Fault diagnosis based on support vector machines with parameter optimisation by artificial immunisation algorithm

作者：Yuan Shengfa; Chu Fulei^*

来源：Mechanical Systems and Signal Processing, 2007, 21(3): 1318-1330.

DOI：10.1016/j.ymssp.2006.06.006

Support vector machines (SVM) is a new general machine-learning tool based on the structural risk minimisation principle that exhibits good generalisation when fault samples are few, it is especially fit for classification, forecasting and estimation in small-sample cases such as fault diagnosis, but some parameters in SVM are selected by man's experience, this has hampered its efficiency in practical application. Artificial immunisation algorithm (AIA) is used to optimise the parameters in SVM in this paper. The AIA is a new optimisation method based on the biologic immune principle of human being and other living beings. It can effectively avoid the premature convergence and guarantees the variety of solution. With the parameters optimised by AIA, the total capability of the SVM classifier is improved. The fault diagnosis of turbo pump rotor shows that the SVM optimised by AIA can give higher recognition accuracy than the normal SVM.

• 出版日期2007-4
• 单位清华大学; 江西理工大学