubber Joint

Rotary arm positioning rubber joint (hereinafter referred to as rubber joint) is an important component of railway vehicle which affects the stability and safety of the vehicle. So it’s of great significance to construct a high-precision mechanical model for rubber joint. This paper proposes a mechanism and data-driven hybrid mechanical model for rubber joint, mechanism part which is based on a superposition of elastic, friction and viscous forces calculates the trend of damping force. Then, data-driven part which is based on BP neural network optimizes the calculation precision of calculated damping force. Combined with the rail vehicle dynamic model, The simulation results show that the proposed model can characterize the non-linear damping force precisely of rubber joint in larger amplitude and wider frequency domain. Moreover, compared with normal temperature, the dynamic performance of rubber joints in low ambient temperature will worsen the curve passing performance and curve safety of the vehicle, which needs to be paid attention to in vehicle operation.

Pengcheng Zeng, Liangcheng Dai, Maoru Chi, Zhaotuan Guo
High Speed Train Bracket Arm Visualization Experiment System

In recent years, with the rapid development of high-speed train, its bracket arm structure is one of the main load-bearing structures. In this paper, Abaqus software is used to simulate, fiber Bragg grating (FBG) sensor is used to build a test system, static load test is applied, load identification and strain field reconstruction of the structure are carried out based on load-strain linear superposition algorithm, and the error of the results is less than 8%, which verified the effectiveness of the method. At the same time, the three-dimensional visualization software of the bracket arm model is realized to display its load identification results/strain field status and related data curves, which provides a reasonable reference for the regular maintenance of the train and can effectively improve the operation safety of the train.

Shuxian Wang, Yangyang Cheng, Shangen Li, Faye Zhang, Mingshun Jiang, Lei Zhang
Design of Cabinet-Level Refrigeration System in Subway Station Communication Signal Room

The area of the subway communication signal room is limited, equipment layout is dense, heating equipment concentrated in some cabinets, equipment heating is uneven, in order to improve the refrigeration effect, reduce energy loss, save energy, for high heat cabinet This paper proposes the solution of using cabinet-level liquid cooling heat dissipation solution. Introduces the composition of the cabinet liquid cooling system, and introduces the composition of the refrigeration module and each part of the function in detail, At the same time, combining with the Internet of Things communication technology, the refrigeration system is intelligent, a and the data can be queried in real time on the computer and mobile terminal, which greatly improves the reliability and operability of the equipment and reduces the workload of maintenance personnel.

Jianna Li, Yanhua Qiao, Huijuan Ma, Xiangfang Mao
Active Control of Pantograph Sliding Mode Under Fluctuating Wind Excitation

Considering the effects of fluctuating wind excitation on the dynamic performance of the pantograph-catenary coupling system, the ideal contact force between the pantograph and the catenary is taken as the control target, and the control of the pantograph is achieved through an actuator. Firstly, based on the three-mass block pantograph model, a pantograph-catenary coupling model is established for control purposes. Then, the equivalent vibration force on the contact line caused by the fluctuating wind excitation is derived, and the model of the pantograph-catenary system under fluctuating wind excitation is modified. Finally, a sliding-mode control method is adopted to design the pantograph active controller. The results indicate that the designed sliding mode controller is capable of suppressing the vibrations of the pantograph-contact wire system, thereby improving the quality of current collection.

Zedong Ren, Ying Wang, Xiuqing Mu, Xiaoqiang Chen, Zhanning Chang
Time Synchronized Sensor Network with IEEE1588 for Vibration Measurement in Structural Health Monitoring of Railway System

Sensor network has become an important area of research and various new applications for remote sensing are expected to emerge. One of the promising applications is structural health monitoring of building or civil engineering structure and it often requires vibration measurement. For the vibration measurement via network, time synchronization is indispensable. This paper clarifies the importance of time synchronization of sensor network for vibration measurement. And the rationale of IEEE1588 precision time protocol is described. A distributed synchronized measurement system based on the IEEE1588 is presented in this paper and the test result are also introduced.

Guotao Jiang, Yong Liu, Yu lv, Haiyan Wu
Modeling and Implementation of EMU Traction System

With the improvement of the complexity of rail transit products and the development of intelligent level, the design of EMU traction system needs more effective demand analysis methods, more reliable modeling analysis methods, positive traceability design methods and high quality implementation forms. Taking the traction system of EMU as the research object, through the requirements analysis model based on SysML language, combined with the modeling analysis method based on standard RFLP, starting from the design requirements of the traction system, complete use case analysis is carried out, and the functional model of the traction system including the architecture model and the state machine model is created. The interactive information between the traction system, external system and internal subsystems is displayed through block definition diagram and internal block diagram. The operation scenarios of the traction system are realized through UI interface, and the state changes of the tracton system during operation are displayed. Functional logic simulation of the traction system is realized, and a positive traceable design and implementation scheme of the traction system is formed. The design method based on MBSE is applied to the design process of EMU to provide forward design guidance for the design of EMU.

Haifang Wang, Lin Guan, Baomin Wang, Yiming Lu, Kuanxin Li, Minghui Sun, Peng Zhang
Traffic Operation Status Research Based on Multi-source Data Fusion

At present, modern technologies such as big data, cloud computing and vehicle-road collaboration are developing rapidly, and the existing traffic detection data based on a single detector cannot meet the demand for high-precision data in the vehicle-road cloud environment. Facing the massive, heterogeneous and complex traffic data, this paper selects the data collected by LiDAR, HD camera and V2X communication unit as the data sources for this research, establishing the multi-source traffic data fusion model with wavelet neural network and genetic algorithm optimized BP neural network respectively, and builds the traffic status classification model based on fuzzy C-mean clustering algorithm. The fusion model and the traffic status classification model are verified for the single intersection road section in the vehicle-road cloud cooperative environment. The results show that the fusion accuracy of genetic algorithm optimized BP neural network reaches 93% and the status classification model has high feasibility, which can provide data support for intersection signal control and traffic guidance optimization.

