Algorithm Study on Physical Adaptive Regulation Based on BP Neural Network

Abstract:

As a kind of empirical model, artificial neural network is playing an increasingly important role in the actual theoretical research and practical development. On the basis of principles, this paper has analyzed the model structure of artificial neural network and its related properties, and has made further analysis of the network structure of BP algorithm and its detailed derivation process. Based on this, the paper has made a comparative analysis on the improvement of the three algorithms, and has applied the method for self-regulation learning rate into the empirical analysis of the effectiveness of athletes physical strength by combining with the realities. Finally, the results show that the method has got the obvious effect, and can provide theoretical and technical support, to a certain extent, for the research of the related fields.

• Periodical: Applied Mechanics and Materials (Volumes 513-517)
• Pages: 2364-2368
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.513-517.2364
• Online since: February 2014
• Authors: Zhi Liang Yuan*
• Keywords: Automatically Regulation, BP Neural Network (BPNN), Effectiveness, Sport

References

[1] Junli Zheng, Hangjun Yang. Artificial neural network [M]. Beijing: Higher Education Press, 2011(5): 15-30.

[2] Zhonghua Hao. The nonlinear thought of BP neural network [J]. Journal of Luoyang Normal University, 2011, 3 (4): 34-35.

[3] Junrang Ju, Rong Zhuo. The convenient implementation of BP neural network in Matlab [J]. Journal of Xinjiang Petroleum Institute, 2011, 2 (1): 89-90.

[4] Jian Xiao. Research and application of advanced control technology in the active balancing system [D]. Beijing University of Chemical Technology, 2011: 2-11.

[5] Huanling Wang. Research of the hand motion behavior based on SEMG identification technology [D]. Halice Polytechnic University, 2011: 3-9.

[6] Yumei Wang, Na Wang. Research of on-line monitoring for high voltage circuit breaker based on neural network expert system [J]. Measurement & control technology, 2010(3): 78-79.

[7] Chunsong Feng, Buqing Xiao. The predetermined model of molten steel temperature based on BP neural network [J]. Iron and Steel Research, 2012(1): 112-113.

[8] Jia Cai, Gang Tong. Study on detection of shaft damage based on neural network [J]. Journal of Shenyang Aerospace University, 2010(3): 67-68.

[9] Gang Qiu. Electric vehicles estimated by the neural network of the power battery SOC [D]. Liaoning Technical University, 2011: 5-14.

[10] Hongbo Wang, Changqi Chen, Jinshan You. Research on improving precision of vacuum measurement based on BP neural network [J]. Journal of Vacuum Science and technology, 2012(1): 105-106.