By Topic

AFAN: tool for optimizing fuzzy controllers

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Gonzalez, R. ; Seville Univ., Spain ; Torralba, A. ; Franquelo, L.G.

Various tools have recently been proposed to automate the hardware design of neural and fuzzy controllers. Some of the approaches these tools use are digital, analog, or mixed-signal. The digital tools provide an HDL file with a description of the controller on hand. This file is later processed by using a commercial HDL synthesizer. However, these tools have not paid attention to the optimization of the controller architecture. In most cases, this architecture is fixed, or the designer has to make a selection among a fixed set of alternatives. AFAN is unique as it uses a high-level approach to architecture optimization, instead of considering the micro-operations to be performed in the controller. It includes both fuzzy and neural systems. By using backpropagation, AFAN is able to include the necessary hardware for controller learning. AFAN accounts for user requirements like controller resolution, speed, and gate complexity to select the controller architecture that best accommodates the set of user requirements. AFAN then produces a VHDL file containing the hardware description of the controller with the selected architecture

Published in:

Micro, IEEE  (Volume:17 ,  Issue: 5 )