{"title":"LED device fault diagnosis base on neural network and SVM model analysis","authors":"Haisu Jiang, Qingzhong Ma, Fuqin Yang, Mingming Shen","doi":"10.1109/IFWS.2017.8245971","DOIUrl":null,"url":null,"abstract":"LED as the 4th generation new energy lighting device, it is widely used in many lighting fields with its green environmental protection, energy saving, long life and high reliability. It is of great significance to study the common fault diagnosis technology of LED devicesto determine the fault point and improve the design of LED devices. This article from the common failure mode of the LED devices, combined with the monitoring the related parameters of the LED devices, use based on BP neural network and SVM algorithm, analyze the fault diagnosis of LED Devices, concluded from the results, the SVM method in effective under the condition of small sample has good diagnosis effect.","PeriodicalId":131675,"journal":{"name":"2017 14th China International Forum on Solid State Lighting: International Forum on Wide Bandgap Semiconductors China (SSLChina: IFWS)","volume":"237 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 14th China International Forum on Solid State Lighting: International Forum on Wide Bandgap Semiconductors China (SSLChina: IFWS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IFWS.2017.8245971","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
LED as the 4th generation new energy lighting device, it is widely used in many lighting fields with its green environmental protection, energy saving, long life and high reliability. It is of great significance to study the common fault diagnosis technology of LED devicesto determine the fault point and improve the design of LED devices. This article from the common failure mode of the LED devices, combined with the monitoring the related parameters of the LED devices, use based on BP neural network and SVM algorithm, analyze the fault diagnosis of LED Devices, concluded from the results, the SVM method in effective under the condition of small sample has good diagnosis effect.