论文部分内容阅读
从距离判别的思想出发,对未确知聚类理论中的置信度准则进行优化,并将该理论应用于顶板沉降量预测中。选取岩体抗拉强度、埋藏深度、暴露面积等9个影响因子,构建顶板沉降量预测的未确知聚类预测模型。根据收集的15组样本数据确定了未确知测度函数,并利用熵权法计算指标权重,预测得出顶板沉降的分类等级及顶板沉降量。经计算验证,该方法的平均预测误差为7.38%,较模糊数学、灰色关联及神经网络3种方法有更高的预测精度。为进一步验证其实用性,以辰州矿业沃溪矿区为例,采用该方法对4142采场进行顶板沉降量预测。结果表明,预测结果与实际监测结果相吻合,证明该方法用于采场顶板沉降量预测是客观合理的,可为矿山安全生产提供决策依据。
Based on the idea of distance discrimination, the confidence criterion in unascertained clustering theory is optimized, and the theory is applied to the prediction of roof settlement. Nine influencing factors such as tensile strength, burial depth and exposed area of rock mass are chosen to construct the unascertained clustering prediction model for roof settlement prediction. Based on the collected data of 15 samples, the unascertained measure function is determined. The entropy weight method is used to calculate the index weight, and the classification level of roof settlement and roof settlement are predicted. The calculated results show that the average prediction error of this method is 7.38%, which has higher prediction accuracy than fuzzy mathematics, gray relation and neural network. In order to further verify its practicality, taking the mining area of Quzhou Mining as an example, this method is used to predict the roof settlement of 4142 stope. The results show that the prediction results are in good agreement with the actual monitoring results. It is proved that this method is objective and reasonable for the prediction of the roof settlement of stope and can provide the decision-making basis for the mine safety production.