Application of Genetic BP Neural Network in Safety Comprehensive Evaluation of Tailing

Abstract:

Based on safety assessment factors determined by operation characteristics of a certain tailing ,genetic BP neural network evaluation model is established. To overcome such problems of BP neural network as slow convergence ,poor generalization ability and easy to fall into local minimum value,this paper proposes to use genetic algorithm to optimize threshold value,weights and structure of neural network. Thus,by taking advantage of extensive mapping ability of neural network and global search ability of genetic algorithm,neural network and genetic algorithm will have complementary advantages and the learning speed of network will be accelerated. The application of the described method shows optimized fitting precision,improved accuracy and efficiency ,and enhanced generalization ability of BP neural network. In conclusion,this model can effectively reflect and accurately evaluate non-linear relations between security levels and evaluation factors in tailing.

• Periodical: Applied Mechanics and Materials (Volumes 687-691)
• Pages: 2402-2406
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.687-691.2402
• Online since: November 2014
• Authors: Song Jiang, Hui Wen He, Hong Bo Liu, Kang Ting Lv
• Keywords: BP Neural Network (BPNN), Genetic Algorithm (GA), Safety Comprehensive Evaluation, Tailing

References

[1] Li Xiaojun, Yuan Ziqing. 18 river tailing online monitoring engineering practice [J]. Journal of nonferrous metals, 2011, (3) : 30-33.

[2] Tung - Chiung Chang and Yue - Hone Chien. The application of genetic algorithm in debris flows prediction[J]. Environmental Geology，2007，53（2）：339-347.

DOI: 10.1007/s00254-007-0649-2

[3] jian-feng cao, JHF, SUMARE Oumar, etc. To improve the application of BP neural network in groundwater environment quality evaluation [J]. Water conservancy and hydropower science and technology progress, 2006, 26 (3) : 21-23.

[4] Fourier A B，Blight G E， Rampageous G . Static liquefactions as a possible explanation for the merriespruit tailings dam failure[J]Canadian Geotechnical Journal，2001，38(4): 707一719.

DOI: 10.1139/t00-112

[5] ying-bo wang, wang, Li Zhongxue. Based on the HS - BP algorithm of the tailings safety evaluation [J]. Journal of systems engineering theory and practice, 2012, 32 (11) : 2585-2590.

[6] Ye Siqiao, hong-mei tang, jin-xu shi. Improved BP NN in the application of the three gorges reservoir area landslide stability analysis [J]. Journal of Chongqing university of architecture, 2006, 28 (6) : 38-41 turned.

[7] Li Duan have, peng-xiao Chen, bao-jun zhang. Maoping landslide displacement prediction of BP network method applied research [J]. Journal of Yangtze river, proceedings of the national academy of sciences, 2005, 22 (6) : 3-5, 9.

[8] Meng Xianyao，Han Xinjie，Xu Qingyang. BP network optimized with genetic algorithm and apply on the fault diagnose of complex equipment[C]/2007 IEEE International Conference on Control and Automation（ICCA 2007），2008：1630-1633.

DOI: 10.1109/icca.2007.4376636

[9] KuaiShengLong Zhang Gongzhen, yun-hui li. Environmental quality evaluation based on genetic neural network [J]. Journal of shenyang university, 2006, 19 (2) : 43-45.