Human-knowledge-augmented Gaussian process regression for state-of-health prediction of lithium-ion batteries with charging curves

Quan Zhou, Chongming Wang, Zeyu Sun, Ji Li, Huw Williams, Hongming Xu

Research output: Contribution to journalArticlepeer-review

1 Downloads (Pure)

Abstract

Abstract Lithium-ion batteries have been widely used in renewable energy storage and electric vehicles, and state-of-health (SoH) prediction is critical for battery safety and reliability. Following the standard SoH prediction routine based on charging curves, a human-knowledge-augmented Gaussian process regression (HAGPR) model is proposed by incorporating two promising artificial intelligence techniques, i.e., the Gaussian process regression (GPR) and the adaptive neural fuzzy inference system (ANFIS). Human knowledge on voltage profile during battery degradation is first modeled with an ANFIS for feature extraction that helps reduce the need for physical testing. Then, the ANFIS is integrated with a GPR model to enable SoH prediction. Using a GPR model as the baseline, a comparison study is conducted to demonstrate the advantage of the proposed HAGPR model. It indicates that the proposed HAGPR model can reduce at least 12% root-mean-square error with 31.8% less battery aging testing compared to the GPR model.
Original languageEnglish
Article number030907
Number of pages10
JournalJournal of Electrochemical Energy Conversion and Storage
Volume18
Issue number3
Early online date29 Apr 2021
DOIs
Publication statusPublished - Aug 2021

Keywords

  • analysis and design of components
  • devices and systems
  • batteries
  • novel numerical and analytical simulations
  • artificial intelligence

Fingerprint

Dive into the research topics of 'Human-knowledge-augmented Gaussian process regression for state-of-health prediction of lithium-ion batteries with charging curves'. Together they form a unique fingerprint.

Cite this