标题：Prediction for gas emission quantity of the working face based on LSSVM optimized by improved particle swarm optimization
作者：Feng, Yu-Xi ;Zhang, Kai-Zhi ;Yu, Xi-Zhan ;Liu, Qing-Zhi
作者机构：[Feng, Yu-Xi ;Yu, Xi-Zhan ;Liu, Qing-Zhi ] Department of Economic Management, ShanDong University of Science and Technology, Taian; Shandong, China;[Z 更多
会议名称：2014 International Conference on Green Materials and Environmental Engineering, GMEE 2014
会议日期：September 21, 2014 - September 22, 2014
来源：Advanced Materials Research
摘要：Gas emission quantity may forecast the quantity of gas inside the coal, which has important significance for predicting the outburst of gas, but the problem always has not been well solved. Traditional Particle swarm optimization (PSO) algorithm lacks the ability to track the optimal solution while the fitness function changes. An improved algorithm named Time Variant PSO (TVPSO) was proposed to track the optimal solution online. Then it was used to choose the parameters of Least Square Support Vector Machine (LSSVM), which could avoid the man-made blindness and enhance the efficiency of online forecasting. The TVPSO-LSSVM method is based on the minimum structure risk of SVM and the globally optimizing ability of TVPSO to forecast continuously the gas emission quantity of the working face. The method was applied to solve the problem of nonlinear chaos time series prediction. Result shows that the method satisfies the need of online forecasting. © (2014) Trans Tech Publications, Switzerland.