journal article·2022-04Open access

Physics-constrained deep neural network method for estimating parameters in a redox flow battery

QiZhi He, Panos Stinis, Alexandre M. Tartakovsky

Abstract

In this paper, we present a physics-constrained deep neural network (PCDNN) method for parameter estimation in the zero-dimensional (0D) model of the vanadium redox flow battery (VRFB). In this approach, we use deep neural networks (DNNs) to approximate the model parameters as functions of the operating conditions. This method allows the integration of the VRFB computational models as the physical constraints in the parameter learning process, leading to enhanced accuracy of parameter estimation and cell voltage prediction. Using an experimental dataset, we demonstrate that the PCDNN method can estimate model parameters for a range of operating conditions and improve the 0D model prediction of voltage compared to the 0D model prediction with constant operation-condition-independent parameters estimated with traditional inverse methods. We also demonstrate that the PCDNN approach has an improved generalization ability for estimating parameter values for operating conditions not used in the DNN training.
Source: openaire · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Advanced battery technologies research · Advanced Battery Technologies Research · Electrocatalysts for Energy Conversion

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (47)

Show source-provided references
1. Recent progress in redox flow battery research and development10.1002/adfm.201200694 ↗
2. The chemistry of redox-flow batteries10.1002/anie.201410823 ↗
3. Redox flow batteries: a review10.1007/s10800-011-0348-2 ↗
4. A study of the V (II)/V (III) redox couple for redox flow cell applications10.1016/0378-7753(85)80071-9 ↗
5. Investigation of the V (V)/V (IV) system for use in the positive half-cell of a redox battery
6. New all-vanadium redox flow cell10.1149/1.2108706 ↗
7. Development of the all-vanadium redox flow battery for energy storage: a review of technological, financial and policy aspects10.1002/er.1863 ↗
8. A dynamic performance model for redox-flow batteries involving soluble species10.1016/j.electacta.2008.05.067 ↗
9. Development and perspective in vanadium flow battery modeling10.1016/j.apenergy.2014.06.077 ↗
10. A dynamic unit cell model for the all-vanadium flow battery10.1149/1.3561426 ↗
11. Verified reduction of dimensionality for an all-vanadium redox flow battery model10.1016/j.jpowsour.2015.01.019 ↗
12. Low grade heat recovery for power generation through electrochemical route: Vanadium redox flow battery, a case study10.1016/j.apsusc.2018.02.025 ↗
13. Open data, models, and codes for vanadium redox batch cell systems: A systems approach using zero-dimensional models
14. Analysis of a model for the operation of a vanadium redox battery10.1016/j.energy.2010.03.060 ↗
15. An enhancement toVynnycky’s model for the all-vanadium redox flow battery10.1016/j.electacta.2013.12.074 ↗
16. A simple model for the vanadium redox battery10.1016/j.electacta.2009.06.086 ↗
17. The quasi-steady state of all-vanadium redox flow batteries: A scale analysis10.1016/j.electacta.2014.09.134 ↗
18. A three-dimensional model for negative half cell of the vanadium redox flow battery10.1016/j.electacta.2011.09.042 ↗
19. Numerical investigations of flow field designs for vanadium redox flow batteries10.1016/j.apenergy.2012.12.041 ↗
20. Non-isothermal modelling of the all-vanadium redox flow battery10.1016/j.electacta.2009.08.009 ↗
21. Modelling the effects of oxygen evolution in the all-vanadium redox flow battery10.1016/j.electacta.2009.12.085 ↗
22. An optimal strategy of electrolyte flow rate for vanadium redox flow battery10.1016/j.jpowsour.2011.11.036 ↗
23. Data-driven electrode parameter identification for vanadium redox flow batteries through experimental and numerical methods10.1016/j.apenergy.2020.115530 ↗
24. Modelling of redox flow battery electrode processes at a range of length scales: a review10.1039/D0SE00667J ↗
25. Chen · 2021
26. Machine learning coupled multi-scale modeling for redox flow batteries
27. Parameters estimation and model discrimination for solid–liquid reactions in batch processes10.1016/j.ces.2018.05.040 ↗
28. Multiple parameter identification using genetic algorithm in vanadium redox flow batteries
29. Determination of rate constants and reaction orders of vanadium-ion kinetics on carbon fiber electrodes
30. Jokar · 2016
31. Multi-objective optimization of lithium-ion battery model using genetic algorithm approach10.1016/j.jpowsour.2014.07.110 ↗
32. Precision dynamic equivalent circuit model of a vanadium redox flow battery and determination of circuit parameters for its optimal performance in renewable energy applications10.1016/j.jpowsour.2018.06.017 ↗
33. Real-time parameter estimation of an electrochemical lithium-ion battery model using a long short-term memory network10.1109/ACCESS.2020.2991124 ↗
34. Data-efficient parameter identification of electrochemical lithium-ion battery model using deep bayesian harmony search10.1016/j.apenergy.2019.113644 ↗
35. Goodfellow · 2016
36. Physics-informed neural networks for multiphysics data assimilation with application to subsurface transport10.1016/j.advwatres.2020.103610 ↗
37. Physics-informed deep neural networks for learning parameters and constitutive relationships in subsurface flow problems10.1029/2019WR026731 ↗
38. Tipireddy · 2019
39. Reyes · 2020
40. Open circuit voltage of vanadium redox flow batteries: Discrepancy between models and experiments10.1016/j.elecom.2011.01.020 ↗
41. Newman · 2012
42. Bird · 2002
43. Water uptake by and transport through nafion® 117 membranes
44. Polymer electrolyte fuel cell model10.1149/1.2085971 ↗
45. A limited memory algorithm for bound constrained optimization10.1137/0916069 ↗
46. Kingma · 2015 · 1
47. Comparison of single particle and equivalent circuit analog models for a lithium-ion cell10.1016/j.jpowsour.2011.06.007 ↗