论文部分内容阅读
为解决煤矿瓦斯涌出量预测不准确的问题,提出基于多种方法优化融合的瓦斯涌出量预测方法,建立瓦斯涌出量预测模型.采用适用于瓦斯涌出量系统特点的加权策略函数对最小二乘支持向量机进行改进,利用免疫遗传算法对加权最小二乘支持向量机进行核参数和正则化参数寻优.应用状态转移概率修正预测误差残值,使瓦斯涌出量预测模型的预测精度得到提高.研究结果表明:矿井瓦斯涌出量预测模型具有较好的快速性和准确性,具有广泛的应用前景.
In order to solve the problem of inaccurate prediction of gas emission from coal mines, a gas emission prediction method based on a variety of methods to optimize the fusion is proposed and a gas emission prediction model is established.With the weighted strategy function suitable for gas emission system Least squares support vector machine to improve the use of immune genetic algorithm for weighted least square support vector machine kernel parameter and regularization parameter optimization.The application of state transition probability to amend the prediction error residual value so that prediction of gas emission prediction model The accuracy is improved.The results show that the prediction model of mine gas emission has a good speed and accuracy and has a wide range of applications.