Data-Driven Modeling and Monitoring of Fuel Cell Performance

Abstract A mathematical framework that provides practical guidelines for user adoption is proposed for fuel cell performance evaluation. By leveraging the mathematical framework, two measures that describe the average and worst-case performance are presented. To facilitate the computation of the performance measures in a practical setting, we model the distribution of the voltages at different current points as a Gaussian process. Then the minimum number of samples needed to estimate the performance measures is obtained using information-theoretic notions. Furthermore, we introduce a sensing algorithm that finds the current points that are maximally informative about the voltage. Observing the voltages at the points identified by the proposed algorithm enables the user to estimate the voltages at the unobserved points. The proposed performance measures and the corresponding results are validated on a fuel cell dataset provided by an industrial user whose conclusion coincides with the judgement from the fuel cell manufacturer.

[1]  H. Vincent Poor,et al.  Stealth Attacks on the Smart Grid , 2018, IEEE Transactions on Smart Grid.

[2]  Diego A. Gómez-Gualdrón,et al.  Attainable Volumetric Targets for Adsorption-Based Hydrogen Storage in Porous Crystals: Molecular Simulation and Machine Learning , 2018, The Journal of Physical Chemistry C.

[3]  D. B. Talange,et al.  Modeling and performance evaluation of PEM fuel cell by controlling its input parameters , 2017 .

[4]  R. Deo,et al.  Computational intelligence approach for modeling hydrogen production: a review , 2018 .

[5]  Fei Gao,et al.  Data-driven proton exchange membrane fuel cell degradation predication through deep learning method , 2018, Applied Energy.

[6]  Lin Wang,et al.  A parametric study of PEM fuel cell performances , 2003 .

[7]  Noureddine Zerhouni,et al.  A hybrid remaining useful life prognostic method for proton exchange membrane fuel cell , 2018, International Journal of Hydrogen Energy.

[8]  Antonia Maria Tulino,et al.  Linear Analog Coding of Correlated Multivariate Gaussian Sources , 2013, IEEE Transactions on Communications.

[9]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[10]  M. Y. El-Sharkh,et al.  Economics of hydrogen production and utilization strategies for the optimal operation of a grid-parallel PEM fuel cell power plant , 2010 .

[11]  A. Stefanopoulou,et al.  Control-oriented model of fuel processor for hydrogen generation in fuel cell applications , 2006 .

[12]  Jerry D. Gibson,et al.  Rate Distortion Functions and Rate Distortion Function Lower Bounds for Real-World Sources , 2017, Entropy.

[13]  Q. Liao,et al.  Current density distribution in air-breathing microfluidic fuel cells with an array of graphite rod anodes , 2020 .

[14]  Ay Su,et al.  Development of a small vehicular PEM fuel cell system , 2008 .

[15]  Lei Mao,et al.  Selection of optimal sensors for predicting performance of polymer electrolyte membrane fuel cell , 2016 .

[16]  Bin Jiang,et al.  Improved data driven model free adaptive constrained control for a solid oxide fuel cell , 2016 .

[17]  Satoshi Nakano,et al.  A Panoramic Analysis of Hydrogen Utilization Systems: Using an Input-output Table for Next Generation Energy Systems☆ , 2017 .

[18]  V. A. Danilov,et al.  A new technique of estimating anodic and cathodic charge transfer coefficients from SOFC polarization curves , 2009 .

[19]  Daniel Hissel,et al.  Sensor development and optimization for a proton exchange membrane fuel cell system in automotive applications , 2021 .

[20]  Kwang Y. Lee,et al.  Data-driven oxygen excess ratio control for proton exchange membrane fuel cell , 2018, Applied Energy.

[21]  T. Nejat Veziroglu,et al.  “Green” path from fossil-based to hydrogen economy: An overview of carbon-neutral technologies , 2008 .

[22]  Yongdong Li,et al.  Fault detection and isolation for Polymer Electrolyte Membrane Fuel Cell systems by analyzing cell voltage generated space , 2015 .

[23]  Xu Guo,et al.  Multi-objective decision analysis for data-driven based estimation of battery states: A case study of remaining useful life estimation , 2020 .

[24]  Hong-Wei Li,et al.  Performance prediction and power density maximization of a proton exchange membrane fuel cell based on deep belief network , 2020 .

[25]  M. Hirscher,et al.  Concepts for improving hydrogen storage in nanoporous materials , 2019, International Journal of Hydrogen Energy.

[26]  G. Zhu,et al.  Parameter study of high-temperature proton exchange membrane fuel cell using data-driven models , 2019, International Journal of Hydrogen Energy.

[27]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[28]  Davood Toghraie,et al.  Performance prediction and analysis of a dead-end PEMFC stack using data-driven dynamic model , 2019 .

[29]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[30]  Xi Li,et al.  Fault detection and assessment for solid oxide fuel cell system gas supply unit based on novel principal component analysis , 2019, Journal of Power Sources.

[31]  Mohammad Jafar Kermani,et al.  Influences of bipolar plate channel blockages on PEM fuel cell performances , 2016 .

[32]  Junye Wang,et al.  System integration, durability and reliability of fuel cells: Challenges and solutions , 2017 .

[33]  Alireza Rahnama,et al.  Machine learning based prediction of metal hydrides for hydrogen storage, part II: Prediction of material class , 2019, International Journal of Hydrogen Energy.

[34]  A. Rahnama,et al.  Machine learning based prediction of metal hydrides for hydrogen storage, part I: Prediction of hydrogen weight percent , 2019, International Journal of Hydrogen Energy.

[35]  Bowen Wang,et al.  AI-based optimization of PEM fuel cell catalyst layers for maximum power density via data-driven surrogate modeling , 2020 .

[36]  Randall Q. Snurr,et al.  Energy-based descriptors to rapidly predict hydrogen storage in metal–organic frameworks , 2019, Molecular Systems Design & Engineering.

[37]  Xiaofang Cheng,et al.  A Comparative Study of Using Polarization Curve Models in Proton Exchange Membrane Fuel Cell Degradation Analysis , 2020, Energies.

[38]  Shaker Haji,et al.  Analytical modeling of PEM fuel cell i–V curve , 2011 .

[39]  Daniel Hissel,et al.  Fault diagnosis for fuel cell systems: A data-driven approach using high-precise voltage sensors , 2019, Renewable Energy.

[40]  P. Shearing,et al.  Effect of reactant gas flow orientation on the current and temperature distribution in self-heating polymer electrolyte fuel cells , 2020, International Journal of Hydrogen Energy.

[41]  Fei Gao,et al.  Data-driven Prognostics for PEM Fuel Cell Degradation by Long Short-term Memory Network , 2018, 2018 IEEE Transportation Electrification Conference and Expo (ITEC).

[42]  H. Vincent Poor,et al.  An Introduction to Signal Detection and Estimation , 1994, Springer Texts in Electrical Engineering.

[43]  Daniel Hissel,et al.  Data-driven diagnosis of PEM fuel cell: A comparative study , 2014 .

[44]  Vincenzo Antonucci,et al.  Data driven models for a PEM fuel cell stack performance prediction , 2013 .

[45]  Ibrahim Dincer,et al.  Technical, environmental and exergetic aspects of hydrogen energy systems , 2002 .

[46]  Khalil Benmouiza,et al.  Analysis of proton exchange membrane fuel cells voltage drops for different operating parameters , 2017 .