南方电网技术2018，Vol.12Issue(10)：14-19,6.DOI:10.13648/j.cnki.issn1674-0629.2018.10.003
基于自适应深度学习模型的变压器故障诊断方法
Fault Diagnosis Method of Transformer Based on Adaptive Deep Learning Model
摘要
Abstract
In order to improve the accuracy of transformer fault diagnosis, a transformer fault diagnosis method based on adaptive deep learning model is proposed. The method uses dissolved gas in oil as fault diagnosis feature, and builds diagnostic model based on deep learning theory. To solve the shortcomings of slowconvergence speed and lowconvergence precision in the training process of traditional fixed learning rate based deep learning model, an adaptive deep learning model construction method is proposed. This method adaptively adjusts the learning rate according to the changing characteristics of the iterative process, and effectively improves the training accuracy and speed of the deep learning model. Parameters of adaptive deep learning model for transformer fault diagnosis such as hidden layer number, learning rate adjustment coefficient are proposed. The experimental results showthat the proposed method has a strong ability of feature extraction and analysis and has better convergence speed and convergence precision, which can effectively improve the accuracy of transformer fault diagnosis.关键词
变压器/故障诊断/自适应/深度学习模型Key words
transformer/fault diagnosis/adaptive/deep learning model分类
信息技术与安全科学引用本文复制引用
牟善仲,徐天赐,符奥,王萌,白茹..基于自适应深度学习模型的变压器故障诊断方法[J].南方电网技术,2018,12(10):14-19,6.基金项目
国家电网公司科技项目 (GY71-17-031). （GY71-17-031）
