A FAULT DIAGNOSIS METHOD BASED ON IMPROVED ARTIFICAL BEE COLONY OPTIMIZE SUPPORT VECTOR MACHINE
WU YinHua
XU QiongYan
Abstract：Aiming at the fact that the fault diagnosis performance of support vector machine (SVM) highly depends on the parameters selection,a fault diagnosis method based on improved artificial bee colony (IABC) optimize SVM was proposed.In order to improve search ability of ABC,Levy flight strategy was introduced and improved the original ABC algorithm.Use the IABC to optimize SVM parameters can effectively improve the classification performance of SVM.Different fault type and different fault degree of roiling bearing fault diagnosis experiment results show that the IABC can obtain better parameters when compared with ABC,GA and PSO,improved the fault diagnosis accuracy of SVM and can applied to fault diagnosis efficiently.
Keywords：Artificial bee colonyLevy flightSupport vector machineParameters optimizationFault diagnosis
Publication Date：2018-01-01
Online Publishing Date：2026-09-12(First online date of this platform, not the publication date of the document)
Pages：6( 287-292 )