基于随机森林的地表下沉系数求取方法

Calculation of surface subsidence factor based on random forest

地表下沉系数是开采沉陷预计的重要参数。文章介绍了随机森林回归算法的基本原理以及基本的实现流程,讨论了影响地表下沉系数的地质采矿因素,建立了一种用于计算下沉系数的随机森林回归预测模型。对模型的测试结果表明,预测值与实际值的最大相对误差为3.52%,最小相对误差仅为1.06%。利用该预测模型求取下沉系数不仅速度快,而且具有较高的精度,可以在实际工程中推广应用,该模型为求取下沉系数提供了新的途径。

The surface subsidence factor is an important parameter of mining subsidence prediction. Firstly, the basic principles and the process of random forest regression algorithm are introduced. Secondly, the geological and mining factors influencing the surface subsidence factor are discussed. Finally, a random forest regression prediction model for calculating the value of the subsidence factor is established. The test results show that the minimum relative error between the predictive values and the actual values is only 1.06%, and the maximum relative error is 3.52%. The subsidence factor can be calculated by the prediction model quickly and accurately. This method can be applied in practi- cal engineering, and it provides a new way to calculate the subsidence factor.