Abstract

Aimed at the difficulty in fault diagnosis of wind turbine transmission system under variable working conditions, the paper proposes a novel health condition monitoring method based on correlative features domain adaptation. Firstly, the envelope analysis of the collected signals is carried out, and the time–frequency features of the signals are extracted to construct the feature set. The feature sets under the similar working conditions to target are selected as the auxiliary sample sets in source domain through the transferability evaluation. Then, a transformation matrix is found to adapt the marginal and conditional distributions of wind turbine sample data under different working conditions, and its weight is adjusted. While reducing the discrepancy between domains, the class imbalance problem is taken into consideration, so as to improve the accuracy of fault diagnosis under the target working condition. Finally, the classifier is trained with the adjusted source domain and tested in the target domain. Experiments show that the proposed method can effectively improve the accuracy of wind turbine fault diagnosis.

Graphic Abstract

中文翻译：

---

基于相关特征域自适应的新型风轮机健康状况监测方法

摘要

针对风力发电机组变工况下故障诊断的难点，提出了一种基于相关特征域自适应的健康状态监测新方法。首先，对采集到的信号进行包络分析，提取信号的时频特征以构建特征集。通过可转移性评估，选择与目标工作条件相似的特征集作为源域中的辅助样本集。然后，找到一个变换矩阵，以适应不同工作条件下风力涡轮机样本数据的边际和条件分布，并调整其权重。在减少域之间的差异的同时，考虑了类不平衡问题，从而提高目标工况下故障诊断的准确性。最后，分类器在调整后的源域中进行训练，并在目标域中进行测试。实验表明，该方法可以有效提高风机故障诊断的准确性。

图形摘要