Failure mode diagnosis in proton exchange membrane fuel cells using local electrochemical noise
Source abstract
Abstract
Early diagnosis of fuel cell failure modes is a very active research topic, as it improves robustness and durability of fuel cells used in commercial applications. The diagnosis method should be suited for being applied in real time, without interfering with the fuel cell operation, and it should be implemented using inexpensive hardware and light equipment. A novel method of failure diagnosis in PEM fuel cells, based on the analysis of local electrochemical noise, is proposed. Seven electrochemical noise signals are acquired in different parts of the cell, significantly increasing the information for an effective diagnosis, since previous studies have only analyzed a single signal from the electrochemical noise in the cell. Each electrochemical noise signal is frequency decomposed using wavelet transform to create a characteristic pattern. These patterns are used in a deep learning neural network to perform the cell state classification. The proposed method has been successfully applied to the classification of 26 different states achieved in experiments where the following factors have been varied: (1) average current density; (2) airflow; (3) drying; and (4) air pressure. The mean successful identification rate of the 26 states is above 85%. The proposed diagnosis method is well-suited for real-time diagnosis, and it can be implemented using lightweight and inexpensive hardware.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Fuel Cells and Related Materials · Advanced Chemical Sensor Technologies · Fault Detection and Control Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (65)
Show source-provided references
1. System integration, durability and reliability of fuel cells: Challenges and solutions10.1016/j.apenergy.2016.12.083 ↗
2. Supervised classification approach dedicated to proton exchange membrane fuel cell diagnostic
3. A transfer function approach for a generalized electrochemical impedance spectroscopy10.1149/1.2054888 ↗
4. Methanol as antifreeze agent for cold start of automotive polymer electrolyte membrane fuel cells10.1016/j.apenergy.2019.01.036 ↗
5. Diagnosis of performance degradation phenomena in PEM fuel cells10.1016/j.ijhydene.2009.03.054 ↗
6. Application of buckingham Pi theorem for scaling-up oriented fast modelling of proton exchange membrane fuel cell impedance10.1016/j.jpowsour.2017.03.116 ↗
7. Advancements on scaling-up simulation of proton exchange membrane fuel cells impedance through buckingham Pi theorem10.1016/j.apenergy.2019.04.067 ↗
8. Diagnosis of PEM fuel cells through current interruption10.1016/j.jpowsour.2007.06.072 ↗
9. Measurement of ohmic voltage losses in individual cells of a PEMFC stack10.1016/S0378-7753(02)00391-9 ↗
10. Evaluation of current distribution in a proton exchange membrane fuel cell by segmented cell approach10.1016/S0378-7753(02)00352-X ↗
11. Study of low concentration CO poisoning of pt anode in a protonexchange membrane fuel cell using spatial electrochemical impedancespectroscopy10.1016/j.jpowsour.2014.06.146 ↗
12. Study of acetylene poisoning of Pt cathode on proton exchange membrane fuel cell spatial performance using a segmented cell system10.1016/j.jpowsour.2015.04.073 ↗
13. Segmented cells as tool for development of fuel cells and error prevention/prediagnostic in fuel cell stacks10.1016/j.jpowsour.2007.03.055 ↗
14. Local impact of load cycling on degradation in polymer electrolyte fuel cells10.1016/j.apenergy.2019.114210 ↗
15. Pressure voltage oscillations as diagnostic tool for PEFC cathode10.1016/j.elecom.2009.11.003 ↗
16. Studying mass transport dynamics in polymer electrolyte membrane fuel cells using concentration-alternating frequency response analysis10.1016/j.jpowsour.2018.11.065 ↗
17. Comprehensive analysis of galvanostatic charge method for fuel cell degradation diagnosis10.1016/j.apenergy.2018.01.005 ↗
18. Extended Kalman filter for prognostic of proton exchange membrane fuel cell10.1016/j.apenergy.2015.11.071 ↗
19. Online implementation of SVM based fault diagnosis strategy for PEMFC systems10.1016/j.apenergy.2015.11.060 ↗
20. Fault diagnosis for fuel cell systems: A data-driven approach using high-precise voltage sensors10.1016/j.renene.2018.09.077 ↗
21. PEMFC stack voltage singularity measurement and fault classification10.1016/j.ijhydene.2014.09.117 ↗
22. Remaining useful life estimation for proton exchange membrane fuel cells using a hybrid method10.1016/j.apenergy.2019.01.023 ↗
23. Fault tolerance control for proton exchange membrane fuel cell systems10.1016/j.jpowsour.2016.05.066 ↗
