Artificial Neural Network Modeling of PEM Fuel Cells

2005 ◽  
Vol 2 (4) ◽  
pp. 226-233 ◽  
Author(s):  
Shaoduan Ou ◽  
Luke E. K. Achenie
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fuel Cells ◽  
Fuel Cell ◽  
Back Propagation ◽  
Pem Fuel Cell ◽  
Pem Fuel Cells ◽  
Optimal Operating ◽  
Cell Systems ◽  
Artificial Neural

Artificial neural network (ANN) approaches for modeling of proton exchange membrane (PEM) fuel cells have been investigated in this study. This type of data-driven approach is capable of inferring functional relationships among process variables (i.e., cell voltage, current density, feed concentration, airflow rate, etc.) in fuel cell systems. In our simulations, ANN models have shown to be accurate for modeling of fuel cell systems. Specifically, different approaches for ANN, including back-propagation feed-forward networks, and radial basis function networks, were considered. The back-propagation approach with the momentum term gave the best results. A study on the effect of Pt loading on the performance of a PEM fuel cell was conducted, and the simulated results show good agreement with the experimental data. Using the ANN model, an optimization model for determining optimal operating points of a PEM fuel cell has been developed. Results show the ability of the optimizer to capture the optimal operating point. The overall goal is to improve fuel cell system performance through numerical simulations and minimize the trial and error associated with laboratory experiments.

Application of artificial neural network in performance prediction of PEM fuel cell

2011 ◽  
Vol 36 (13) ◽  
pp. 1215-1225 ◽  
Author(s):  
Yamini Sarada Bhagavatula ◽  
Maruthi T. Bhagavatula ◽  
K. S. Dhathathreyan
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fuel Cell ◽  
Performance Prediction ◽  
Pem Fuel Cell ◽  
Artificial Neural

scholarly journals Review of Latest Developments in PEM Fuel Cell Research with Application to Hydrogen Powered Drones

2021 ◽  
Vol 19 ◽  
pp. 7-11
Author(s):  
B. Day ◽  
A. Pourmovahed ◽  
Keyword(s):  
Fuel Cells ◽  
High Temperature ◽  
Fuel Cell ◽  
Low Temperature ◽  
Energy Content ◽  
Pem Fuel Cell ◽  
Pem Fuel Cells ◽  
Cell Systems ◽  
Cell Technology ◽  
Current State

Fuel cells are becoming an increasingly more enticing option to power drones for extended use applications. This is because under certain conditions, fuel cell systems are able to more efficiently store fuel and, therefore, energy compared to standard battery options. This reality has been proven through multiple research efforts and is reviewed in this paper. It is necessary to review the current state of PEM fuel cell technology for drone applications to determine the extent of its limitations and feasibility. For this reason, the latest developments in low temperature and high temperature PEM fuel cells were studied including their limitations and sensitivity to contamination with a focus on drone applications. It has been reported that hydrogen powered fuel cell systems are more efficient than conventional battery applications when the energy content is higher than 4 MJ. A hybrid fuel cell and battery powertrain is preferred for the purpose of counterbalancing the deficiencies of both individual cases. Currently available products were explored, and it was found that there are fuel cell systems available that are capable of powering drones in excess of 23 kg (50 lb).

Modeling and Performance Simulation of a Reformer and Fuel Cell System for Electricity Generation From Digester Gas Using PEM Fuel Cells

2017 ◽  
Author(s):  
Sebastian Roa Prada ◽  
Oscar Eduardo Rueda Sanchez
Keyword(s):  
Power Generation ◽  
Wastewater Treatment ◽  
Fuel Cells ◽  
Fuel Cell ◽  
Electricity Generation ◽  
Wastewater Treatment Plants ◽  
Pem Fuel Cell ◽  
Pem Fuel Cells ◽  
Cell Systems ◽  
Power Recovery

