On neural network modeling to maximize the power output of PEMFCs

Nanadegani, Fereshteh Salimi; Lay, Ebrahim Nemati; Iranzo, Alfredo; Salva, J. Antonio; Sundén, Bengt

doi:10.1016/j.electacta.2020.136345

Cited by 52 publications

(18 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…From the results, it was found that the implementation of the studied model able to improve the maximum net power boost can be estimated as being up to 3.74%, which is essential for the optimal operation of the integrated PEMFC system to achieve a higher system efficiency [70]. In another study by Salimi et al, the neural network modeling is found able to increase the power output of the PEMFC systems [71].Through the designated model named an artificial neural network (ANN), the operating performance increased up to 28.9%. A comprehensive stack model is developed based on the integration of a 1 + 1 dimensional multiphase stack sub-model and a flow distribution sub-model has been developed [72].…”

Section: Polymer Electrolyte Membrane Fuel Cell (Pemfcs)mentioning

confidence: 87%

New Perspectives on Fuel Cell Technology: A Brief Review

et al. 2020

View full text Add to dashboard Cite

Energy storage and conversion is a very important link between the steps of energy production and energy consumption. Traditional fossil fuels are a natural and unsustainable energy storage medium with limited reserves and notorious pollution problems, therefore demanding a better choice to store and utilize the green and renewable energies in the future. Energy and environmental problems require a clean and efficient way of using the fuels. Fuel cell functions to efficiently convert oxidant and chemical energy accumulated in the fuel directly into DC electric, with the by-products of heat and water. Fuel cells, which are known as effective electrochemical converters, and electricity generation technology has gained attention due to the need for clean energy, the limitation of fossil fuel resources and the capability of a fuel cell to generate electricity without involving any moving mechanical part. The fuel cell technologies that received high interest for commercialization are polymer electrolyte membrane fuel cells (PEMFCs), solid oxide fuel cells (SOFCs), and direct methanol fuel cells (DMFCs). The optimum efficiency for the fuel cell is not bound by the principle of Carnot cycle compared to other traditional power machines that are generally based on thermal cycles such as gas turbines, steam turbines and internal combustion engines. However, the fuel cell applications have been restrained by the high cost needed to commercialize them. Researchers currently focus on the discovery of different materials and manufacturing methods to enhance fuel cell performance and simplify components of fuel cells. Fuel cell systems’ designs are utilized to reduce the costs of the membrane and improve cell efficiency, durability and reliability, allowing them to compete with the traditional combustion engine. In this review, we primarily analyze recent developments in fuel cells technologies and up-to-date modeling for PEMFCs, SOFCs and DMFCs.

show abstract

Section: Polymer Electrolyte Membrane Fuel Cell (Pemfcs)mentioning

confidence: 87%

New Perspectives on Fuel Cell Technology: A Brief Review

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The operation of each exerts a considerable impact on the performance and durability of the stack as a complete electrochemical power source. The impact of these subsystems on the dynamic response of fuel cells was taken into consideration in simulations, modelling, and experimental studies [34][35][36][37].…”

Section: Analysis Of Hydrogen Fuel Consumption During V-type Pemfc Stmentioning

confidence: 99%

Design, Development, and Performance of a 10 kW Polymer Exchange Membrane Fuel Cell Stack as Part of a Hybrid Power Source Designed to Supply a Motor Glider

et al. 2020

View full text Add to dashboard Cite

A 10 kW PEMFC (polymer exchange membrane fuel cell) stack consisting of two 5 kW modules, (A) and (B), connected in series with a multi-function controller unit was constructed and tested. The electrical performance of the V-shaped PEMFC stack was investigated under constant and variable electrical load. It was found that the PEMFC stack was capable of supplying the required 10 kW of electrical power. An optimised purification process via ‘purge’ or humidification, implemented by means of a short-circuit unit (SCU) control strategy, enabled slightly improved performance. Online monitoring of the utilisation of the hydrogen system was developed and tested during the operation of the stack, especially under variable electrical load. The air-cooling subsystem consisting of a common channel connecting two 5 kW PEMFC modules and two cascade axial fans was designed, manufactured using 3D printing technology, and tested with respect to the electrical performance of the device. The dependence of total partial-pressure drop vs. ratio of air volumetric flow for the integrated PEMFC stack with cooling devices was also determined. An algorithm of stack operation involving thermal, humidity, and energy management was elaborated. The safety operation and fault diagnosis of the PEMFC stack was also tested.

show abstract

“…During the experiment, hydrogen concentration sensor 44 can be used to obtain the accumulation of inert gas, but it cannot be used to realize real‐time monitoring when the assembled fuel cell stack is completed. The neural network is an important means of using data to study fuel cells, such as remaining useful life‐time identification, 45,46 fault diagnosis, 47,48 and performance optimization 49,50 …”

Section: Introductionmentioning

confidence: 99%

Methods for estimating the accumulated nitrogen concentration in anode of proton exchange membrane fuel cell stacks based on back propagation neural network

Chen

et al. 2022

Intl J of Energy Research

View full text Add to dashboard Cite

Excellent performance is an important indicator to ensure the commercial development of fuel cells. During the operation of a fuel cell system, nitrogen accumulation will occur at the anode of the fuel cell stack because of hydrogen circulation and nitrogen permeation across the membrane. Nitrogen accumulation will lead to the degradation of fuel cell performance. A suitable purge strategy can effectively reduce the excessive nitrogen concentration. The formulation of the purge strategy is closely related to the change in nitrogen concentration, so the accurate estimation of nitrogen concentration is quite important. In this paper, the effect of nitrogen concentration on fuel cell performance under different current densities is studied, and the anode nitrogen concentration in the fuel cell stack is estimated by back propagation neural network. The identification result of nitrogen concentration based on the voltage of every single cell is more accurate. Without considering aging and working condition changes, mean absolute errors of estimated results are 0.75%, 0.67%, 0.62%, and 0.73%, and root mean square errors are 1.09%, 0.97%, 0.88%, and 0.99% at different current densities of 0.6, 0.8, 1.0, and 1.2 AÁcm À2 , respectively. The results indicate that the estimation method of nitrogen concentration for fuel cell anode based on back propagation neural network has a high accuracy, which can provide a new method for formulating purge strategy for fuel cell system.

show abstract

On neural network modeling to maximize the power output of PEMFCs

Cited by 52 publications

References 40 publications

New Perspectives on Fuel Cell Technology: A Brief Review

New Perspectives on Fuel Cell Technology: A Brief Review

Design, Development, and Performance of a 10 kW Polymer Exchange Membrane Fuel Cell Stack as Part of a Hybrid Power Source Designed to Supply a Motor Glider

Methods for estimating the accumulated nitrogen concentration in anode of proton exchange membrane fuel cell stacks based on back propagation neural network

Contact Info

Product

Resources

About