因子分析与支持向量机相结合的煤炭自燃预测

Coal spontaneous combustion prediction model of support vector machine combined with factor analysis

针对煤炭自然发火预测问题,将因子分析理论与支持向量机算法相结合,构建了煤炭自燃的预测模型.采用SPSS软件对所选取预测煤炭自燃的8个指标进行因子分析,提取出4个主要因子,利用Matlab实现支持向量机模式识别,通过实际数据对模型训练与检验.研究结果表明:经因子分析降维后的SVM预测准确率高于未经因子分析的SVM预测结果,并验证了因子分析与支持向量机相结合可以较高精度实现对煤炭自燃的预测.

In order to complete the prediction of coal spontaneous combustion, a prediction model was built based on factor analysis and support vector machine. SPSS software was used to extract 4 main factors from 8 related variables, and Matlab was applied to implement support vector machine for pattern recognition. Training and testing were carried out using actual data. The result shows that its prediction accuracy is higher than the one without factor analysis, and the model based on factor analysis and support vector machine can complete the prediction of coal spontaneous combustion with a high accuracy.