Progressive and Integrative Ideas and Applications of Engineering Systems Under the Framework of IOT and AI

To identify voids around underground concrete sewer pipes, we investigate an automated in-pipe detection method. This method uses a robotic platform with a mechanical impactor to generate non-destructive stress waves at any angular position on the pipe's inner circumference. The resulting acoustic waves are recorded with a microphone and are analyzed to make a void location map around the pipe. To characterize the method, we developed numerical models where we examine the influence of void width, height, and shape, and the thickness of the pipe and the presence of reinforcement in the pipe on the void detection. We validated the proposed method by conducting experiments inside a concrete pipe with custom-made voids, and differently compacted areas in the pipe’s surrounding. The results showed that the method was able to detect voids and areas with less compacted sand around the pipe.

This paper presents the analysis of grasping mechanism for random regular object of improved prosthetic robotic arm. The prosthetic robotic arm is intended to assist in increasing movement, managing everyday activities, and promoting independence for physically disadvantaged individuals. The device utilizes 3D printing technology to make it more affordable than current market options. The prosthetic arm is controlled by a compact microcontroller (ESP32) and a force sensor that detects muscle flex activity, allowing for precise object grasping. The ability to grasp objects is crucial for disabled children to improve their quality of life and maintain independence, which is directly contribute to the development of a prosthetic robotic arm with grasping capabilities is essential. The results of testing show that the prosthetic arm can successfully grasp regular shape objects such as cylinder, rectangular and cube. The goal of this study is to analysis the grasping on random regular objects, create an affordable, user-friendly prosthetic robotic arm that can improve the quality of life for disabled children. In conclusion, the results of this study suggest that a prosthetic robotic arm can successfully be used by children with limb disabilities.

This research extends the study of a former Master thesis, “Implementation of A Swing System Based on Fuzzy Control” to establish a human-like intelligent swing system using machine vision. Humans having ability to accomplish dexterous operations stems from sophisticated sensing organs in human body, such as skin and eyes for tactile and visual information, respectively. Therefore, in this research, a camera, which mimics a human eye to provide human-like visual capability, is added to a two-bar linkage swing mechanism. First of all, the optical flow for the swing's movement is derived through the relative reference model of the camera with respect to the environment. In order to evaluate the swing’s behavior according to visual input, an optical flow approach to extract motion of the swing system is therefore proposed. For the purpose of excluding regions with inaccurate optical flow in the image, the brightness standard deviation method and the feature orientation threshold method are applied. A reliable optical flow reference value, which is able to effectively detect the movement of the swing system, can therefore be determined by the statistical and filtering techniques. Besides, three different control modes including the swing-up, the hold-on, and the swing-down are developed to correspond to three stages in a whole swing cycle. The leg’s motor is driven by three control strategies so that the entire swing system can achieve human-like swinging skills based on visual information.

Robot positioning technology is a crucial area of research in robotics. The positioning accuracy, stability, and speed of robots directly impact their effectiveness, and ultimately, their success or failure. This paper presents a positioning technology for mobile robots in industrial settings, encompassing an in-depth study of the positioning process, positioning algorithm, multi-target positioning, and anti-interference issues. Experimental tests demonstrate that this technology boasts excellent positioning accuracy and speed, enables simultaneous tracking of multiple targets, exhibits a certain degree of anti-interference ability, and has promising application prospects.

With the rapid development of science and technology, smart furniture has become a technological trend. After the COVID-19 epidemic swept the world, we are in the post-epidemic era and disinfection has become an important part of life. This paper illustrates the design of an intelligent disinfection hanger, which uses the modernist design concept and conforms to ergonomic theory. It improves the single function of the traditional vertical hanger and changes the way of manual disinfection, making it more convenient and faster. And it can improve the quality of life. In view of the background of the times and the needs of the market, intelligent disinfection hangers will develop into a trend.

