A batch data based PSO identification method for Hammerstein systems

For a single input-output Hammerstein model with a polynomial nonlinear part, the standard particle swarm optimization (PSO) method loses some accuracy, due to computing fitness only based on a set of input-output data in each iteration. Therefore, to promote the identification accuracy, this paper investigates a batch data based particle swarm optimization (BD-PSO) method to identify parameters of the system. The simulation results prove that the BDPSO method has a fast convergence speed and has a good estimation accuracy.