TR2016-097

Online Battery State-of-Charge Estimation Based on Sparse Gaussian Process Regression

    •  Ozcan, G., Pajovic, M., Sahinoglu, Z., Wang, Y., Orlik, P.V., "Online Battery State-of-Charge Estimation Based on Sparse Gaussian Process Regression", IEEE Power & Energy Society General Meeting (PES), DOI: 10.1109/​PESGM.2016.7741980, July 2016.
      BibTeX TR2016-097 PDF
      • @inproceedings{Ozcan2016jul,
      • author = {Ozcan, Gozde and Pajovic, Milutin and Sahinoglu, Zafer and Wang, Yebin and Orlik, Philip V.},
      • title = {Online Battery State-of-Charge Estimation Based on Sparse Gaussian Process Regression},
      • booktitle = {IEEE Power \& Energy Society General Meeting (PES)},
      • year = 2016,
      • month = jul,
      • doi = {10.1109/PESGM.2016.7741980},
      • url = {https://www.merl.com/publications/TR2016-097}
      • }
  • MERL Contacts:
  • Research Areas:

    Control, Machine Learning, Signal Processing

Abstract:

This paper presents a new online method for state-of charge (SoC) estimation of Lithium-ion (Li-ion) batteries based on sparse Gaussian process regression (GPR). Building upon sparse approximation of the regular GPR, the proposed method is computationally more efficient. The battery SoC is estimated based on measured voltage, current and temperature. The accuracy of the proposed method is verified using LiMn2O4/hardcarbon battery data collected from a constant-current discharge test. In addition, the estimation performance of the proposed method is compared with a SoC estimation method using regular GPR with different covariance functions.