最优组合预测在煤系地层含水量预测中的应用

利用电测深法能够获得半衰时St/2、衰减度D和视极化率ηs这些与煤系地层含水量相关的指标,通过分析,再引入含水层相对因子参数T"这一指标,选取以上4个物探观测指标作为预测煤系地层含水量的输入参数。通过实例,分别采用多元线性回归模型、人工神经网络模型和最优组合预测模型来预测煤系地层的含水量,研究各个模型的预测精度。结果表明:最优组合预测模型的预测精度最高,证明采用最优组合预测模型预测煤系地层含水量的准确性和实用性。

Application of Optimal Combination Prediction Method in Water Content Prediction of Coal-Bearing Strata

Using the electrical sounding method,the half decay time,decay rate and apparent polarizability which are relevant to water content of coal-bearing strata can be obtained.Through the analysis,we also introduced aquifer relative factor,select the above four geophysical observation indicators as input parameters to predict the water content of coal-bearing strata.According to instances,multiple linear regression model,artificial neural network model and the optimal combination prediction model were respectively used to predict the water content of the coal-bearing strata,and the prediction accuracy of each model is studied.The results show that: the prediction accuracy of the optimal combination prediction model is the highest,and it is effective and practical.