粒子群优化-BP神经网络对岩爆的预测

Prediction of Rock Bursts Based on Particle Swarm Optimization-BP Neural Network

岩爆是典型高地应力区主要地质灾害之一,其预测理论和发生机制的研究目前并不成熟.本文通过选择合适的影响岩爆程度的主要因素,应用BP神经网络对岩爆样本进行训练并利用预测样本进行检验,由于BP神经网络的初始权值和阀值对网络学习效率和预测结果有影响,因此其对检验样本的预测结果往往不够理想.利用粒子群算法(PSO)对BP网络的初始权值和阀值进行优化,将改进后的BP神经网络算法应用于预测,预测的结果优于BP神经网络.表明利用PSO-BP神经网络算法对实际工程中的岩爆进行预测是可行的.

Rock burst, as a basic kind of geological disaster, usually occurs in high geostress zones. There is no perfect prediction theory or occurrence mechanism so far. In this study, by choosing the main influence factors of rock bursts, BP neural network is used to train and predict the samples of rock bursts. Because initial weight values and threshold of the neural network have great effects on efficiency of learning and prediction of results, the prediction of testing samples using BP neural network are not satisfactory. The particle swarm optimization（PSO） algorithm is utilized to optimize the initial weight values and threshold of BP neural network. The improved BP neural network has a good prediction result for rock bursts. The results indicate that it is feasible to predict rock bursts based on PSO-BP neural network in practical engineering.