Physics-Guided Continual Learning for Predicting Emerging Aqueous Organic Redox Flow Battery Material Performance

Fu, Yucheng; Howard, Amanda; Zeng, Chao; Chen, Yunxiang; Gao, Peiyuan; Stinis, Panos

doi:10.1021/acsenergylett.4c00493

Title: Physics-Guided Continual Learning for Predicting Emerging Aqueous Organic Redox Flow Battery Material Performance

Journal Article · 16 May 2024 · ACS Energy Letters

DOI: https://doi.org/10.1021/acsenergylett.4c00493 · OSTI ID:2378039

^[1];

^[1]; Chen, Yunxiang ^[1];

^[1]; Stinis, Panos ^[1]

Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)

Aqueous organic redox flow batteries (AORFBs) have gained popularity in renewable energy storage due to their low cost, environmental friendliness and scalability. The rapid discovery of aqueous soluble organic (ASO) redox-active materials necessitates efficient machine learning surrogates for predicting battery performance. The physics-guided continual learning (PGCL) method proposed in this study can incrementally learn data from new ASO electrolytes while addressing catastrophic forgetting issues in conventional machine learning. Using a AORFB database with a thousand potential materials generated by a 780 $$\text{cm}^2$$ interdigitated cell model, PGCL incorporates AORFB physics to optimize the continual learning task formation and training strategies to retain previously learned battery material knowledge. Finally, the trained PGCL demonstrates its capability in assessing emerging ASO materials within the established parameter space when evaluated with the dihydroxyphenazine isomers.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)

Sponsoring Organization:: USDOE Laboratory Directed Research and Development (LDRD) Program

Grant/Contract Number:: AC05-76RL01830

OSTI ID:: 2378039

Report Number(s):: PNNL-SA--192565

Journal Information:: ACS Energy Letters, Journal Name: ACS Energy Letters Journal Issue: 6 Vol. 9; ISSN 2380-8195

Publisher:: American Chemical Society (ACS)Copyright Statement

Country of Publication:: United States

Language:: English

References (40)

