Data driven models for a PEM fuel cell stack performance prediction

Napoli, G.; Ferraro, M.; Sergi, Francesco; Brunaccini, Giovanni

doi:10.1016/j.ijhydene.2013.04.135

Cited by 38 publications

(17 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The control-oriented black box model obtained was implemented in embedded hardware with limited capacity for memory and processing. In [13], the performance of classical neural network (NN) models and stacked models was compared. The stacking approach using partial least squares as a combining algorithm obtained the best prediction.…”

Section: Related Workmentioning

confidence: 99%

PEM Fuel Cell Voltage Neural Control Based on Hydrogen Pressure Regulation

et al. 2019

View full text Add to dashboard Cite

Fuel cells are promising devices to transform chemical energy into electricity; their behavior is described by principles of electrochemistry and thermodynamics, which are often difficult to model mathematically. One alternative to overcome this issue is the use of modeling methods based on artificial intelligence techniques. In this paper is proposed a hybrid scheme to model and control fuel cell systems using neural networks. Several feature selection algorithms were tested for dimensionality reduction, aiming to eliminate non-significant variables with respect to the control objective. Principal component analysis (PCA) obtained better results than other algorithms. Based on these variables, an inverse neural network model was developed to emulate and control the fuel cell output voltage under transient conditions. The results showed that fuel cell performance does not only depend on the supply of the reactants. A single neuro-proportional–integral–derivative (neuro-PID) controller is not able to stabilize the output voltage without the support of an inverse model control that includes the impact of the other variables on the fuel cell performance. This practical data-driven approach is reliably able to reduce the cost of the control system by the elimination of non-significant measures.

show abstract

Section: Related Workmentioning

confidence: 99%

PEM Fuel Cell Voltage Neural Control Based on Hydrogen Pressure Regulation

et al. 2019

View full text Add to dashboard Cite

show abstract

“…With the hypothesis that the influence of the hydrogen diffusion can be neglected face to the oxygen ones, the final expression is (2). Indeed during measurements it can be noticed that the diffusion at the cathode has a bigger influence than the diffusion on the anode side [38].…”

Section: Static Part Of the Modelmentioning

confidence: 99%

“…2, the recomposing block is using the two outputs of the static and dynamic model. For the static model, the output U DC is simply described in equation (2). For the dynamic model, the expression of U AC can be developed as:…”

Section: State Space Representationmentioning

confidence: 99%

See 1 more Smart Citation

Proton exchange membrane fuel cell behavioral model suitable for prognostics

Lechartier

Laffly

Péra

et al. 2015

International Journal of Hydrogen Energy

View full text Add to dashboard Cite

Proton exchange membrane fuel cell Prognostics and health management Behavioral model Static Dynamic a b s t r a c t Prognostics and Health Management (PHM) is a discipline that enables the estimation of the Remaining Useful Life (RUL) of a system and is not yet much applied to Proton Exchange Membrane Fuel Cell PEMFC. However it could permit the definition of adequate conditions allowing extending PEMFC's too short life duration. For that purpose, a model that can reproduce the behavior of a PEMFC is needed. This paper presents a model of a PEMFC that could serve for a prognostics purpose. The model is composed of a static part and a dynamic parts that are independent. On one side, the static part is developed thanks to equations describing the physical phenomena and is based on the ButlereVolmer law.On the other side, the dynamic part is an electrical equivalency of physical phenomenon.The models are validated thanks to experimental data gathered in long term tests. For that purpose the parameters are successively updated based on characterization measurements (polarisation curves and EIS (electrochemical impedance spectroscopy)). Then the results of the model are compared to the ageing data in order to evaluate if the model is able to reproduce the behavior of the fuel cell. The usefulness of this model for prognostics is finally discussed.

show abstract

“…Extensive research has been carried out on modelling dynamic characteristics of fuel cells. On this topic, there exists three major ideas: i) physical models that are based on the material property, physical structure and chemical reaction, i.e., lumped models [6], [7], hierarchical models [8], threedimensional models [9]- [11]; ii) data-driven models which consider the fuel cell as a black box modelling by artificial intelligence-based approaches, i.e., Neural Network [12]; iii)…”

Section: Introductionmentioning

confidence: 99%

Adaptive Online Parameter Estimation Algorithm of PEM Fuel Cells

Xing

Costa‐Castelló

2019

2019 18th European Control Conference (ECC)

View full text Add to dashboard Cite

Since most of fuel cell models are generally nonlinearly parameterized functions, existing modeling techniques rely on the optimization approaches and impose heavy computational costs. In this paper, an adaptive online parameter estimation approach for PEM fuel cells is developed in order to directly estimate unknown parameters. The general framework of this approach is that the electrochemical model is first reformulated using Taylor series expansion. Then, one recently proposed adaptive parameter estimation method is further tailored to estimate the unknown parameters. In this method, the adaptive law is directly driven by the parameter estimation errors without using any predictors or observers. Moreover, parameter estimation errors can be guaranteed to achieve exponential convergence. Besides, the online validation of regressor matrix invertibility are avoided such that computation costs can be effectively reduced. Finally, comparative simulation results demonstrate that the proposed approach can achieve better performance than least square algorithm for estimating unknown parameters of fuel cells.

show abstract

Data driven models for a PEM fuel cell stack performance prediction

Cited by 38 publications

References 35 publications

PEM Fuel Cell Voltage Neural Control Based on Hydrogen Pressure Regulation

PEM Fuel Cell Voltage Neural Control Based on Hydrogen Pressure Regulation

Proton exchange membrane fuel cell behavioral model suitable for prognostics

Adaptive Online Parameter Estimation Algorithm of PEM Fuel Cells

Contact Info

Product

Resources

About