Ling Cao, Pangwei Wang, Honghui Dong
Isochronous Deterministic Ethernet System Research

Distributed control systems based on real-time Ethernet have been widely used in rail transit and other industrial fields. Currently, switched Ethernet has switching queuing delay, which limits the application scope of real-time Ethernet. In addressing this issue, this paper proposes an Isochronous Deterministic Ethernet (IDE) technology based on precise clock synchronization and deterministic scheduling. This technology ensures strict determinism in end-to-end communication latency on Ethernet networks. The paper presents the principles of Isochronous Deterministic Ethernet and conducts system simulations. Simulation results indicate that the end-to-end latency jitter for deterministic communication is less than 2 μs. Furthermore, the paper describes the performance metrics of the technology prototype and compares them with the results of current prototype testing.

Jiang Guotao, Wu Haiyan
Data-Driven Fault Text Classification of Urban Rail Transit Vehicle On-Board Signal System

In response to the problem of imbalanced textual records of urban rail transit faults, this paper proposes a data-driven method for automatically classifying urban rail transit vehicle on-board signal system fault texts. By leveraging the vehicle on-board signal system fault logs of urban rail transit, the pkuseg domain segmenter was trained to identify out-of-vocabulary words and perform Chinese word segmentation. Term Frequency-Inverse Document Frequency (TF-IDF) was employed for feature extraction, transforming the failure texts into word vectors. Adaptive Synthetic Sampling (ADASYN) was utilized for data augmentation to balance the minority class samples. Finally, the Support Vector Machine (SVM) algorithm was applied for fault text classification. Through the analysis of vehicle on-board signal system fault logs from a certain urban rail line spanning from 2016 to 2021, experimental results demonstrate that the proposed model can enhance word segmentation and fault classification performance in the field of rail transit.

Qijia Xi, Shenghua Dai
Research on Temperature Rise Modeling of Traction Inverter Module Based on Surrogate Model

As a key component of train traction and transmission system, inverter module temperature has an important relationship with the stability of train operation and system energy consumption. Because the inverter is a multi-disciplinary equipment with strong coupling, the temperature calculation of the module is related to the parameters of the device itself, the control strategy, the vehicle operating environment and other factors. Therefore, it is difficult to establish an exact mathematical model to describe the input-output relationship from the mechanism, which brings challenges to the analysis of its temperature characteristics. Based on the surrogate model modeling theory, this paper adopts the Kriging surrogate model to model the temperature calculation of the traction inverter with train running speed (motor speed) and traction braking force (or motor torque) as decision variables through sampling test design and surrogate model training. Finally, the accuracy of the proxy model for calculating the temperature of the inverter is verified by taking a but interval train motor speed and traction brake torque as inputs.

Guangming Qing, Zhaoyang Zhang, Yu Zhang, Miao Zhang
Analysis on the Current Situation and Development of Urban Rail Transit Test and Certification Center

Rail transit test and certification centers have been built at home and abroad, and rail transit technology certification platforms have been built to meet the requirements of comprehensive system testing of vehicles and the inspection and test of urban rail professional operating equipment systems. Firstly, this paper describes the construction and testing business of representative testing and certification centers at home and abroad. Identify the challenges and difficulties faced by domestic testing and certification centers; Finally, based on the analysis of the status quo of foreign test certification centers, it provides sustainable development trends and suggestions for the problems and challenges faced by domestic test certification centers.

Jiali Wang, Xun Xiao, Mengting Lu, Zhengyu Xie
Research on Intelligent Intrusion Detection System Model for Train Network Based on TCN

Onboard network of trains has high requirements on the performance of attack detection algorithm, and the network traffic contains characteristics of Time-series data. Therefore, a model of intelligent intrusion detection system based on Temporal Convolutional Network (TCN) is proposed to detect unknown threats. This method not only keeps the advantage of Convolutional neural network in less resource consumption, but also can better process the vehicle network traffic with temporal characteristics. The model was tested using the UNSW-NB15 dataset, compared and analyzed with the LSTM, Lenet-5, MLenet-5, and HAST models. The accuracy of Intelligent Intrusion Detection System Model Based on TCN is 90.1%, it increases by 2.6% compared with the other four models; the false-alarm rate is 6.5%, it decreases by 25.3% compared with the other four models; the false-negative rate is 12.4%, it decreases by 10.8% compared with the other four models. The results show that, the model proposed in this article greatly improves the accuracy of intrusion detection and reduces the false positive rate, which verifies the effectiveness of the method model.

Mingming Liu, Jianying Liang, Jiewei Du, Hongjing Yao, Shaoqing Liu, Zhenchen Chang, Dongxiao Jia
Reliability Analysis of Circuit Board Based on Probability Box Failure Physical Model

This paper focuses on the issue of on-board circuit boards being prone to failure due to environmental factors such as vibration and heat during the actual operation of trains. Finite element simulation is conducted on the actual vibration data of the train, and it is considered that the distribution of heating components on the circuit board is unbalanced, which can lead to the uneven heat distribution of the entire circuit board during operation. Therefore, icepak is used for thermal simulation of the circuit board, using the results of thermal simulation as input for thermal fatigue simulation, the results show that the maximum equivalent stress and equivalent plastic strain are located between the electronic component and the solder joint. In addition, considering the effects of random uncertainty and cognitive uncertainty, a probability box failure physical model for weak components is established to complete reliability analysis at the component level in the circuit board.

Chuang Zhang, Xiang Li, Xinlin Fan, Tian Tang, Yong Qin, Limin Jia, Zhipeng Wang
A Turnout Anomaly Detection Method Based on Kernel-Aligned Mixed Kernel Function SVDD

Undertaking anomaly detection on turnout with missing fault data shows an important role in ensuring railway safety. In this paper, the kernel alignment technique is used to calculate the weights of each base kernel function, to construct a hybrid kernel function to replace the single kernel function in the traditional SVDD, a new KASVDD model is obtained to avoid the dependence on the model performance on the kernel parameters selection. In addition, we discuss the adaptive power curve segmentation algorithm and feature selection optimization algorithm based on mRMR to reduce the unnecessary features in the extracted time domain features and avoid information redundancy. For validation, the method was applied to the power data collected from the Guangzhou Metro Test Platform for S700 K-type switch machines, and the validity and feasibility of the framework are verified.

