| 引用本文: | 孙 抗,李腾飞,王 浩,杨 明,赵来军.基于双分支-交叉注意力融合的风电齿轮箱故障诊断方法[J].电力系统保护与控制,2026,54(01):83-93.[点击复制] |
| SUN Kang,LI Tengfei,WANG Hao,YANG Ming,ZHAO Laijun.Wind turbine gearbox fault diagnosis method based on dual-branch cross-attention fusion[J].Power System Protection and Control,2026,54(01):83-93[点击复制] |
|
| 摘要: |
| 针对风电齿轮箱故障诊断数据存在时序性和单通道模型难以有效提取复合故障特征信息的问题，提出一种基于改进正交卷积胶囊网络(orthogonal convolutional capsule network, OCCN)和双向长短期记忆神经网络(bi-directional long short-term memory, BiLSTM)融合的故障诊断方法。首先，对原始信号进行预处理。其次，将经过预处理操作后的信号输入构建的OCCN-BiLSTM双通道模型中，分别提取复合故障特征的空间特征、时域特征。最后将提取的时空特征通过交叉注意力机制进行特征融合，输入到全连接层中进行信号的分类，实现风电齿轮箱智能故障诊断。试验结果表明，所提诊断方法可有效实现风电齿轮箱智能故障诊断，其在测试集上的准确率达到99.53%。 |
| 关键词: 故障诊断 胶囊网络 并行双通道 特征融合 风电齿轮箱 |
| DOI：10.19783/j.cnki.pspc.250397 |
| 投稿时间：2025-04-13修订日期：2025-07-20 |
| 基金项目:国家自然科学基金项目资助(U1804143)；河南省科技攻关计划项目资助(242102241056) |
|
| Wind turbine gearbox fault diagnosis method based on dual-branch cross-attention fusion |
| SUN Kang,LI Tengfei,WANG Hao,YANG Ming,ZHAO Laijun |
| (School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo 454003, China) |
| Abstract: |
| Aiming at the problems that fault diagnosis data of wind turbine gearboxes have time series and the single-channel model is difficult to effectively extract the composite fault feature information, a fault diagnosis method integrating an improved orthogonal convolutional capsule network (OCCN) and a bidirectional long short-term memory neural network (BiLSTM) is proposed. First, the original signals are preprocessed. Then, the preprocessed signals are fed into a constructed OCCN-BiLSTM dual-branch model to extract the spatial features and time domain features of composite faults, respectively. Finally, the extracted spatiotemporal features are fused through a cross-attention mechanism and input into a fully connected layer for signal classification, enabling intelligent fault diagnosis of wind turbine gearboxes. Experimental results show that the proposed diagnosis method can effectively achieve intelligent fault diagnosis for wind turbine gearboxes, with an accuracy of 99.53% on the test set. |
| Key words: fault diagnosis capsule network parallel dual-channel architecture feature fusion wind turbine gearbox |
