基于IPSO-SVM的瓦斯突出危险信号预测模型

Prediction model of gas outburst hazard signal based on IPSO-SVM

煤与瓦斯突出是主要矿难形式之一,危害极大。依据现场监测瓦斯突出的相关数据,对瓦斯突出的危险程度进行预测,提前做好防范措施,可大大降低事故危害。文中提出支持向量机算法与改进粒子群算法相结合的瓦斯突出危险程度预测模型:通过对容易陷入局部最优的粒子群进行改进,并应用改进粒子群算法求解影响支持向量机分类预测性能的最佳参数,然后把最佳参数应用于擅长模式识别的支持向量机算法,进行瓦斯突出样本数据的训练,构建瓦斯预测模型;最后,使用瓦斯预测模型对新的瓦斯突出数据进行预测。实验结果表明,采用该方法进行瓦斯突出预测的准确率,比纯支持向量机算法提高4.6%。

Coal and gas outburst accident endangers miners' lives and damages production site. The relevant data of gas outburst is monitored, the risk degree of gas outburst is predicted, and so gas outburst hazard reduces. Therefore, this paper propose a gas outburst risk prediction model based on combination of vector machine(SVM) algorithm and improved particle swarm optimization(PSO) algorithm. Firstly, the optimal parameters for SVM is solved by improved particle swarm optimization(PSO) algorithm,which has better inspiration performance and relapses into local optimal solution less. Secondly, the solved optimal parameters are used by SVM algorithm to train sample data for data classification, because SVM algorithm is good at pattern recognition. At last,gas outburst risk prediction model has built up. The experimental results show that the method adopted to improve the accuracy of fault detection by 4.6%.