Prediction for Gas Emission Quantity of the Working Face Based on LSSVM Optimized by Improved Particle Swarm Optimization

Abstract:

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.

• Periodical: Advanced Materials Research (Volume 1051)
• Pages: 1028-1031
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1051.1028
• Online since: October 2014
• Authors: Yu Xi Feng, Kai Zhi Zhang, Xi Zhan Yu, Qing Zhi Liu
• Keywords: Continuous Forecasting, Gas Emission Quantity, Improved Particle Swarm Optimize, Least Square Support Vector Machine

References

[1] Hongqing Zhu, Wenjie Chang, Bin Zhang. Difference-source gas emission prediction model of working face based on BP artificial neural network and its application[J], JOURNAL OF CHINA COAL SOCIETY, 2007, 32(5): pp.504-505.

[2] Yujing Liu, Guangzhi Xiao. Applying artificial neural network to predict gas emission of working face, [J]. Safety In Coal Mines, 2003, 34(1): pp.11-13.

[3] Zhanyou Sa, Xueqiu He, Enyuan Wang, Prediction for amount of gas emission from extracted coal face based on self-adapting neural network[J], JOURNAL OF CHINA COAL SOCIETY, 2001, 26(10): pp.96-99.

[4] Lin Sun, Shiyuan Yang, Prediction for gas emission quantity of the working face based on LS-SVM[J], JOURNAL OF CHINA COAL SOCIETY, 2008, 33(5): pp.1378-1380.

[5] Weiwu Yan, Huihe Shao, The study of comparing and application for support vector machines and least squares support vector machines[J], CONTROL AND DECISION, 2003, 18(3): pp.358-340.

DOI: 10.1109/acc.2003.1239851

[6] Liping Zhang. The Theory and Practice of Particle Swarm Optimization Algorithm [D]. HangZhou: ZheJiang Universit, (2005).