论文部分内容阅读
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 .
In this paper, genetic algorithm and error backpropagation algorithm (BP) are used to train the feedforward artificial neural network (BPN), that is to use the genetic learning algorithm for global training, and then use the BP algorithm to accurately train the network Convergence speed and avoid local minimum.As an example, this method is applied to multi-dimensional timing problems.According to the mine water filling conditions of the mine in Shandong Province Wangwang established a network to mine the various control factors related information As a sample, the network is trained and a well-trained network is used to predict the amount of water in the pit.The training speed and forecasting results of the network show that the algorithm converges fast and the prediction accuracy is high, which provides a new idea for forecasting the water inflow in the pit. new method .