基于模糊粗糙集与支持向量机的瓦斯涌出量预测研究

Research on Forecasting of Gas Emission Quantity Based on Fuzzy-Rough Set and SVM

支持向量机(Support Vector Machine)具备很强的非线性建模能力,而且具有全局最优、结构简单等优点,近年来被广泛的应用于煤矿瓦斯预测方面,但其在处理样本时,不能确定数据中哪些知识是冗余的、不能将输入的信息空间维数简化,因此,会降低系统预测的精确性;将模糊粗糙集理论引入瓦斯涌出量的预测中,建立基于模糊粗糙集与支持向量机的瓦斯涌出量预测模型,用模糊粗糙集作为前端预处理器对数据进行约简,剔除冗余信息,以实现两种算法的优势互补。实验结果显示,该方法预测准确,具有较高的应用价值。

Support vector machine not only has strong nonlinear modeling capabilities, but also has the advantages of global optimum and simple structure. In recent years, it has been widely applied in coal mine gas forecast. But in the processing of samples, it can＇t be sure what knowledge is in the data redundancy, therefore, it will decrease the predictive accuracy. The fuzzy rough set theory is introduced into the pre diction of gas emission and the gas emission prediction model is established based on fuzzy rough set and support vector machine. Fuzzy rough set is as a front-end processor for data reduction, eliminate the redundant information, in order to realize the compiementary advantages of two algorithms. The experimental results show, the prediction of the method is accurate and it has a very high use value.