神经网络在煤与瓦斯突出预测中的应用

Application of Neural Network to Predict Coal and Gas Outburst

应用神经网络中的BP网络模型对金竹山矿区煤与瓦斯突出进行了预测。为了加快神经网络模型的收敛速度,增强其跳出局部极小点的能力,采用了自适应变步长法和改进模拟退火法(SA法)相结合的方法。实际应用表明,该模型预测准确性高,是一种有效的煤与瓦斯突出危险性预测方法。

The prediction of coal and gas outburst in Jinzhushan Mine was conducted with the use of BP network model in neural network. In order to speed up the convergence speed of the neural network model and avoid its falling into a local minimum point a mixed method was adopted by means of changing network iteration step-length and the Simulated Annealing SA method. Practical application demonstrated that the prediction model has fast convergence speed and good prediction accuracy which is also an effective prediction method for mine coal and gas outburst and has practical significance to mine safe production.