Recent Progress in Redox Flow Battery Research and Development Wang, Wei; Luo, Qingtao; Li, Bin Advanced Functional Materials, Vol. 23, Issue 8, p. 970-986 https://doi.org/10.1002/adfm.201200694	journal	September 2012
Machine Learning Coupled Multi‐Scale Modeling for Redox Flow Batteries Bao, Jie; Murugesan, Vijayakumar; Kamp, Carl Justin Advanced Theory and Simulations, Vol. 3, Issue 2 https://doi.org/10.1002/adts.201900167	journal	November 2019
Redox-Flow Batteries: From Metals to Organic Redox-Active Materials Winsberg, Jan; Hagemann, Tino; Janoschka, Tobias Angewandte Chemie International Edition, Vol. 56, Issue 3 https://doi.org/10.1002/anie.201604925	journal	November 2016
Redox flow batteries a review Weber, Adam Z.; Mench, Matthew M.; Meyers, Jeremy P. Journal of Applied Electrochemistry, Vol. 41, Issue 10, p. 1137-1164 https://doi.org/10.1007/s10800-011-0348-2	journal	September 2011
Aqueous organic redox flow batteries Singh, Vikram; Kim, Soeun; Kang, Jungtaek Nano Research, Vol. 12, Issue 9 https://doi.org/10.1007/s12274-019-2355-2	journal	March 2019
An efficient sampling scheme: Updated Latin Hypercube Sampling Florian, Aleš Probabilistic Engineering Mechanics, Vol. 7, Issue 2 https://doi.org/10.1016/0266-8920(92)90015-A	journal	January 1992
A coupled machine learning and genetic algorithm approach to the design of porous electrodes for redox flow batteries Wan, Shuaibin; Liang, Xiongwei; Jiang, Haoran Applied Energy, Vol. 298 https://doi.org/10.1016/j.apenergy.2021.117177	journal	September 2021
Lifelong learning with deep conditional generative replay for dynamic and adaptive modeling towards net zero emissions target in building energy system Chen, Siliang; Ge, Wei; Liang, Xinbin Applied Energy, Vol. 353 https://doi.org/10.1016/j.apenergy.2023.122189	journal	January 2024
A review of energy storage types, applications and recent developments Koohi-Fayegh, S.; Rosen, M. A. Journal of Energy Storage, Vol. 27 https://doi.org/10.1016/j.est.2019.101047	journal	February 2020
Performance of a low cost interdigitated flow design on a 1 kW class all vanadium mixed acid redox flow battery Reed, David; Thomsen, Edwin; Li, Bin Journal of Power Sources, Vol. 306 https://doi.org/10.1016/j.jpowsour.2015.11.089	journal	February 2016
Physics-constrained deep neural network method for estimating parameters in a redox flow battery He, QiZhi; Stinis, Panos; Tartakovsky, Alexandre M. Journal of Power Sources, Vol. 528 https://doi.org/10.1016/j.jpowsour.2022.231147	journal	April 2022
Physics-informed CoKriging model of a redox flow battery Howard, Amanda A.; Yu, Tong; Wang, Wei Journal of Power Sources, Vol. 542 https://doi.org/10.1016/j.jpowsour.2022.231668	journal	September 2022
Enhanced physics-constrained deep neural networks for modeling vanadium redox flow battery He, QiZhi; Fu, Yucheng; Stinis, Panos Journal of Power Sources, Vol. 542 https://doi.org/10.1016/j.jpowsour.2022.231807	journal	September 2022
Response surface design evaluation and comparison Anderson-Cook, Christine M.; Borror, Connie M.; Montgomery, Douglas C. Journal of Statistical Planning and Inference, Vol. 139, Issue 2 https://doi.org/10.1016/j.jspi.2008.04.004	journal	February 2009
Continual lifelong learning with neural networks: A review Parisi, German I.; Kemker, Ronald; Part, Jose L. Neural Networks, Vol. 113 https://doi.org/10.1016/j.neunet.2019.01.012	journal	May 2019
Regularization-based Continual Learning for Fault Prediction in Lithium-Ion Batteries Maschler, Benjamin; Tatiyosyan, Sophia; Weyrich, Michael Procedia CIRP, Vol. 112 https://doi.org/10.1016/j.procir.2022.09.091	journal	January 2022
Embracing Change: Continual Learning in Deep Neural Networks Hadsell, Raia; Rao, Dushyant; Rusu, Andrei A. Trends in Cognitive Sciences, Vol. 24, Issue 12 https://doi.org/10.1016/j.tics.2020.09.004	journal	December 2020
Electrolyte Lifetime in Aqueous Organic Redox Flow Batteries: A Critical Review Kwabi, David G.; Ji, Yunlong; Aziz, Michael J. Chemical Reviews, Vol. 120, Issue 14 https://doi.org/10.1021/acs.chemrev.9b00599	journal	February 2020
On Lifetime and Cost of Redox-Active Organics for Aqueous Flow Batteries Brushett, Fikile R.; Aziz, Michael J.; Rodby, Kara E. ACS Energy Letters, Vol. 5, Issue 3 https://doi.org/10.1021/acsenergylett.0c00140	journal	February 2020
Redox Flow Batteries Kamat, Prashant V.; Schanze, Kirk S.; Buriak, Jillian M. ACS Energy Letters, Vol. 2, Issue 6 https://doi.org/10.1021/acsenergylett.7b00361	journal	May 2017
Materials and Systems for Organic Redox Flow Batteries: Status and Challenges Wei, Xiaoliang; Pan, Wenxiao; Duan, Wentao ACS Energy Letters, Vol. 2, Issue 9 https://doi.org/10.1021/acsenergylett.7b00650	journal	August 2017
High-Performance Alkaline Organic Redox Flow Batteries Based on 2-Hydroxy-3-carboxy-1,4-naphthoquinone Wang, Caixing; Yang, Zhen; Wang, Yanrong ACS Energy Letters, Vol. 3, Issue 10 https://doi.org/10.1021/acsenergylett.8b01296	journal	September 2018
