Skip to main content

Über dieses Buch

The 2010 International Conference on Life System Modeling and Simulation (LSMS 2010) and the 2010 International Conference on Intelligent Computing for Susta- able Energy and Environment (ICSEE 2010) were formed to bring together resear- ers and practitioners in the fields of life system modeling/simulation and intelligent computing applied to worldwide sustainable energy and environmental applications. A life system is a broad concept, covering both micro and macro components ra- ing from cells, tissues and organs across to organisms and ecological niches. To c- prehend and predict the complex behavior of even a simple life system can be - tremely difficult using conventional approaches. To meet this challenge, a variety of new theories and methodologies have emerged in recent years on life system mod- ing and simulation. Along with improved understanding of the behavior of biological systems, novel intelligent computing paradigms and techniques have emerged to h- dle complicated real-world problems and applications. In particular, intelligent c- puting approaches have been valuable in the design and development of systems and facilities for achieving sustainable energy and a sustainable environment, the two most challenging issues currently facing humanity. The two LSMS 2010 and ICSEE 2010 conferences served as an important platform for synergizing these two research streams.



The First Section: Advanced Evolutionary Computing Theory and Algorithms

Co-Evolutionary Cultural Based Particle Swarm Optimization Algorithm

Particle swarm optimization (PSO), cultural algorithm (CA) and co-evolutionary algorithm (CEA) are all research hotspots in the field of intelligent computing. In order to apply their advantages, a hybrid algorithm CECBPSO is proposed in this paper. In the hybridization, PSO is introduced into the framework of CA, and then a co-evolutionary mechanism between two cultural based PSO algorithms is established. In this way, useful experiences can be exchanged among the populations, and randomly reinitialized particles are introduced into the algorithm. Both of them can help the algorithm improving the efficiency and escape the local optima when the particles get premature. The performance is evaluated on five test functions. Simulation results show that the hybridizing of the three algorithms greatly improves the performance.

Yang Sun, Lingbo Zhang, Xingsheng Gu

Non-cooperative Game Model Based Bandwidth Scheduling and the Optimization of Quantum-Inspired Weight Adaptive PSO in a Networked Learning Control System

In this paper, under a framework of Networked two-layer Learning Control Systems (NLCSs), optimal network scheduling is studied. Multi networked feedback control loops called subsystems in a NLCS share common communication media and therefore there is a competition for available bandwidth and data rate. A non-cooperative game(NG) model is first formulated for the problem studied. The existence and uniqueness of Nash Equilibrium point is proved. Subsequently, the utility function of subsystems is designed, taking account of both transmission data rate and control sampling period according to the feature of scheduling pattern and network control. Following this, a quantum-inspired weight adaptive particle swarm optimization algorithm is developed to obtain an optimal solution. Simulation results presented in the paper have demonstrated the effectiveness of the proposed theoretical approach and the algorithm developed.

Lijun Xu, Minrui Fei, T. C. Yang

Modified Bacterial Foraging Optimizer for Liquidity Risk Portfolio Optimization

Recently, bacterial foraging optimizer (BFO) is gaining popularity in the community of researchers because of its efficiency in solving some real-world optimization problems. But very little research work has been undertaken to deal with portfolio optimization problem using BFO approach. This article comes up with a novel approach by involving a linear variation of chemotaxis step in the basic BFO for finding the optimal portfolios. Our proposed approach is evaluated on application on an improved portfolio optimization model considering both the market and liquidity risk. The experimental results demonstrate the positive effects of the strategy.

Ben Niu, Han Xiao, Lijing Tan, Li Li, Junjun Rao

A Combined System for Power Quality Improvement in Grid-Parallel Microgrid

The aim of this paper is to investigate the use of combined system constructed by Shunt Active Power Filter (SAPF) and Static Var Compensator (SVC) for power quality improvement in grid-parallel microgrid. Microgrid configuration is introduced first and appropriate control system is designed to ensure the microgrid operate well in grid-connected mode. In order to improve the power quality of the microgrid, this paper proposes a combined system, in which SAPF is adopted near the microsource to mitigate harmonic currents and SVC near the load to compensate reactive power so as to relieve the voltage variation. Simulation results show the effectiveness of the combined system.

