Performance prediction of PEM fuel cell with wavy serpentine flow channel by using artificial neural network

Seyhan, Mehmet; Akansu, Yahya Erkan; Murat, Miraç; Korkmaz, Yusuf; Akansu, Selahaddin Orhan

doi:10.1016/j.ijhydene.2017.04.001

“…However, only 4 factors were considered: the inlet pressures of hydrogen and oxygen, stack temperature and relative humidity. Other similar works also investigated only specific variables such as the flow channel and stacking strategies . In addition, several pioneering studies have investigated working life prediction using recurrent neural networks (RNNs) and time‐delay neural networks (TDNNs), which were trained on small‐scale datasets.…”

Section: Introductionmentioning

confidence: 99%

Designing AI‐Aided Analysis and Prediction Models for Nonprecious Metal Electrocatalyst‐Based Proton‐Exchange Membrane Fuel Cells

Ding

¹

,

Wang

²

,

Ding

³

et al. 2020

View full text Add to dashboard Cite

Traditionally,alarger number of experiments are needed to optimize the performance of the membrane electrode assembly (MEA) in proton-exchange membrane fuel cells (PEMFCs) since it involves complex electrochemical, thermodynamic,a nd hydrodynamic processes.H erein, we introduce artificial intelligence (AI)-aided models for the first time to determine key parameters for nonprecious metal electrocatalyst-based PEMFCs,t hus avoiding unnecessary experiments during MEA development. Among 16 competing algorithms widely applied in the AI field, decision tree and XGBoost showed good accuracy (86.7 %and 91.4 %) in determining key factors for high-performance MEA. Artificial neural network (ANN) shows the best accuracy (R2 = 0.9621) in terms of predictions of the maximum power density and ad ecent reproducibility (R2 > 0.99) on uncharted I-V polarization curves with 26 input features.H ence,m achine learning is shown to be an excellent method for improving the efficiency of MEA design and experiments.

show abstract

“…[26] However,restricted by the volume of data and computational abilities,t hese works merely focused on af ew operating parameters.F or example,H an et al [27] constructed both ANN and SVM models trained on simulation data to predict and analyze PEMFC performances. However,only 4f actors were considered:the inlet pressures of hydrogen and oxygen, stack temperature and relative humidity.O ther similar works also investigated only specific variables such as the flow channel [28] and stacking strategies. [29] In addition, several pioneering studies have investigated working life prediction using recurrent neural networks (RNNs) [30] and time-delay neural networks (TDNNs), [31] which were trained on small-scale datasets.…”

Section: Introductionmentioning

confidence: 99%

Designing AI‐Aided Analysis and Prediction Models for Nonprecious Metal Electrocatalyst‐Based Proton‐Exchange Membrane Fuel Cells

Ding

¹

,

Wang

²

,

Ding

³

et al. 2020

View full text Add to dashboard Cite

Traditionally,alarger number of experiments are needed to optimize the performance of the membrane electrode assembly (MEA) in proton-exchange membrane fuel cells (PEMFCs) since it involves complex electrochemical, thermodynamic,a nd hydrodynamic processes.H erein, we introduce artificial intelligence (AI)-aided models for the first time to determine key parameters for nonprecious metal electrocatalyst-based PEMFCs,t hus avoiding unnecessary experiments during MEA development. Among 16 competing algorithms widely applied in the AI field, decision tree and XGBoost showed good accuracy (86.7 %and 91.4 %) in determining key factors for high-performance MEA. Artificial neural network (ANN) shows the best accuracy (R2 = 0.9621) in terms of predictions of the maximum power density and ad ecent reproducibility (R2 > 0.99) on uncharted I-V polarization curves with 26 input features.H ence,m achine learning is shown to be an excellent method for improving the efficiency of MEA design and experiments.

show abstract

“…Once this network is trained, it can predict different operational parameters of the fuel cell reducing the computation time [14]. This strategy has many possibilities [15]: spectroscopic analysis, prediction of reactions, chemical process control, and the analysis of electrostatic potentials. The ANN is trained to learn the internal relationships from data.…”

Section: Introductionmentioning

confidence: 99%

How to Build Simple Models of PEM Fuel Cells for Fast Computation

Deseure¹

2020

Thermodynamics and Energy Engineering

0

View full text Add to dashboard Cite

Hydrogen is one of the leading candidates in the search for an alternative to fossil hydrocarbon fuels. The spread of these technologies requires a real-time control of generator performances. Artificial intelligence (AI) and mathematic tools can make smarter the smart grid. The electrochemical modeling can be coupled successfully with artificial intelligent approach, if these models can be quickly computed with a large numerical stability. This chapter shows a methodology to build this kind of modeling work. Thanks to a simplified but physically reasonable model of PEM fuel cell, we will show that the reactant access (oxygen) or water management (a product of the reaction) and the reaction rate can be easily described with low computing time consuming. In addition, the artificial neural network could be trained with a reduced amount of data generated by these cell models.

show abstract

Performance prediction of PEM fuel cell with wavy serpentine flow channel by using artificial neural network

Cited by 103 publications

References 46 publications

Designing AI‐Aided Analysis and Prediction Models for Nonprecious Metal Electrocatalyst‐Based Proton‐Exchange Membrane Fuel Cells

Designing AI‐Aided Analysis and Prediction Models for Nonprecious Metal Electrocatalyst‐Based Proton‐Exchange Membrane Fuel Cells

Designing AI‐Aided Analysis and Prediction Models for Nonprecious Metal Electrocatalyst‐Based Proton‐Exchange Membrane Fuel Cells

How to Build Simple Models of PEM Fuel Cells for Fast Computation

Contact Info

Product

Resources

About