Sixin Han, Huiyue Zhang, Zhaoyu Li, Bidong Miao, Limin Jia, Yong Qin, Zhipeng Wang
Wave Propagation in the Overhead Conductor Rail System

The purpose of this paper is to research the wave propagation process in the overhead conductor rail system. The overhead conductor rail system is modeled based on absolute nodal coordinate formulation. The initial state of the overhead conductor rail under initial static load is calculated using the Newton iteration method, and the wave propagation process is numerically reproduced in the model using Newmark iteration. The results show that, during the propagation, there are high-speed waves with small amplitude and low-speed waves with large amplitude. And single node on the overhead conductor rail vibrates at a main frequency of 4.8 Hz, which is the natural frequency of the system. The propagation velocity of the main wave is identified as 92.15 m/s by analyzing the time-space distribution of the wave on the overhead conductor rail system. This paper presents a methodology to research the wave phenomena on the overhead conductor rail system, and the wave velocity identified can be referred to in the following research.

Long Chen, Zeyao Hu, Zhigang Liu
Overview of Traction System Testing Indicators for Rail Transit Equipment

With the rapid development of China’s high-speed rail and other rail transit systems, the evaluation and quantitative assessment of traction performance have become increasingly significant. Traction systems, which are responsible for the propulsion of trains, play a crucial role in ensuring the efficiency, reliability, and safety of rail transportation. In this context, this study delves into the composition equipment and evaluation standards of traction systems, providing a valuable academic contribution to the design, manufacturing, and operation of new vehicle models. The paper extensively discusses the various components that constitute a traction system, including motors, control systems, power converters, and auxiliary equipment. It emphasizes the importance of evaluating the traction system’s performance and provides a comprehensive understanding of the evaluation criteria. Among these criteria, the paper focuses on three crucial aspects: no-load tests, load tests, and temperature rise tests.In addition to discussing the evaluation criteria for traction systems, the paper also introduces and explores the testing indicators specific to rail transit equipment. These indicators encompass factors such as tractive effort, energy efficiency, traction-to-weight ratio, and acceleration capability. By providing a comprehensive overview of these indicators, the paper offers valuable insights and guidance for researchers and practitioners in the field of rail transportation.

Jiaxin Liao, Zhengyu Xie
Noise Testing Methods and Indicators for Transport Equipment

With the development of transportation technology for carrying equipment, the noise during the operation of carrying equipment has become a key concern with increasing speed. In response to the above requirements and in order to better test noise indicators and ensure that the development of transportation equipment meets national standards, this article studies the methods and indicators of noise testing in recent years, and explores the construction of a noise testing indicator system, providing strong theoretical knowledge for the development of transportation equipment.

Zengqing Wang, Zengyu Xie
Research on Testing Methods for Urban Rail Transit Braking Systems

Currently, with the rapid development of urban rail transit in major cities nationwide, the braking systems, with the brake control device as the core, are widely utilized. The train braking system is crucial for the safe operation of the entire train and plays a vital role in passenger safety. Considering the current needs, in order to enhance the testing of urban rail transit braking systems and align their development with national standards, this article reviews the testing methods for urban rail braking systems in recent years. The aim is to provide a theoretical basis for the future development of testing urban rail braking systems.

Jianfan Wu, Zhengyu Xie
Power Flow Calculation of Vehicle Network Coupling in Traction Power Supply System

This paper presents an analysis of the fully parallel AT traction network using a six conductor transmission line. An equivalent model is derived and simulation models for traction substations, section posts, AT posts, traction networks, and electric locomotives are comprehensively built using RT-plus/Simulink to enhance the practicality of the simulation. Based on these models, a simulation software for electrified railway traction power supply system is developed using vehicle network coupling power flow calculation. The results of the example calculation demonstrate that this method effectively considers the interaction between the train and the traction power supply network, leading to a more accurate reflection of power flow distribution in the traction power supply system. So, the proposed method has significant application value in electrified railway engineering.

Cong Bao Li, Li Peng Liu, Yang Liu, Xing Jun Tian, Wei Song, Shuai Cao
Data Augmentation of Aerial Traffic Images Based on Optimal Transport Theory

Due to the issue of UAV perspective, aerial traffic images often fail to achieve full-area full-angle coverage. In order to solve the problem of scarce and low-quality samples of aerial traffic images, data augmentation using image generation models has become a popular method for integrating advanced information technology in the transportation field. Currently, images generated by image generation models suffer from issues such as low image quality and difficulty in generating diverse samples. Therefore, to address these challenges, this paper proposes a new image generation model: the Autoencoder-Optimal transport model. This paper explains the image generation task from a geometric perspective, which involves two steps: manifold learning and probability distribution transformation. Firstly, an autoencoder is constructed to learn the underlying manifold. Secondly, a semi-discrete optimal transport network is established for probability distribution transformation. Finally, these two parts are combined to form an Autoencoder-Optimal transport model. Experimental results using aerial traffic images are analyzed to demonstrate the model's ability to generate realistic aerial traffic images.

Zexuan Zhang, Limin Jia, Yong Qin, Xinlin Fan, Tian Tang, Zhipeng Wang
Analysis of the EMU Switching Overvoltage During Pantograph Raising Base on Multiple Re-strikes Arc Model

As the core system of the railway vehicle power supply, the current collection system transmits electric energy to the vehicle through the catenary to ensure the normal operation of the vehicle. The normal operation of the current collection system is very important. Arcing occurs during the action of the pantograph system, and the arcing directly affects the quality of the power system, and at the same time, it will have a certain impact on the electromagnetic interference and overvoltage of the whole vehicle. Therefore, it is necessary to analyze and study the influence of pantograph arc. This paper analyzes the dynamic change process of the arc during the lifting of the pantograph system, establishes an arc model based on mutiple restrikes theory, and obtains the transient overvoltage change process of the pantograph arc. The transient overvoltage caused by the process arc decreases as the arc length decreases.

Shiyu Zhang, Yingqiang Guo, Dajie Lin
Design of Environmental Monitoring System for Subway Machine Room

In order to ensure the stable and reliable operation of the electronic computer system in the subway machine room and maintain a good working environment for the staff, strict control of the machine room environment is necessary. Based on this, this article uses the STM32 microcontroller as the core controller, combined with external sensor circuits and 4G wireless communication technology, to design a subway machine room environment monitoring system. The system can monitor the machine room environment in real-time through a mobile app, When there is an abnormality in the data, the buzzer will directly alarm. This system can monitor real-time parameters such as the environment of subway machine rooms, which has significant practical significance for the maintenance of machine room equipment and ensuring the personal safety of staff.

