A Fast Fuel Cell Parametric Identification Approach Based on Machine Learning Inverse Models

To identify important fuel cell performance parameters for predicting its performance and assessing its health from its operating data (without performing special tests), this paper describes a model based parameter identification approach. It employs a non-linear programming method to identify optimal values of parameters of a fuel cell model that minimize the difference between the voltage trajectory predicted by the model and that of an actual fuel cell when both are subjected to the same current draws. Using an existing fuel cell model, simulation studies were carried out to demonstrate the feasibility. Specifically, the membrane resistance and a coefficient of the concentration loss term were identified. The study shows that both can be identified accurately even poor initial guesses were used.

Download Full-text

Operando Diagnostics of Solid Oxide Fuel Cell Stack Via Electrochemical Impedance Spectroscopy Simulation-Informed Machine Learning

ECS Meeting Abstracts ◽

10.1149/ma2021-03138mtgabs ◽

2021 ◽

Vol MA2021-03 (1) ◽

pp. 38-38

Author(s):

Giang Tra Le ◽

Luca Mastropasqua ◽

Stuart B. Adler ◽

Jack Brouwer

Keyword(s):

Machine Learning ◽

Electrochemical Impedance Spectroscopy ◽

Fuel Cell ◽

Impedance Spectroscopy ◽

Solid Oxide Fuel Cell ◽

Electrochemical Impedance ◽

Solid Oxide ◽

Oxide Fuel ◽

Fuel Cell Stack

Download Full-text

A Sequential Algebraic Parametric Identification Approach for Nonlinear Vibrating Mechanical Systems

Asian Journal of Control ◽

10.1002/asjc.1474 ◽

2017 ◽

Vol 19 (4) ◽

pp. 1564-1574 ◽

Cited By ~ 4

Author(s):

F. Beltran-Carbajal ◽

G. Silva-Navarro ◽

L. G. Trujillo-Franco

Keyword(s):

Mechanical Systems ◽

Parametric Identification ◽

Identification Approach

Download Full-text

A Lithology Identification Approach Based on Machine Learning With Evolutionary Parameter Tuning

IEEE Geoscience and Remote Sensing Letters ◽

10.1109/lgrs.2019.2911473 ◽

2019 ◽

Vol 16 (12) ◽

pp. 1819-1823 ◽

Cited By ~ 5

Author(s):

Camila Martins Saporetti ◽

Leonardo Goliatt da Fonseca ◽

Egberto Pereira

Keyword(s):

Machine Learning ◽

Parameter Tuning ◽

Lithology Identification ◽

Identification Approach

Download Full-text

Analysis of the dynamic performance of a microbial fuel cell using a system identification approach

Journal of Power Sources ◽

10.1016/j.jpowsour.2013.03.061 ◽

2013 ◽

Vol 238 ◽

pp. 218-226 ◽

Cited By ~ 8

Author(s):

Hitesh C. Boghani ◽

Jung Rae Kim ◽

Richard M. Dinsdale ◽

Alan J. Guwy ◽

Giuliano C. Premier

Keyword(s):

Fuel Cell ◽

System Identification ◽

Microbial Fuel Cell ◽

Dynamic Performance ◽

Identification Approach

Download Full-text

On calculation of recursive M- and GM-estimates in LQG control systems

Lietuvos matematikos rinkinys ◽

10.15388/lmr.2008.18099 ◽

2008 ◽

Vol 48 ◽

Author(s):

Rimantas Pupeikis

Keyword(s):

Maximum Likelihood ◽

Linear Time ◽

Parametric Identification ◽

Parameter Estimates ◽

Linear Quadratic ◽

Unknown Parameters ◽

Linear Time Invariant ◽

Identification Approach ◽

Recursive Techniques ◽

Time Invariant

The aim of the given paper is development of a parametric identification approach for a closedloop system when the parameters of a discrete-time linear time-invariant (LTI) dynamic system as well as that of LQG (Linear Quadratic Gaussian) controller are not known and ought to be calculated. The recursive techniques based on an the maximum likelihood(M) and generalized maximum likelihood(GM) estimator algorithms are applied here in the calculation of the system as well as noise filter parameters. Afterwards, the recursive parameter estimates are used in each current iteration to determine unknown parameters of the LQG-controller, too. The results of numerical simulation by computer are discussed.

Download Full-text

Machine Learning Approach for Modeling and Control of a Commercial Heliocentris FC50 PEM Fuel Cell System

Mathematics ◽

10.3390/math9172068 ◽

2021 ◽

Vol 9 (17) ◽

pp. 2068

Author(s):

Mohamed Derbeli ◽

Cristian Napole ◽

Oscar Barambones

Keyword(s):

Machine Learning ◽

Fuel Cell ◽

Pem Fuel Cell ◽

Cell System ◽

Operating Conditions ◽

Effect Of Temperature ◽

Fuel Cell System ◽

Wide Range ◽

Temperature And Humidity ◽

Predicted Model

In recent years, machine learning (ML) has received growing attention and it has been used in a wide range of applications. However, the ML application in renewable energies systems such as fuel cells is still limited. In this paper, a prognostic framework based on artificial neural network (ANN) is designed to predict the performance of proton exchange membrane (PEM) fuel cell system, aiming to investigate the effect of temperature and humidity on the stack characteristics and on tracking control improvements. A large part of the experimental database for various operating conditions has been used in the training operation to achieve an accurate model. Extensive tests with various ANN parameters such as number of neurons, number of hidden layers, selection of training dataset, etc., are performed to obtain the best fit in terms of prediction accuracy. The effect of temperature and humidity based on the predicted model are investigated and compared to the ones obtained from real-time experiments. The control design based on the predicted model is performed to keep the stack operating point at an adequate power stage with high-performance tracking. Experimental results have demonstrated the effectiveness of the proposed model for performance improvements of PEM fuel cell system.

Download Full-text