基于STOA-XGBoost的风电机组滚动轴承故障诊断

Wind Turbine Rolling Bearing Fault Diagnosis Based on STOA-XGBoost

为保证风电机组的正常运行,提高风电机组滚动轴承故障诊断的可靠性,提出了一种基于STOA-XGBoost的风电机组滚动轴承故障诊断方法,提取振动信号时域特征作为故障特征,使用乌燕鸥优化算法对极端梯度提升树的超参数进行优化,提高模型的泛化能力和预测精度,利用训练好的模型进行故障诊断。实例表明,此诊断模型可以更加高效地识别风电机组滚动轴承故障。

The proposed method for rolling bearing fault diagnosis in wind turbines is based on STOA-XGBoost,aiming to ensure the smooth operation of wind turbines and enhance the reliability of the diagnostic process.Initially,fault characteristics are extracted from vibration signals through time-domain analysis.The Ultern optimization algorithm is employed to optimize hyperparameters of the extreme gradient lifting tree,so as to promote model generalization and prediction accuracy.Subsequently,the trained model is utilized for efficient fault diagnosis in wind turbines.Experimental results demonstrate that the proposed diagnostic model effectively identifies rolling bearing faults.