Yanhua Qiao, Huijuan Ma, Jianna Li, Xiangfang Mao, Lingyu Yang
Design and Application of Rigid-Flex Printed Circuit Board in Special Vehicles

Rigid-flex printed circuit boards (PCBs) have emerged as a transformative technology in the realm of special vehicles, introducing a novel approach to address complex electronic system requirements. This paper delves into the design and application of rigid-flex PCBs in the context of special vehicles, highlighting their unique features and benefits. The article investigates the challenges faced in traditional rigid PCBs and demonstrates how rigid-flex PCBs effectively mitigate these issues, offering enhanced durability, reduced space consumption, and improved reliability. Through case studies and real-world examples, the study showcases the seamless integration of rigid-flex PCBs in various specialized vehicles, such as military, aerospace, and autonomous platforms. Moreover, the research underlines the significant role played by advanced manufacturing processes in optimizing the fabrication of these hybrid PCBs. By exploring cutting-edge applications and advancements, this article elucidates the potential avenues for future innovations in the field, further solidifying the indispensability of rigid-flex PCBs in shaping the future of special vehicles.

Lu Xu, Zhiyuan Wang, Fengpu Qiao, Quan Gao, Tingting Wu
Analysis and Optimization of Dynamic Performance of High-Speed United Type Transition Section

With the development of Chinese railway, especially the urban metro transport and the electrified railway under the mountainous long tunnels, the dynamic performance of overhead conductor rail (OCR) system has become a popular research issue. The united type transition section is an important structure that restricts the current collection quality of high-speed pantograph and OCR system. In this paper, a pantograph-catenary model was developed based on finite element method, which consists of OCR, overhead contact line (OCL), and a united type transition section. Based on the pantograph-catenary model, the effects of operating speed and cut depth of the conductor rail on the dynamic performance of the pantograph-catenary are analyzed. The results show that the transition section is the position where the dynamic performance is the worst, and the dynamic performance of the system when the pantograph enters the OCR from the OCL are worse than that from the OCR to the OCL at 160 km/h, 180 km/h, and 200 km/h. As the speed increasing continuously, the dynamic performance of the pantograph-catenary system deteriorates significantly. From the OCR to the OCL, the maximum value of contact force becomes significantly larger (191.48N → 340.41N), the minimum value of contact force becomes significantly smaller (28.26N → 0N), the standard deviation of contact force becomes larger (29.64N → 70.83N). By designing a type of cut section of the united type transition section scheme, the times of contact loss can be reduced to 0 at 200 km/h.

Sheng Zhou, Xiaohe Feng, Fuchuan Duan, Long Chen, Zhigang Liu
Vehicle Safety Braking Model Based on Cyber-Physical System

Transportation intelligent development has become inevitable, intelligent is the future direction of industrial development, and Cyber-Physical system is an intelligent way to realize. As communication, digital twin, perception and other technologies become more and more mature, the realization of intelligence becomes more and more possible. This paper analyzes the components and system characteristics of each part of the Cyber-Physical system of intelligent vehicles, and constructs an intelligent vehicle model based on the Cyber-Physical system. Simulink module is used as the control decision system to process the data. By simulating the vehicle braking scenario, the basic braking system as well as the improved braking system are evaluated in terms of safety and comfort indexes to judge the system performance. The experimental results show that the improved model built based on the Cyber-Physical system reduces the risk of accidents and realizes the safety control of the vehicle in the multi-vehicle cooperative scenario. Meanwhile, the built simulation can also be optimized for different traffic scenarios.

Haichuan Chen, Honghui Dong
Fundamental-Frequency Positive/Negative-Sequence Detection Under Unbalanced and Distorted Grid Voltage Conditions

The correct value of the fundamental frequency positive/negative-sequence voltage vector and synchronous angle are essential for the normal operation of grid-connected applications. The paper proposed a method to detect this information under unbalanced and distorted grid voltage conditions. By the use of moving average filter (MAF), the harmonics were filtered with the fundamental and orthogonal components detected. After this, the fundamental frequency positive/negative-sequence voltage vector and synchronous angle were calculated. Uniting the MAF with DSOGI-FLL and improving it, the method based on enhanced MAF-DSOGI-FLL was reached which improved the frequency tracing speed efficiently. Simulation and experimental results prove that the proposed method not only can detect the fundamental frequency positive/negative-sequence voltage vector and synchronous angle quickly and accurately, but also can track the frequency mutation rapidly.

Xiaobo Wu, Jianying Liang, Junhong Tian, Conglei Song, Qinggao Fu
Application of Digital Verification Technology in Brake System

As one of the key subsystems of train, brake system plays an important role in the development of railway. The test verification of the braking system is an important part of the research and development design; And it is the basis to ensure the safe operation of the train. Traditional test verification is mainly carried out by physical test bench, but it has the disadvantages of high construction cost, long construction period and needs to spend a lot of human resources. Digital verification is introduced into the development process of brake system because of its flexible and configurable advantages, which provides a new means for brake system testing and verification.This paper will mainly introduce the status of brake system test research, the application of digital verification technologies such as numerical simulation and semi-physical simulation in the field of brake system, and finally look forward to the verification methods of rail transit equipment in the future.

Junhong Tian, Lingjun Wang, Xiaobo Wu, Chao Wang, Tong Wu
Real-Time Simulation of Traction Step-Down Transformer-Uncontrolled Rectifier Based on FPGA

Accuracy and real-time are the two important factors to ensure the reliability and effectiveness of digital test verification. In this paper, a digital model of traction step-down transformer-twelve pulse wave uncontrolled rectifier is established, and a hardware experimental system is built based on FPGA to simulate the digital model in real time. At the same time, it is compared and verified with the physical system, combined with the analysis of experimental phenomena, which proves the accuracy of the established model and the real-time nature of the digital system.

