Fault diagnosis method for ship electric driving system based on wavelet analysis

The invention provides a fault diagnosis method for a ship electric driving system based on wavelet analysis. Scale transformation and wavelet transformation of sensor data are used for filtering optimal areas with rich information, fault types are maximally separated, then data of the areas is subjected to characteristic extraction and used for training a classifier for fault diagnosis, the diagnosis accuracy can be improved accordingly, and the computation complexity of the classifier is lowered. Compared with the prior art, the fault diagnosis method has the advantages of high correct classification rate, low false alarm rate and low detection omission rate. 本发明提出了种船舶电力驱动系统故障诊断的方法，利用传感器数据的尺度转换以及小波变换来过滤最佳的信息丰富的区域，使故障类别分离最大化，然后利用这些区域的数据进行特征提取，并用于分类器训练进行故障诊断，这样可以提高诊断的准确性，降低分类器的计算复杂度。与现有技术相比，具有较高的正确分类率，误报率低，漏检率低。