Estimation of End of Life of Lithium-Ion Battery Based on Artificial Neural Network and Machine Learning Techniques

Various vehicle manufacturers are launching electric vehicles, which are more sustainable and environmentally friendly. The major component in electric vehicles is the battery, and its performance plays a vital role. Usually, the end of life of a battery in the automobile sector is when the battery capacity reaches 80% of its maximum rated capacity. The capacity of a lithium-ion cell declines with the number of cycles. So, a semi-empirical model is developed for estimating the maximum stored capacity at the end of each cycle. The parameters considered in the model explain the changes in battery internal structure, like capacity losses at different conditions. The capacity estimated using the semi-empirical model is further taken as the inputs for estimating capacity using the Artificial Neural Network (ANN) and Machine Learning (ML) techniques i.e., Linear Regression (LR), Gaussian Process Regression (GPR), Support Vector Machine methods (SVM). Artificial Neural Network model has been trained in the neural fitting application in MATLAB and the trained neural network model is exported to Simulink and analysed. From the Simulink model, the capacity is estimated until the end of life of the battery. Similarly, regression learning application in MATLAB is studied to estimate the capacity using different Machine Learning techniques. The results are compared and the maximum error percentage of 0.5-0.6% is observed using the SVM method due to the vector-based analysis and the minimum error of 0.003-0.004% is observed using LR method for estimating capacity. These techniques can be implemented in the battery management system of the electric vehicle for estimating the present capacity of the vehicle.

• Record URL:
  https://doi.org/10.4271/2021-26-0218
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/01487191
• Supplemental Notes:
  • Abstract reprinted with permission of SAE International.
• Authors:
  • Lahari, Kothala
  • Sharma, Minakshi
  • Baidya, Kapil
• Conference:
  • Symposium on International Automotive Technology
  • Location: Pune , India
  • Date: 2021-9-29 to 2021-10-1
• Publication Date: 2021-9-22

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Serial:
  • SAE Technical Paper
  • Publisher: Society of Automotive Engineers (SAE)
  • ISSN: 0148-7191
  • EISSN: 2688-3627
  • Serial URL: http://papers.sae.org/

Subject/Index Terms

• TRT Terms: Electric batteries; Electric vehicles; Lithium batteries; Machine learning; Neural networks
• Subject Areas: Highways; Vehicles and Equipment;

Filing Info

• Accession Number: 01829143
• Record Type: Publication
• Source Agency: SAE International
• Report/Paper Numbers: 2021-26-0218
• Files: TRIS, SAE
• Created Date: Dec 9 2021 10:39AM