Evaluation of Deep Learning Architectures for Aqueous Solubility Prediction Panapitiya, Gihan; Girard, Michael; Hollas, Aaron ACS Omega, Vol. 7, Issue 18 https://doi.org/10.1021/acsomega.2c00642	journal	April 2022
Vanadium Flow Battery for Energy Storage: Prospects and Challenges Ding, Cong; Zhang, Huamin; Li, Xianfeng The Journal of Physical Chemistry Letters, Vol. 4, Issue 8 https://doi.org/10.1021/jz4001032	journal	March 2013
Redox flow batteries go organic Wang, Wei; Sprenkle, Vince Nature Chemistry, Vol. 8, Issue 3 https://doi.org/10.1038/nchem.2466	journal	February 2016
A biomimetic high-capacity phenazine-based anolyte for aqueous organic redox flow batteries Hollas, Aaron; Wei, Xiaoliang; Murugesan, Vijayakumar Nature Energy, Vol. 3, Issue 6 https://doi.org/10.1038/s41560-018-0167-3	journal	June 2018
Emerging chemistries and molecular designs for flow batteries Zhang, Leyuan; Feng, Ruozhu; Wang, Wei Nature Reviews Chemistry, Vol. 6, Issue 8 https://doi.org/10.1038/s41570-022-00394-6	journal	June 2022
SOMAS: a platform for data-driven material discovery in redox flow battery development Gao, Peiyuan; Andersen, Amity; Sepulveda, Jonathan Scientific Data, Vol. 9, Issue 1 https://doi.org/10.1038/s41597-022-01814-4	journal	December 2022
Organic Redox Species in Aqueous Flow Batteries: Redox Potentials, Chemical Stability and Solubility Wedege, Kristina; Dražević, Emil; Konya, Denes Scientific Reports, Vol. 6, Issue 1 https://doi.org/10.1038/srep39101	journal	December 2016
Cost, performance prediction and optimization of a vanadium flow battery by machine-learning Li, Tianyu; Xing, Feng; Liu, Tao Energy & Environmental Science, Vol. 13, Issue 11 https://doi.org/10.1039/D0EE02543G	journal	January 2020
Graphical Gaussian process regression model for aqueous solvation free energy prediction of organic molecules in redox flow batteries Gao, Peiyuan; Yang, Xiu; Tang, Yu-Hang Physical Chemistry Chemical Physics, Vol. 23, Issue 43 https://doi.org/10.1039/D1CP04475C	journal	January 2021
Machine learning-assisted design of flow fields for redox flow batteries Wan, Shuaibin; Jiang, Haoran; Guo, Zixiao Energy & Environmental Science, Vol. 15, Issue 7 https://doi.org/10.1039/D1EE03224K	journal	January 2022
Machine learning for flow batteries: opportunities and challenges Li, Tianyu; Zhang, Changkun; Li, Xianfeng Chemical Science, Vol. 13, Issue 17 https://doi.org/10.1039/D2SC00291D	journal	January 2022
Overcoming catastrophic forgetting in neural networks Kirkpatrick, James; Pascanu, Razvan; Rabinowitz, Neil Proceedings of the National Academy of Sciences, Vol. 114, Issue 13 https://doi.org/10.1073/pnas.1611835114	journal	March 2017
Learning without Forgetting Li, Zhizhong; Hoiem, Derek IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 40, Issue 12 https://doi.org/10.1109/TPAMI.2017.2773081	journal	December 2018
Lifelong Learning for Complementary Generation Control of Interconnected Power Grids With High-Penetration Renewables and EVs Zhang, Xiao Shun; Yu, Tao; Pan, Zhen Ning IEEE Transactions on Power Systems, Vol. 33, Issue 4 https://doi.org/10.1109/TPWRS.2017.2767318	journal	July 2018
Battery Diagnosis: A Lifelong Learning Framework for Electric Vehicles Zhao, Jingyuan; Nan, Jinrui; Wang, Junbin 2022 IEEE Vehicle Power and Propulsion Conference (VPPC) https://doi.org/10.1109/VPPC55846.2022.10003378	conference	November 2022
CLeaR: An adaptive continual learning framework for regression tasks He, Yujiang; Sick, Bernhard AI Perspectives, Vol. 3, Issue 1 https://doi.org/10.1186/s42467-021-00009-8	journal	July 2021
An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks Goodfellow, Ian J.; Mirza, Mehdi; Xiao, Da arXiv https://doi.org/10.48550/arXiv.1312.6211	preprint	January 2013
Physics-Guided Continual Learning for Predicting Emerging Aqueous Organic Redox Flow Battery Material Performance Fu, Yucheng; Howard, Amanda; Zeng, Chao arXiv https://doi.org/10.48550/arXiv.2312.08481	preprint	January 2023

Similar Records

Computationally efficient models for aqueous organic redox flow batteries

Journal Article · 2025 · Journal of Energy Storage · OSTI ID:2585163

Bao, Jie; Howard, Amanda; El Bendali, Ayoub; +13 more

Evaluating large scale aqueous organic redox flow battery performance with a hybrid numerical and machine learning framework

Technical Report · 2024 · OSTI ID:2476870

Chen, Yunxiang; Zeng, Chao; Fu, Yucheng; +7 more

A hybrid numerical and machine learning framework for evaluating the performance of a 780 cm² aqueous organic redox flow battery

Journal Article · 2025 · Journal of Power Sources · OSTI ID:2526234

Chen, Yunxiang; Zeng, Chao; Fu, Yucheng; +7 more

Related Subjects

25 ENERGY STORAGE
Elastic Weight Consolidation
Learning without Forgetting
aqueous organic redox flow battery
continual learning
energy storage

Title: Physics-Guided Continual Learning for Predicting Emerging Aqueous Organic Redox Flow Battery Material Performance

Citation Formats

References (40)

Similar Records

Related Subjects