Estimation of Water Coverage Ratio in Low Temperature PEM-Fuel Cell Using Deep Neural Network

Mehnatkesh, Hossein; Alasty, Aria; Boroushaki, Mehrdad; Khodsiani, Mohammad Hassan; Hasheminasab, Mohammadreza; Kermani, M.J.

doi:10.1109/jsen.2020.2993181

Cited by 16 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For estimation and prediction of fuel cell status and performance, DNN containing convolutional layers is used to estimate the water coverage ratio for PEMFC (Mehnatkesh et al, 2020). A total of 32 images with a shape of 176 3 17633 is used as input to train the DNN model.…”

Section: Application Of Machine Learning For Fuel Cellsmentioning

confidence: 99%

Machine learning toward advanced energy storage devices and systems

Gao

2021

iScience

118

View full text Add to dashboard Cite

Technology advancement demands energy storage devices (ESD) and systems (ESS) with better performance, longer life, higher reliability, and smarter management strategy. Designing such systems involve a trade-off among a large set of parameters, whereas advanced control strategies need to rely on the instantaneous status of many indicators. Machine learning can dramatically accelerate calculations, capture complex mechanisms to improve the prediction accuracy, and make optimized decisions based on comprehensive status information. The computational efficiency makes it applicable for real-time management. This paper reviews recent progresses in this emerging area, especially new concepts, approaches, and applications of machine learning technologies for commonly used energy storage devices (including batteries, capacitors/supercapacitors, fuel cells, other ESDs) and systems (including battery ESS, hybrid ESS, grid and microgrid-containing energy storage units, pumped-storage system, thermal ESS). The perspective on future directions is also discussed.

show abstract

Section: Application Of Machine Learning For Fuel Cellsmentioning

confidence: 99%

Machine learning toward advanced energy storage devices and systems

Gao

2021

iScience

118

View full text Add to dashboard Cite

show abstract

“…[107][108][109][110][113][114][115][116][117][118] DNN containing convolutional layers was used to predict the water coverage ratio for PEMFCs as a metric for performance. 119 The prediction results showed that the trained DNN achieved 94.23% accuracy in the identification of the water coverage ratio. As important as the feed substrate type, six different ML algorithms, namely, LRM, RF, STBS, NN, KNN, and SVM, with radial kernel were used to predict the feed substrates (including acetate, carbohydrate, and wastewater) for microbial fuel cells (MFCs) based on genomic data.…”

Section: Application Of Ai-based Approaches Of Performance Prediction...mentioning

confidence: 96%

“…To predict the fuel cell performance and status, DNN with convolutional layers was utilized to calculate the water coverage ratio for a proton-exchange membrane fuel cell (PEMFC). 119 The DNN model was trained using a total of 32 pictures with 176 Â 176 Â 3 shapes. Particularly, the evolutionary algorithm was used to optimize the structure of the DNN model, which consisted of two dense layers and four convolutional hidden layers.…”

Section: Integrated the Calculation Of Density Functional Theory (Dft...mentioning

confidence: 99%

Artificial intelligence-navigated development of high-performance electrochemical energy storage systems through feature engineering of multiple descriptor families of materials

et al. 2023

View full text Add to dashboard Cite

show abstract

“…To analyze the emergence of water flooding and the hazards it brings, scholars have developed different physical models for the gas–liquid two-phase flow in the cathode of fuel cells [ 12 , 13 , 14 , 15 , 16 ]. In 2020, Mehnatkesh et al [ 17 ] used a deep neural network model to measure water coverage in fuel cells. The distribution of water in the flow field and the identification of areas of water accumulation in the gas channels were analyzed.…”

Section: Introductionmentioning

confidence: 99%

Water Management for μDMFC with Foamed Stainless Steel Cathode Current Collector

Zhang

Zhao

2022

Nanomaterials

View full text Add to dashboard Cite

For micro direct methanol fuel cell (μDMFC), water flooding on the cathode seriously affects the performance stability. Additionally, the effect of material and wettability of the cathode current collector (CCC) on the drainage capacity is studied to improve the μDMFC’s performance. To this end, a CCC with foamed stainless steel was prepared to assemble the μDMFC due to its absorbency. Further, based on analyzing the gas–liquid two-phase flow characteristics of the μDMFC cathode, it was found that the gradient wettability CCC could accelerate the discharge of cathode water. Hence, the foam stainless steel CCC was partially immersed in a KOH solution to complete the gradient corrosion using its capillary force. Then, four different types of gradient wettability CCC were prepared by controlling the time of chemical corrosion. Finally, the performance of the μDMFC with different gradient wettability CCC was tested at room temperature using electrochemical impedance spectroscopy (EIS) and discharge voltage. The experimental results show that the gradient wettability CCC can improve the performance of the μDMFC by slowing down the rate of cathode flooding. The optimum corrosion time is 5 min at a concentration of 1 mol/L. Under these conditions, the CCC has the best gradient wettability, and the μDMFC has the lowest total impedance. The discharge voltage of the μDMFC with corroded CCC is increased by 33.33% compared to the uncorroded CCC μDMFC. The gradient wettability CCC designed in this study is economical, convenient, and practical for water management of the μDMFC.

show abstract

Estimation of Water Coverage Ratio in Low Temperature PEM-Fuel Cell Using Deep Neural Network

Cited by 16 publications

References 19 publications

Machine learning toward advanced energy storage devices and systems

Machine learning toward advanced energy storage devices and systems

Artificial intelligence-navigated development of high-performance electrochemical energy storage systems through feature engineering of multiple descriptor families of materials

Water Management for μDMFC with Foamed Stainless Steel Cathode Current Collector

Contact Info

Product

Resources

About