Xiaozhi Gao, Linchuan Li, Wenyan Chen

A Distance Sorting Based Multi-Objective Particle Swarm Optimizer and Its Applications

Multi-objective particle swarm optimization (MOPSO) is an optimization technique inspired by bird flocking, which has been steadily gaining attention from the research community because of its high convergence speed. On the other hand, in the face of increasing complexity and dimensionality of today’s application coupled with its tendency of premature convergence due to the high convergence speeds, there is a need to improve the efficiency and effectiveness of MOPSO. A novel crowding distance sorting based particle swarm optimizer is proposed (called DSMOPSO). It includes three major improvements: (I) With the elitism strategy, the evolution of the external population is achieved based on individuals’ crowding distance sorting by descending order, to delete the redundant individuals in the crowded area; (II) The update of the global optimum is performed by selecting individuals with a relatively bigger crowding distance, which leading particles evolve to the disperse region; (III) A small ratio mutation is introduced to the inner swarm to enhance the global searching capability. Experiment results on the design of single-stage air compressor show that DSMOPSO handling problems with two and three objectives efficiently, and outperforms SPEA2 in the convergence and diversity of the Pareto front.

Zhongkai Li, Zhencai Zhu, Shanzeng Liu, Zhongbin Wang

A Discrete Harmony Search Algorithm

Harmony search (HS), inspired by the music improvisation process, is a new meta-heuristic optimization method and has been used to tackle various optimization problems in discrete and continuous space successfully. However, the standard HS algorithm is not suitable for settling discrete binary problems. To extend HS to solve the binary-coded problems effectively, a novel discrete binary harmony search (DBHS) algorithm is proposed in this paper. A new pitch adjustment rule is developed to enhance the optimization ability of DBHS. Then parameter studies are performed to investigate the properties of DBHS, and the recommended parameter values are given. The results of numerical experiments demonstrate that the proposed DBHS is valid and outperforms the discrete binary particle swarm optimization algorithm and the standard HS.

Ling Wang, Yin Xu, Yunfei Mao, Minrui Fei

CFBB PID Controller Tuning with Probability based Binary Particle Swarm Optimization Algorithm

The high combustion efficiency, extensive fuel flexibility and environment friendly characteristics have made circulating fluidized bed boiler (CFBB) an alternate choice for coal fired thermal power plants for clean energy production. But CFBB is a highly nonlinear and complex combustion system because of coupling characteristics and time delays. PID controller tuning of such a complex system with traditional tuning methods cannot meet required control performance. In this paper, a new variant of binary particle swarm optimization algorithm (PSO), called probability based binary PSO is presented to tune the parameters of CFBB. The simulation results show that PBPSO can effectively optimize the controller parameters and achieve s a better control performance than those based on that of a standard discrete binary PSO and a modified binary PSO.

Muhammad Ilyas Menhas, Ling Wang, Hui Pan, Minrui Fei

A Novel Cultural Algorithm and Its Application to the Constrained Optimization in Ammonia Synthesis

A novel cultural differential evolution algorithm with multiple populations (MCDE) is proposed. The single individual in each population is affected by the situational and normative knowledge from belief space simultaneously. The populations communicate with each other following a rule of knowledge exchange, which helps to enhance the search rate of evolution. The concept of culture fusion is introduced to develop an adaptive mechanism of preserving the population diversity. The mechanism ensures that populations are diverse along the whole evolution and excellent candidate solutions are not rejected. The performance of MCDE algorithm is validated by typical constrained optimization problems. Finally, MCDE is applied to maximizing the net value of ammonia in an ammonia synthesis loop. The results indicate that the proposed algorithm has the potential to be used in other problems.

Wei Xu, Lingbo Zhang, Xingsheng Gu

Pareto Ant Colony Algorithm for Building Life Cycle Energy Consumption Optimization

This article aims at realizing optimal building energy consumption in its whole life cycle, and develops building life cycle energy consumption model (BLCECM), as well as optimizes the model by Ant Colony Algorithm (ACA). Aiming at the complexity and multi-objective principle of building life cycle energy consumption, this research tries to modify Pareto Ant Colony Algorithm (PACA), making it fit the needs of finding solution to least energy consumption in a building’s whole life cycle. In the initial stage of ant colony constructing solution, each objective weighing is defined randomly, which improves the optimal determination mechanism of Pareto solution, perfects the renovation principle of pheromone, and finally realize the goal of optimization. This research is a innovative application of ACA in building energy-saving area, and it provides definite as well as practical calculation method for building energy consumption optimization in terms of a whole life cycle.

