Fault Diagnosis for Engine by Support Vector Machine and Improved Particle Swarm Optimization Algorithm

Fault diagnosis of engine is the key to ensure the safe operation of automobile. Aiming to solve the problems, such as the tendency to fall into local optimal solution and relatively low diagnostic accuracy, etc., which are found in the fault diagnosis model that based on particle swarm optimization algorithm to optimize support vector machine. Then, an improved particle swarm optimization algorithm is proposed in this paper. Here, we collect the common faults data of engine misfire to study the complicated relation between automobile exhaust and engine failure. It is obvious that the accuracy of fault diagnosis for engine of the hybrid model of support vector machine and improved particle swarm optimization algorithm is higher than the hybrid model of support vector machine and genetic algorithm, and the hybrid model of support vector machine and particle swarm optimization algorithm.