Applying machine learning to boost the development of high-performance membrane electrode assembly for proton exchange membrane fuel cells

Recent research has proven that the incorporation of machine learning could significantly shorten the development cycle of energy materials. However, this rising multidisciplinary field still needs a standard research paradigm to instruct on how the potential of algorithms could be comprehensively exploited to optimize the performance. Hence, we set up a standard workflow consisting of four processing modules, starting with feature selection followed by decision modeling, regression modeling and extremum optimization. The optimization of the membrane electrode assembly (MEA) in proton exchange membrane fuel cells (PEMFCs) was taken as a demonstration. By applying 35 different algorithms on the largest database so far, 27 key factors out of 66 complex parameters were screened out to provide decision aids and build prediction models with errors less than 15%. Without trial-and-error processes, final optimization immediately inferred 13 optimal parameters based on existing conditions provided by users. A glimpse into the future of energy material research has therefore been brought by this great precedent.

[1]  Çağla Odabaşı,et al.  Performance analysis of perovskite solar cells in 2013–2018 using machine-learning tools , 2019, Nano Energy.

[2]  Stefano Ermon,et al.  Closed-loop optimization of fast-charging protocols for batteries with machine learning , 2020, Nature.

[3]  S. Jang,et al.  Application of DFT-based machine learning for developing molecular electrode materials in Li-ion batteries , 2018, RSC advances.

[4]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[5]  Hyunjung Shin,et al.  Missing Value Imputation with Attribute Value Propagation using Graph-based Semi-Supervised Learning , 2019 .

[6]  Michael I. Jordan,et al.  Machine learning: Trends, perspectives, and prospects , 2015, Science.

[7]  Travis Williams,et al.  Enabling Catalyst Discovery through Machine Learning and High-Throughput Experimentation , 2020 .

[8]  G. Maggio,et al.  Modeling polymer electrolyte fuel cells: an innovative approach , 2001 .

[9]  Wei Li,et al.  Predicting the thermodynamic stability of perovskite oxides using machine learning models , 2018, Computational Materials Science.

[10]  D. Muller,et al.  Tuning oxygen reduction reaction activity via controllable dealloying: a model study of ordered Cu3Pt/C intermetallic nanocatalysts. , 2012, Nano letters.

[11]  Maria Chan,et al.  Ultralow-loading platinum-cobalt fuel cell catalysts derived from imidazolate frameworks , 2018, Science.

[12]  Wenbin Gu,et al.  Impact of Platinum Loading and Catalyst Layer Structure on PEMFC Performance , 2012 .

[13]  Gregor S. Harzer,et al.  Tailoring Catalyst Morphology towards High Performance for Low Pt Loaded PEMFC Cathodes , 2018 .

[14]  Kui Jiao,et al.  Multi-physics-resolved digital twin of proton exchange membrane fuel cells with a data-driven surrogate model , 2020 .

[15]  R. Yıldırım,et al.  Data mining in photocatalytic water splitting over perovskites literature for higher hydrogen production , 2019, Applied Catalysis B: Environmental.

[16]  B. Vinayan,et al.  Catalytic activity of platinum–cobalt alloy nanoparticles decorated functionalized multiwalled carbon nanotubes for oxygen reduction reaction in PEMFC , 2012 .

[17]  J. Mahmoudimehr,et al.  Technical study of a PEM fuel cell on the Psychrometric chart , 2016 .

[18]  D. Muller,et al.  Structurally ordered intermetallic platinum-cobalt core-shell nanoparticles with enhanced activity and stability as oxygen reduction electrocatalysts. , 2013, Nature materials.

[19]  Shahaboddin Shamshirband,et al.  State of the Art of Machine Learning Models in Energy Systems, a Systematic Review , 2019, Energies.

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

[21]  Hyuck-Mo Lee,et al.  Synthesis of Chemically Ordered Pt3Fe/C Intermetallic Electrocatalysts for Oxygen Reduction Reaction with Enhanced Activity and Durability via a Removable Carbon Coating. , 2017, ACS applied materials & interfaces.

[22]  T. Lim,et al.  The effects of Nafion® ionomer content in PEMFC MEAs prepared by a catalyst-coated membrane (CCM) spraying method , 2010 .

[23]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[24]  Weirong Chen,et al.  Remaining useful life prediction of PEMFC based on long short-term memory recurrent neural networks , 2019, International Journal of Hydrogen Energy.

