{"title":"基于概率神经网络的ZPW-2000轨道电路衰减器性能分类","authors":"Minggui Huang","doi":"10.1145/3495018.3495070","DOIUrl":null,"url":null,"abstract":"ZPW-2000 uninsulated frequency-shifted rail circuit equipment requires manual testing of electrical parameters in daily maintenance work, resulting in high labor intensity and low work efficiency of maintenance personnel in the field. The intelligent ZPW-2000 track circuit attenuator designed in this article can monitor and display the relevant parameters and equipment status of the track circuit in real time, so that maintenance personnel can directly view the information of the equipment without tedious operation, which can improve maintenance efficiency and equipment reliability. Safety of railroad operation can be ensured. Fault diagnosis of rail circuits is of great importance for the safe operation of railroad operations. First of all, the parameters are collected by using the track circuit wearer and the data are divided into 5 classes according to the existing maintenance experience. The performance classes of the track circuits were diagnosed using probabilistic fault neural networks (PNN). The experimental results show that the correct rate reaches more than 95% and achieves good results, which provides theoretical basis and practical experience for the maintenance of railroad turnout system and improvement of turnout performance.","PeriodicalId":6873,"journal":{"name":"2021 3rd International Conference on Artificial Intelligence and Advanced Manufacture","volume":"130 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Performance Class Classification of ZPW-2000 Track Circuit Attenuator Based on Probabilistic Neural Network\",\"authors\":\"Minggui Huang\",\"doi\":\"10.1145/3495018.3495070\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"ZPW-2000 uninsulated frequency-shifted rail circuit equipment requires manual testing of electrical parameters in daily maintenance work, resulting in high labor intensity and low work efficiency of maintenance personnel in the field. The intelligent ZPW-2000 track circuit attenuator designed in this article can monitor and display the relevant parameters and equipment status of the track circuit in real time, so that maintenance personnel can directly view the information of the equipment without tedious operation, which can improve maintenance efficiency and equipment reliability. Safety of railroad operation can be ensured. Fault diagnosis of rail circuits is of great importance for the safe operation of railroad operations. First of all, the parameters are collected by using the track circuit wearer and the data are divided into 5 classes according to the existing maintenance experience. The performance classes of the track circuits were diagnosed using probabilistic fault neural networks (PNN). The experimental results show that the correct rate reaches more than 95% and achieves good results, which provides theoretical basis and practical experience for the maintenance of railroad turnout system and improvement of turnout performance.\",\"PeriodicalId\":6873,\"journal\":{\"name\":\"2021 3rd International Conference on Artificial Intelligence and Advanced Manufacture\",\"volume\":\"130 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-10-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 3rd International Conference on Artificial Intelligence and Advanced Manufacture\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3495018.3495070\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 3rd International Conference on Artificial Intelligence and Advanced Manufacture","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3495018.3495070","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Performance Class Classification of ZPW-2000 Track Circuit Attenuator Based on Probabilistic Neural Network
ZPW-2000 uninsulated frequency-shifted rail circuit equipment requires manual testing of electrical parameters in daily maintenance work, resulting in high labor intensity and low work efficiency of maintenance personnel in the field. The intelligent ZPW-2000 track circuit attenuator designed in this article can monitor and display the relevant parameters and equipment status of the track circuit in real time, so that maintenance personnel can directly view the information of the equipment without tedious operation, which can improve maintenance efficiency and equipment reliability. Safety of railroad operation can be ensured. Fault diagnosis of rail circuits is of great importance for the safe operation of railroad operations. First of all, the parameters are collected by using the track circuit wearer and the data are divided into 5 classes according to the existing maintenance experience. The performance classes of the track circuits were diagnosed using probabilistic fault neural networks (PNN). The experimental results show that the correct rate reaches more than 95% and achieves good results, which provides theoretical basis and practical experience for the maintenance of railroad turnout system and improvement of turnout performance.