煤与瓦斯突出预测的QGA-LSSVM模型

为快速、有效地对煤与瓦斯突出类型作出预测，运用灰色关联和因子分析模型对所选主要的判别指标进行分析提取，利用量子遗传算法(QGA)对最小二乘支持向量机(LSSVM)的参数作寻优处理，最终建立QGA-LSSVM煤与瓦斯突出预测模型。选取从砚石台矿区历史实测的数据,以96∶20的比例对该模型进行训练与测试，并将预测结果与其他预测模型的预测效果进行了比较。研究结果表明:对判别指标进行灰色关联分析可以有效去除对煤与瓦斯突出影响作用小的指标；用因子分析进行公共因子提取，可以有效减少数据信息冗余；利用QGA优化的LSSVM模型能使结果避免陷入局部最优解，用该模型可以有效预测煤与瓦斯突出类型，误判率为0。

Prediction model for outburst of coal and gas based on QGA-LSSVM

To predict the outburst type of coal and gas quickly and effectively, the main influence factors were analyzed and extracted by gray correlation and factor analysis model. The quantum genetic algorithm(QGA) was applied to optimize the parameters of the least squares support vector machine(LSSVM). Finally, the prediction model for outburst of coal and gas based on QGA-LSSVM was established . By selecting the historical measured data sets in Yanshitai mining area, the model was trained and tested by the proportion of 96:20, and the prediction results were compared with the results of other prediction models. The results showed that it can effectively remove the factors which have a little impact on the outburst of coal and gas by gray correlation analysis, and it can reduce data redundancy by using factor analysis to extract the common factors. The LSSVM model after optimization by QGA can avoid the results to fall into the local optimal solution, and it can effectively predict the outburst type of coal and gas with an error rate of zero.