Research on the Safety Evaluation of Large Recreation Facilities Based on BP Neural Network

Abstract:

A safety evaluation index system regarding to the current safety situation of large recreation facilities in China is established. 13 secondary standard items are built by considerring human factor, equipment factor, environment factor and management factor. The existing safety evaluation of large recreation facilities are conducted by qualitative evaluation methods with highly fuzziness. The evaluation results are uncertain. After the network training, a safety evaluation model based on BP neural network is built. It can reduce the subjectivity of qualitative evaluation effectively with more scientific and objective results. Through the model based on BP neural network, the present safety situation of one large amusement facility is evaluated. The evaluation result is consistent with the actual situation. The method based on BP neural network in the paper provides a new method for safety evaluation of large recreation facilities.

• Periodical: Applied Mechanics and Materials (Volumes 522-524)
• Pages: 881-886
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.522-524.881
• Online since: February 2014
• Authors: Yu Zhang*, Zhi Rong Wang, Qing Qing Zuo, Xin Dong Zhang, Xiang Dong Li
• Keywords: BP Neural Network (BPNN), Evaluation Index System, Large Recreation Facilities, Safety Evaluation

References

[1] X. D. Li, Security technology of large amusement facilities [M]. (Beijing: China Planning Press, 2010).

[2] D. Q. Zhu, H. Shi. The principle and application of artificial neural network [M]. (Beijing: Science Press, 2006).

[3] K. L. Zhou, Y. H. Kang. Neural network model and MATLAB simulation program design[M] (Beijing: Tsinghua University Press, 2005).

[4] C. M. Shen, X. H. Li, D. Y. Xuan. Application of BP networks in safety assessment[J] (Industrial Safety and Environmental Protection, 2008), 34(11): 59-60.

[5] Y. Zhang, X. D. Zhang, X. D. Li. Review of investigation of risk analysis of large recreation facilities[J] (Journal of Safety Science and Technology, 2013), 9(9): 160-164.

[6] D. X. Sun, Y. B. Niu, H. Chang. Aviation maintenance errors risk assessment model based on integrated neural network[J] (Journal of Sichuan Ordnance, 2009), 30(8): 86-88.

[7] D. F. Millie, G. R. Weckma. Modeling microalgal abundance with artificial neural network: Demonstration of a heuristic Grey-Box to deconvolve and quantify environmental influences [J]. Environmental Modelling&Software, 38(2012): 27-39.

DOI: 10.1016/j.envsoft.2012.04.009

[8] H. Taghavifar, A. Mardani. Artifical neural network estimation of wheel rolling resistance in clay loam soil[J]. Applied soft computing, 13(2013): 3544-3551.

DOI: 10.1016/j.asoc.2013.03.017

[9] H. J. Sun, X. H. Wang. Determination of the weight of evaluation indexes with artificial neural network method[J]. Journal of Shandong University of Science and Technology (Natural Science) , 2001, 20(3): 38-42.

[10] J. H. Meng. Application of BP neural network model on failure analysis of safety valves[D]. Lanzhou: Lanzhou University of Technology, (2009).

[11] X. Y. Wang, X. L. Fang, H. Guo, Study on the current safety situation and evaluation of amusement ride[J] (Safety and Environmental Engineering, 2012) 19(5): 102-106.

[12] W. J. Huang. Research on the safety evaluation of urban rail transit based on BP neural network[J]. Science Technology and Engineering, 2009, 9(18): 5607-5609.

[13] Q. L. Liu, X. H. Wei, J. W. Shi. Mine ventilation system assessment model based on ANN and grey correlation[J] (MINING R&D, 2012), 32(2): 63-66.

[14] C. Q. Zhang, X. L. Jin, Z. F. Yang. Evaluation of risks in new product development based on improved BP neural network model[C]. The tenth national enterprise information and industrial engineering academic essays, 2006. 11.