1 March 2021 in Applied Energy
22 August 2022 in Applied Energy
20 January 2023 in Green Energy and Intelligent Transportation
5 November 2020 in Transactions of the Institute of Measurement and Control
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.
3 February 2026 in IEEE Transactions on Industrial Electronics
Multistate joint estimation enables more effective monitoring and assessment of battery operation conditions. This article proposes a multitimescale framework for asynchronous joint estimation of multiple coupled yet time-varying battery states, namely state of charge (SOC), state of energy (SOE), and state of health (SOH). First, an improved convolutional neural network (CNN) architecture is designed to enhance the model feature extraction capability. Specifically, inception modules are integrated into the CNN model for long timescale feature extraction, while the feature map stacking combined with attention mechanisms is employed for short timescale feature extraction, leveraging the inherent multiscale receptive fields of Inception to model global dependencies and the dynamic feature refinement capability of attention-enhanced stacking to emphasize local transient details. Second, a nature inspired r-GA optimization algorithm is proposed to enhance the training efficiency and performance of the CNN model by optimizing the network parameters. Besides, a Kalman filter is integrated to further improve the accuracy of state estimation by introducing physical information about the battery dynamics. Finally, the input dimensions and update strategies of the framework are tailored for different states to enable joint state estimation across multiple timescales. Experimental results demonstrate that the proposed framework produces much more precise estimation of SOC, SOE, and SOH with mixed-rate updates, while also exhibiting robustness when dealing with data corrupted with Gaussian white noise.
13 January 2026 in IEEE Transactions on Industrial Informatics
Recent advances in data-driven methods have significantly improved battery capacity estimation, yet most existing approaches remain constrained by their reliance on supervised learning, requiring substantial amounts of labeled cycling data that are often costly to obtain. To address this challenge, this study proposes a dual-branch network-based semi supervised framework that integrates self-supervised learning and transfer learning mechanisms. First, the framework derives meaningful degradation-aware auxiliary labels from both labeled and unlabeled samples, creating reliable self-supervised signal for model training. Second, the designed dual-branch neural network architecture employs a shared feature extractor that processes input data for both the primary capacity estimation task and the auxiliary label prediction task, enabling effective knowledge transfer between labeled and unlabeled domains through their common representation space. Third, a pseudolabel filtering strategy is proposed to dynamically select high-confidence samples from the unlabeled dataset for self-training, thereby effectively expanding the training set with high-quality pseudolabels and enhancing the capacity estimation accuracy. Finally, extensive experiments validate the framework’s superior performance, achieving a worst-case root-mean-square error of only 0.0143 Ah with merely 5% labeled data, representing a 27.04% reduction compared with the best-performing semi supervised baseline (Co-training) under the same conditions.