应用粒子群优化算法(particle swarm optimization,PSO)训练多层前馈(back propagation,BP)神经网络,提出毛竹导热系数的PSO-BP模型,将神经网络的学习过程映射为粒子群体的迭代寻优过程,达到优化神经网络权值及阈值的目的.结果表明:毛竹导热系数PSO-BP模型在泛化性能、拟合精度、训练及验证误差等方面均优于标准BP网络模型.%By applying PSO( particle swarm optimization) algorithm to train BP(back propagation)neural network, this article puts forward a PSO-BP model of Phyllostachys edulis ' thermal conductivity and regards the process of neural network learning as that of iterative optimization for particle swarm, with the purpose of optimizing neural network weights and thresholds. The research results show that the PSO-BP model of Phyllostachys edulis' thermal conductivity is superior to the standard BP network model in several aspects, such as generalization performance, fitting precision, training, error validation, etc., which provides a new method for the application of intelligent information processing technology in bamboo material analyses.
展开▼