Yan Yuan, Jingling Yuan, Hongfu Du, Li Li

Particle Swarm Optimization Based Clustering: A Comparison of Different Cluster Validity Indices

Most of clustering algorithms based on natural computation aim to find the proper partition of data to be processed by optimizing certain criteria, so–called as cluster validity index, which must be effective and can reflect a similarity measure among objects properly. Up to now, four typical cluster validity indices such as Euclid distance-based PBM index, the kernel function induced CS measure, Point Symmetry (PS) distance-based index, Manifold Distance (MD) induced index have been proposed. But, there is not a detailed comparison among these indexes. In this paper, we design a particle swarm optimization based clustering algorithm, in which, four different cluster validity index above mentioned are used as the fitness of a particle respectively. By applying the proposed algorithm to a number of artificial synthesized data and UCI data, the performance of different validity indices are compared in terms of clustering accuracy and robustness at length.

Ruochen Liu, Xiaojuan Sun, Licheng Jiao

A Frequency Domain Approach to PID Controllers Design in Boiler-Turbine Units

This paper proposes a frequency domain approach—direct Nyquist array (DNA) method, to the design of PID controllers for multivariable boiler-turbine units based on gain and phase margins. The main objective is to propose an integrated method for the design and auto-tuning of simple yet robust PID controllers that can be more easily implemented for the boiler-turbine units in modern power plants. For this, the model of the original multi-input multi-output (MIMO) system is first transformed into a diagonal or diagonal dominance matrix after the system is appropriately compensated. Then, various PID controller design methods for single-input single-output (SISO) systems can be easily extended to decoupled or quasi-decoupled MIMO systems. In particular, the proposed method allows the user to specify the robustness and other key performances of the system through the gain and phase margin specifications. Simulation results illustrate the efficacy of the proposed method, showing that the designed controller for a boiler-turbine unit has a reduced number of elements by a half and produces much better dynamic performances than the one designed by Tan’s method.

Hui Pan, Minrui Fei, Ling Wang, Kang Li

An Estimation of Distribution Algorithm Based on Clayton Copula and Empirical Margins

Estimation of Distribution Algorithms (EDAs) are new evolutionary algorithms which based on the estimation and sampling the distribution model of the selected population in each generation. The way of copula used in EDAs is introduced in this paper. The joint distribution of the selected population is separated into the univariate marginal distribution and a function called copula to represent the dependence structure. And the new individuals are obtained by sampling from copula and then calculating the inverse of the univariate marginal distribution function. The empirical distribution and Clayton copula are used to implement the proposed copula Estimation of Distribution Algorithm (copula EDA). The experimental results show that the proposed algorithm is equivalent to some conventional continuous EDAs in performance.

L. F. Wang, Y. C. Wang, J. C. Zeng, Y. Hong

Clonal Selection Classification Algorithm for High-Dimensional Data

Many important problems involve classifying high-dimensional data sets, which is very difficult because learning methods suffer from the curse of dimensionality. In this paper, Clonal Selection Classification Algorithm is proposed for high-dimensional data. First, an automatic non-parameter uncorrelated discriminant analysis (UDA) is adopted for dimensionality reduction (DR). Due to the favorable global search and local search, Clonal Selection Algorithm (CSA) is used to design classifier. The proposed method has been extensively compared with nearest neighbor (NN) based on Principal Component Analysis and linear discrimination analysis (PCA+LDA), nearest neighbor (NN) based on UDA (UDA+NN) and FCM based on UDA (FCM+UDA) when classifying six UCI data sets and a SAR image classification problems. The results of experiment indicate the superiority of the proposed algorithm over the three other classification algorithms in term of classification accuracy and stability.