Nowadays, there have been many entertainments to enrich our free time. Watching sporting events on the spot is one of the popular entertainments for people. However, the spectators do not interact much with the players most of the time. Moreover, spectators are sometimes occupied by their cellphones during the game. Although spectators get together in a stadium, they are actually farther apart from one another. To improve spectators’ interaction. Television directors use cameras to capture fun scenes and project them onto the screen. This scheme cannot only entertain the spectators but also increase the interaction between spectators and players. So far, this process is fully controlled by a cameraman. Therefore, it is required that the cameraman pays a lot of full concentration during games, especially at half-time. This job increases the cameraman's burdens. Hence, the purpose of this study is to automate this process using modern technology to reduce the pressure on cameramen and manpower. Besides, the advantages are high efficiency and flexibility to accommodate interactive experiences. The proposed scheme includes three stages. Firstly, facial recognition detects pairs of females and males. Secondly, a cellphone app collects all the detected couples, according to the distance between a female and a male. Users can choose one of those images with an interaction model. Finally, a spotlight will be aligned to the selected couple so that the cameraman can know where the camera should shoot for. A small-scale experimental system was implemented to demonstrate the feasibility of the proposed intelligent framework.

Conventional vehicle suspension system is mainly composed of coil springs and hydraulic dampers, and the elasticity coefficient K ad damping coefficient C are fixed values, so the traditional suspension system cannot adjust the suspension system according to different road conditions. Due to the varying road quality, many potholes, patches and manhole covers, and rainy climate, the comfort and maneuverability of driving are reduced. Therefore, this study proposes the application of embedded technology combined with road image to determine and control the class of Analogous Active Suspension System. In this study, the Analogous Active Suspension System is composed of air springs, proportional valve hydraulic dampers instead of traditional suspension system, and various sensors. For different types of uneven road surfaces such as potholes, speed bump, manhole covers, etc., the Controller Area Network (CAN bus) communication is used to transmit the road surface information to the vehicle embedded system, and then the control decision is calculated to adjust the corresponding air spring coefficients according to the corresponding conditions. At the same time, the optimal damping coefficients are calculated by using neural-like algorithms, so that the system can adjust the suspension parameters immediately according to the current road conditions to achieve better driving comfort and handling.

Finally, the dynamic characteristics of the suspension system and the vehicle are investigated in a real vehicle dynamic test to optimize the control decision parameters to achieve the best driving comfort and to give the best driving safety.

This paper proposes the development strategy for Intelligent manufacturing transformation, with the help of both SWOT analysis and AHP analysis, in the case of focusing on the Jilin city Automobile Industry. Firstly found the influence factors of Jilin city automobile industry’s intelligent manufacturing transformation, based on SWOT analysis. Secondly, the AHP quantitative analysis model is constructed, and the Delphi survey method is used for quantitative calculation that had been taken Consistency checking results. Then determine the strategic quadrilateral, to obtain the development strategy azimuth and strategic strength. The strategic positioning and trend of the intelligent transformation and development of the automobile industry in Jilin City are determined, and the implementation countermeasures of the development strategy are formulated.

First responders use Unmanned Aerial Vehicles (UAV) in disaster response to obtain a situational overview. Flying in a formation has the advantage of having multiple airborne sensors and cameras. However, UAV formations are limited in terms of flight time. In this paper we present a system that is capable of achieving persistent formation flight. The system does not need a central coordination unit and is self-organizing by triggering UAVs on the ground to take-off and join the formation whenever a UAV in the formation is about to run out of battery. The replacement process allows the formation to be kept intact for as long as possible. Onboard each UAV, the flight controller handles the formation-keeping and trajectory following while a higher level multi-agent-coordination unit accesses the flight controller to send commands. The leader-follower formation is designed to be rigid and independent of the number of UAVs present in the formation. A prototype consisting of four simulated UAVs was implemented as a proof of concept, which worked as expected.

With the advanced manufacturing technology of organic light-emitting diode (OLED) displays, yield loss in the manufacturing process became the most important index for display manufacturers. However, the reason that the most direct causes for the yield loss come from different defects on thin film. If the defect type can be successfully classified, it will be easier to find out the cause and effectively reduce the yield loss by adjusting the condition and parameters for the fabrication processes.

