ADB9D91Cd01 - Supercapacitor thermal- and...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Supercapacitor thermal- and electrical-behaviour modelling using ANN J.-N. Marie-Francoise, H. Gualous and A. Berthon Abstract: The paper presents the development of a modelling tool for evaluation of the thermal and electrical behaviour of supercapacitors, using an artiFcial neural network (ANN). The principle consists of a black-box multiple-input single-output (MISO) model. The system inputs are temperature, current and supercapacitor values, and the output is the supercapacitor voltage. The relationship between inputs and output is established by the learning and the validation of the ANNmodelfromexperimentalcharge and discharge cycles of supercapacitors at different currents and different temperatures. Once the training parameters are known, the ANN simulator can predict different operational parameters of the supercapacitors. The update parameters of the ANN model are performed using the Levenberg–Marquardt method to minimise the error between the output of the system and the predicted output. This methodology using ANN networks may provide useful information on the transient behaviour of the supercapacitors taking into account thermal influences. Experimental results will also validate the simulation results. 1 Introduction The supercapacitor is an interesting energy-storage device. It can be used to provide peak power requirements in power-electronic systems, in parallel with batteries or fuel cells, for hybrid vehicles, to provide the power requirement in the transient state and to store the regenerative energy. Thanks to their long lives, supercapacitors can be used to start internal-combustion engines in order to reduce the battery size and power. However, in such applications, the temperature is a very important parameter because supercapacitor behaviour is very sensitive to temperature. ±or power-electronic-system simulation, it is necessary to establish a supercapacitor model, which takes into account temperature variations. In the literature, a supercapacitor is modelled by an equivalent electrical circuit with two or Fve RC cells or like a transmission line [1–7] . These parameters can be determined using Helmholtz, Gouy and Chapman theories. In fact, practical situations are more complicated. Measuring capacitance of activated carbon shows a non- linear relationship depending on the surface area because of the types of activated carbon used and their treatments. To establish an equivalent electric circuit for supercapacitor which takes into account these problems, Conway [8] and other authors [1–10] , propose an equivalent electric circuit based on a transmission-line model, which involves distributed capacitance C i and resistance R i , R i C i can be considered as the resistance and capacitance of the pores. However, it is very difFcult to establish an analytical model of a supercapacitor which takes into account This paper therefore deals with a new approach using an artiFcial neural network (ANN). ANN can represent any linear or nonlinear system, even when no physical model or mathematic equations are needed. The relationship between
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 8

ADB9D91Cd01 - Supercapacitor thermal- and...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online