Li Liangmin,Qu Liangsheng
(School of Mechanical Engineering,Xi'an Jiaotong University,Xi'an 710049,China)
Abstract:A new classification model based on genetic programming and support vector machine for machine fault diagnosis was proposed.In this model,genetic programming constructs and selects features from original feature set.The selected features form input feature set of support vector machines.Then multi-class support vector machine is applied to detect abnormal cases from normal ones.Experiments of rolling bearings fault detection are carried out to test the performance of this model.Practical results show that the compound features generated by genetic programming possess better recognition ability than the initial time domain features do.The classification ability of multi-class support vector machine is improved after feature extraction and selection．
Keywords:fault detection;support vector machines;genetic programming;rolling bearing