容错度因子, 增量学习, 支持向量机, 多分类, 故障诊断

 ,

According to poor performance of the traditional method in large dataset and strong noise environment, the various kinds of fault class and atrocious work conditions of hydraulic pumps,a novel state recognition method called fault-tolerant adaptive SVM (FTASVM) was proposed herein. It achieved a fast classification by: ①importing fault-tolerant;②selecting the binary SVMs which can divide one class from all other classes; ③selecting the binary SVMs with the fewest average number of support vectors (SVs); ④To improve the adaptability of multi-fault diagnosis,an incremental learning algorithm was imported to train the model. In order to verify the superiority of FTASVM , it was applied to the fault diagnosis of hydraulic pump of concrete pump truck. Experiments demonstrate FTASVM can speed up the test phase remarkably and remain the high accuracy of classification.