A Novel Fusion Approach Consisting of GAN and State-of-Charge Estimator for Synthetic Battery Operation Data Generation

Kei Long Wong, Ka Seng Chou, Rita Tse, Su Kit Tang, Giovanni Pau

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

The recent success of machine learning has accelerated the development of data-driven lithium-ion battery state estimation and prediction. The lack of accessible battery operation data is one of the primary concerns with the data-driven approach. However, research on battery operation data augmentation is rare. When coping with data sparsity, one popular approach is to augment the dataset by producing synthetic data. In this paper, we propose a novel fusion method for synthetic battery operation data generation. It combines a generative, adversarial, network-based generation module and a state-of-charge estimator. The generation module generates battery operation features, namely the voltage, current, and temperature. The features are then fed into the state-of-charge estimator, which calculates the relevant state of charge. The results of the evaluation reveal that our method can produce synthetic data with distributions similar to the actual dataset and performs well in downstream tasks.

Original languageEnglish
Article number657
JournalElectronics (Switzerland)
Volume12
Issue number3
DOIs
Publication statusPublished - Feb 2023

Keywords

  • battery data
  • generative adversarial network
  • lithium-ion battery
  • machine learning
  • state-of-charge estimation
  • synthetic data

Fingerprint

Dive into the research topics of 'A Novel Fusion Approach Consisting of GAN and State-of-Charge Estimator for Synthetic Battery Operation Data Generation'. Together they form a unique fingerprint.

Cite this