Gas Emission Prediction of Coal Mine Based on Evidence Theory Combining with Neural Network

Abstract:

In order to improve the prediction accuracy of gas emission, propose a prediction method of evidence theory combining with neural network. According to the experimental data of gas emission, three different particle swarm optimization-neural network models are used for the initial prediction. And use the BP and RBF network to get the credibility of model by analyzing forecasting errors and its influence factors. Then the evidence theory is used to obtain the weights of combination model, realize the gas emission combination forecasting. Examples results show that the error of evidence theory is less than error of the neural network and equal weight method, and it is suitable for gas emission prediction of coal mine.

• Periodical: Advanced Materials Research (Volumes 756-759)
• Pages: 3799-3803
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.756-759.3799
• Online since: September 2013
• Authors: Zhi Mei Duan, Jia Tang Cheng
• Keywords: Evidence Theory, Gas Emission, Neural Network (NN), Prediction

References

[1] SHI Qing-jun，QI Chang-lin, YANG Song-tao, etal: Prediction of gas emission based on least squares support vector machines [J]. Journal of Jiamusi University(Natural Science Edition). 29(1): 47-49(2011).

[2] WANG He, SHAO Liang-shan, QIU Yun-fei: Predicting model of gas content based on ant colony neural network [J]. Microcomputer Information. 27(5): 197-198, 226(2011).

[3] HAO Tian-xuan, SONG Chao. Study on prediction of coal seam gas content based on fuzzy neural network [J]. China Safety Science Journal. 21(8)：36-42(2011).

[4] LI Guo-zhen, LI Xi-jian, MENG Zhao-jun, etal: Prediction on gas emission value from unmined block of mine base on grey theory[J]. Coal Engineering. 9: 85-87(2010).

[5] NIE Bai-sheng, DAI Lin-chao, YAN Ai-hua, etal: Study on prediction of coal seam gas content based on support vector regression [J]. China Safety Science Journal. 20(6): 28-32(2010).

[6] ZENG Ming, FENG Yi, LIU Da: Electricity price forecasting based on multi-models combined by evidential theory [J]. Proceedings of the CSEE. 28(6): 84-89(2008).

[7] HUANG Wei-yong, TONG Min-ming, REN Zi-hui: Nonlinear combination forecast of gas emission amount based on SVM[J]. Journal of China University of Mining & Technology. 38(2): 234-239(2009).

[8] CHENG Hui-jie, ZHANG Guo-yin, HE Ying: Study of tumor classification based on particle swarm neural network ensemble [J]. Computer Engineering. 36(10): 209-211(2010).

[9] MATLAB Chinese Forum. MATLAB Neural Network Analysis of 30 Cases[M]. Beijing: Beijing Aerospace University Press. 236-242(2010).