Conglei Song, Donglei Sha, Xiaobo Wu, Zhen Shen, Chao Wang, Wenqin Wang, Sheng Jiang
Research on Optimal Adhesion Control of High-Speed Train Based on Extremum Seeking Algorithm

The safe and smooth operation of High-Speed trains depends on the adhesion between the wheels and the tracks. In complex track conditions such as rain and snow, wheel slip frequently occurs, leading to a significant reduction in the adhesion between the wheels and tracks. This reduction in adhesion negatively impacts the train's traction and braking performance, resulting in safety concerns. To fully utilize the maximum adhesion capacity between the wheels and tracks, this paper proposes an optimal adhesion control strategy for High-Speed trains based on extremum seeking algorithm. Firstly, a dynamic model for High-Speed trains is established, and a Full-Dimensional state observer is designed to estimate the adhesion coefficient. Next, an extremum seeking algorithm is employed to find the optimal slip velocity for the current track condition. An equivalent sliding mode torque controller is then designed to achieve closed-loop control of the optimal torque. Finally, a semi-physical real-time simulation platform is built to verify the real-time performance and effectiveness of the proposed method. Experimental results demonstrate that the proposed method can maintain the adhesion coefficient near its maximum value, achieving optimal adhesion control.

Zhen Shen, Song Wang, Xiaobo Wu, Guangquan Zhang, Conglei Song, Fenghe Zheng, Yikun Yang
Research on Requirement Management of Railway Vehicle Design Based on MBSE

Model-Based Systems Engineering (MBSE) is a model-oriented system analysis method with a high degree of normalization, standardization and reusability. At present, in the process of railway vehicle design and development, there are problems such as non-uniformity, discontinuity, lack of meticulousness and non-standardization of requirements management. Railway vehicle design requirement management is an important link in the process of railway vehicle research and development, which is directly related to the quality and utility of railway vehicle products. At present, the domestic railway vehicle design requirement management is still in the initial stage of research and application, and lacks systematic method system and implementation experience. This paper proposes a railroad vehicle design requirement management method based on MBSE, which provides ideas for guiding railroad vehicle design requirement management, improving product quality and benefit, and promoting the improvement of railroad vehicle requirement management level.

Minghui Sun, Haifang Wang, Huijun Liu, Kuanxin Li, Chaobao He
A Safe Vision Method for Train Positioning

Train positioning is crucial for safe operation of a train. In this paper, we propose a novel safe vision method to achieve train positioning by recognizing wayside kilometer posts. The proposed method contains three parts: kilometer posts detection, kilometer posts semantic recognition, and runtime safe monitoring. A YOLO v5 model is developed to detect kilometer posts from the wayside while a train is running. A Convolutional Recurrent Neural Network (CRNN) model is used to recognize the information on the kilometer posts indicating an absolute position of the railway line. In addition, a safety monitor is proposed to avoid machine learning-based vision methods resulting incorrect recognition results. The monitor verifies whether the recognition results satisfy rule-based properties at runtime. Following the fail-safe principle, the monitor prevents the recognition results from being used for train positioning whenever a violation is detected. We evaluate our method on several benchmarks on a semi-physical simulation platform. Experiment results show that our models efficiently recognize kilometer posts with 88.32% accuracy. With the safety monitor, the safe positioning rate reaches 99.50%, providing a new idea for train visual positioning.

Ye Sun, Mushan Liao, Ming Chai, Hongjie Liu, Dong Yang
Analysis on Electrical Characteristics of Interconnected Power Supply System of Traction Substation Group

The interconnected power supply system of traction substation group is an effective means to reduce the phase separation of electrified railway, and it is imperative to analyze its distinct electrical characteristics. Firstly, the mathematical model of group through power supply system of traction substation based on AT power supply mode is established, and the expressions of current distribution of each branch, equivalent impedance of system, voltage drop and voltage loss at train are deduced. Using actual line parameters as an example, the electrical characteristics are analyzed. The results demonstrate that the equivalent impedance of the system is significantly lower than that of the existing power supply system. The traction load is more evenly distributed among the traction stations, allowing for reduced transformer capacity requirements. Although the voltage in between two traction substations on the line is lowest, it still maintains a higher level compared to existing systems. Regenerative energy from trains effectively improves voltage loss in the traction network while achieving higher utilization rates for regenerative energy. This discussion confirms its superiority in terms of power supply capability and economy.

Dushuo Han, Fan Wang, Guangquan Zhang, Chao Wang, Fenghe Zheng, Zhen Shen
Current Status and Development Trend of Experimental Verification Technology of Traction Drive System

Traction drive system experimental verification technology after many years of development, gradually from the physical test bench mainly simulation experiments supplemented by experimental verification means for the development of physical test bench, computer simulation, semi-physical simulation and other means of experimental verification means, the future in the physical test bench, hardware in the loop simulation, etc., on the basis of the development of digital twins, based on the information-physical technology, digital and physical fusion of the integration of digital virtual test Simulation technology, through higher simulation accuracy and simulation coverage, to reduce the number of physical test tests of traction components and systems, reduce the cost of testing and certification of traction power systems on board, is an important development trend of the experimental verification technology of traction drive systems.

Chao Wang, Dushuo Han, Conglei Song, Junhong Tian, Fenghe Zheng, Xiaobo Wu, Tong Wu, Jing Zhou
Research of Integration and Simulation Technology for Multi-source Heterogeneous Models of Trains

This article introduces the research scheme of multi-source heterogeneous model integration and simulation technology, which integrates and interacts model data composed of multiple software and hardware sources (multi-source) and multiple data types (electrical, control, mechanical, and other heterogeneous data). The application of the combined simulation test of electrical, control and mechanical data of the door system of a Multiple unit is introduced. The integration of multi-source heterogeneous models and the opening of the simulation Technology roadmap can verify the integrity and correctness of the system design by means of digital simulation verification, so as to eliminate potential design errors to the greatest extent, quickly locate faults, improve quality and efficiency, and shorten the actual vehicle commissioning cycle.

