基于遗传学习算法和BP算法的神经网络在矿坑涌水量计算中的应用

本文采用遗传学习算法和误差反向传播算法(BP)相结合的混合算法来训练前馈人工神经网络(BPN)，即先用遗传学习算法进行全局训练，再用BP算法进行精确训练，使网络收敛速度加快和避免局部极小。作为实例，本文将该方法运用于多维时序问题。根据山东省黑旺铁矿的矿坑充水条件建立了一个网络，以矿坑充水的各种控制因素相关资料作为样本，对网络进行训练并用训练好的网络预测矿坑涌水量。网络的训练速度及预测结果表明，该算法收敛速度较快，预测精度很高，为矿坑涌水量预报提供了一种新思路和新方法。

Application of ANN to predict the drainage in mine

A new method for training the artificial neural network is presented. In this method, the genetic algorithm (GA), a general-purpose global search algorithm is used to train the network with updating the weights to minimize the error between the network output and the desired output. Then the back-propagation (BP) algorithm is used to further train the artificial neural network. This method is used to speed up the convergence and improve the performance. To demonstrate the procedures and performance of this neural network-training algorithm, the case of Heiwang Iron Mine, Shangdong Province, is analyzed and discussed. The major control factors of mining water-inrush are adopted as training pattern. The quantity of drainage is predicted.