A novel multi-class classifier with kernels, namely kernel Subspace Methods (KSPM), was presented, and a multi-fault classifier based on the algorithm was constructed.
提出了一种基于核的多类别模式识别算法(简称核子空间法，KSPM)，依据此算法建立了多故障分类器。
Training the multi-fault classifier only needs a small quantity of fault data samples in time domain, and does not need signal preprocessing for extracting signal features.
应用结果表明，不必进行信号预处理以提取特征量，只需要用少量的时域故障数据样本建立故障分类器。
The twin screw extruder fault diagnosis by multi-fault classifier based on SVM is mainly discussed and the retest proves that this SVM really has preferable ability of classification.
诊断实例表明，基于支持向量机的多故障分类器对设备故障具有很好的分类效果。
应用推荐