24. Model-based diagnosis through structural analysis and causal computation for automotive polymer electrolyte membrane fuel cell systems10.1016/j.jpowsour.2017.04.089 ↗
25. Intelligent simultaneous fault diagnosis for solid oxide fuel cell system based on deep learning
26. Hierarchical model predictive control via deep learning vehicle speed predictions for oxygen stoichiometry regulation of fuel cells10.1016/j.apenergy.2020.115460 ↗
27. Analysis of electrochemical noise generated by corroding electrodes under open-circuit conditions10.1149/1.2096177 ↗
28. Review of applications of impedance and noise analysis to uniform and localized corrosion10.5006/1.3315878 ↗
29. Corrosion monitoring system based on measurement and analysis of electrochemical noise10.5006/1.3293594 ↗
30. Review - electrochemical noise applied in corrosion science: theoretical and mathematical models towards quantitative analysis10.1149/1945-7111/ab8de3 ↗
31. Evaluation of coating degradation with electrochemical impedance spectroscopy and electrochemical noise analysis10.1149/1.2055121 ↗
32. Comparison of electrochemical impedance and noise data in frequency domain10.1016/S0013-4686(97)00060-1 ↗
33. On the interpretation of the electrochemical noise data for coating10.1016/S0300-9440(00)00096-5 ↗
34. Voltage noise measurements on sealed lead-acid batteries10.1016/0378-7753(89)80131-4 ↗
35. Application of electrochemical noise analysis to the study of batteries: state-of-charge determination and overcharge detection10.1016/S0378-7753(99)00272-4 ↗
36. Small bandwidth measurement of the noise voltage of batteries10.1016/S0378-7753(02)00599-2 ↗
37. New methodology of electrochemical noise analysis and applications for commercial Li-ion batteries10.1007/s10008-015-2855-2 ↗
38. Study on glucose biofuel cells using an electrochemical noise device10.1002/elan.200804220 ↗
39. An analysis of fluidic voltage statistical correlation for a diagnosis of PEM fuel cell flooding10.1016/j.ijhydene.2013.01.060 ↗
40. Fuel cell diagnostics using identification measurement theory10.1115/1.4027395 ↗
41. Electrochemical noise of a hydrogen-air polymer electrolyte fuel cell operating at different loads10.1007/s10008-018-3892-4 ↗
42. Fluctuations in electrochemical systems. I. General theory on diffusion limited electrochemical reactions10.1063/1.465440 ↗
43. Fluctuations in electrochemical systems. II. Application to a diffusion limited redox process10.1063/1.465417 ↗
44. Electrochemical noise measurement of polymer membrane fuel cell under load10.1134/S1023193518060034 ↗
45. First results on PEMFC diagnosis by electrochemical noise10.1016/j.elecom.2011.10.007 ↗
46. An analysis of fluidic voltage statistical correlation for a diagnosis of PEM fuel cell flooding10.1016/j.ijhydene.2013.01.060 ↗
47. A signal-based method for fast PEMFC diagnosis10.1016/j.apenergy.2015.12.084 ↗
48. Proton exchange membrane fuel cell failure mode early diagnosis with wavelet analysis of electrochemical noise10.1016/j.ijhydene.2016.05.292 ↗
49. Prognostics of proton exchange membrane fuel cells stack using an ensemble of constraints based connectionist networks10.1016/j.jpowsour.2016.05.092 ↗
50. Kaz · 2004
51. Kaz · 2006
52. Deep Learning Toolbox, Mathworks, URL https://www.mathworks.com/help/deeplearning.
53. Wavelets Toolbox, Mathworks, URL https://www.mathworks.com/help/wavelet.
54. Review of deep learning algorithms and architectures10.1109/ACCESS.2019.2912200 ↗
55. Deep learning for time series classification: a review10.1007/s10618-019-00619-1 ↗
56. Sparse autoencoder and softmax regression based diagnosis method for the attachment on the blades of marine current turbine10.3390/s19040826 ↗
57. Deep learning approach for active classification of electrocardiogram signals10.1016/j.ins.2016.01.082 ↗
58. Transient response of performance in a proton exchange membrane fuel cell under dynamic loading10.1016/j.enconman.2020.113492 ↗
59. Dynamic performance of an in-rack proton exchange membrane fuel cell battery system to power servers10.1016/j.ijhydene.2017.03.004 ↗
60. Oscillations of PEM fuel cells at low cathode humidification10.1016/j.jelechem.2010.04.005 ↗
61. PEMFC operation failure under severe dehydration10.1016/j.ijhydene.2011.11.059 ↗
62. Analysis of the influence of temperature and gas humidity on the performance stability of polymer electrolyte membrane fuel cells10.1149/2.0071603jes ↗
63. Experimental and numerical studies of local current mapping on a PEM fuel cell10.1016/j.ijhydene.2008.07.035 ↗
64. Effect of the inlet gas humidification on PEMFC behavior and current density distribution10.1149/06403.0603ecst ↗
65. Performance improvement of self-humidifying PEM fuel cells using water injection at various start-up conditions10.1016/j.energy.2019.06.154 ↗