Ruochen Liu, Ping Zhang, Licheng Jiao

The Second Section: Advanced Neural Network Theory and Algorithms

A General Framework for High-Dimensional Data Reduction Using Unsupervised Bayesian Model

In this paper, we propose a general framework for high-dimensional data reduction using unsupervised Bayesian model. The framework assumes that the pixel reflectance results from linear combinations of pure component spectra contaminated by an additive noise. The constraints are naturally expressed in unsupervised Bayesian literature by using appropriate abundance prior distributions. The posterior distributions of the unknown model parameters are then derived. Experimental results on hyperspectral data demonstrate useful properties of the proposed reduction algorithm.

Longcun Jin, Wanggen Wan, Yongliang Wu, Bin Cui, Xiaoqing Yu

The Model Following Neural Control Applied to Energy-Saving BLDC Air Conditioner System

An AC inverter has been widely used to air conditioner systems for energy saving. But the AC driver will generate high heat dissipation and induce high operating temperature in low speed operation conditions. The modern brushless DC motor (BLDC motor) will improve the high heat generation problem in wide operation speed. This study utilizes the model following neural control applied to modern BLDC driver. A simple approximation of plant Jacobian is proposed, the appropriate speed performance of the BLDC motor for energy saving is defined. The simulation results reveal that the proposed control system is available to control the DC air conditioner system and save energy.

Ming Huei Chu, Yi Wei Chen, Zhi Wei Chen

Develop of Specific Sewage Pretreatment and Network Monitoring System

After analyzing the current status of sewage treatment system, a construction method of specialization and specificity of sewage treatment is proposed. The huge urban sewage treatment pipe network and processing of mixed water to sewage treatment of specific sources of pollution are simplified, which not only reduces the urban construction scale of urban sewage pipe network but also creates the conditions of reclaimed water using. Therefore, the sewage treatment system can bring many advantages including low cost of investment, incremental regulation, and good treatment effect.

Rongbao Chen, Liyou Qian, Yuanxiang Zhou, Xuanyu Li

Application of Radial Basis Function Neural Network in Modeling Wastewater Sludge Recycle System

Sludge recycle system is an important part of wastewater treatment plants(WWTP), which can ensure the required reactor sludge concentration, maintenance the dynamic balance between secondary sedimentation tanks and sludge reactor sludge concentration. This work proposes development of a Radial Basis Function (RBF) Neural Network model for prediction of the Sludge recycling flowrate, which ultimately affect the Sludge recycling process. Compared with the traditional constant sludge recycle ratio control, new idea is better in response to actual situation. According to analyzing and Evolutionary RBF Neural Network theory, a RBF Neural Network is designed. The data obtained from wastewater treatment were used to train and verify the model. Simulation shows good estimates for the sludge recycling flowrate. So the idea and model is a good way to the sludge recycle flow rate control. It is a meaningful Evolutionary Neural Network application in industry.

Long Luo, Liyou Zhou

Improved Stability Criteria for Delayed Neural Networks

This paper is concerned with the stability problem of delayed neural networks. An improved integral inequality Lemma is proposed to handle the cross-product terms occurred in the derivative of Lyapunov functional. By using the new lemma and a novel delay decomposition approach, we propose the new delay-range-dependent stability criteria for time varying delay neural networks. The sufficient conditions obtained in this paper are less conservative than those in the former literature.

Min Zheng, Minrui Fei, Taicheng Yang, Yang Li

Aplication of the Single Neuron PID Controller on the Simulated Chassis Dynamometer

The single neuron self-adaptive PID controller was introduced after analyzing MCG-200 simulated chassis dynamometer control system. The simulation process of running resistance in the laboratory was improved. The suitable single neuron self-adaptive PID controller was designed, the new control system using single neuron self-adaptive PID algorithm was simulated and laboratory dates obtained on the improved chassis dynamometer was compared with datas conducted on the real road. Results show that: the single neuron self-adaptive PID controller has simpler structure, stronger self-adaptive ability and can replace the traditional PID controller.

