Degradation Mode Recognition for Battery of Electric Vehicle Based on ART2 Network

Abstract:

In the process of describing the degradation process of battery of electric vehicle, degradation models under dynamic running conditions need to be analyzed in order to effectively forecast the remaining useful mileage and life of battery. This paper proposed a new method of pattern recognition based on ART2 network to distinguish the degradation mode of the battery of electric vehicle. First, the degradation mechanism is analyzed of the battery to extract the features of degradation process. Then the learning process of ART2 is designed for recognition of the degradation mode. After that, HMM is applied to research the dynamic changes of the degradation mode and predict future degradation mode sequences. Finally, experimental analysis based on batterys charge and discharge data proves the effectiveness of the proposed approach.

• Periodical: Applied Mechanics and Materials (Volume 455)
• Pages: 574-579
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.455.574
• Online since: November 2013
• Authors: Gang Yu*, Mi Mi Guo
• Keywords: ART2, Battery, Degradation Mode, Pattern Recognition

References

[1] GaoFei, Li Jianling, Zhao Shuhong and Wang Zidong: submitted to Electronic Components & Materials (2009).

[2] G.A. Carpenter, S. Grossberg: submitted to Applied Optics (1987).

[3] Duan Xiaxia, Liu Yanming and Li Xiaoping: submitted to Computer Engineering and Applications (2008).

[4] Information on http: /www. nasa. gov.

[5] Li Shan, Shi Yuan and Liu Hongjun: submitted to Computer Integrated Manufacturing Systems (2011).

[6] M. Harvey, C. Arthur: Fitting Modes to Biological Data Using Linear and Nonlinear Regression: A Practical Guide to Curve Fitting (Oxford University Press, Oxford 2004).

DOI: 10.1002/sim.2181

[7] J.H. Yan: submitted to Mechanical Systems and Signal Processing (2011).