Life prediction of lithium-ion batteries based on stacked denoising autoencoders

Xu, Fan; Yang, Fangfang; Fei, Zicheng; Huang, Zhelin; Tsui, Kwok‐Leung

doi:10.1016/j.ress.2020.107396

Cited by 107 publications

(20 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xu et al. ( Xu et al., 2021 ) proposed a stacked denoising autoencoder method based on a deep learning mechanism to predict battery life from the essential battery features including discharging temperatures and voltage curves filtered by clustering fast search (CFS) method. The model was validated using experimental data and showed more accurate and efficient prediction results than the one without using the CFS method.…”

Section: Operating Characteristicsmentioning

confidence: 99%

Connecting battery technologies for electric vehicles from battery materials to management

2022

View full text Add to dashboard Cite

Summary Vehicle electrification has always been a hot topic and gradually become a major role in the automobile manufacturing industry over the last two decades. This paper presented comprehensive discussions and insightful evaluations of both conventional electric vehicle (EV) batteries (such as lead-acid, nickel-based, lithium-ion batteries, etc.) and the state-of-the-art battery technologies (such as all-solid-state, silicon-based, lithium-sulphur, metal-air batteries, etc.). Battery major component materials, operating characteristics, theoretical models, manufacturing processes, and end-of-life management were thoroughly reviewed. Different from other reviews focusing on theoretical studies, this review emphasized the key aspects of battery technologies, commercial applications, and lifecycle management. Useful battery managing technologies such as health prediction, charging and discharging, as well as thermal runaway prevention were thoroughly discussed. Two novel hexagon radar charts of all-round evaluations of most reigning and potential EV battery technologies were created to predict the development trend of the EV battery technologies. It showed that lithium-ion batteries (3.9 points) would be still the dominant product for the current commercial EV power battery market in a short term. However, some cutting-edge technologies such as an all-solid-state battery (3.55 points) and silicon-based battery (3.3 points) are highly likely to be the next-generation EV onboard batteries with both higher specific power and better safety performance.

show abstract

Section: Operating Characteristicsmentioning

confidence: 99%

Connecting battery technologies for electric vehicles from battery materials to management

2022

View full text Add to dashboard Cite

show abstract

“…These feature-based methods reveal the predictive ability of machine learning methods, and some advanced algorithms have been employed to improve prediction accuracy. 18,26,27 On the other hand, end-to-end methods open a new way for battery life prediction by directly using raw data as input. Zhang et al 28 directly fed electrochemical impedance spectra into the Gaussian process regression algorithm to predict battery cycle life.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, Weng et al 25 found that the internal resistance at a low state of charge (SOC) after formation cycles is closely related to battery life, thereby battery cycle life can be estimated by feeding the identified internal resistance into ridge regression. These feature‐based methods reveal the predictive ability of machine learning methods, and some advanced algorithms have been employed to improve prediction accuracy 18,26,27 . On the other hand, end‐to‐end methods open a new way for battery life prediction by directly using raw data as input.…”

Section: Introductionmentioning

confidence: 99%

Data‐driven battery degradation prediction: Forecasting voltage‐capacity curves using one‐cycle data

Tian

Xiong

Shen

et al. 2022

EcoMat

View full text Add to dashboard Cite

With the wide deployment of rechargeable batteries, battery degradation prediction has emerged as a challenging issue. However, battery life defined by capacity loss provides limited information regarding battery degradation. In this article, we explore the prediction of voltage‐capacity curves over battery lifetime based on a sequence to sequence (seq2seq) model. We demonstrate that the data of one present voltage‐capacity curve can be used as the input of the seq2seq model to accurately predict the voltage‐capacity curves at 100, 200, and 300 cycles ahead. This offers an opportunity to update battery management strategies in response to the predicted consequences. Besides, the model avoids feature engineering and is flexible to incorporate different numbers of input and output cycles. Therefore, it can be easily transplanted to other battery systems or electrochemical components. Furthermore, the model features data generation, that is, we can use the data of only one cycle to generate a large spectrum of aging data at the future cycles for developing other battery diagnosis or prognosis methods. In this way, the time and energy consuming battery degradation tests can be sharply reduced.

show abstract

“…Complex models may be learned using deep learning algorithms using large amounts of training data. Deep learning algorithms widely used in RUL estimation include autoencoders ( Xu et al, 2021 ), convolutional neural networks (CNN), CNN with attention mechanism ( Tan & Teo, 2021 ; Wang et al, 2021 ), long-short term memory ( Xia et al, 2021 ), gated recurrent unit ( She & Jia, 2021 ), random forest ( Chen et al, 2020 ) and support vector machines ( Xue et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

Deep learning-based anomaly-onset aware remaining useful life estimation of bearings

Kamat

Sugandhi

Kumar

2021

PeerJ Computer Science

View full text Add to dashboard Cite

Remaining Useful Life (RUL) estimation of rotating machinery based on their degradation data is vital for machine supervisors. Deep learning models are effective and popular methods for forecasting when rotating machinery such as bearings may malfunction and ultimately break down. During healthy functioning of the machinery, however, RUL is ill-defined. To address this issue, this study recommends using anomaly monitoring during both RUL estimator training and operation. Essential time-domain data is extracted from the raw bearing vibration data, and deep learning models are used to detect the onset of the anomaly. This further acts as a trigger for data-driven RUL estimation. The study employs an unsupervised clustering approach for anomaly trend analysis and a semi-supervised method for anomaly detection and RUL estimation. The novel combined deep learning-based anomaly-onset aware RUL estimation framework showed enhanced results on the benchmarked PRONOSTIA bearings dataset under non-varying operating conditions. The framework consisting of Autoencoder and Long Short Term Memory variants achieved an accuracy of over 90% in anomaly detection and RUL prediction. In the future, the framework can be deployed under varying operational situations using the transfer learning approach.

show abstract

Life prediction of lithium-ion batteries based on stacked denoising autoencoders

Cited by 107 publications

References 33 publications

Connecting battery technologies for electric vehicles from battery materials to management

Connecting battery technologies for electric vehicles from battery materials to management

Data‐driven battery degradation prediction: Forecasting voltage‐capacity curves using one‐cycle data

Deep learning-based anomaly-onset aware remaining useful life estimation of bearings

Contact Info

Product

Resources

About