{"title":"A Task Allocation Method in Human-Robot Collaboration (HRC) for the Disassembly of Automotive Traction Batteries","authors":"Ya Liu, Zhigang Jiang, C. Ke","doi":"10.1109/ICCSI55536.2022.9970619","DOIUrl":"https://doi.org/10.1109/ICCSI55536.2022.9970619","url":null,"abstract":"With the development of information technology and intelligence, robots are involved in the disassembly process of end-of-life automotive traction battery recycling. The disassembly task allocation can realize the integration of high decision-making ability of human and high-level efficiency of robot, but the existing allocation lacks consideration of tasks and human-robot characteristics, which leads to unbalanced disassembly task allocation and low overall disassembly efficiency. In order to achieve efficient human-robot collaboration (HRC) disassembly, this paper proposes a human-robot collaborative task allocation method for automotive traction batteries considering disassembly complexity. Firstly, the physical and cognitive loads in the disassembly process are analyzed. Secondly, the disassembly complexity is quantified in terms of disassembly depth, disassembly process and decision process. Finally, disassembly task allocation model is constructed based on a multilayer perceptron neural network. The disassembly of Tesla Model 1s automotive traction battery is used as a case study to verify the effectiveness of the proposed method.","PeriodicalId":421514,"journal":{"name":"2022 International Conference on Cyber-Physical Social Intelligence (ICCSI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132193683","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shengrang Cao, Jun Wang, Xianchun Zhang, Huanyu Yang, Lingqi Kong, Jingzhuang Pang
{"title":"An Improved Method For Multi-agent Systems Avoiding Obstacle Based On Flocking Algorithm","authors":"Shengrang Cao, Jun Wang, Xianchun Zhang, Huanyu Yang, Lingqi Kong, Jingzhuang Pang","doi":"10.1109/ICCSI55536.2022.9970694","DOIUrl":"https://doi.org/10.1109/ICCSI55536.2022.9970694","url":null,"abstract":"In the traditional flocking algorithm, it is basically assumed that the properties of each agent are the same. In this paper, based on the flocking algorithm proposed by Olfati-Saber, the problem of individual differences of the agent is investigated. It is also found that when agents encounter a narrow intersection, it can fall into a local optimal solution causing stagnation due to the balance of the artificial potential field, so the obstacle avoidance of the flocking algorithm is improved to enable the agents to pass through such terrain smoothly and to reach convergence again after passing the terrain. It is demonstrated that the improved algorithm can perform the obstacle avoidance function through suitable parameter selection. Finally, computer simulations are given to verify the feasibility of the algorithm.","PeriodicalId":421514,"journal":{"name":"2022 International Conference on Cyber-Physical Social Intelligence (ICCSI)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132522733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dexu Zou, Yongjian Xiang, Qingjun Peng, Shan Wang, Yong Shi, Z. Hong, Weiju Dai, Tao Zhou
{"title":"Power Transformer Fault Diagnosis Method Based on Machine Learning","authors":"Dexu Zou, Yongjian Xiang, Qingjun Peng, Shan Wang, Yong Shi, Z. Hong, Weiju Dai, Tao Zhou","doi":"10.1109/ICCSI55536.2022.9970667","DOIUrl":"https://doi.org/10.1109/ICCSI55536.2022.9970667","url":null,"abstract":"Transformer is one of the most important power equipment in power systems. The normal operation of transformers is of great importance for the safety and stability of power grids. Therefore, transformer fault monitoring and diagnosis are very important to ensure the stability of power system. This paper summarizes the existing methods for transformer diagnosis. The traditional methods have some apparent disadvantages and limitations. These methods deal with static data and cannot be mapped to the objects at any time. This may cause a untimely detection and a big error. Therefore, a data-driven transformer fault diagnosis method is introduced to solve these problems. The paper summarizes the applications of expert learning, artificial neural network, support vector machine, deep learning and other machine learning methods in transformer fault diagnosis with the advantages and disadvantages of each method analyzed. And This paper summarizes the contribution of machine learning in transformer fault diagnosis. Finally, the paper summarizes and prospects the development of transformer fault diagnosis methods.","PeriodicalId":421514,"journal":{"name":"2022 International Conference on Cyber-Physical Social Intelligence (ICCSI)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114330293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ning Zhou, Zhao Liu, Haojie Yang, S. Meng, Dongming Zhao, Qifeng Sun