In general, thin-film defects can be detected by automated optical inspection (AOI). When a thin-film defect is found, the reviewing module will relocate to the corresponding position and record the defect images. Then, the images will be further judged as normal or with specific defect types by experienced operators.

Therefore, this research proposes a classifier for defect images based on a deep neural network (DNN) ensemble framework to reach a high accuracy of classification. It can help the display industry to save more cost and time in distinguishing the defect types precisely. Moreover, the proposed scheme is able to accelerate the inspection flow and improve the yield to make more profit.

This paper describes a cloud distribution forecasting model based on deep convolutional neural network (CNN) for application of forecasting photovoltaic power generation (PV) output. PV output information is used for stable operation of the electricity grid and electricity trading markets. It is important to forecast cloud distribution because PV output varies mainly affected by clouds position and irradiation. In our previous research, satellite images were used for the input of the forecasting model. However, clouds appear and disappear from time to time by some factors such as topography, temperature, and humidity. In this paper, ground altitude information which is geopotential altitude is added to the input of the forecasting model to improve the forecasting accuracy. Geopotential altitude is a height referenced to earth’s mean sea level. Because the altitude is provided as two-dimensional data, it is suitable for the forecasting model which treats with images. The forecasting results with August dataset show some improvements in terms of the forecasting accuracy.

Within the scope of industry 5.0, mixed reality (MR) is an eminent technology for problem solving and process optimization. The present research aimed to assess how users perceive an augmented reality (AR) application for diagnosis and intervention on industrial equipment. 18 participants with 3 different professional and technological backgrounds (general users (GU), information technology users (SD) and human centered design experts (HF)) took part in this study. Generally, the developed system was valued as slightly positive and some improvement points were identified. The results also revealed differences in the perceived User Experience (UX) between different user profiles. Also, there are important differences in perception depending on the person's analysis experience, with less rigor for new users and higher rigor for people who work with human factors, for example. This reinforce the concept of user centered design and the importance to understand the human being in its relation with the novel user interface and tendency to new technologies.

EXtended Reality (XR) has numerous applications in industrial contexts, including to assist in activities such as preventive maintenance and/or reactive interventions in machinery, wherein time-effectiveness is required to mitigate the costs of inactive production lines or the need to subcontract specialized technicians to perform those operations. However, developing an Augmented Reality (AR) application capable of being user-friendly and truly serviceable for aiding in the referred context requires keeping in mind human factors as key aspects and, as such, interaction must be a concern to address, namely, considering user feedback. Therefore, starting from a previous AR system oriented to industrial interventions that was developed and assessed with users and considering the feedback of the participant, the duly alterations were done and a new test was conducted, with a total of 27 participants, divided into 2 groups: 11 users who participated in the first experience and 16 general users who had never contacted with the solution before. A qualitative improvement in the user experience was noticed from the questionnaires feedback. Points such as fluidity, responsiveness, ease, speed, and intuitiveness were highlighted. Voice commands matched the tap commands in terms of user preferences.

The number of people with food allergies has been on the rise in recent years. Recent data estimate that between 1.1% and 10.8% of the global population suffer from food allergies. Confirming whether the corresponding allergic substances are present in the food is very important for people with allergic reactions. Through the investigation of allergens, we know that for people with allergies, the distribution of allergen information is scattered, it is relatively difficult to query, and there is also a lack of allergen information when eating out. In addition, with the gradual recovery of the tourism industry, for people with food allergies if they travel abroad, catering will become a problem for them. In order to face different situations and solve these problems, this article takes Japan as a tourist destination and collects allergen information scattered on various restaurant websites. Creates tables in MySQL, a database designed to unify the data, and the recommendation system accesses the database—a dataset of restaurant allergens with 340 menus in 13 restaurants. In the system, we search the database for foods and restaurants that meet the requirements according to the user's allergen information and preferences and recommend this information to the user as a reference. In order to test the function of the software and the effect of data collection, we used the software to conduct experiments on 30 Chinese people. The experiments assumed allergens according to the selection of allergens, regions, and dishes. From the results of the experimental data, 28 out of 30 people could find a suitable menu. Fundamental problems for users traveling, such as information confusion, language barriers, and lack of information when dining out, have been solved.