Health Prediction for Lithium-Ion Batteries Under Unseen Working Conditions. Che, Y., Forest, F., Zheng, Y., Xu, L., & Teodorescu, R. IEEE Transactions on Industrial Electronics, April, 2024. 
![Health Prediction for Lithium-Ion Batteries Under Unseen Working Conditions [link]](https://bibbase.org/img/filetypes/link.svg "link")
Link doi abstract bibtex 1 download Battery health prediction is significant while challenging for intelligent battery management. This article proposes a general framework for both short-term and long-term predictions of battery health under unseen dynamic loading and temperature conditions using domain-adaptive multitask learning (MTL) with long-term regularization. First, features extracted from partial charging curves are utilized for short-term state of health predictions. Then, the long-term degradation trajectory is directly predicted by recursively using the predicted features within the multitask framework, enhancing the model integrity and lowering the complexity. Then, domain adaptation (DA) is adopted to reduce the discrepancies between different working conditions. Additionally, a long-term regularization is introduced to address the shortcoming that arises when the model is extrapolated recursively for future health predictions. Thus, the short-term prediction ability is maintained while the long-term prediction performance is enhanced. Finally, predictions are validated through aging experiments under various dynamic loading profiles. By using partial charging capacity–voltage data, the results show that the early-stage long-term predictions are accurate and stable under various working profiles, with root mean square errors below 2% and fitting coefficients surpassing 0.86.
@article{che2024health,
title = {Health {Prediction} for {Lithium}-{Ion} {Batteries} {Under} {Unseen} {Working} {Conditions}},
issn = {1557-9948},
doi = {10.1109/TIE.2024.3379664},
abstract = {Battery health prediction is significant while challenging for intelligent battery management. This article proposes a general framework for both short-term and long-term predictions of battery health under unseen dynamic loading and temperature conditions using domain-adaptive multitask learning (MTL) with long-term regularization. First, features extracted from partial charging curves are utilized for short-term state of health predictions. Then, the long-term degradation trajectory is directly predicted by recursively using the predicted features within the multitask framework, enhancing the model integrity and lowering the complexity. Then, domain adaptation (DA) is adopted to reduce the discrepancies between different working conditions. Additionally, a long-term regularization is introduced to address the shortcoming that arises when the model is extrapolated recursively for future health predictions. Thus, the short-term prediction ability is maintained while the long-term prediction performance is enhanced. Finally, predictions are validated through aging experiments under various dynamic loading profiles. By using partial charging capacity–voltage data, the results show that the early-stage long-term predictions are accurate and stable under various working profiles, with root mean square errors below 2\% and fitting coefficients surpassing 0.86.},
journal = {IEEE Transactions on Industrial Electronics},
author = {Che, Yunhong and Forest, Florent and Zheng, Yusheng and Xu, Le and Teodorescu, Remus},
year = {2024},
month = apr,
keywords = {Aging, Batteries, Battery, Degradation, domain adaptation (DA), Feature extraction, health and trajectory prediction, Loading, multi-task learning, Predictive models, Testing, transfer learning},
pages = {1--11},
url_Link = {https://ieeexplore.ieee.org/document/10500447},
bibbase_note = {<img src="assets/img/papers/battery-conditions.png">}
}
Downloads: 1
{"_id":"FcjqATJFs6qQTqna4","bibbaseid":"che-forest-zheng-xu-teodorescu-healthpredictionforlithiumionbatteriesunderunseenworkingconditions-2024","author_short":["Che, Y.","Forest, F.","Zheng, Y.","Xu, L.","Teodorescu, R."],"bibdata":{"bibtype":"article","type":"article","title":"Health Prediction for Lithium-Ion Batteries Under Unseen Working Conditions","issn":"1557-9948","doi":"10.1109/TIE.2024.3379664","abstract":"Battery health prediction is significant while challenging for intelligent battery management. This article proposes a general framework for both short-term and long-term predictions of battery health under unseen dynamic loading and temperature conditions using domain-adaptive multitask learning (MTL) with long-term regularization. First, features extracted from partial charging curves are utilized for short-term state of health predictions. Then, the long-term degradation trajectory is directly predicted by recursively using the predicted features within the multitask framework, enhancing the model integrity and lowering the complexity. Then, domain