摘要
研究瓦斯涌出量预测问题,瓦斯涌出量受到开采深度、通风系统等多种因素影响,是一种复杂的非线性预测问题,传统预测方法难以建立准确数学模型,导致预测精度低。为了有效提高瓦斯涌出量预测精度,提出一种非线性的瓦斯涌出量预测算法。采用粒子群优化支持向量机对瓦斯涌出量与各种因素之间非线性关系进行建模,并对瓦斯涌出量预测进行仿真。结果表明,非线性预测算法有效提高了瓦斯涌出量的预测精度,降低了预测误差,对有效防止瓦斯爆炸有重要意义。
Gas emission is affected by the mining depth, atmospheric pressure, ventilation system and other fac- tors, and is a complex nonlinear prediction problem. The paper proposed a particle swarm optimization support vector machine algorithm to predict gas emission quantity. First, the particle swarm algorithm was used to optimize the pa- rameters of support vector machine, then the support vector machine was usd to build the relationship between gas gushing quantity and the various nonlinear factors. Finally, the gas emission prediction simulation experiment was carted out. The results show that, compared with other gas emission prediction models, the PSO - SVM can improve gas emission prediction accuracy, reduce the prediction error, and obtain ideal prediction effects.
出处
《计算机仿真》
CSCD
北大核心
2012年第8期207-210,共4页
Computer Simulation
基金
齐齐哈尔市工业攻关项目(GYGG-09009)
