Modeling of a single cell micro proton exchange membrane fuel cell by a new hybrid neural network method

Mehrpooya, Mehdi; Ghorbani, Bahram; Jafari, Bahram; Aghbashlo, Mortaza; Pouriman, Mohammadhosein

doi:10.1016/j.tsep.2018.04.012

Cited by 25 publications

(11 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the studied database is a sparse matrix with around 5,000 data, which is restricted by Eq. ( 32) - (37). Moreover, the memory cell of RNN is unique, which could process the sparse matrix with continuity in the data, and LSTM enhances this function in the algorithm.…”

Section: Ai Modellingmentioning

confidence: 99%

“…1, six parameters are permutations and combinations under the restriction of Eq. ( 32), ( 33), ( 36) and (37). It obtains about 5000 nodes.…”

Section: Evaluation Of Data-driven Surrogate Modelmentioning

confidence: 99%

“…The commonly used ML algorithms mainly include artificial neural network (ANN), support vector machine (SVM) et al 36 . These algorithms are generally used in cell performance prediction, life prediction and material optimization of PEMFCs [37][38][39] . The evaluation criterion of the algorithms is accuracy.…”

Section: Introductionmentioning

confidence: 99%

“…The evaluation criterion of the algorithms is accuracy. Mehrpooya et al 37 used the Group Method of Data Handling -Genetic algorithms (GMDH-GA) neural network to explore the internal relationship between temperature, humidity, oxygen, hydrogen flow rate and the PEMFC performance. The accuracy of the training set and test set were 0.982 and 0.9723 respectively.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Designing Graded Fuel Cell Electrodes for Proton Exchange Membrane (Pem) Fuel Cells with Recurrent Neural Network (Rnn) Approaches

et al. 2022

View full text Add to dashboard Cite

Section: Ai Modellingmentioning

confidence: 99%

“…1, six parameters are permutations and combinations under the restriction of Eq. ( 32), ( 33), ( 36) and (37). It obtains about 5000 nodes.…”

Section: Evaluation Of Data-driven Surrogate Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Designing Graded Fuel Cell Electrodes for Proton Exchange Membrane (Pem) Fuel Cells with Recurrent Neural Network (Rnn) Approaches

et al. 2022

View full text Add to dashboard Cite

“…For example, Ghorbani et al (2014) and Shirmohammadi et al (2015) proposed a GA-optimized group method of data handling (GMDH-GA) artificial neural network to obtain efficient polynomial correlation to estimate oil viscosity, and optimize power consumption for cascade refrigerant systems, respectively. Mehrpooya et al (2018) on the other hand, also applied GMDH-GA to predict the behavior of micro proton exchange membrane fuel cells at various operational conditions. All in all, the application of GA optimization in ANN generated better predictions.…”

Section: Introductionmentioning

confidence: 99%

Wind speed modeling over complex terrain with the artificial neural network in the measure-correlate-predict technique: A case study of Malaysia

et al. 2021

View full text Add to dashboard Cite

This study aimed to create a Malaysian wind map of greater accuracy. Compared to a previous wind map, spatial modeling input was increased. The Genetic Algorithm-optimized Artificial Neural Network Measure–Correlate–Predict method was used to impute missing data, and managed to control over- or under-prediction issues. The established wind map was made more reliable by including surface roughness to simulate wind flow over complex terrain. Validation revealed that the current wind map is 33.833% more accurate than the previous wind map. Furthermore, the correlation coefficient between wind map-simulated data and observed data was high as 0.835. In conclusion, the new and improved wind map for Malaysia simulates data with acceptable accuracy.

show abstract

Deep learning from three-dimensional multiphysics simulation in operational optimization and control of polymer electrolyte membrane fuel cell for maximum power

et al. 2021

View full text Add to dashboard Cite

Modeling of a single cell micro proton exchange membrane fuel cell by a new hybrid neural network method

Cited by 25 publications

References 47 publications

Designing Graded Fuel Cell Electrodes for Proton Exchange Membrane (Pem) Fuel Cells with Recurrent Neural Network (Rnn) Approaches

Designing Graded Fuel Cell Electrodes for Proton Exchange Membrane (Pem) Fuel Cells with Recurrent Neural Network (Rnn) Approaches

Wind speed modeling over complex terrain with the artificial neural network in the measure-correlate-predict technique: A case study of Malaysia

Deep learning from three-dimensional multiphysics simulation in operational optimization and control of polymer electrolyte membrane fuel cell for maximum power

Contact Info

Product

Resources

About