Yiming Lu, Jiaying Zhao, Siyu Liu, Haifang Wang, Kuanxin Li
Design of CBTC Real-Time Simulation System Based on FPGA

By analyzing the architecture of the Communication Based Train Control (CBTC) physical system and the functional logic of each subsystem, the model architecture of the CBTC simulation system is simplified, and the hardware resources and communication capacity occupied by the simulation system can be reduced. By establishing the digital simulation model of each subsystem, determining the hardware system selection and implementation method, a real-time simulation system of CBTC system based on Field-Programmable Gate Array (FPGA) is formed. By creating a virtual line with three stations and two sections and a virtual train to simulate the actual operating environment of the CBTC system, and inputting relevant parameters into the simulation system, the simulation system can correctly use the functional logic to control the train operation and related equipment actions, which shows that The function of the simulation system is verified. The CBTC simulation system constructed in this paper can provide an experimental verification environment for the model test of rail transit transportation equipment, and is of great significance to the research and development of key components or systems of rail transportation transportation equipment such as simulation, optimization, and verification.

Fenghe Zheng, Qinggao Fu, Baojie Gao, Guangquan Zhang, Junhong Tian, Jing Zhou, Mingjun Sui
Digital Simulation Study of the Pantograph-Catenary

The research of pantograph-catenary digitalization is an important method for the design of pantograph-catenary scheme of high-speed train, and it is an important way to break through the key theoretical foundation and technology of pantograph-catenary, and also an important process to adapt to the research and development of pantograph-catenary of higher-speed train, and the simulation of pantograph-catenary flow performance based on digitalization is the requirement of higher-speed train for the stability and safety of pantograph-catenary flow performance. In this paper, we mainly use the independently derived three-mass block bow network coupling model equations, and use MATLAB to build the simulation model of the pantograph and catenary, and simulate the contact force fluctuation characteristics of the pantograph and catenary at the train operating speeds of 100 km/h, 200 km/h, and 300 km/h, and obtain the contact force fluctuation characteristics of the pantograph and the contact network when the train operating speeds are 100 km/h, 200 km/h, and 300 km/h respectively. The change characteristics of the contact force of the pantograph-catenary with time at 300 km/h are obtained, and it is found that the average value of the contact pressure between the pantograph and the catenary increases gradually and the fluctuation is more and more intense with the increasing of the running speed of the train. Therefore, the digital simulation of the pantograph-catenary performance can reduce the cost of research and development, reduce the cycle of research and development, and improve the efficiency of research and development.

Guangquan Zhang, Xiaobo Wu, Longqing Fan, Qinggao Fu, Zhen Shen, Dushuo Han, Tong Wu
An Electromagnetic Tri-Stable Energy Harvester for Freight Train Condition Maintenance

The abundant vibration energy from freight train operation can be used to power a self-powered monitoring system. However, current research of this type focuses mainly on the utilization of longitudinal vibration. In this paper, a tri-stable electromagnetic vibration energy harvester that converts horizontal vibration energy into electrical energy is proposed for freight train system maintenance. The tri-stable state is realized by a limiting spring through a fixed magnet attraction. Theoretical analysis and experiments are carried out on the harvester. The experimental results show that the harvester’s operating bandwidth is skewed towards low frequencies, with a maximum output voltage of 4.26 V and a maximum peak-to-peak value of 8.68 V at an excitation frequency of 6 Hz and an excitation acceleration of 1 g. This proves that the harvester has the potential to be used as a source of power for self-powered systems for condition maintenance of freight trains.

Yuan Zhang, Dilong Tu, Lei Zhu, Xiaowei Li, Rui Han, Yanzhe Wang, Jiaxing Guo
A Moving Obstacles Detection Method Based on Millimeter-Wave Radar

An increasing amount of research is dedicated to ensuring train safety through obstacle detection. This study focuses on addressing dynamic targets in front of trains, as they pose higher uncertainty and potential risks compared to static targets. The proposed approach leverages the integration of millimeter wave radar with the DBSCAN clustering algorithm and velocity filtering algorithm to achieve accurate and reliable detection of dynamic targets along the train's path. Practical experiments were conducted to evaluate the effectiveness of the proposed approach. The results demonstrated an impressive 90% accuracy rate when the millimeter wave radar was in a state of constant motion, showcasing the proficiency of the DBSCAN and velocity filtering algorithm in identifying genuine dynamic targets while effectively filtering out false positives. Moreover, compared to the Kalman filtering algorithm, the processing speed was significantly faster, taking only a few milliseconds. These research findings contribute to enhancing train operation safety through improved dynamic target detection.

Zelong Tang
Feasibility Analysis of RT-DETR in the Context of Foreign Object Intrusion at Railway Boundaries

Detection of railway perimeter intrusion is of great significance for railway safety operation, but existing object detection algorithms cannot fully meet the needs of actual railway perimeter foreign object intrusion detection. This article is based on a self-built dataset for railway perimeter intrusion problem. Under the same computer environment, three target recognition algorithms, YOLOv5, YOLOv8, and RT-DETR, are trained and evaluated for their performance indicators. The experimental results showed that in terms of accuracy, RT-DETR achieved better performance than YOLOv5 and YOLOv8 with fewer training rounds and fewer data augmentation strategies. In terms of FPS, RT-DETR’s FPS value after removing NMS was much higher than that of the YOLO series. This comparison verified the feasibility of RT-DETR in the field of railway perimeter intrusion and can be applied to the actual use needs of railway perimeter intrusion.

Xianhui Liu, Rui Huang, Jiali Cai, Xiangdong Yang, Zhengyu Xie
A Review of Research Intrusion Monitoring Technology for Railway Carrier Equipment

With China’s rail transit operating speed and transport loads continue to improve and the continuous expansion of the railway network scale, railway safety in the human defence, physical defence, technical defence “three in one” security system of the initial establishment of the railway perimeter security put forward higher requirements. Object detection and other detection technologies have received more and more attention, and the accuracy. The accuracy, reliability and robustness of the detection of technical defence means are the pain points and problems that need to be solved in the application of railway security engineering. The article firstly outlines the development history and technical process of railway perimeter intrusion object detection technology. Then it describes the research progress of image-based object detection, focusing on the RT-DETR real-time object detection algorithm based on Transformer. After that, the article compares the RT-DETR real-time target detection algorithm with YOLO series and traditional DETR in terms of improving accuracy and speed, and introduces image datasets and performance evaluation metrics. Finally, it analyses the main problems faced by railway perimeter intrusion object detection technology and points out to the future development direction of railway perimeter object detection technology.

