Accord Ignition Diagnosis Based on Improved GA-BP

Abstract

BP neural network as a kind of intelligent method is widely used in fault diagnosis, due to the single BP neural network’s error is big, GA algorithm is often used in optimizing BP neural network, but the standard GA algorithm’s searching efficiency is low and it is easy to fall into local convergence. According to the characters of Accord car ignition diagnosis and BP neural network, this article puts forward an improved scheme of the standard GA algorithm optimizing BP net, calculate and analyze different simulation results gotten by MATLAB program. Through calculation: the single BP neural network’s convergence step number is 101, the final mean square error is 0.000997167; the convergence step number that standard GA algorithm optimizes the BP neural net is 83, the final mean square error is 0.000142126; the convergence step number that GA algorithm improved optimizes the BP neural net is 73, the final mean square error is 0.000137508. By the comparison, the improved GA algorithm has a better search efficiency and it’s computation can avoid falling into a local convergence.

DOI : http://dx.doi.org/10.11591/telkomnika.v12i2.3839