摘要：The ability to detect a new fault class can be a useful feature for an intelligent fault classification and diagnosis system.We adopt two novelty detection methods,the support vector data description (SVDD) and the Parzen density estimation, to represent known fault class samples,and to detect new fault class samples.The experiments on real multi-class bearing fault data show that the SVDD can give both high novelty detection rate and target recognition rate,respectively for the prescribed’ un- known’ fault samples and the known fault samples by choosing the appropriate SVDD algorithm parameters;but the Parzen densi- ty estimation only give a better novelty detection rate in our experiments.

注：因版权方要求，不能公开全文，如需全文，请咨询杂志社