A novel parameter estimation method based on PSOSQP optimization
Dali Zhao, Xiaoguang Li, Qibing Jin · 2008
The particle swam optimization (PSO) technique is an effective global convergence method, but its local search speed is slow. The sequential quadratic programming (SQP) method can solve a nonlinear programming problem quickly, but may be trapped into a local minimum. In this paper, a novel optimization method PSO-SQP by combining the PSO and SQP is proposed. In this method, PSO is employed for a global search. SQP is employed for a local minimum search in each PSO main loop to get the best group fitness particle. Then the PSO-SQP method is used in closed-loop parameter estimation. Several examples are simulated to illustrate effectiveness of the PSO-SQP method used in the parameter estimation. The results of simulations have demonstrated the effectiveness of the algorithms.