Fault diagnosis of engine misfire based on genetic optimized support vector machine

In this paper an intelligent algorithm for commen misfire fault of automobile engines is proposed, in which the support vector machine(SVM) is used to extract the volume fractions of the automobile emission and to improve the accuracy of fault diagnosis, the genetic algorithms(GA) is adopted to optimize the parameters of SVM algorithm. Simulation results demonstrate GA-SVM algorithm can obtain satisfied classification result, the diagnosis speed and accuracy by GA-SVM algorithm are better than traditional SVM algorithm. The result shows that the GA-SVM algorithm has a very high accuracy for small sample fault diagnosis, thus the proposed algorithm is suitable for mechanical fault diagnosis of misfire fault of automobile engines.