矿井涌水量的支持向量机-马尔科夫链预测模型

Support Vector Machine-Markov Chain Prediction Model for Mine Water Inflow

为准确预测矿井涌水量,将支持向量机理论与马尔科夫链理论相结合,构建了支持向量机—马尔科夫预报模型。支持向量机—马尔科夫预报模型是基于原始数据首先建立起支持向量机模型,得到的预测值通过马尔科夫状态概率转移矩阵预报的方法进行二次拟合,通过对一些指标进行分析,从而实现对预测结果进行改善。矿井涌水量的支持向量机—马尔科夫链预测模型进一步提高了对波动性影响较大的随机变量的预报精度。本次研究扩大了支持向量机预报模型的应用范围,同时对煤炭开采矿井涌水量预报具有重要意义。

In order to accurately predict the mine water inflow,the support vector machine theory and the Markov chain theory are combined to construct a support vector machine-Markov forecasting model.The support vector machine-Markov prediction model is based on the original data to first establish the support vector machine model,and the predicted value is quadratically fitted by the Markov state probability transfer matrix prediction method.Through the analysis of some indicators,the prediction results are improved.Support vector machine-Markov chain prediction model of mine water inflow further improves the prediction accuracy of random variables which have great influence on volatility.This study expands the application scope of support vector machine prediction model,and is of great significance to the prediction of water inflow in coal mining mines.