• Home|About JOPS|Editorial Board| Ethics Statement|Indexed-in|Contact us|Peer Review|Chinese
Latest Papers more>>
ZHAO Danyang,DONG Weiguang,GAO Fengyang.Improved Inverter Fault Diagnosis Based on Convolutional Neural Network[J].JOURNAL OF POWER SUPPLY,2020,18(3):124-132
Improved Inverter Fault Diagnosis Based on Convolutional Neural Network
Received:September 18, 2018  Revised:December 12, 2018
View Full Text  View/Add Comment  Download reader
DOI:10.13234/j.issn.2095-2805.2020.3.124
Keywords:inverter  fault diagnosis  regularization  adaptive regularization coefficient  convolutional neural network
Fund Project:The National Basic Research Program of China (973 Program)
        
AuthorInstitutionEmail
ZHAO Danyang School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou , China
DONG Weiguang School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou , China
GAO Fengyang School of Automation and Electrical Engineering, Lanzhou Jiaotong University, Lanzhou , China
Hits: 191
Download times: 327
Abstract:
      In view of the low diagnostic efficiency and low accuracy of the traditional diode clamping three-level inverter fault diagnosis method, adaptive regularization coefficient is introduced into convolutional neural network(CNN) for the inverter fault diagnosis. In the de-fitting of the traditional CNN model with the introduction of regularization, the regularization coefficient often uses global unified constant parameters; meanwhile, it is necessary to continuously try and fail in the training process but with little effect. To solve this problem, adaptive adjustment of regularization coefficient is proposed according to the gradient change in the target loss function to speed up the convergence speed of the CNN model in the inverter fault diagnosis, enhance the model’s generalization capability, and improve the accuracy of fault identification. Experimental results show that compared with the traditional BP neural network and the original CNN model, the improved CNN model can make a real-time and accurate diagnosis of the complex fault of the inverter.
Close