| 引用本文: | 孙 章,金炜东,吴 帆,等.考虑非平稳特性的Vienna整流器鲁棒故障诊断方法[J].电力系统保护与控制,2025,53(17):102-113. |
| SUN Zhang,JIN Weidong,WU Fan,et al.Robust fault diagnosis method for Vienna rectifiers considering non-stationary characteristics[J].Power System Protection and Control,2025,53(17):102-113 |
|
| 摘要: |
| Vienna整流器开路故障信号具有非平稳特性，并且易受传感器噪声、基准偏移和负载变化的干扰，导致传统故障诊断方法的精度降低。因此，提出一种基于重要特征提取和改进随机森林故障诊断方法，用于提高Vienna整流器开路故障诊断的精度与鲁棒性。首先分析了Vienna整流器开路故障信号的非平稳特性及其产生机理。然后定义最优离散小波变换聚焦信号细节，实现多尺度故障特征提取。同时考虑特征的相互影响，采用改进的ReliefF算法优选重要特征。在此基础上，提出鲁棒精度加权的随机森林算法，表征重要故障特征与故障类别的映射关系，通过袋外(out-of-bag, OOB)数据的噪声鲁棒测试，调整决策树的投票权重，从而增强故障诊断的精度与鲁棒性。最后通过对比实验结果表明：所提方法具有鲁棒非平稳变化的能力，准确率可达99.84%。 |
| 关键词: Vienna整流器 故障诊断 特征提取 随机森林 非平稳特性 |
| DOI：10.19783/j.cnki.pspc.240924 |
| 分类号: |
| 基金项目:国家自然科学基金青年基金项目资助(62203368) |
|
| Robust fault diagnosis method for Vienna rectifiers considering non-stationary characteristics |
|
SUN Zhang1, JIN Weidong1, WU Fan2, ZHANG Youhua3, WU Yunpu3
|
|
1. School of Electrical Engineering, Southwest Jiaotong University, Chengdu 611756, China; 2. School of Automation
Engineering, University of Electronic Science and Technology of China, Chengdu 610095, China; 3. School of
Electrical Engineering and Electronic Information, Xihua University, Chengdu 610039, China
|
| Abstract: |
| The open-circuit fault signals of Vienna rectifiers exhibit non-stationary characteristics and are susceptible to sensor noise, reference offset, and load variations, which reduces the performance of traditional fault diagnosis methods. To address this, a fault diagnosis method based on significant feature extraction and improved random forests is proposed to improve the open-circuit fault diagnosis accuracy and robustness of Vienna rectifiers. First, the non-stationary characteristics and underlying mechanisms of open-circuit fault signals in Vienna rectifiers are analyzed. Then, an optimal discrete wavelet transform is defined to focuse on signal details, enabling multi-scale fault feature extraction. Meanwhile, considering the mutual effects of the features, the improved ReliefF algorithm is employed to select the most important features. On this basis, a robust accuracy-weighted random forest algorithm is utilized to map important fault features to fault categories. By performing noise robustness testing with the out-of-bag (OOB) data, the voting weights of decision trees are adjusted, thereby enhancing the accuracy and robustness of the fault diagnosis method. Finally, comparative experimental results show that the proposed method is robust to non-stationary variations and achieves an accuracy rate of 99.84%. |
| Key words: Vienna rectifier fault diagnosis feature extraction random forest non-stationary characteristics |
