journal article·2023-07

Predicting optimal membrane hydration and ohmic losses in operating fuel cells with machine learning

Joshua Paciocco, Taylr Cawte, Aimy Bazylak

Publisher page

Abstract

The absence of proper membrane hydration in membrane electrode assembly (MEA)-based electrochemical energy conversion technologies can lead to disastrous effects, such as reactant crossover, material degradation, and cell failure. In this work, we are the first to apply machine learning to predict if the optimal membrane hydration has been reached in polymer electrolyte membrane (PEM) fuel cells. We evaluate the ability of machine and deep learning algorithms to predict the high frequency resistance (HFR) and whether the optimal hydration current density (OHCD) has been reached via parameters measured from electrochemical impedance spectroscopy (EIS). We accurately predict the HFR using a long short-term memory recurrent neural network model (3.11% mean absolute percentage error and over 0.95 R 2 ). We also accurately predict OHCD with precision and recall values over 98% using deep learning and a k-nearest neighbours model. Furthermore, our models provide a powerful tool for real-time parameter estimation and control systems to monitor and improve the performance of PEM fuel cells and other electrochemical energy devices, such as water and carbon dioxide electrolyzers.
Source: expertdata · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Fuel Cells and Related Materials · Advanced Battery Technologies Research · Electrocatalysts for Energy Conversion

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

References (69)

