论文部分内容阅读
为有效提高煤矿瓦斯涌出量预测的准确性,进一步保障煤矿生产安全,提出经免疫遗传算法(IGA)优化的加权最小二乘支持向量机(LS-SVM),并用其建立煤矿瓦斯涌出量预测模型。首先针对瓦斯涌出量系统非线性、时变性、复杂性等特点,提出一种新的加权策略函数来改进LS-SVM。然后引入IGA,对改进的LS-SVM进行核参数δ和正则化参数γ寻优。最后,利用煤矿历史瓦斯涌出数据进行试验分析。结果表明,利用该模型预测的最大相对误差为2.763%,最小相对误差为0.705%,平均相对误差为1.329 8%,该模型较其他预测模型具有更快的收敛速度,更强的泛化能力和更高的预测精度。
In order to effectively improve the accuracy of coal mine gas emission prediction and further guarantee coal mine production safety, a weighted least square support vector machine (LS-SVM) optimized by immune genetic algorithm (IGA) is proposed and used to establish gas emission Predictive model. Firstly, a new weighted strategy function is proposed to improve the LS-SVM in view of the non-linear, time-varying and complexity of gas emission system. Then IGA is introduced to optimize the kernel parameter δ and regularization parameter γ of the improved LS-SVM. Finally, the use of coal mine gas emission data for experimental analysis. The results show that the maximum relative error predicted by the model is 2.763%, the minimum relative error is 0.705% and the average relative error is 1.329 8%. Compared with other models, the model has faster convergence rate, stronger generalization ability and Higher prediction accuracy.