当前位置: X-MOL 学术Front. Energy Res. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Cost-sensitive LightGBM based Online Fault Detection Method for Wind Turbine Gearboxes
Frontiers in Energy Research ( IF 3.4 ) Pub Date : 2021-06-30 , DOI: 10.3389/fenrg.2021.701574
Mingzhu Tang , Qi Zhao , Huawei Wu , Zimin Wang

In practice, fault samples of wind turbine (WT) gearboxes are far smaller than normal samples during operation, and most of existing fault diagnosis methods for WT gearboxes only focusing on the improvement of classification accuracy, ignore the decrease of missed alarms and reduction of the average cost. To this end, a new framework is proposed through combining Spearman rank correlation feature extraction and cost-sensitive LightGBM algorithm for WT gearboxes fault detection. In this paper, features from wind turbines supervisory control and data acquisition (SCADA) systems are firstly extracted. Then the feature selection is employed by using the expert experience and Spearman rank correlation coefficient to analyze the correlation between the big data of WT gearboxes. Moreover, the cost-sensitive LightGBM fault detection framework is established by optimizing the misclassification cost. The false alarm rate and the miss detection rate of the WT gearbox under different working conditions are finally obtained. Experiments have demonstrated that the proposed method can significantly improve the fault detection accuracy. Meanwhile, the proposed method can consistently outperform traditional classifiers such as Adacost, cost-sensitive GBDT and cost-sensitive XGBoost in terms of low false alarm rate and miss detection rate. Owing to its high Matthews correlation coefficient scores, low average misclassification cost, cost-sensitive LightGBM (CS-LightGBM) method is preferred for imbalanced WT gearbox fault detection in practice.

中文翻译:

基于成本敏感的LightGBM的风电齿轮箱在线故障检测方法

在实践中,风电机组(WT)齿轮箱在运行过程中的故障样本远小于正常样本,现有的WT齿轮箱故障诊断方法大多只注重提高分类精度,忽略了漏报的减少和故障率的降低。平均成本。为此,通过结合Spearman秩相关特征提取和成本敏感的LightGBM算法,提出了一种用于WT齿轮箱故障检测的新框架。在本文中,首先提取了风力涡轮机监控和数据采集 (SCADA) 系统的特征。然后利用专家经验和Spearman秩相关系数进行特征选择,分析WT齿轮箱大数据之间的相关性。而且,通过优化误分类成本建立了成本敏感的LightGBM故障检测框架。最终得到WT齿轮箱在不同工况下的误报率和漏检率。实验表明,所提出的方法可以显着提高故障检测的准确性。同时,所提出的方法在低误报率和漏检率方面始终优于传统分类器,如 Adacost、成本敏感的 GBDT 和成本敏感的 XGBoost。由于其高 Matthews 相关系数得分、低平均误分类成本,成本敏感的 LightGBM (CS-LightGBM) 方法在实践中是不平衡 WT 齿轮箱故障检测的首选方法。最终得到WT齿轮箱在不同工况下的误报率和漏检率。实验表明,所提出的方法可以显着提高故障检测的准确性。同时,所提出的方法在低误报率和漏检率方面始终优于传统分类器,如 Adacost、成本敏感的 GBDT 和成本敏感的 XGBoost。由于其高 Matthews 相关系数得分、低平均误分类成本,成本敏感的 LightGBM (CS-LightGBM) 方法在实践中是不平衡 WT 齿轮箱故障检测的首选方法。最终得到WT齿轮箱在不同工况下的误报率和漏检率。实验表明,所提出的方法可以显着提高故障检测的准确性。同时,所提出的方法在低误报率和漏检率方面始终优于传统分类器,如 Adacost、成本敏感的 GBDT 和成本敏感的 XGBoost。由于其高 Matthews 相关系数得分、低平均误分类成本,成本敏感的 LightGBM (CS-LightGBM) 方法在实践中是不平衡 WT 齿轮箱故障检测的首选方法。所提出的方法在低误报率和漏检率方面始终优于传统分类器,如 Adacost、成本敏感的 GBDT 和成本敏感的 XGBoost。由于其高 Matthews 相关系数得分、低平均误分类成本,成本敏感的 LightGBM (CS-LightGBM) 方法在实践中是不平衡 WT 齿轮箱故障检测的首选方法。所提出的方法在低误报率和漏检率方面始终优于传统分类器,如 Adacost、成本敏感的 GBDT 和成本敏感的 XGBoost。由于其高 Matthews 相关系数得分、低平均误分类成本,成本敏感的 LightGBM (CS-LightGBM) 方法在实践中是不平衡 WT 齿轮箱故障检测的首选方法。
更新日期:2021-06-30
down
wechat
bug