adaptation (DA) is adopted to reduce the discrepancies between different working conditions. Additionally, a long-term regularization is introduced to address the shortcoming that arises when the model is extrapolated recursively for future health predictions. Thus, the short-term prediction ability is maintained while the long-term prediction performance is enhanced. Finally, predictions are validated through aging experiments under various dynamic loading profiles. By using partial charging capacity–voltage data, the results show that the early-stage long-term predictions are accurate and stable under various working profiles, with root mean square errors below 2% and fitting coefficients surpassing 0.86.","journal":"IEEE Transactions on Industrial Electronics","author":[{"propositions":[],"lastnames":["Che"],"firstnames":["Yunhong"],"suffixes":[]},{"propositions":[],"lastnames":["Forest"],"firstnames":["Florent"],"suffixes":[]},{"propositions":[],"lastnames":["Zheng"],"firstnames":["Yusheng"],"suffixes":[]},{"propositions":[],"lastnames":["Xu"],"firstnames":["Le"],"suffixes":[]},{"propositions":[],"lastnames":["Teodorescu"],"firstnames":["Remus"],"suffixes":[]}],"year":"2024","month":"April","keywords":"Aging, Batteries, Battery, Degradation, domain adaptation (DA), Feature extraction, health and trajectory prediction, Loading, multi-task learning, Predictive models, Testing, transfer learning","pages":"1–11","url_link":"https://ieeexplore.ieee.org/document/10500447","bibbase_note":"<img src=\"assets/img/papers/battery-conditions.png\">","bibtex":"@article{che2024health,\n\ttitle = {Health {Prediction} for {Lithium}-{Ion} {Batteries} {Under} {Unseen} {Working} {Conditions}},\n\tissn = {1557-9948},\n\tdoi = {10.1109/TIE.2024.3379664},\n\tabstract = {Battery health prediction is significant while challenging for intelligent battery management. This article proposes a general framework for both short-term and long-term predictions of battery health under unseen dynamic loading and temperature conditions using domain-adaptive multitask learning (MTL) with long-term regularization. First, features extracted from partial charging curves are utilized for short-term state of health predictions. Then, the long-term degradation trajectory is directly predicted by recursively using the predicted features within the multitask framework, enhancing the model integrity and lowering the complexity. Then, domain adaptation (DA) is adopted to reduce the discrepancies between different working conditions. Additionally, a long-term regularization is introduced to address the shortcoming that arises when the model is extrapolated recursively for future health predictions. Thus, the short-term prediction ability is maintained while the long-term prediction performance is enhanced. Finally, predictions are validated through aging experiments under various dynamic loading profiles. By using partial charging capacity–voltage data, the results show that the early-stage long-term predictions are accurate and stable under various working profiles, with root mean square errors below 2\\% and fitting coefficients surpassing 0.86.},\n\tjournal = {IEEE Transactions on Industrial Electronics},\n\tauthor = {Che, Yunhong and Forest, Florent and Zheng, Yusheng and Xu, Le and Teodorescu, Remus},\n\tyear = {2024},\n\tmonth = apr,\n\tkeywords = {Aging, Batteries, Battery, Degradation, domain adaptation (DA), Feature extraction, health and trajectory prediction, Loading, multi-task learning, Predictive models, Testing, transfer learning},\n\tpages = {1--11},\n\turl_Link = {https://ieeexplore.ieee.org/document/10500447},\n\tbibbase_note = {<img src=\"assets/img/papers/battery-conditions.png\">}\n}\n\n","author_short":["Che, Y.","Forest, F.","Zheng, Y.","Xu, L.","Teodorescu, R."],"key":"che2024health","id":"che2024health","bibbaseid":"che-forest-zheng-xu-teodorescu-healthpredictionforlithiumionbatteriesunderunseenworkingconditions-2024","role":"author","urls":{" link":"https://ieeexplore.ieee.org/document/10500447"},"keyword":["Aging","Batteries","Battery","Degradation","domain adaptation (DA)","Feature extraction","health and trajectory prediction","Loading","multi-task learning","Predictive models","Testing","transfer learning"],"metadata":{"authorlinks":{}},"downloads":1},"bibtype":"article","biburl":"https://florentfo.rest/files/publications.bib","dataSources":["2puawT8ZAQyYRypA3","DgnR6pzJ98ZEp97PW","pBkCjKbyeirr5jeAd"],"keywords":["aging","batteries","battery","degradation","domain adaptation (da)","feature extraction","health and trajectory prediction","loading","multi-task learning","predictive models","testing","transfer learning"],"search_terms":["health","prediction","lithium","ion","batteries","under","unseen","working","conditions","che","forest","zheng","xu","teodorescu"],"title":"Health Prediction for Lithium-Ion Batteries Under Unseen Working Conditions","year":2024,"downloads":1}