Fast battery capacity estimation using convolutional neural networks
Open Access
- 5 November 2020
- journal article
- research article
- Published by SAGE Publications in Transactions of the Institute of Measurement and Control
- Vol. 47 (15) , 3035-3048
Abstract
Lithium-ion batteries have been widely used in electric vehicles, smart grids and many other applications as energy storage devices, for which the aging assessment is crucial to guarantee their safe and reliable operation. The battery capacity is a popular indicator for assessing the battery aging, however, its accurate estimation is challenging due to a range of time-varying situation-dependent internal and external factors. Traditional simplified models and machine learning tools are difficult to capture these characteristics. As a class of deep neural networks, the convolutional neural network (CNN) is powerful to capture hidden information from a huge amount of input data, making it an ideal tool for battery capacity estimation. This paper proposes a CNN-based battery capacity estimation method, which can accurately estimate the battery capacity using limited available measurements, without resorting to other offline information. Further, the proposed method only requires partial charging segment of voltage, current and temperature curves, making it possible to achieve fast online health monitoring. The partial charging curves have a fixed length of 225 consecutive points and a flexible starting point, thereby short-term charging data of the battery charged from any initial state-of-charge can be used to produce accurate capacity estimation. To employ CNN for capacity estimation using partial charging curves is however not trivial, this paper presents a comprehensive approach covering time series-to-image transformation, data segmentation, and CNN configuration. The CNN-based method is applied to two battery degradation datasets and achieves root mean square errors (RMSEs) of less than 0.0279 Ah (2.54%) and 0.0217 Ah (2.93% ), respectively, outperforming existing machine learning methods.Keywords
Funding Information
- Engineering and Physical Sciences Research Council (EP/R030243/1)
This publication has 35 references indexed in Scilit:
- Co-estimation of state-of-charge, capacity and resistance for lithium-ion batteries based on a high-fidelity electrochemical modelApplied Energy, 2016
- State-of-health monitoring of lithium-ion battery modules and packs via incremental capacity peak trackingApplied Energy, 2016
- Real-time state-of-health estimation for electric vehicle batteries: A data-driven approachApplied Energy, 2016
- Modeling of Lithium-Ion Battery Degradation for Cell Life AssessmentIEEE Transactions on Smart Grid, 2016
- A dynamic capacity degradation model and its applications considering varying load for a large format Li-ion batteryApplied Energy, 2016
- Online estimation of lithium-ion battery capacity using sparse Bayesian learningJournal of Power Sources, 2015
- Battery modelling methods for electric vehicles - A review2014
- On-board state of health monitoring of lithium-ion batteries using incremental capacity analysis with support vector regressionJournal of Power Sources, 2013
- Behavior and state-of-health monitoring of Li-ion batteries using impedance spectroscopy and recurrent neural networksInternational Journal of Electrical Power & Energy Systems, 2012
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998