A Misfire Fault Diagnosis System Based on Improved Neural Network


Article Preview

Misfiring fault is one of the common faults of automobile engines. This paper presents an algorithm based improved neural network which is used for misfiring fault. It calculates the memberships of inputs and initializes the weights and thresholds of the neural network by genetic algorithm firstly, and then trains the improved neural network and uses it for diagnosis. By applying GUI function of MATLAB, a new man-machine interaction interface was designed. The results of experiment indicate that this algorithm can effectively carry out misfiring fault diagnosis.



Advanced Materials Research (Volumes 383-390)

Edited by:

Wu Fan






K. Y. Zhang et al., "A Misfire Fault Diagnosis System Based on Improved Neural Network", Advanced Materials Research, Vols. 383-390, pp. 1549-1554, 2012

Online since:

November 2011




[1] J. Williams, An overview of misfiring cylinder engine diagnostic techniques based on crankshaft angular velocity measurements, SAE Technical Paper 960039, (1996).

DOI: 10.4271/960039

[2] S.M. Jakubek, T.I. Strasser, Artificial neural networks for fault detection in large scale data acquisition systems, Engineering Applications of Artificial Intelligence, vol. 17, p.233–248, (2004).

DOI: 10.1016/j.engappai.2004.03.002

[3] B. Samanta. Artificial neural networks and genetic algorithms for gear fault detection, Mech, Syst, Signal Process, vol. 18, p.1273–1282, May (2004).

DOI: 10.1016/j.ymssp.2003.11.003

[4] Guoyong Li, Qingfo Yang, FNN-based intelligent fault diagnosis system for vehicle engine, Journal of system simulation, vol. 19, p.1034–1037, Mar. 2007. (in Chinese).

[5] Liang Zhang, Duanmin Wang, Youyun Zhou, The model of information Fusion fault diagnosis based fuzzy neural network, Journal of projectiles, Rockets, Missiles and guidance, vol. 25, p.389–391, 2005. (in Chinese).

In order to see related information, you need to Login.