A New Fault Diagnosis Method Based on Immune Model

An immune-based model is proposed to accomplish a non-linear mapping from feature space to a two dimensional classification space in fault diagnosis. The mapping is conducted to create the best cluster effect for training samples belonging to the same class. Especially artificial immune regulation (AIR) scheme used to generate automatically the antibodies (memory B-cells) in the model is explained in detail. Finally the numerical experiments in fault diagnosis of a tapered roller bearing are performed. The results show that the method is simple and effective through comparing with NN