论文部分内容阅读
将BP神经网络与遗传算法相结合,使用遗传算法优化神经网络的权值和阈值,然后用BP算法训练网络,避免了单独使用BP神经网络训练时易于陷入局部极小值的问题,建立了一种新的岩爆预测模型。采集国内外具有代表性的一些岩爆案例作为BP训练样本,将样本数据经过多次迭代之后,达到指定误差停止训练,利用训练好的模型对某铜矿部分岩爆进行预测,预测结果与实际岩爆等级一致。
Combining BP neural network and genetic algorithm, genetic algorithm is used to optimize the weights and thresholds of neural network, and then the BP neural network training network is used to avoid the problem of easily falling into local minimum when BP neural network training alone is used. New Rock Burst Prediction Model. Some representative cases of rockburst at home and abroad were collected as BP training samples. After many iterations of the sample data, the training was stopped with the specified error and the rockburst of a copper mine was predicted by the trained model. The prediction results were in good agreement with the actual Rock burst level consistent.