论文部分内容阅读
为了对煤层瓦斯含量进行准确预测,应用支持向量回归机(SVR)理论建立煤层瓦斯含量预测模型,结合现场实测数据利用支持向量机(SVM)工具箱进行模型的求解及预测,并从均方根误差、希尔不等系数和平均绝对百分误差3个不同误差指标与人工神经网络预测模型进行比较分析。研究结果表明:SVR模型其预测精度及可行性高于神经网络模型,而且运算快,实时性较好,用于煤层瓦斯含量的预测较理想,具有良好的应用前景,可以为煤矿瓦斯防治提供理论依据。
In order to accurately predict the gas content of coal seam, the gas content prediction model of coal seam is established by using support vector regression (SVR) theory. The model is solved and predicted by the support vector machine (SVM) Error, Hill unequal coefficient and average absolute percentage error three different error indicators and artificial neural network prediction model for comparative analysis. The results show that the prediction accuracy and feasibility of the SVR model is higher than that of the neural network model, and the calculation is fast and the real-time performance is good. The forecast of the gas content in the coal seam is ideal and has good application prospects, which can provide theory for coal mine gas prevention and control in accordance with.