论文部分内容阅读
为了探讨地下工程中围岩稳定性分级情况,运用粗糙集理论(RS)中的属性约简和条件属性重要度评价,对影响煤层顶底板围岩稳定性分级的评价指标进行数据挖掘,确定影响煤层顶底板围岩分级的主要评价指标。在此基础上,利用径向基神经网络(RBF)拟合评价指标和围岩等级之间映射关系。建立围岩分级预测的遗传优化的RBF模型。将模型应用于贵州某矿山的M17-1煤层底板围岩稳定性分级。预测结果证明,遗传优化的RBF模型评价结果与围岩分级情况较为一致。
In order to discuss the stability classification of surrounding rock in underground engineering, the data mining is carried out by using attribute reduction and conditional attribute importance evaluation in rough set theory (RS) to determine the influence Main Evaluation Index of Surrounding Rock Classification of Roof and Floor of Coal Seam. Based on this, the RBF neural network (RBF) is used to fit the mapping relationship between the evaluation index and the surrounding rock level. Establishment of Genetic Optimization RBF Model for Surrounding Rock Classification and Prediction. The model was applied to the stability classification of surrounding rock of M17-1 coal seam in a mine in Guizhou Province. The prediction results show that the results of genetic evaluation based on RBF model are more consistent with the surrounding rock classification.