Black-Box Fuzzy Identification of a Nonlinear Hydrogen Fuel Cell Model

Abstract

ABSTRACT.A fuzzy identification of the system's dynamic is developed with a data generated by a hydrogen fuel cell simulator. The data obtained is single input/single output, without having previous knowledge of the system model, and showing nonlinear behavior. The choice of the fuzzy method for identification is based on those particular data features, and the malleability of the mathematical fuzzy technique. The objective of the fuzzy identification is to reach an analytic formula for a better understanding of the causeeffect relationships of the data, followed by its validation. The dynamic system identification process is performed using fuzzy clustering through the Gustafson and Kessel algorithm, followed by a Takagi and Sugeno fuzzy inference method. The k-fold technique, is the cross validation tool, used to confirm the lack of data over-training. The novelty of this approach covers mathematical and engineering features that makes this study interdisciplinary. For the mathematical contribution, there is a three-dimensional graphic interpretation of the data clustering geometry, obtained through own code computer simulations. Concerning to the engineering context, the novelty is based on the use of the fuzzy approach to the hydrogen fuel cell. Both contributions have no precedent in the literature. The results of the fuzzy identification show high reliability in terms of cross validation, making the fuzzy approach a promising tool for black-box identification. Combining this technique with others will provide powerful instrument for industrial problems.

Controle Automático de Volume em Tempo Real Utilizando Inferência Fuzzy em um Sistema Embarcado

“…A lógica Fuzzy, proposta inicialmente em 1965 [40], tem sido aplicada em diversasáreas [3,4,5,11]. O conceito fundamental da lógica Fuzzyé flexibilizar a pertinência dos elementos através do conceito de graus de pertinência [16,34], permitindo assim modelar a incerteza e a subjetividade de sistemas complexos.…”

Development of neural­network and fuzzy models of multimass electromechanical systems

“…A model of a system in a form of a neural net or a system of neuro-fuzzy inference is constructed on the basis of known input signals and the signals measured at the system output. Some papers devoted to identification of complex technological processes and systems using neural nets [17][18][19][20][21][22][23][24][25][26], systems of fuzzy inference [27][28][29][30][31][32][33][34][35] and neuro-fuzzy systems [36][37][38][39][40][41] are given in the reference list. However, the problems of synthesis of neural-network and fuzzy models of electromechanical systems with complex kinematic connections were not considered.…”

Model approach of a robotic manipulator 3DOF using Machine Learning

“…One of the characteristics of a robotic manipulator in general is the presence of a claw at the end of its link, and is designed for components to be transported taking into account the characteristics of the material, such as weight and shape, and must be adjusted to handle such objects. The [3] makes the study of a fuzzy modeling of the dynamics of the system that is developed with data generated by a hydrogen fuel cell simulator.…”