Prediction of Mine Inrush Water Based on BP Neural Network Method

Abstract:

Based on predictions of the mine inflow of water and the complexity of influential factors, a method of BP neural network is put forward for mine inrush water prediction in this paper. We chose proper impact factors and establish non-linear artificial neural network prediction model after analyzed the impact factors of mine water inflow in Shandong Heiwang iron, and also made one prediction with normal mine water inflow during the iron mining operation. It turned out that the result can match with the actual prediction data, which make it possible to predict the mine water inflow with the prediction of Artificial Neural Network.

• Periodical: Advanced Materials Research (Volumes 989-994)
• Pages: 1814-1820
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.989-994.1814
• Online since: July 2014
• Authors: Ai Jun Shao*, Qing Xin Meng, Shi Wen Wang, Ying Liu
• Keywords: BP Neural Network (BPNN), Mine Water Inflow, Prediction Model

References

[1] Ha Gen. Neural network design [M]. China Machine Press, (2002).

[2] Wei Haikun. The theory and method of neural network structure design [M]. National Defense Industry Press, (2005).

[3] Shao Aijun, Zhang Fawang, Shao Taisheng. Mine ground water [M]. Beijing: Geological publishing house, (2005).

[4] Chen Peipei, Liu Hongquan. Height forecast ofwater conducted zone with top coal caving based on artificial neural network [J]. Journal of China Coal Society, 2005, 30(4).

[5] Guan Entai, Wu Qiang. Prediction of mine water inrush [J]. Zhongzhou Coal, 2005, 1.

[6] Wu Wei. Neural network calculation [M], Higher Education Press, (2003).

[7] Li Yunfeng, Xu Guofu, Zuo Chuanming. Lianghuayuan Mine Water Inflow Estimation [J]. Coal Geology of China, 2007, 19.

[8] Qian Xuezhong. Grey Markov Model for predicting mine discharge [J], Journal of China Coal Society, 25(1), (2000).

[9] Huang Jingpo, Wang Weibiao. Relationship between the Jiawang mining area precipitation and discharge [J]. Coal Science and Technology Magazine, 2006(1).

[10] Liu Zhiming, Wang Guiling, Zhang Wei. Application of BP neural network to the quality assessment of groundwater dynamic monitoring network [J]. Hydrogeology and engineering geology, 2006, 33(2): 114-117.

[11] Dong Deyao. Neural network and Computational Intelligence [M]. Zhejiang University Press, (2002).

[12] Yin, Y. Y., and X. M. Xu, Applying neural works technology for multiobjective landus planning, Journal of Environmental Management, 32, 349-356, (1991).

[13] Zhang, B., Govindaraju, R. S., Prediction of watershed run off using Bayesian concepts and modular neural networks [J]. Water Resour. Res. 2000(6): 753-762.

DOI: 10.1029/1999wr900264

[14] Zhu, M. L., Fujita, M., and N. Hashimoto, Application of neural networks to runoff prediction, International conference on stochastic and statistical methods in hydrology and environmental engineering, Ontario, Canada, (1993).

[15] Marshall, S. J., and R. F. Harrison, Optimization and training of feed forward neural networks by genetic algorithms, 2nd, IEEE Int. Conf. on ANN, 39-43, (1991).

[16] Wang Z X, Dang Y G, Wang Y M. A grey verhulst model and its application [C]. Proceedings of 2007 IEEE ICCSIS, 2007, Nan-Jing, China, 571-574.

[17] Emery A C, Charles F M, Mary M P. Predicting Conductance Due to Upcoming Using Neural Network [J]. Ground Water, 2005, 43(6), 827-836.