Research on the hybrid Fault Diagnosis Approach Based on Artificial Immune Algorithm

A hybrid fault diagnosis approach is proposed, combining the real-valued negative selection (RNS) algorithm and the support vector machine (SVM), after researching the shortcoming of the conventional classification algorithm in the fault diagnosis. In the new method, the RNS algorithm is used to generate the detector (non-self) as the unknown fault samples, which are used as input to SVM algorithm for training purpose. The problem, lacking the training samples, is solved to use the new method on the conventional classification algorithm. At last, this hybrid approach is compared against SVM algorithm through the experiment to classify the Iris data set. The classification correct rate of the new method is above 90%, so it is valid to the fault diagnosis.