Gravitational search algorithm with Gaussian process for lithium-ion batteries state of health (SOH) estimation

DOI

10.2991/icitmi-15.2015.203How to use a DOI?

Keywords

Gaussian process regression, gravitational search algorithm optimization, lithium-ion battery, state of health.

Abstract

State of health (SOH) estimation plays a significant role in battery prognostics. In this paper, Gaussian Process Regression (GPR) is used as a data-driven approach to perform SOH estimation, which supports uncertainty representation and management. At present, the hyper- parameters of GPR are optimized by conjugate gradient algorithm. However, the conjugate gradient algorithm has the shortcomings of too strong dependence on initial value and easily falling into local optimum. In order to improve the prediction precision and generalization ability of GPR, we utilized Gravitational Search Algorithm (GSA) replace of conjugate gradient to search the optimal hyper-parameters during the training process automatically then formed the GSA-GPR algorithm. Experimental results confirm that the proposed method can be effectively applied to lithium-ion batteries SOH estimation by quantitative comparison with the standard GPR algorithms, Genetic Algorithm (GA)-GPR and Particle Swarm Optimization (PSO)-GPR algorithms.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Jing Ye
AU  - Santong Zhang
AU  - Wei Yang
PY  - 2015/10
DA  - 2015/10
TI  - Gravitational search algorithm with Gaussian process for lithium-ion batteries state of health (SOH) estimation
BT  - Proceedings of the 4th International Conference on Information Technology and Management Innovation
PB  - Atlantis Press
SP  - 1203
EP  - 1210
SN  - 2352-538X
UR  - https://doi.org/10.2991/icitmi-15.2015.203
DO  - 10.2991/icitmi-15.2015.203
ID  - Ye2015/10
ER  -