基于PCA-GA-BP的回采工作面瓦斯涌出量预测模型研究

Study on Prediction Model for Gas Emission of Coal Mining Face Based on PCA-GA-BP

为进一步提高回采工作面瓦斯涌出量预测的准确性,建立了主成分分析法(PCA)、遗传算法(GA)、BP神经网络相结合的预测模型。该模型采用主成分分析法降维处理原始输入数据;将主成分分析结果作为BP神经网络的输入,消除冗余信息;然后采用遗传算法优化BP神经网络的初始权值和阈值,有效克服BP神经网络极易陷入局部最优的问题。选取某矿井回采工作面的实测数据进行分析,结果表明,该模型较单一BP神经网络预测精度高,能更有效地实现回采工作面瓦斯涌出量的高准确度预测。

In order to further improve prediction accuracy of the gas emission of coal face, the prediction model is established combining principal component analysis （PCA）, genetic algorithm （GA） ,with BP neural network. In the model, the princi- pal component analysis method is used to reduce the dimension of the original input data. And the results of principal com- ponent analysis is taken as the input of BP neural network. Then the redundant information of initial data is eliminated. U- sing genetic algorithm to optimize the weights and threshold of BP neural network, the problem that the BP neural network is easy to fall into local solution can be avoided. Analyzing the data from mining working face of a coal mine, it＇s shown that the model has higher prediction accuracy than single BP neural network. The accuracy prediction of mine gas emission can be realized effectively bv the model.