Weichun Zhang, Bingbing Ma, Peng Yu, Baohao Pei

Research on the Neural Network Information Fusion Technology for Distinguishing Chemical Agents

For implementing effectively detection and rapid exact identification for the chemical agents in sea-battlefield, firstly, the conception, treatment model and system structure of the information fusion, are introduced; secondly, the neural network(NN) information fusion system model are built by the multi-sensors information fusion (MSIF) technology; At the same time, connecting the wavelet analysis with the NN organically, and based on the wavelet transfer and the NN, the system of the speedy features extraction and identification for chemical agents -the NN Distinguishing Chemical Agents (NNDCA) system- is founded. The model of the NNDCA and the method of the feature extraction for the chemical agents based on the wavelet analysis are established, and the hardware accomplishment and the software structure of the NNDCA system are put forward; lastly, the experimental and simulated results show: it is feasible that the analyses for the chemical agents with the NNDCA system based on the MSIF technology and the wavelet analysis. The method can remarkably heighten the accuracy and credibility of the measurement results, and the results are of repeatability.

Minghu Zhang, Dehu Wang, Lv Shijun, Jian Song, Yi Huang

The Third Section: Innovative Education in Systems Modeling and Simulation

Simulating Energy Requirements for an MDF Production Plant

The main focus of this paper is to look at production management in a manufacturing facility and correlate it with the energy consumption. The end result of this process will be a better understanding of the production system and the energy loses. This will be closely followed by the creation of different scenarios that ideally will lead to a lowering in the energy consumption. So far, simulation has been used in manufacturing facilities for modelling supply chain management, production management and business processes. This research brings a novel approach to investigating the adaptability of industrial simulation processes and tools for modelling the energy consumption with respect to a variable production output.

Cristina Maria Luminea, David Tormey

Three-Dimensional Mesh Generation for Human Heart Model

Mesh generation is the precondition of finite element analysis. The quality of the mesh determines the precision of the computational results, and low-quality meshes might lead to incorrect results. Therefore, it is necessary to produce high-quality meshes for finite element analysis. Most commercial software generates meshes on the basis of the entity of an object, while seldom uses the discrete point data to produce meshes directly. Furthermore, the compatibility problem among different software always slows down the progress of research. This paper aims at producing Constrained Delaunay Tetrahedral meshes for human heart anatomy model with TetGen.

Dongdong Deng, Junjie Zhang, Ling Xia

Interactive Identification Method for Box-Jenkins Models

This paper converts a Box-Jenkins model into two identification submodels with the system model parameters and the noise model parameters, respectively. However, the information vectors in the submodels contain unmeasurable variables, which leads the conventional recursive least squares algorithm impossible to generate the parameter estimates. In order to overcome this difficulty, the interactive least squares algorithm is derived by using the auxiliary model identification idea and the hierarchical identification principle. The simulation results indicate that the proposed algorithm has less computational burden and more accurate parameter estimation compared with the auxiliary model based recursive generalized extended least squares algorithm.

Li Xie, Huizhong Yang, Feng Ding

Research on Nano-repositioning of Atomic Force Microscopy Based on Nano-manipulation

Nano-manipulation technology is an emerging field in the development of modern science and technology. Thus, the improvement of its positioning and repositioning precision has become each nano worker’s dream and ultimate goal. However, due to the hysteresis, creep, and other nonlinearity of piezoelectric ceramics tube (PZT) as well as the probe’s tip deviations caused by cantilever deformation, it leads larger error of relative displacement between probe and sample, which adds enormous inconvenience to the nano-manipulation and repositioning. The subject is to research and design a 3-D repositioning control technology to improve repositioning accuracy.

Sun Xin, Jin Xiaoping

Research on Expression Method of a Unified Constraint Multi-domain Model for Complex Products

This paper studies the modeling method based on the unified constraint systems for complex products’ designing and analyzing. The method describes the complex product’s multi-domain optimization in a unified constraint model. The unified constraint expression for the product’s multi-domain simulation and optimization model can implemented by the mapping mechanism transferring the physical models into the mathematical models. Aiming at designing and analyzing for the complex mechanical products of the multi-field mixture and the sub-hierarchy, the paper studies the product’s associated constraints of the different areas’ hierarchical relationship, the constitutive constraints expressing the product areas’ constitutive relations, the body constraints describing the relationship between the association and the constitution, and the discrete constraints representing the discrete events to extract the commonality in different areas for these four constraints on the basis of the geometric constraints’ representation and the physical systems’ modeling. In connection with the commonality in the constraints, the products’ model formulation in the various fields is unified in the constraint level based on equations using the various structural elements’ constraints based on a unified expression of mathematical equations.

