With the development of information theory and image analysis theory, the studies on fault diagnosis methods based on image processing have become a hot spot in the recent years in the field of fault diagnosis. The gearbox of wind turbine generator is a fault-prone subassembly. Its time frequency of vibration signals contains abundant status information, so this paper proposes a fault diagnosis method based on time-frequency image characteristic extraction and artificial immune algorithm. Firstly, obtain the time-frequency image using wavelet transform based on threshold denoising. Secondly, acquire time-frequency image characteristics by means of Hu invariant moment and correlation fusion gray-level co-occurrence matrix of characteristic value, thus, to extract the fault information of the gearing of wind turbine generator. Lastly, diagnose the fault type using the improved actual-value negative selection algorithm. The application of this method in the gear fault diagnosis on the test bed of wind turbine step-up gearbox proves that it is effective in the improvement of diagnosis accuracy.

中文翻译：

---

基于图像特征提取和实值负选择算法的风电齿轮箱故障诊断方法

随着信息论和图像分析理论的发展，基于图像处理的故障诊断方法的研究成为近年来故障诊断领域的热点。风力发电机的齿轮箱是一个容易出现故障的组件。其振动信号的时频包含丰富的状态信息，因此本文提出了一种基于时频图像特征提取和人工免疫算法的故障诊断方法。首先，利用基于阈值去噪的小波变换得到时频图像。其次，利用Hu不变矩和特征值的相关融合灰度共生矩阵获取时频图像特征，从而提取风力发电机传动装置的故障信息。最后，使用改进的实际值负选择算法诊断故障类型。该方法在风力发电机升压箱试验台齿轮故障诊断中的应用证明其对提高诊断精度是有效的。