基于PCA-GA-BP神经网络的瓦斯含量预测分析

发布时间：2018-07-25 16:55

【摘要】：为提高煤层瓦斯含量预测的效率和准确率,提出了先采用主成份分析(PCA)方法来降低变量间的相关性,然后将遗传算法(GA)与BP神经网络相结合的煤层瓦斯含量预测的新方法。为了避免BP神经网络收敛速度慢、易陷入局部极小值等问题,算法采用GA对BP神经网络的权值和阈值进行优化,利用Matlab软件进行编程,建立了BP神经网络和GA-BP神经网络瓦斯含量预测模型。选取淮南某矿瓦斯含量及其影响因素作为实验数据对该模型进行了实例分析,将主成份回归和BP网络算法预测结果与该模型进行了对比分析。结果表明:PCA-GA-BP网络预测模型平均相对误差为2.759%,预测效果明显优于主成份回归和BP网络预测模型,可以准确的预测煤层瓦斯含量。
[Abstract]:In order to improve the efficiency and accuracy of coal seam gas content prediction, a new method of coal seam gas content prediction based on the combination of genetic algorithm (GA) and BP neural network (BP neural network) is put forward, which uses principal component analysis (PCA) method to reduce the correlation between variables. In order to avoid the problem of slow convergence speed and local minimum value of BP neural network, GA is used to optimize the weight and threshold of BP neural network, and Matlab software is used to program. The gas content prediction models of BP neural network and GA-BP neural network are established. The gas content of Huainan mine and its influencing factors are selected as experimental data to analyze the model. The prediction results of principal component regression and BP network algorithm are compared with the model. The results show that the average relative error of the prediction model is 2.759, and the prediction effect is obviously better than that of the principal component regression and BP network prediction model, which can accurately predict the coal seam gas content.
【作者单位】：辽宁工程技术大学矿业学院;辽宁工程技术大学安全科学与工程学院;矿山热动力灾害与防治教育部重点实验室;安徽省煤矿安全监察局淮北监察分局;
【基金】：国家自然科学基金青年基金资助项目(51104084)
【分类号】：TD712.5;TP183

【参考文献】