Chen Guojin, Su Shaohui, Gong Youping, Zhu Miaofen

The Fourth Section: Intelligent Methods in Developing Vehicles, Engines and Equipments

An Automatic Collision Avoidance Strategy for Unmanned Surface Vehicles

Unmanned marine vehicles are useful tools for various hydrographical tasks especially when operating for extended periods and in hazardous environments. The autonomy of these vehicles depends on the design of robust navigation, guidance and control systems. This paper concerns the preliminary design of an automatic guidance system for unmanned surface vehicles based on standardised rules defined by the International Maritime Organisation. A guidance system determines “reasonable” and safe actions in order to complete a task at hand. Thus, autonomous guidance can be regarded as the mechanism that brings self-reliance to the whole system. The strategy here is based on waypoint guidance by line-of-sight coupled with a manual biasing scheme. Simulation results demonstrate the functioning of the proposed approach for multiple stationary as well as dynamic obstacles.

Wasif Naeem, George W. Irwin

Research on Fire-Engine Pressure Balance Control System Based Upon Neural Networks

The pressure produced by the water coming out of the fire-engine pump outlet is controlled by the rotate speed of the fire pump. However, this RS is controlled through fire-engine accelerator voltage which is controlled by the ECU. In order to control and keep the fire-engine pressure balanced, it is necessary to take pressure, rotate speed and current rate as input parameters and control voltage as output parameter through BP neural network control system. Related researches indicate that BP neural network is appropriate for building the system whose target is to keep the pressure balanced. And, some modification can be done to the standard BP neural network algorithm. These modified BP neural network algorithms are BP neural network with momentum factors and self-adapting learning speed which can improve the response speed and performance of this control system dramatically.

Xiao-guang Xu, Hong-da Shen

The Summary of Reconstruction Method for Energy Conservation and Emission Reduction of Furnace

With the raising of the third session of the CPPCC national committee first proposal” promote the development of china’s law-carbon economy on the pro- postal”, the R&D and result. This article studies deeply and reconstructs cosmically the structure of the furnace, aiming at the energy saving method of the furnace’s energy saving application, in order to achieve the saving of fuel as could be under the temperature of material outputting and ensuring the safety. What has been discussed above still need more proofs during the practice, achieving the best result through various kinds of technic improvement and cooperation.

Xiaoxiao Wang, Xin Sun

Osmotic Energy Conversion Techniques from Seawater

This paper firstly introduces the principles of Pressure Retarded Osmosis (PRO) and Reverse Electro Dialysis (RED). It is concluded that the RED method is more suitable than the PRO method for power generation from seawater. Theoretical analysis of RED stack is made for the design of a test RED compartment. Tests were carried out to study the relationship between produced energy power density, test compartment width and ion exchange membrane area. Experimental conclusions are drawn out at the end of the paper.

Yihuai Hu, Juan Ji

The Fifth Section: Fuzzy, Neural, and Fuzzy-Neuro Hybrids

Vibration Monitoring of Auxiliaries in Power Plants Based on AR (P) Model Using Wireless Sensor Networks

There are many auxiliaries with high rotating speed in a power plant, such as pumps, fans, motors and so on.To warrant their safe and reliable operation, their state of vibration has to be monitored. But because of their scattered location, the traditional way of online monitoring with shielded cable connections is costly and work expensive and the precision, reliability and safety of itinerant measurements are unable to meet the requirements of customers. A novel method of vibration monitoring for auxiliaries in power plant based on wireless sensor networks (WSN) has therefore been proposed to realize vibration data acquisition, on-line-detection and data analyzing in this paper, which meets the requirements of auxiliaries with less expenditure and warrants safe operation in the long run. The multi-sink topological structure of WSN can improve the transmission efficiency of multi-hop network to meet the vibration test requirements of low-latency, high frequency sampling and high data throughput. The sensor node can schedule its sampling and communication time to minimize sampling frequency and communication traffic, reduce the energy consumption and prolong the lifetime of WSN according to the prediction value of the sample data probability mode.