Show source-provided references
1. A review of the main parameters influencing long-term performance and durability of PEM fuel cells10.1016/j.jpowsour.2008.01.070 ↗
2. Water uptake by and transport through Nafion® 117 membranes10.1149/1.2056194 ↗
3. Polymer electrolyte fuel cell model10.1149/1.2085971 ↗
4. Proton conductors for heavy-duty vehicle fuel cells10.1016/j.joule.2021.05.016 ↗
5. Boosting membrane hydration for high current densities in membrane electrode assembly CO2 electrolysis10.1021/acsami.0c14832 ↗
6. Bubbles: the good, the bad, and the ugly10.1016/j.joule.2020.12.024 ↗
7. Advancing proton exchange membrane electrolyzers with molecular catalysts10.1016/j.joule.2020.06.001 ↗
8. Impact of intermittent operation on lifetime and performance of a PEM water electrolyzer10.1149/2.0421908jes ↗
9. Polymer electrolyte membrane water electrolysis: restraining degradation in the presence of fluctuating power10.1016/j.jpowsour.2016.11.118 ↗
10. A review on PEM voltage degradation associated with water management: impacts, influent factors and characterization10.1016/j.jpowsour.2008.04.037 ↗
11. Properties of Nafion membranes under PEM water electrolysis conditions10.1016/j.ijhydene.2011.05.127 ↗
12. Water transport characteristics of a PEM fuel cell at various operating pressures and temperatures10.1016/j.ijhydene.2012.12.076 ↗
13. Anode-design strategies for improved performance of polymer-electrolyte fuel cells with ultra-thin electrodes10.1016/j.joule.2018.03.022 ↗
14. Review: durability and degradation issues of PEM fuel cell components10.1002/fuce.200700053 ↗
15. Characterization of membrane degradation growth in fuel cells using X-ray computed tomography10.1149/2.0251806jes ↗
16. Research priorities for seasonal energy storage using electrolyzers and fuel cells10.1016/j.joule.2021.12.020 ↗
17. All‐hydrocarbon MEA for PEM water electrolysis combining low hydrogen crossover and high efficiency
18. Engineering catalyst layers for next‐generation polymer electrolyte fuel cells: a review of design, materials, and methods10.1002/aenm.202101025 ↗
19. Research trends in proton exchange membrane fuel cells during 2008–2018: a bibliometric analysis10.1016/j.heliyon.2019.e01724 ↗
20. Bollini Braga · 2013
21. 2004
22. Fuel cell and hydrogen power plants
23. Fuel cells: a call for total design10.1016/j.joule.2018.07.004 ↗
24. Accelerating materials development via automation, machine learning, and high-performance computing10.1016/j.joule.2018.05.009 ↗
25. Machine learning for guiding high-temperature PEM fuel cells with greater power density10.1016/j.patter.2020.100187 ↗
26. Fundamentals, materials, and machine learning of polymer electrolyte membrane fuel cell technology10.1016/j.egyai.2020.100014 ↗
27. Machine learning modeling for proton exchange membrane fuel cell performance10.1016/j.egyai.2022.100183 ↗
28. Latorrata · 2018
29. Anion-exchange membranes in electrochemical energy systems10.1039/C4EE01303D ↗
30. Comprehensive investigation of novel pore-graded gas diffusion layers for high-performance and cost-effective proton exchange membrane electrolyzers10.1039/C7EE01240C ↗
31. Water electrolysis: from textbook knowledge to the latest scientific strategies and industrial developments10.1039/D0CS01079K ↗
32. Electrochemical polarization analysis for optimization of external operation parameters in zinc fuel cells10.1039/D0RA04454G ↗
33. Femtosecond laser-induced surface structuring of the porous transport layers in proton exchange membrane water electrolysis10.1039/C9TA12127G ↗
34. Analysis and modeling of PEMFC degradation: effect on oxygen transport10.1016/j.jpowsour.2012.04.069 ↗
35. Effect of operating conditions on current density distribution and high frequency resistance in a segmented PEM fuel cell10.1016/j.ijhydene.2012.02.024 ↗
36. Three-dimensional computational analysis of transport phenomena in a PEM fuel cell—a parametric study10.1016/S0378-7753(03)00816-4 ↗
37. Proton exchange membrane fuel cell degradation: a parametric analysis using Computational Fluid Dynamics10.1016/j.jpowsour.2015.11.042 ↗
38. Membrane dehydration with increasing current density at high inlet gas relative humidity in polymer electrolyte membrane fuel cells10.1016/j.jpowsour.2019.03.001 ↗
39. Modelling and control of vehicle integrated thermal management system of PEM fuel cell vehicle10.1016/j.energy.2020.117495 ↗
40. PEM fuel cell system control: a review10.1016/j.renene.2017.06.027 ↗
41. Performance prediction and power density maximization of a proton exchange membrane fuel cell based on deep belief network10.1016/j.jpowsour.2020.228154 ↗
42. Performance prediction of proton-exchange membrane fuel cell based on convolutional neural network and random forest feature selection10.1016/j.enconman.2021.114367 ↗
43. Comparative study on prediction of fuel cell performance using machine learning approaches
44. AI-based optimization of PEM fuel cell catalyst layers for maximum power density via data-driven surrogate modeling10.1016/j.enconman.2019.112460 ↗
45. Prediction of high frequency resistance in polymer electrolyte membrane fuel cells using long short term memory based model10.1016/j.egyai.2020.100045 ↗
46. Estimating PEMFC ohmic internal impedance based on indirect measurements10.1002/ese3.878 ↗
47. Recent advances and summarization of fault diagnosis techniques for proton exchange membrane fuel cell systems: a critical overview10.1016/j.jpowsour.2021.229932 ↗
48. Failure mode diagnosis in proton exchange membrane fuel cells using local electrochemical noise10.1016/j.jpowsour.2022.231582 ↗
49. Fault detection and isolation of high temperature proton exchange membrane fuel cell stack under the influence of degradation10.1016/j.jpowsour.2017.05.021 ↗
50. Data-based flooding fault diagnosis of proton exchange membrane fuel cell systems using LSTM networks10.1016/j.egyai.2021.100056 ↗
51. Resolving the gas diffusion layer substrate land and channel region contributions to the oxygen transport resistance of a partially-saturated substrate10.1016/j.electacta.2019.135001 ↗
52. Graded microporous layers for enhanced capillary-driven liquid water removal in polymer electrolyte membrane fuel cells
53. 2022
54. Scikit-learn: machine learning in Python
55. Abadi
56. An overview of the supervised machine learning methods10.20544/HORIZONS.B.04.1.17.P05 ↗
57. Machine learning from theory to algorithms: an overview10.1088/1742-6596/1142/1/012012 ↗
58. Machine learning methods for solar radiation forecasting: a review10.1016/j.renene.2016.12.095 ↗
59. Forecasting with artificial neural networks: the state of the art10.1016/S0169-2070(97)00044-7 ↗
60. Creating artificial neural networks that generalize10.1016/0893-6080(91)90033-2 ↗
61. Haykin · 2008
62. Stock market prediction using LSTM recurrent neural network10.1016/j.procs.2020.03.049 ↗
63. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network10.1016/j.physd.2019.132306 ↗
64. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
65. Root mean square error (RMSE) or mean absolute error (MAE)?-Arguments against avoiding RMSE in the literature10.5194/gmd-7-1247-2014 ↗
66. Mean absolute percentage error for regression models10.1016/j.neucom.2015.12.114 ↗
67. The correlation coefficient: an overview10.1080/10408340500526766 ↗
68. Zheng · 2015
69. Foley · 2015