高压电器2025，Vol.61Issue(5)：170-178,9.DOI:10.13296/j.1001-1609.hva.2025.05.018
基于堆叠降噪自编码网络和多源数据加权融合的发电机故障诊断方法
Fault Diagnosis Method of Generator Based on Stacked Denoising Autoencoder Network and Multi-source Data Weighted Fusion
摘要
Abstract
With the continuous increase of units involving in the regulation in power system and the gradual increase in the proportion of industrial load,a sole data source has no way to meet the accuracy requirement of on-line moni-toring of unit status in modern power systems.Therefore,in this paper a kind of condition monitoring method of gen-erator is proposed in combination with a stacked denoising autoencoder network and multi-source data fusion technol-ogy.Firstly,a SCADA-PMU data fusion method based on weighted D-S evidence theory is proposed.Then,the auto-encoder technology is introduced to construct a staked denoising autoencoder deep learning network model,extract deep features from the training dataset to construct the fault detection model of generator.Finally,the fault determina-tion is achieved by smoothing reconstruction errors and detecting trend variation in monitored parameters using an adaptive threshold.The simulation results show that the method proposed in this paper,compared to traditional meth-od based on a sole data source,has superior robustness and accuracy,thereby enhancing the precision of fault diagno-sis and condition monitoring of generator.关键词
D-S证据理论/堆叠降噪自编码网络/故障诊断/状态检测Key words
D-S evidence theory/stacked denoising autoencoder network/fault diagnosis/condition monitoring引用本文复制引用
邢超,马红升,覃日升,张明强,鄢晶,刘焱..基于堆叠降噪自编码网络和多源数据加权融合的发电机故障诊断方法[J].高压电器,2025,61(5):170-178,9.基金项目
国家自然科学基金项目(52067009).Project Supported by National Natural Science Foundation of China(52067009). （52067009）
