本文介绍了一种全局随机优化算法一粒子群优化算法,并将其用于BP网络模型,对模型参数进行优化来提高模型的收敛速度和精度,最后利用参数优化前后的BP模型进行径流预测,结果表明模型收敛速度和精度明显提高。
Particle swarm optimizer(PSO) algorithm with the global stochastic optimization technique is introduced and applied to BP neural networks to optimize the parameters of BP neural networks so as to improve the convergence speed and precision of BP neural networks. The runoff predicting results are obtained from two different kinds of BP neural networks, it is shown that convergence speed and precision of BP neural networks are improved.