Jiali Cai, Xianhui Liu, Rui Huang, Xiangdong Huang, Zhengyu Xie
Application of 10G Ethernet Communication in Train Autonomous Control System of Urban Rail Transit

The development of digitization and intelligence of train control and signal system of rail transit has improved the level of autonomy and transportation efficiency. However, the high-speed and low-delay transmission of big data has become a bottleneck that limits the development of autonomous train control. To overcome the above challenge, we propose an autonomous train control system of urban rail transit with simplified system architecture and refine resource allocation and optimized safety management based on 10 Gigabit Ethernet communication. And a case study was conducted on the key technologies of high-reliability, high-speed, and large-flow data communication in the train’s autonomous control system. The simulation is carried out by building a 10 Gigabit Ethernet data communication test platform based on FPGA (Field Programmable Gate Array). The results show that: FPGA GTX transceiver is used to transmit 1.0G bytes data at the communication rate of 10.0 Gbit/s and there is no received data error. Besides, the bit error rate (BER) is 2.835e-12 and the eye diagram has good openness, high signal integrity, and reliability, which provides technical support for the engineering of train autonomous control.

Jiewei Du, Jianying Liang, Shaoqing Liu, Zhenchen Chang, Dongxiao Jia, Mingming Liu, Yanrong Xu
MBSE Development Process of Urban Rapid Train Based on DODAF

With the guidance of model-based Systems engineering (MBSE) method and reference to the Department of Defense Architecture Frame work (DoDAF), this paper carries out the operation scenario analysis of Urban Rapid Train (URT), uses the scenario modeling and requirement capture methods, and integrates the function driving of structural analysis with the object-oriented thought of UPDM. This paper presents a design idea of URT based on UPDM language architecture. The block graph and activity graph of UPDM are used to design the enhanced structure. Combining the “departure scene” of URT, the whole process of DODAF product generation is described in combination with specific operation scenarios, and the application of UPDM model in architecture design is described graphically. The integration of requirement analysis, function decomposition and system integration is a behavior-driven system engineering process.

Haifang Wang, Juange Zhang, Huijun Liu, Jiaying Zhao, Xin Wang, Zhongchen Wu
Research on Evaluation Method for Autonomous Combat Effectiveness of Unmanned Aerial Vehicle System

Unmanned Aerial Vehicle system (UAVs) has been extensively deployed in a variety of military operations thanks to the advancement of artificial intelligence technology. The autonomous combat effectiveness evaluation of UAVs is an increasingly important area in exploring the core UAVs technologies and reaching the pinnacles of military technology. Current study has shifted its attention to how to better understand UAVs’ autonomy and foster their trust. This study explores and analyzes the essence of UAVs combat connotation and autonomy, as well as the primary evaluation methods, based on study done at domestic and foreign on the evaluation methods of UAVs autonomy. The study also aims to assess the extent to the shortcomings of current domestic UAVs autonomous methods in test environment, assessment mode, and evaluation criteria. Finally, this section has attempted to provide a brief summary of improvement ideas including how to adjust to the advancement of intelligent technology, direct evaluation with tasks, and create a quantitative grading model. This study set out to serve as a beneficial resource for the creation of UAVs autonomy evaluation techniques.

Mingda Zhai, Hao Wang, Pinglang Yi, Zhiqiang Long
Design of Train Traction System for EMU Based on MBSE

Model-Based Systems Engineering (MBSE) has been widely applied in the aerospace field and is gradually attracting attention in the railway transportation sector. With the advancement of railway technology, shortening the design cycle and improving design quality have become important guarantees to enhance market competitiveness. This paper focuses on the traction system of electric multiple units (EMU) and adopts a model-based systems engineering design approach. A functional prototype of the traction system based on SysML is established, and the functional logic simulation of the traction system is carried out by simulating the state changes during operation. The preliminary simulation validation of the traction system’s functionality is completed to improve design quality and reduce design iterations caused by errors or changes.

Chaobao He, Kuanxin Li, Minghui Sun
Adversarial Adaptation Based on Bidirectional Temporal Convolutional Network for RUL Prediction

Remaining useful life (RUL) prediction is one of the key techniques in prognostics and health management (PHM). Deep learning-based prognostics methods, which can automatically mine useful degradation information from monitoring data and infer causal relationships, have received a lot of attention in RUL prediction of machinery. However, in some industrial application scenarios, the operating conditions of the actual data often differ significantly from those of the training data, which greatly limits the predictive performance of the prediction methods. To overcome the above limitations, an anti-adaptive residual life prediction framework is proposed for RUL prediction under different operating conditions. First, a new network, named bidirectional temporal convolutional network (BDTCN), is proposed to capture the interdependence of the input data on the time scale through forward and reverse convolution operations. Then, an anti-adaptive training strategy is developed to help the BDTCN further extract the operating condition invariant degradation features so that it can perform RUL prediction across operating conditions. The proposed framework is evaluated through ablation experiments and comparison with existing methods. The experimental results demonstrate the effectiveness and superiority of the framework in RUL prediction.

Jirui Guan, Yang Gao, Xiaoqing Cheng, Dexi Wang, Lianfu Wang, Xiangyu Ren
Vibration Analyze of High Speed Train Carriage During Special Running Condition

High-speed trains are subjected to random excitation and vibration due to the track environment, airflow influence, weather changes, etc. Such vibration has different degrees of influence on the train’s operation safety, operation quality and the comfort of the people inside. In order to analyze the generation mechanism of such vibration, study its vibration characteristics for targeted vibration damping design. In this paper, several special sections of high-speed train with the most obvious vibration are studied and tested. The vibration signals of the carriages are collected by arranging vibration acceleration sensors, and the vibration characteristics of the sampled carriages are analyzed by using time-frequency transform, after that the samples are categorized based on the types of the special sections and the excitation factors to build the time frequency characteristics of the vibration in high-speed train carriages. The samples are categorized and summarized based on the types of special road sections and excitation factors to build a sample set of vibration time-frequency characteristics about high-speed train carriages in special road sections.

