An Application of Genetic programming for Lithium-ion Battery Pack Enclosure Design: Modelling of Mass, Minimum Natural Frequency and Maximum Deformation Case

International Conference on Sustainable Energy and Green Technology 2018

能源学;生态环境科学

Shahin, M.E.^1 ; Yun, Liu^2 ; Chin, C.M.M.^1 ; Gao, Liang^4 ; Wang, Chin-Tsan^5 ; Niu, Xiaodong^2^3 ; Goyal, Ankit^2 ; Garg, Akhil^2

Department of Mechanical, Materials and Manufacturing Engineering, University of Nottingham, Malaysia Campus, Malaysia^1

Intelligent Manufacturing Key Laboratory, Ministry of Education, Shantou University, Guangdong, China^2

Shantou Ruixiang Mould Co. Ltd., Jinping SandT Park, Chaoshan Road, Shantou

515064, China^3

State Key Lab of Digital Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China^4

Department of Mechanical and Electro-Mechanical Engineering, National i Lan University, ILan, Taiwan^5

关键词: Evolutionary approach;    Finite element simulations;    Independent parameters;    Mechanical design;    Mechanical performance;    Minimum natural frequencies;    Safety of batteries;    Vehicle industry;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/268/1/012065/pdf
DOI  :  10.1088/1755-1315/268/1/012065

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

For ensuring the safety of battery pack and its enclosure, the mechanical design is crucial for generating lower deformation, lower stresses and vibrations during its actual operation. In addition, the minimum mass of battery pack is needed for lower energy consumption of pack. Therefore, the problem to be solved can be formulated as multi-objective optimization and much desire one for electric vehicle industry application. In this paper, the application of evolutionary approach of Genetic programming (GP) is illustrated for battery pack casing design considering the design requirements having higher mechanical performance. Data generated from finite element simulation was used as input in GP. The analysis concluded that the GP perform satisfactorily. GP models for three design outputs predicted the values in compare to actual values with errors RMSE and MAPE of .00154 and .00715, .000033 and 1.16, .52 and .48, respectively. These results can be used to design the battery pack enclosures. The similar models can be applied to different independent parameters to find out the possible relation in between them to correlate the results, find out the criticality of the individual parameter and then optimize the design accordingly.