Abstract:

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.

Key words: Phyllostachys edulis&rsquo, thermal conductivity;neural network;particle swarm optimization(PSO);nonlinear fitting