Tai Zhang
Research on Multi-AGV Task Allocation for Warehousing in Railway Logistics Park Based on Improved CBBA Algorithm

With the reform of railway transport and the introduction of the “Belt and Road” initiative, the market share of railway transport has gradually increased, and the volume of goods in railway logistics parks has increased dramatically, and the traditional manual sorting has been unable to meet the huge demand for goods, and it is necessary to improve the operational efficiency of warehousing with the help of intelligent logistics equipment represented by AGV. Task allocation is one of the key issues of AGV task scheduling system. AGV task allocation algorithm, as the core technology of AGV scheduling, can affect the efficiency of AGV operation. Based on this, this paper introduces the grouping strategy into the CBBA algorithm, reduces the computation of the AGVs in the conflict resolution phase, and improves the operation speed of the algorithm. In order to verify the performance of the method, simulation experiments are carried out in this paper, and the results show that the improved CBBA algorithm can effectively shorten the AGV task execution time and the average path of executing tasks, which verifies the effectiveness and feasibility of the method.

Dou Shuihai, Ding Jie, Wang Zhaohua, Li Yingxue, Wang Xiaofeng, Du Yanping
Vibration Characteristics of High-Speed Train Axle Box Bearing with Raceway Defects Considering Track Irregularity

Axle box bearing (ABB) of a high-speed train transmits the loads and motions between the wheelset and bogie, which is essential to the operation. The ABBs may experience raceway defects during long-term operation, which threatens the running safety. The vibration signal of ABB is widely used to the condition monitoring, while it is often limited by the noise in operation. To reveal the vibration features of raceway defects, a vehicle-track longitudinal-vertical coupled dynamics model considering ABBs is established. The bearing nonlinear frictions and contact stiffness, wheel-rail interactions, and track irregularity are comprehensively considered. In the model, the raceway defect is performed by displacement excitation function. Compared to the classical bearing models, the proposed model can simulate the bearing vibration characteristics more accurately. On the basis, the vibration characteristics of ABB with raceway defects are revealed and discussed at different running speeds. Besides, the statistical indicators are used to evaluate the vibration features.

Zhonghui Yin, Zhiwei Wang, Weihua Zhang
Enabling Safety Guarantees of Urban Rail Transit: A New Digital Twin Framework for Data-Model Driven Track Condition Diagnosis

Urban rail transit has become a significant part of transportation. With the growth of its service period, various defects have begun to appear in the track, which threatens the safety of the vehicle operation. Some research has been implemented to detect the track condition based on visual instruments, which is cost-consuming. Thus, a method based on digital twin is proposed to diagnose the track condition. At first, in the virtual environment, a vehicle-track coupling dynamics model considering axle-box bearings is constructed as the digital twin model of the vehicle-track system existing in the physical environment. Then, the models of rail corrugation and rail welds are coupled into the track random irregularity for simulating the axle-box vibration characteristics in the case of track defects. The axle-box accelerations simulated under different track conditions are considered as templates after de-noising and enveloping. These templates are transferred to the physical environment from the virtual environment later. Finally, when a vehicle passes through a section of track, the track condition is diagnosed through comparing the processed axle-box signals collected from the vehicle and templates. The experimental results present that the proposed method can accurately diagnose different track conditions.

Yaoxiang Yu, Liang Guo, Kang Deng, Hongli Gao, Biao Wang
Multi-scale Siamese Network for Few-Shot Fault Diagnosis of Bogie Component

The diagnosis of the key components of train bogies is of great significance to the reliability and safety of train operation, and the intelligent diagnosis method shows great potential due to its excellent end-to-end capability. However, the traditional methods based on deep learning have the following limitations: 1. They require sufficient samples to drive model learning, and the acquisition cost of fault samples in actual engineering is high. 2. They did not fully take into account the deformation of features on a time scale under varying working conditions, resulting in the inability to improve the diagnostic accuracy. To overcome these limitations, a multi-scale siamese network is proposed in this paper. On the one hand, the siamese network realizes the effective learning of fault features by maximizing the similarity of similar samples and minimizing the similarity of different samples, and overfitting is effectively overcome. On the other hand, multi-scale convolution is introduced for siamese networks to extract time-scale complete features and achieve accurate diagnosis under variable operating conditions. The experimental results show that the proposed method has better diagnostic performance than the traditional deep learning network under the condition of changing working conditions and limited fault samples.

Liyun Zhang, Honghui Dong, Limin Jia, Biao Wang
Methods and Indexes for Testing the Safety Status of Transportation Equipment

With the development of China’s transportation industry, a large number of transportation equipment has been applied to transportation scenarios. With a wide variety of transportation equipment, complex application scenarios, and various states, standard safety testing methods and indicators are needed to determine whether they meet the safety standards. Common safety testing methods include real vehicle testing, simulation testing and analog testing, and common testing methods include cameras and LiDAR. This paper studies the safety condition testing methods and indexes in recent years, tries to construct a safety condition testing index system, and provides important theoretical support for guaranteeing the safe operation of China’s transportation industry.

Rui Huang, Xianhui Liu, Xiangdong Yang, Jiali Cai, Zhengyu Xie
Fault Mechanism and System Structure of In-Transit Vehicles Safety Condition Monitoring in Rail Transit

With the fast development of rail transit in recent years in China, it has now become one of the most significant parts of the country’s transportation system. It is therefore in this background that we find the safety of in-transit vehicles in rail transit in dire need of attention. Thus this paper focuses on the safety condition monitoring of in-transit vehicles in rail transit, and namely two aspects of it, the fault mechanism of certain components and the structure of the monitoring system. First, a review and a summary of past works on the safety condition monitoring of in-transit vehicles are done on a scope of studies both domestic and international. From there, we focus our analysis on the fault mechanism of a key component, the bearing of the running gear in the rail transit vehicle, providing insight into the monitoring of it and the prevention of its fault. Finally, a structure of an in-transit vehicle safety condition monitoring system is proposed, offering theoretical support for designing such monitoring systems.

Xiangdong Yang, Rui Huang, Xianhui Liu, Jiali Cai, Zhengyu Xie
Proceedings of the 6th International Conference on Electrical Engineering and Information Technologies for Rail Transportation (EITRT) 2023
Ming Gong
Limin Jia
Yong Qin
Jianwei Yang
Zhigang Liu
Min An
Copyright Year
Springer Nature Singapore
Electronic ISBN
Print ISBN