Tongying Li, Minrui Fei

Performance Prediction for a Centrifugal Pump with Splitter Blades Based on BP Artificial Neural Network

Based on MATLAB, a BP artificial neural network (BPANN) model for predicting the efficiency and head of centrifugal pumps with splitters were built. 85 groups of test results were used to train and test the network, where the Levenberg—Marquardt algorithm was adopted to train the neural network model. Five parameters













were chosen in the input layer,




were the output factors. Through the analysis of prediction results, the conclusion was got that, the accuracy of the BP ANN is good enough for performance prediction. And the BP ANN can be used for assisting design of centrifugal pumps with splitters. Meanwhile, the method of CFD flow field simulation was also used to predict the head and power for a centrifugal pump with splitters, and compared with that from the BPANN model. The comparison of prediction results and experimental value demonstrated that the prediction values acquired through numerical simulation and BPANN were uniform with the test data. Both methods could be used to predict the performance of low specific speed centrifugal pump with splitters.

Jinfeng Zhang, Shouqi Yuan, Yanning Shen, Weijie Zhang

Short-Term Traffic Flow Prediction Based on Interval Type-2 Fuzzy Neural Networks

In this paper, a TSK interval type-2 fuzzy neural network is proposed for predicting the short-term traffic flow. The proposed fuzzy neural network is adaptively organized from the collected short-term traffic flow data. The whole process includes structure identification and parameter learning. In structure identification, the hierarchical fuzzy clustering algorithm performs the training traffic flow data set in order to generate the network structure. After the structure identification is finished, the BP algorithm is adopted to perform the parameter learning. Then the trained fuzzy neural network is employed the collected short-term traffic flow test set and the prediction result verifies that the TSK interval type-2 fuzzy neural network has high prediction accuracy.

Liang Zhao

Neural Network and Sliding Mode Control Combining Based Reconfigurable Control

This paper introduces a neural network adaptive control and sliding mode control combining reconfigurable control for aircraft. The control law is based on the nonlinear dynamic inversion. Sliding model control and fuzzy neural network adaptive control are used to compensate twice the inversion error induced by aircraft actuator failures. Thereby the robustness of dynamic inversion control is greatly improved, and the modeling accuracy has been solved. The simulation shows that this method is feasible.

Gongcai Xin, Zhengzai Qian, Weilun Chen, Kun Qian, Li Li

Study on Membrane Protein Interaction Networks by Constructing Gene Regulatory Network Model

At present, about a quarter of all genes in most genomes contain transmembrane (TM) helices, and among the overall cellular interactome, helical membrane protein interaction is a major component. Interactions between membrane proteins play a significant role in a variety of cellular phenomena, including the transduction of signals across membranes, the transfer of membrane proteins between the plasma membrane and internal organelles, and the assembly of oligomeric protein structures. However, current experimental techniques for large-scale detection of protein-protein interactions are biased against membrane proteins. In this paper, we construct membrane protein interaction network based on gene regulatory network model. GRN model is proposed to understand the dynamic and collective control of developmental process and the characters of membrane protein interaction network, including small-world network, scale free distributing and robustness, and its significance for biology. The proposed method is proved to be effective for the study of membrane protein interaction network. The results show that the approach holds a high potential to become a useful tool in prediction of membrane protein interactions.

Yong-Sheng Ding, Yi-Zhen Shen, Li-Jun Cheng, Jing-Jing Xu


Weitere Informationen

BranchenIndex Online

Die B2B-Firmensuche für Industrie und Wirtschaft: Kostenfrei in Firmenprofilen nach Lieferanten, Herstellern, Dienstleistern und Händlern recherchieren.



Globales Erdungssystem in urbanen Kabelnetzen

Bedingt durch die Altersstruktur vieler Kabelverteilnetze mit der damit verbundenen verminderten Isolationsfestigkeit oder durch fortschreitenden Kabelausbau ist es immer häufiger erforderlich, anstelle der Resonanz-Sternpunktserdung alternative Konzepte für die Sternpunktsbehandlung umzusetzen. Die damit verbundenen Fehlerortungskonzepte bzw. die Erhöhung der Restströme im Erdschlussfall führen jedoch aufgrund der hohen Fehlerströme zu neuen Anforderungen an die Erdungs- und Fehlerstromrückleitungs-Systeme. Lesen Sie hier über die Auswirkung von leitfähigen Strukturen auf die Stromaufteilung sowie die Potentialverhältnisse in urbanen Kabelnetzen bei stromstarken Erdschlüssen. Jetzt gratis downloaden!