Inconsistency modeling of lithium-ion battery pack based on variational auto-encoder considering multi-parameter correlation

Xitian He, Bingxiang Sun, Weige Zhang, Xiaojia Su, Shichang Ma, Hao Li, Haijun Ruan

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)

Abstract

—The accurate battery pack model is of great significance for the strategy development and functional verification of battery management system with the advantages of the high repeatability, fast state switching, and high safety. In this paper, a total of 49 dimensions of battery pack parameters are obtained through systematic experiments, including equivalent circuit model parameters and thermal characteristic parameters. Since the variational auto-encoder (VAE) can well preserve the correlation between parameters by training the neural network with small samples (95 samples), a novel battery pack inconsistency method is proposed based on VAE. Moreover, the parameter correlation and similarity are further considered based on the original loss function, which enables parameters generation for any amount of samples. The simulation results of the 95 and 500 generated samples illustrated that the proposed method can well maintain the similarity with the original parameters in both parameters distribution and parameters correlation, compared with the Copula-based and Metropolis-Hastings-based method. The average temperature error of the VAE-based method (0.02%) is much smaller than that of the Copula-based method (0.80%), and the temperature standard deviation error of the VAE-based method can be reduced to 4.53%, while the Copula-based method can reach 105.38%.

Original languageEnglish
Article number127409
Number of pages12
JournalEnergy
Volume277
Early online date15 Apr 2023
DOIs
Publication statusPublished - 15 Aug 2023
Externally publishedYes

Funder

This work is supported by the Joint Funds of Equipment Pre-Research and Ministry of Education of China (Grant NO. 8091B022130) and the National Natural Science Foundation of China (Grant No. 52177206\51907005).

Keywords

  • Lithium-ion battery pack
  • Inconsistency modeling
  • Variational auto-encoder
  • Multi-parameter correlation

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Modelling and Simulation
  • Renewable Energy, Sustainability and the Environment
  • Building and Construction
  • Fuel Technology
  • Energy Engineering and Power Technology
  • Pollution
  • Mechanical Engineering
  • Energy(all)
  • Management, Monitoring, Policy and Law
  • Industrial and Manufacturing Engineering
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Inconsistency modeling of lithium-ion battery pack based on variational auto-encoder considering multi-parameter correlation'. Together they form a unique fingerprint.

Cite this