Diagnosis Model Based on Least Squares Support Vector Machine Optimized by Multi-swarm Cooperative Chaos Particle Swarm Optimization and Its Application

The classification accuracy of the least squares support vector machine (LSSVM) models strongly depends on proper setting of its parameters. An optimal selection approach of LSSVM parameters is put forward based on multi-swarm cooperative chaos particle swarm optimization (MCCPSO) algorithm. Chaos particle swarm optimization (CPSO) can improve the ability of local search optimization with good robust and adaptable. Multi-swarm cooperative particle swarm optimization (MCPSO) algorithm is masterslave heuristic method with a good global search. Then the MCCPSO-LSSVM diagnosis model is used to diagnosing analog circuit fault. Simulation results show that MCCPSO algorithm can jump out of local optimums with fast convergence and good stability. Results for analog circuit fault diagnosis show that the proposed method has strong robustness, and high accuracy.