Research on Automobile Engine Failure Recognition Technology Based on Improved PSO-RVM Algorithm

Abstract:

For vehicles in use, may be due to an engine misfire malfunction problem, a new and improved intelligent diagnosis method. The establishment of a volume fraction and fire fault automobile exhaust gases generated mapping between various reasons for data normalization processing for machine training, the trained models relevance vector machine used in failure analysis, classification diagnosis. The algorithm of the penalty factor and radial basis kernel function parameters on classification accuracy rate has a great impact, the use of super-particle swarm optimization parameters. Relevance vector machine model to optimize the trained and now mature neural networks and genetic algorithms support vector machine method were compared with experimental results show that the new method than the traditional methods have some improvement in diagnostic accuracy and robustness aspects .

• Periodical: Applied Mechanics and Materials (Volumes 727-728)
• Pages: 757-760
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.727-728.757
• Online since: January 2015
• Authors: Huan Jin*
• Keywords: Fault Identification, Kernel Function, Particle Swarm Algorithm, Relevance Vector Machine

References

[1] Yann Cooren, Maurice Clerc, Patrick Siarry.  Performance evaluation of TRIBES, an adaptive particle swarm optimization algorithm[J]. Swarm Intelligence . 2009 (2).

DOI: 10.1007/s11721-009-0026-8