| 引用本文: | 石 鑫,朱永利,宁晓光,王刘旺,孙 岗,陈国强.基于深度自编码网络的电力变压器故障诊断[J].电力自动化设备,2016,36(5): |
| SHI Xin,ZHU Yongli,NING Xiaoguang,WANG Liuwang,SUN Gang,CHEN Guoqiang.Transformer fault diagnosis based on deep auto-encoder network[J].Electric Power Automation Equipment,2016,36(5): |
|
| 摘要: |
| 基于深度自编码网络（DAEN），构建了分类深度自编码网络（CDAEN）模型。结合电力变压器在线监测油中溶解气体分析（DGA）数据，提出了基于CDAEN的变压器故障诊断方法。所提方法利用大量无标签样本进行预训练，优化模型参数，并利用少量有标签样本进行微调。实例分析表明，与基于反向传播神经网络（BPNN）、支持向量机（SVM）的故障诊断方法相比，所提方法的诊断正确率更高。 |
| 关键词: 深度自编码网络 电力变压器 故障诊断 油中溶解气体分析 反向传播神经网络 支持向量机 |
| DOI： |
| 分类号: |
| 基金项目: |
|
| Transformer fault diagnosis based on deep auto-encoder network |
|
SHI Xin1, ZHU Yongli1, NING Xiaoguang1, WANG Liuwang1, SUN Gang2, CHEN Guoqiang2
|
|
1.School of Control and Computer Engineering，North China Electric Power University，Baoding 071003，China;2.State Grid Corporation of China，Beijing 100031，China
|
| Abstract: |
| A CDAEN（Classified Deep Auto-Encoder Network） model is built based on the DAEN（Deep Auto-Encoder Network）. Combined with the on-line monitored data of DGA（Dissolved Gas-in-oil Analysis） for power transformer，a method of transformer fault diagnosis based on CDEAN is proposed，which optimizes the parameters of CDAEN model by the pre-training with massive unlabeled samples and adjusts them with a few labeled samples. Results of case analysis show that the proposed method has higher diagnosis accuracy than those based on the BPNN（Back Propagation Neural Network） and the SVM（Support Vector Machine）. |
| Key words: deep auto-encoder network power transformers fault diagnosis dissolved gas-in-oil analysis back propagation neural network support vector machines |
