The Thermal Process Identification with Radial Basis Function Network Based on Quantum Particle Swarm Optimization

The particle swarm optimization algorithm is an extremely effective method in evolutionary computation. But it also has some disadvantages such as finite sampling space and being easy to run into prematurity. In this paper, a new particle swarm optimization algorithm based on quantum individual is proposed (QPSO,). On basis of QPSO, a novel method of nonlinear system identification is proposed with constructing radial basis function neural network. The simulation results of a nonlinear system reveal the effectiveness of this method. A special program is compiled to identify the object model of the thermal process, and the dynamic process between primary air feed rate and bed temperature is identified. The results show that the approach is easy to be used for identification and has a certain practical value.