{"title":"Series-Parallel Active Damping to Improve the Robustness of Inverter in Weak Grid","authors":"Ning Zhou, Zhao Liu, Haojie Yang, S. Meng, Dongming Zhao, Qifeng Sun","doi":"10.1109/ICCSI55536.2022.9970654","DOIUrl":"https://doi.org/10.1109/ICCSI55536.2022.9970654","url":null,"abstract":"Since weak grid introduces non-negligible inductive line impedance, the parameters of grid connected inverter will change, which may lead to system collapse in serious cases. This paper proposes to add series-parallel active damping at Point of Common Coupling (PCC) that equivalents resistance characteristics in specific frequency band to suppress harmonic components. Compared with independent parallel active damping, series-parallel active damping introduces extra positive real part in correcting the equivalent output impedance of inverter. It can completely decouple the grid connected inverter and grid impedance within the control bandwidth. This method ensures the high modularity and passivity of output impedance and suppresses harmonics in a wide range. Finally, the effectiveness of the proposed strategy is verified by simulation and experimental results.","PeriodicalId":421514,"journal":{"name":"2022 International Conference on Cyber-Physical Social Intelligence (ICCSI)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127352015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Research on the Perception Method of Traffic Volume in Open Pit Mining Area Based on Yolov5 and Deepsort","authors":"Xiaoming Zhong, Dawei Li, Dawei Jiang, Wennan Yuan, Xuyang Qiu, Zeyu Liu","doi":"10.1109/ICCSI55536.2022.9970587","DOIUrl":"https://doi.org/10.1109/ICCSI55536.2022.9970587","url":null,"abstract":"The traffic volume of open-pit mining area is one of the indicators to measure the traffic saturation degree of open-pit mining area. Accurate perception of the traffic volume in the open-pit mining area can provide a basis for the dispatching and command of production scheduling and supervisal in the mining area, promote the improvement of transportation efficiency, enhance the transportation safety in the mining area, achieve intelligence for the construction of intelligent mine, and better meet the actual requirements of customers. On the scene of open-pit mining area, this paper uses the image acquisition module of RSU(roadside unit) at the height of the pit to detect traffic volume in open-pit mining area based on yolov5 and deepsort algorithm. The results of experiments show that this method can detect traffic volume accurately and effectively, and has strong robustness and good generalization ability.","PeriodicalId":421514,"journal":{"name":"2022 International Conference on Cyber-Physical Social Intelligence (ICCSI)","volume":"os-15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127764595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Air Collision Avoidance Method of Civil Aircraft Based on Reinforcement Learning","authors":"Jing Ruan, Shiqian Liu, Weizhi Lyu","doi":"10.1109/ICCSI55536.2022.9970657","DOIUrl":"https://doi.org/10.1109/ICCSI55536.2022.9970657","url":null,"abstract":"This paper studies on the high-density airspace route planning problem. A Q-Learning algorithm is proposed by considering the time series of states. Furthermore, a N-round loop algorithm is introduced to improve Q-Learning effectiveness for the large action space. Typical scenario simulations are carried out to illustrate the proposed algorithm performance, including a route collision with multiple aircrafts, no-fly zones and static obstacles. The simulation results validate feasibility and effectiveness of the proposed algorithm.","PeriodicalId":421514,"journal":{"name":"2022 International Conference on Cyber-Physical Social Intelligence (ICCSI)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121190222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xiaowen Yao, Lu Dong, J. Zhu, Wenyang Liu, A. Sheng, Z. Xing
{"title":"A Non-contact Monitoring System for Pantograph Slider Wear","authors":"Xiaowen Yao, Lu Dong, J. Zhu, Wenyang Liu, A. Sheng, Z. Xing","doi":"10.1109/ICCSI55536.2022.9970626","DOIUrl":"https://doi.org/10.1109/ICCSI55536.2022.9970626","url":null,"abstract":"The pantograph is mounted on the roof of the train and is an important electrical device that obtains power from the contact wire for train operation. Real-time monitoring of pantograph slider thickness is critical to ensure reliable train operation. However, the monitoring of pantograph slider thickness is challenging due to the complex dynamic environment of pantographs. In this paper, we propose a non-contact monitoring system for pantograph slider wear. First, the system installation scheme and workflow are introduced. Second, an image-based slider wear calculation method is presented. The slider wear is collected based on image processing algorithms such as image pre-processing, edge detection, and slider wear calculation. The system was installed in Guanhu metro station, Guangzhou Metro Line 13, and the