| 引用本文: | 李东东,赵 阳,赵 耀,蒋海涛.基于深度特征融合网络的风电机组行星齿轮箱故障诊断方法[J].电力系统保护与控制,2022,50(10):1-11.[点击复制] |
| LI Dongdong,ZHAO Yang,ZHAO Yao,JIANG Haitao.A fault diagnosis method for a wind turbine planetary gearbox based on a deep feature fusion network[J].Power System Protection and Control,2022,50(10):1-11[点击复制] |
|
| 摘要: |
| 行星齿轮箱是风电机组中的重要部件，对风电机组的安全可靠运行具有重要意义。为此，提出一种基于深度特征融合网络的行星齿轮箱故障诊断方法，用于实现变速工况、样本不足和强噪声场景下的故障诊断。首先将原始信号扩展到多个特征域。其次利用多维堆栈稀疏自编码器提取各域特征。最后针对传统Softmax分类器对融合信息分类能力不足的问题，提出基于竞争粒子群算法优化的回声状态网络进行特征融合并输出诊断结果。经多场景不同故障诊断方法对比实验，所提方法在行星齿轮箱变速工况下分类效果良好，并对训练样本的减少和外界噪声有很强的鲁棒性。 |
| 关键词: 行星齿轮箱 故障诊断 多场景 深度学习 堆栈稀疏自编码器 回声状态网络 深度特征融合网络 |
| DOI：DOI: 10.19783/j.cnki.pspc.210919 |
| 投稿时间：2021-07-18修订日期：2021-08-26 |
| 基金项目:国家自然科学基金项目资助(51977128)；上海市青年科技启明星计划项目资助(21QC1400200)；上海市自然科学基金项目资助(21ZR1425400) |
|
| A fault diagnosis method for a wind turbine planetary gearbox based on a deep feature fusion network |
| LI Dongdong,ZHAO Yang,ZHAO Yao,JIANG Haitao |
| (College of Electrical Engineering, Shanghai University of Electric Power, Shanghai 200090, China) |
| Abstract: |
| The planetary gearbox is a critical part of a wind turbine. It is of great significance for safety and reliability. Therefore, a fault diagnosis method for a planetary gearbox based on a deep feature fusion network is proposed to operate under variable speed conditions, with limited numbers of samples and in strong noise scenarios. First, the original signal is expanded into multiple characteristic domains. Then a multi-dimensional stack sparse autoencoder is used to extract the features of each domain. Finally, to solve the problem that the traditional Softmax classifier is not capable of classifying the fusion information, an echo state network optimized by competitive swarm optimizer is proposed to perform feature fusion and output the diagnostic results. The experimental results of fault diagnosis in multiple scenarios show that the proposed method has a good classification performance in variable speed conditions. In addition, it is also robust to a reduction in the number of training samples and external noise.
This work is supported by the National Natural Science Foundation of China (No. 51977128). |
| Key words: planetary gearbox fault diagnosis multiple scenarios deep learning stack sparse autoencoder echo state network deep feature fusion network |
