A new method to adjust weights of BP network was proposed based on particle swarm optimization.The new model was based on the weight adjustments of error back propagation of BP algorithm and the weight modification using particle swarm optimization (PSO).The model can not only overcome the limitations both the slow convergence and the local extreme values by basic BP algorithm

but also improve the learning ability and generalization ability with a higher precision.The new model was used in simulation test of four typical complex functions

results of which were analysed and compared with that of basic BP algorithm

BP network optimized based on genetic algorithm (GA-BP) and traditional BP network of signal forward propagation based on particle swarm optimization.Results show the performances of new PSO-BP model are superior to that of other 3 kinds of optimized BP network models

especially in generalization ability.