Investigation of PEM electrolyzer modeling: Electrical domain, efficiency, and specific energy consumption

Hernández-Gómez, Ángel; Ramirez, Victor; Guilbert, Damien

doi:10.1016/j.ijhydene.2020.03.195

Cited by 120 publications

(36 citation statements)

References 108 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…PSO algorithm parameters: particle swarm size at 150, 200 iteration times, learning factor c 1 = c 2 = 2, penalty term C rang [1][2][3][4][5][6][7][8][9][10], and ε-insensitive loss parameter ranging from…”

Section: Energy Consumption Prediction Model Of Electrolytic Copper Foil Preparation Based On Psvmmentioning

confidence: 99%

“…Hence, the energy consumption is not under the specific control. Due to it is difficult to establish a mathematical model to describe the functional relationship between the energy consumption of electrolysis and the process parameters, most researches try to reduce energy consumption by restructuring the electrolytic cell [1], [2], developing new cathode materials [3], [4] and ion exchange membranes [5], etc.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Stacked Generalization Ensemble-Based Hybrid PSVM-PMLP-MLR Model for Energy Consumption Prediction of Copper Foil Electrolytic Preparation

Liao

Ning

et al. 2021

IEEE Access

View full text Add to dashboard Cite

At present, the energy consuming during the electrolytic copper foil preparation accounts for more than 75% of the total energy consumption. In real-life production, the process parameters are set by the operator empirically and the system may not work at the operating point with minimum energy consumption. Therefore, it is critical to establish an effective model for predicting electrolysis energy consumption to guide the parameters design. In this paper, a novel hybrid model (named PSVM-PMLP-MLR) based on stacked ensemble learning is proposed. The model is divided into two parts: the baselearning model and the meta-learning model. The support vector machine (SVM) model and multilayer perceptron (MLP) model with different input structures are established by the former first. Then the particle swarm algorithm is employed to determine the optimal value of SVM parameters and the optimal weight of MLP by minimizing the mean absolute percentage error (MAPE). The multiple linear regression (MLR) is finally employed as a meta-learning machine to compute the final predictions. Experimental results show that the regression coefficient of this model reached 0.987, and compared with the traditional SVM and MLP models, the accuracy of the model is improved by 10.29% and 8.28%, respectively.INDEX TERMS Ensemble learning, electrolytic preparation of copper foil, energy consumption, machine learning.

show abstract

Section: Energy Consumption Prediction Model Of Electrolytic Copper Foil Preparation Based On Psvmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Novel Stacked Generalization Ensemble-Based Hybrid PSVM-PMLP-MLR Model for Energy Consumption Prediction of Copper Foil Electrolytic Preparation

Liao

Ning

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The basic component of the research installation was a hydrogen generator equipped with two PEM electrolyzers that were electrically connected in series and directly supplied from the solar panels. An accurate description of the PEM technology was presented in the references [38][39][40]. The generated hydrogen was fed into one discharge pipe.…”

Section: Electrolyzersmentioning

confidence: 99%

Investigation on System for Renewable Electricity Storage in Small Scale Integrating Photovoltaics, Batteries, and Hydrogen Generator

et al. 2020

View full text Add to dashboard Cite

In this article the solution based on hydrogen generation to increase the flexibility of energy storage systems is proposed. Operating characteristics of a hydrogen generator with integrated electrical energy storage and a photovoltaic installation were determined. The key role of the electricity storage in the proposed system was to maintain the highest operating efficiency related to the nominal parameters of the hydrogen generator. The hydrogen generators achieved the highest energy efficiency for the nominal operating point at the highest power output. Lead-acid batteries were used to ensure the optimal operating conditions for the hydrogen generator supplied with renewable energy throughout the day. The proposed system reduces significantly the hydrogen generator nominal power and devices in system operate in such a way to improve their efficiency and durability. The relations between individual components and their constraints were determined. The proposed solution is fully in-line with previously investigated technologies for improving grid stability and can help incorporate renewable energy sources to increase the sustainability of the energy sector and green hydrogen production.

show abstract

“…We explain details of the parameter selection procedure for the electrolyzer and describe the power control algorithm of the electrolyzer using the DC/DC converter in system analysis. Like other DC grid systems from renewable energy resources, AC/DC and one switch DC/DC converters are considered [11][12][13][14][15][16][17][18]. In addition, a selection method of the values of parallel and series capacitors for SEIG is proposed by considering the reactive power losses from the magnetizing and leakage inductances.…”

Section: Introductionmentioning

confidence: 99%

Possibility of Power Electronics-Based Control Analysis of a Self-Excited Induction Generator (SEIG) for Wind Turbine and Electrolyzer Application

Muljadi

Han

et al. 2021

Electronics

View full text Add to dashboard Cite

A self-excited induction generator (SEIG) is very simple and robust, has a reduced unit size, is easy to implement and simple to control, and requires very little maintenance compared to other types of generators. In variable operating conditions, the SEIG requires a power electronics interface to transform from the variable frequency voltage output of the generator to a battery voltage output or the related applications. In our study, we tied the SEIG to the power electronics system comprising a diode rectifier and DC/DC converter, and then a final DC load for fuel cell applications was connected. An example of such an application is an electrolyzer where an equivalent circuit is modeled for use in this study. To accomplish the proposed system, we utilized PSCAD and MATLAB for its simulation, control, and analysis. A new system configuration considering three different wind speeds and breaker conditions is modeled and analyzed. The results show that the suggested strategies in this study would contribute to designing and analyzing a more practical power electronics interface system for a wind turbine generator with a DC load.

show abstract

Investigation of PEM electrolyzer modeling: Electrical domain, efficiency, and specific energy consumption

Cited by 120 publications

References 108 publications

A Novel Stacked Generalization Ensemble-Based Hybrid PSVM-PMLP-MLR Model for Energy Consumption Prediction of Copper Foil Electrolytic Preparation

A Novel Stacked Generalization Ensemble-Based Hybrid PSVM-PMLP-MLR Model for Energy Consumption Prediction of Copper Foil Electrolytic Preparation

Investigation on System for Renewable Electricity Storage in Small Scale Integrating Photovoltaics, Batteries, and Hydrogen Generator

Possibility of Power Electronics-Based Control Analysis of a Self-Excited Induction Generator (SEIG) for Wind Turbine and Electrolyzer Application

Contact Info

Product

Resources

About