基于CPSO-BP神经网络的冲击地压预测

Prediction of Rockburst Based on Chaos Particle Swarm Optimization BP Neural Network

针对预测冲击地压的传统方法存在的弊端,提出了一种基于混沌(Chaos)优化粒子群的BP神经网络算法。该算法将混沌、粒子群、BP神经网络结合起来,通过混沌粒子群算法寻优得到BP神经网络的最优权值和阈值初始值,然后进行网络训练和测试。该算法对冲击地压的预测取得了较好的效果。

Aiming at the drawbacks of traditional methods to predict rockburst, presents a BP neural network algorithm based on chaos particle swarm optimization. The algorithm combines chaos, particle swarm and BP neural network, and obtains the optimal weights and the initial threshold value of BP neural network by chaos particle swarm optimization algorithm, then takes network training and testing.The algorithm has better effect in prediction of rockburst.