{"title":"Prediction method of dedicated power supply for tank commander panoramic based on grey Markov model optimized by PSO","authors":"Yingshun Li, Yu Xiao, X. Yi","doi":"10.1109/SDPC.2019.00043","DOIUrl":null,"url":null,"abstract":"Electrical equipment failure is a monotonous process with a sudden change in performance due to its own life cycle and a sudden change in state deterioration. Taking the dedicated power supply for tank commander panoramic of a certain type tank as the research object. The concepts of grey prediction model and Markov model are introduced. The Markov model is used to classify the residuals of the grey GM(1,1) prediction model, and the state transition matrix is determined. The particle swarm optimization algorithm is used to find the whitening coefficient of the Markov model residual state, and the grey Markov model of particle swarm optimization is established.The dedicated power supply for tank commander panoramic measurement values (highest value, lowest value, median value) are predicted. The results show that the optimized prediction results are better than the original gray GM (1,1) and gray Markov prediction methods. With the increase of the working time of the dedicated power supply of the dedicated power supply for tank commander panoramic, the trend of relative error occurrence state transition is more stable, the accuracy of prediction will be further improved, and the equipment can predict and maintain a certain value for maintenance work.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SDPC.2019.00043","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Electrical equipment failure is a monotonous process with a sudden change in performance due to its own life cycle and a sudden change in state deterioration. Taking the dedicated power supply for tank commander panoramic of a certain type tank as the research object. The concepts of grey prediction model and Markov model are introduced. The Markov model is used to classify the residuals of the grey GM(1,1) prediction model, and the state transition matrix is determined. The particle swarm optimization algorithm is used to find the whitening coefficient of the Markov model residual state, and the grey Markov model of particle swarm optimization is established.The dedicated power supply for tank commander panoramic measurement values (highest value, lowest value, median value) are predicted. The results show that the optimized prediction results are better than the original gray GM (1,1) and gray Markov prediction methods. With the increase of the working time of the dedicated power supply of the dedicated power supply for tank commander panoramic, the trend of relative error occurrence state transition is more stable, the accuracy of prediction will be further improved, and the equipment can predict and maintain a certain value for maintenance work.