基于PSO—SVM的煤与瓦斯突出强度预测模型

为有效预测煤与瓦斯的突出强度，分析了煤与瓦斯突出的主要影响因素，建立了基于粒子群优化支持向量机方法（PSO—SVM）的煤与瓦斯突出强度预测模型，通过实例对该模型的预测效果进行检验，同时还分别采用了BP神经网络（BP—NN）和支持向量机方法（SVM）对该实例进行了预测，进而对这3种方法的预测精度进行了比较。分析结果表明3种方法的预测准确率PSO—SVM为87．5％、BP—NN为50％、SVM为62．5％。可见，PSO—SVM方法的预测效果要好于BP—NN和SVM，对煤矿煤与瓦斯突出强度预测具有一定的参考价值和指导意义。

Predicting Model of Coal and Gas Outburst Based on the Particle Swarm Optimization -support Vector Machine

In order to forecast the coal and gas outburst effectively, the main impact factors of coal and gas outburst were analyzed, and the PSO - SVM prediction model of the coal and gas outburst degree was established. And the PSO - SVM prediction model was tested. At the same time, the BP neural network （ BP - NN） prediction model and support vector machine （SVM） prediction model were established and adopted to predict the same instance. And the prediction results show that the prediction accuracy for the three methods is 87. 5% for PSO - SVM, 50% for BP - NN and 62. 5% for SVM. Therefore, the predicted accuracy of PSO - SVM mode/is better than that of BP network and SVM, and the PSO - SVM method is a very efficient way for coal and gas outburst prediction, and has certain referential value and significance.