关键词: 人工神经网络, 粒子群优化算法, 融合, 水泥水化

Abstract: A novel BP neural networks learning algorithm based on Particle Swarm Optimiation（PSO） is proposed in this paper.A stochastic global optimization technique is used in this proposed algorithm.Comparing experiment between the proposed algorithm and traditional BP-PSO algorithm，the experiment results show that the proposed algorithm does not only superior to BP algorithm，but also has fast congruence speed，and successful applied in simulating Cement Hydration process.

Key words: Artificial Neural Network, Particle Swarm Optimization, syncretize, cement hydration