Paula Fermín-Cueto, Euan McTurk, Michael Allerhand, Encarni Medina-Lopez, Miguel F. Anjos, Joel Sylvester et Gonçalo dos Reis
Article de revue (2020)
|
Libre accès au plein texte de ce document Version officielle de l'éditeur Conditions d'utilisation: Creative Commons: Attribution-Utilisation non commerciale-Pas d'oeuvre dérivée (CC BY-NC-ND) Télécharger (1MB) |
Abstract
High-performance batteries greatly benefit from accurate, early predictions of future capacity loss, to advance the management of the battery and sustain desirable application-specific performance characteristics for as long as possible. Li-ion cells exhibit a slow capacity degradation up to a knee-point, after which the degradation accelerates rapidly until the cell’s End-of-Life. Using capacity degradation data, we propose a robust method to identify the knee-point within capacity fade curves. In a new approach to knee research, we propose the concept ‘knee-onset’, marking the beginning of the nonlinear degradation, and provide a simple and robust identification mechanism for it. We link cycle life, knee-point and knee-onset, where predicting/identifying one promptly reveals the others. On data featuring continuous high C-rate cycling (1C–8C), we show that, on average, the knee-point occurs at 95% capacity under these conditions and the knee-onset at 97.1% capacity, with knee and its onset on average 108 cycles apart. After the critical identification step, we employ machine learning (ML) techniques for early prediction of the knee-point and knee-onset. Our models predict knee-point and knee-onset quantitatively with 9.4% error using only information from the first 50 cycles of the cells’ life. Our models use the knee-point predictions to classify the cells’ expected cycle lives as short, medium or long with 88–90% accuracy using only information from the first 3–5 cycles. Our accuracy levels are on par with existing literature for End-of-Life prediction (requiring information from 100-cycles), nonetheless, we address the more complex problem of knee prediction. All estimations are enriched with confidence/credibility metrics. The uncertainty regarding the ML model’s estimations is quantified through prediction intervals. These yield risk-criteria insurers and manufacturers of energy storage applications can use for battery warranties. Our classification model provides a tool for cell manufacturers to speed up the validation of cell production techniques.
Mots clés
Lithium-ion battery, Degradation, Knee-point, Knee-onset, Machine learning, Uncertainty quantification
Renseignements supplémentaires: |
Code for knee-point/onset identification is available at https://github.com/pfermined/knee_identification. Code for classification and quantitative prediction is available upon request. ; Supplementary material associated with this article can be found, in the online version, at doi: 10.1016/j.egyai.2020.100006 |
---|---|
Sujet(s): |
2500 Génie électrique et électronique > 2500 Génie électrique et électronique 2800 Intelligence artificielle > 2805 Théories de l'apprentissage et de l'inférence |
Département: | Département de mathématiques et de génie industriel |
Organismes subventionnaires: | The Data Lab – Innovation Centre (Edinburgh (UK)), Dukosi Ltd., Portuguese Foundation for Science and Technology |
Numéro de subvention: | Reg-191072, UIDB/00297/2020 |
URL de PolyPublie: | https://publications.polymtl.ca/10631/ |
Titre de la revue: | Energy and AI (vol. 1) |
Maison d'édition: | Science Direct |
DOI: | 10.1016/j.egyai.2020.100006 |
URL officielle: | https://doi.org/10.1016/j.egyai.2020.100006 |
Date du dépôt: | 01 mars 2023 14:58 |
Dernière modification: | 14 mars 2025 21:50 |
Citer en APA 7: | Fermín-Cueto, P., McTurk, E., Allerhand, M., Medina-Lopez, E., Anjos, M. F., Sylvester, J., & dos Reis, G. (2020). Identification and machine learning prediction of knee-point and knee-onset in capacity degradation curves of lithium-ion cells. Energy and AI, 1, 100006 (10 pages). https://doi.org/10.1016/j.egyai.2020.100006 |
---|---|
Statistiques
Total des téléchargements à partir de PolyPublie
Téléchargements par année

Provenance des téléchargements

Dimensions