Wastewater treatment plants help removing organic matter from wastewater, and at the same time, generate digester gas as a useful byproduct. Digester gas is rich in methane, which can be used to generate electricity. Fuel cell systems are the cleanest technology for power recovery from digester gas, since all other technologies generate electricity by burning all the digester gas. The most commonly used type of fuel cell for power generation from digester gas in wastewater treatment plants is the molten carbonate fuel cell. This type of fuel cell can tolerate the impurities usually found in digester gas, such as CO2 and H2S; however, this kind of fuel cell systems is more suitable for large wastewater treatment plants. This prevents the use of fuel cells for power generation from digester gas in wastewater treatment plants serving medium and small size cities, or even farms. This research attempts to explore solutions to make fuel cell technologies technically and economically feasible for medium and small size wastewater treatment plants. The most suitable type of fuel cells for small applications is the Proton Exchange Membrane, PEM, fuel cell. The main challenge in using PEM fuel cells for power recovery from digester gas is that they are highly sensitive to impurities in its hydrogen gas supply. Therefore, in order to use PEM fuel cells in this application, energy must be spent in cleaning the digester gas before it enters the PEM fuel cell and reformer system. Energy is also required in the form of heat by the reformer system to produce the hydrogen needed by the fuel cell. Both the energy used in the cleaning of the digester gas and the hydrogen generation process comes from burning part of the digester gas. This reduces the amount of digester gas available for hydrogen production and electricity generation, respectively. The approach followed in this investigation seeks to develop a Simulink® model of the reformer and fuel cell so that the modeling tools of Matlab® can be used to simulate the performance of the system under different operating conditions. A sensitivity analysis is carried out to identify critical operating parameters affecting the performance of the overall system. The results obtained in this work provide guidelines for future studies of performance optimization and optimal control using the tools available in Matlab®, in order to get maximum electricity generation from digester gas using PEM fuel cell systems.

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

2017 ◽  
Vol 42 (40) ◽  
pp. 25619-25629 ◽  
Author(s):  
Mehmet Seyhan ◽  
Yahya Erkan Akansu ◽  
Miraç Murat ◽  
Yusuf Korkmaz ◽  
Selahaddin Orhan Akansu
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fuel Cell ◽  
Performance Prediction ◽  
Pem Fuel Cell ◽  
Flow Channel ◽  
Artificial Neural ◽  
Serpentine Flow Channel

scholarly journals Review of Latest Developments in PEM Fuel Cell Research with Application to Hydrogen Powered Drones

2021 ◽  
Vol 19 ◽  
pp. 7-11
Author(s):  
B. Day ◽  
A. Pourmovahed ◽  
Keyword(s):  
Fuel Cells ◽  
High Temperature ◽  
Fuel Cell ◽  
Low Temperature ◽  
Energy Content ◽  
Pem Fuel Cell ◽  
Pem Fuel Cells ◽  
Cell Systems ◽  
Cell Technology ◽  
Current State

Fuel cells are becoming an increasingly more enticing option to power drones for extended use applications. This is because under certain conditions, fuel cell systems are able to more efficiently store fuel and, therefore, energy compared to standard battery options. This reality has been proven through multiple research efforts and is reviewed in this paper. It is necessary to review the current state of PEM fuel cell technology for drone applications to determine the extent of its limitations and feasibility. For this reason, the latest developments in low temperature and high temperature PEM fuel cells were studied including their limitations and sensitivity to contamination with a focus on drone applications. It has been reported that hydrogen powered fuel cell systems are more efficient than conventional battery applications when the energy content is higher than 4 MJ. A hybrid fuel cell and battery powertrain is preferred for the purpose of counterbalancing the deficiencies of both individual cases. Currently available products were explored, and it was found that there are fuel cell systems available that are capable of powering drones in excess of 23 kg (50 lb).

Electrical and Thermal Time Constants Fuel Cell System Identification: A Linear Versus Neural Network Approach

2008 ◽  
Author(s):  
M. T. Outeiro ◽  
Alberto J. L. Cardoso ◽  
R. Chibante ◽  
A. S. Carvalho
Keyword(s):  
Neural Network ◽  
Fuel Cells ◽  
Fuel Cell ◽  
Pem Fuel Cell ◽  
Pem Fuel Cells ◽  
Cell System ◽  
Thermal Time ◽  
Fuel Cell System ◽  
Time Constants ◽  
Made In

The energy generated by PEM fuel cells can be used in many different applications with emphasis to commercial power generation and automotive application. It requires the integration of various subsystems such as chemical, mechanical, fluid, thermal and electrical ones. Their electrical and thermal time constants are important variables to analyze and consider in the development of control strategies of electronic converters. For this purpose, a mathematical model of the PEM fuel cell system was developed in Matlab/Simulink based on a set of equations describing cell operation. The model considers static and dynamic operating conditions of the PEM. Using experimental measurements at different load conditions made in a Nexa™ PEM fuel cell system, analysis based on linear ARX (Autoregressive with Exogenous Input) and neural network methods were made in Matlab in order to identify the electrical and thermal time constant values. Both linear ARX and neural network approaches can successfully predict the values of the time constants variables. However, the identification by the linear ARX is appropriated around the most significant operation points of the PEM system while neural network allows at obtaining a nonlinear global model. The paper intends to be a contribution for the identification of the electrical and thermal time constants of PEM fuel cells through these two methodologies. The linear approach is simple but presents some limitations while the non-linear one is widespread but more complex to be implemented.

Sign in / Sign up

Export Citation Format

Share Document