T. Hollstein et al., COMPUTER-AIDED-DESIGN OF FUZZY-SYSTEMS BASED ON GENERIC VHDL SPECIFICATIONS, IEEE transactions on fuzzy systems, 4(4), 1996, pp. 403-417
Fuzzy systems implemented in hardware can operate with much higher per
formance than software implementations on standard microcontrollers. I
n this paper, three types of fuzzy systems and related hardware archit
ectures are discussed: standard fuzzy controllers, FuNe I fuzzy system
s, and fuzzy classifiers based on a neural network structure. Two comp
uter-aided design (CAD) packages for automatic hardware synthesis of s
tandard fuzzy controllers are presented: a hard-wired implementation o
f a complete fuzzy system on a single or multiple field programmable g
ate arrays (FPGA) and a modular toolbox called fuzzyCAD for synthesis
of reprogrammable fuzzy controllers with architectures due to specifie
d designer constraints. In the fuzzyCAD system, an efficient design me
thodology has been implemented which covers a large design space in te
rms of signal representations and component architectures as well as s
ystem architectures. Very highspeed integrated-circuits hardware-descr
iption language (VHDL) descriptions and usage of powerful synthesis to
ols allow different technologies to be targeted easily and efficiently
. In the last part of this paper, properties and hardware realizations
of fuzzy classifiers based on a neural network are introduced. Finall
y, future perspectives and possible enhancements of the existing toolk
its are outlined.