论文部分内容阅读
针对煤体瓦斯渗透率在预测方法上存在计算量大、样本选取量多、智能化程度低等问题,首先分析了瓦斯压力、有效应力、温度变化和抗压强度等4个影响煤体瓦斯渗透率的主要因子,然后根据煤体的力学特性建立了煤体瓦斯渗透率的PSO-SVM预测模型,应用PSO算法优化了支持向量机模型的参数,最后将该模型应用于实际工程中,并将该模型的预测结果与BP模型的预测结果进行比较,结果表明,在样本数据较少的情况下,PSO-SVM模型的预测误差较小,准度更高,能够更好的对煤体瓦斯渗透率进行预测.
In view of the large amount of calculation, the large amount of samples to be selected and the low degree of intelligence in the prediction of coal gas permeability, the paper first analyzes the influence of gas pressure, effective stress, temperature change and compressive strength on the gas permeation Then the PSO-SVM prediction model of coal gas permeability is established according to the mechanical properties of coal, the PSO algorithm is used to optimize the parameters of SVM model, and finally the model is applied to the actual project, and the The results of the model are compared with those of the BP model. The results show that the prediction error of the PSO-SVM model is smaller and the accuracy is better with less sample data, Rate forecast.