performance of the system was evaluated using real-time pantograph images. The site results show that the presented system can inspect slider wear with good accuracy compared to the manual measurement value.","PeriodicalId":421514,"journal":{"name":"2022 International Conference on Cyber-Physical Social Intelligence (ICCSI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121315548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Research on Multi-Robot Cooperative Handling and Obstacle Avoidance Algorithm","authors":"Wucheng Zhou, Sheng Li, Yiming Chen","doi":"10.1109/ICCSI55536.2022.9970638","DOIUrl":"https://doi.org/10.1109/ICCSI55536.2022.9970638","url":null,"abstract":"In order to improve the efficiency and stability of multi-robot handling, inspired by stretcher handling, this paper is mainly aimed at obstacle avoidance and trajectory tracking in multi-robot handling of deformable sheet materials. When facing the obstacle avoidance problem in multi-robot handling, under the premise of ensuring stability, obstacle avoidance is achieved by improving the geometric obstacle avoidance control method based on the leader-follower formation control method while taking advantage of the characteristics of the deformable material. By improving the sliding mode variable structure control, the tracking of the respective target trajectory by each mobile robot is achieved, and the tracking error converges to zero. The simulation results show that the designed multi-robot cooperative handling algorithm can effectively achieve formation handline and obstacle avoidance.","PeriodicalId":421514,"journal":{"name":"2022 International Conference on Cyber-Physical Social Intelligence (ICCSI)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115403119","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jordan Strobing, Meghan Granit, Jiacun Wang, Lin Zhao
{"title":"Generalized Stochastic Petri Net Based Simulation of IoT Supported Dynamic Navigation in Teaching Building Evacuation","authors":"Jordan Strobing, Meghan Granit, Jiacun Wang, Lin Zhao","doi":"10.1109/ICCSI55536.2022.9970640","DOIUrl":"https://doi.org/10.1109/ICCSI55536.2022.9970640","url":null,"abstract":"Emergency management and evacuation efficiency is important to ensure the safety of faculty and students in college. Teaching buildings are typically of multiple stories. When classes are in session, a teaching building may have a large number of students inside. In case of an event like a fire, people have to be evacuated as soon as possible. Due to panic, people may not use good judgement to choose optimal evacuation path, which can further cause congestion in a path to an exit. This study attempts to leverage the recent advances in information technology to dynamically guide evacuees. We use generalized stochastic Petri nets (GSPN) to model the evacuation process in a teaching building. The layout of the building, sizes of classrooms and hallways, number of people in each room, and people's decision pattern in choosing a direction to move are all parameters of the model. With simulation we can estimate the evacuation time-span. Moreover, by observing the state of GSPN model, we can analyze the congestion status of each simulated pathway, and based on that we can dynamically notify people to select the right path that lead them to an exit with the least amount of time.","PeriodicalId":421514,"journal":{"name":"2022 International Conference on Cyber-Physical Social Intelligence (ICCSI)","volume":"163 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115972063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Forest Fire Detection Method Based on Deep Learning","authors":"Wenjie Wang, Qifu Huang, Haiping Liu, Yanxiang Jia, Qing Chen","doi":"10.1109/ICCSI55536.2022.9970702","DOIUrl":"https://doi.org/10.1109/ICCSI55536.2022.9970702","url":null,"abstract":"Forest fire causes irreparable damage to human beings and ecological environment with the big concealment and the difficulty to fight. However, conventional fire warning technologies suffer from relatively low sensitivity and accuracy. It's of great importance to detect the forest fire accurately in the budding stage. Herein, we reported a technology to improve the forest fire early warning capability. We analyzed common fire detection methods, studied the forest fire detection in combination with the deep learning technology. The calculation efficiency was improved by introduction of the data enhancement and feature enhancement methods. The lightweight real-time fire detection technology is realized by combination training the deep learning YOLO model and conducting experiments. And the results show that the proposed methods have high accuracy and sensitivity in flame data set.","PeriodicalId":421514,"journal":{"name":"2022 International Conference on Cyber-Physical Social Intelligence (ICCSI)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116648464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}