[25]  Ayman El-Baz,et al.  Accurate Diabetes Risk Stratification Using Machine Learning: Role of Missing Value and Outliers , 2018, Journal of Medical Systems.

[26]  Zhengdong Cheng,et al.  Accelerated Design of Catalytic Water-Cleaning Nanomotors via Machine Learning. , 2019, ACS applied materials & interfaces.

[27]  Jianguo Liu,et al.  High-Loading Pt-Co/C Catalyst with Enhanced Durability toward the Oxygen Reduction Reaction through Surface Au Modification. , 2020, ACS applied materials & interfaces.

[28]  Jianguo Liu,et al.  Ternary heterogeneous Pt-Ni-Au nanowires with enhanced activity and stability for PEMFCs. , 2020, Chemical communications.

[29]  Joonhee Kang,et al.  First-principles database driven computational neural network approach to the discovery of active ternary nanocatalysts for oxygen reduction reaction. , 2018, Physical chemistry chemical physics : PCCP.

[30]  Yanghua He,et al.  Ordered Pt3Co Intermetallic Nanoparticles Derived from Metal-Organic Frameworks for Oxygen Reduction. , 2018, Nano letters.

[31]  C. Sung,et al.  Performance improvement by a glue-functioned Nafion layer coating on gas diffusion electrodes in PEM fuel cells , 2014 .

[32]  Tianyou Wang,et al.  Experimental and analytical analysis of polarization and water transport behaviors of hydrogen alkaline membrane fuel cell , 2018 .

[33]  Tengfei Wang,et al.  Performance Evaluation of CO2 Huff-n-Puff Gas Injection in Shale Gas Condensate Reservoirs , 2018, Energies.

[34]  Gaston H. Gonnet,et al.  Fast text searching for regular expressions or automaton searching on tries , 1996, JACM.

[35]  Takafumi Kanamori,et al.  Robust Boosting Algorithm Against Mislabeling in Multiclass Problems , 2008, Neural Computation.

[36]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[37]  Michael Biehl,et al.  Noise robustness in multilayer neural networks , 1997 .

[38]  R. Lin,et al.  Investigation of the effect of humidity at both electrode on the performance of PEMFC using orthogonal test method , 2019, International Journal of Hydrogen Energy.

[39]  Goran Nenadic,et al.  Machine learning methods for wind turbine condition monitoring: A review , 2019, Renewable Energy.

[40]  Souhaib Ben Taieb,et al.  A gradient boosting approach to the Kaggle load forecasting competition , 2014 .

[41]  Tsunenori Ishioka,et al.  Investigations into Missing Values Imputation Using Random Forests for Semi-supervised Data , 2014, iiWAS.

[42]  Zachary W. Ulissi,et al.  Accelerated discovery of CO2 electrocatalysts using active machine learning , 2020, Nature.

[43]  Branko N. Popov,et al.  Development of highly-active and stable Pt/C catalyst for polymer electrolyte membrane fuel cells under simulated start-up/shut-down cycling , 2016 .

[44]  Adam Z. Weber,et al.  Modeling and High-Resolution-Imaging Studies of Water-Content Profiles in a Polymer-Electrolyte-Fuel-Cell Membrane-Electrode Assembly , 2008 .

[45]  M. Erdem Günay,et al.  Constructing global models from past publications to improve design and operating conditions for direct alcohol fuel cells , 2016 .

[46]  R. Borup,et al.  Recent developments in catalyst-related PEM fuel cell durability , 2020, Current Opinion in Electrochemistry.

[47]  Stefan Palkovits,et al.  Using Artificial Intelligence To Forecast Water Oxidation Catalysts , 2019, ACS Catalysis.

[48]  M. Lerch,et al.  Ionomer distribution control in porous carbon-supported catalyst layers for high-power and low Pt-loaded proton exchange membrane fuel cells , 2019, Nature Materials.

[49]  Jianguo Liu,et al.  Designing AI-aided analysis and prediction models for nonprecious metal electrocatalyst-based proton exchange membrane fuel cells. , 2020, Angewandte Chemie.

[50]  Jun Zhang,et al.  Synthesis and oxygen reduction activity of shape-controlled Pt(3)Ni nanopolyhedra. , 2010, Nano letters.

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