Fuzzy control has been widely applied in industrial controls and domestic e
lectrical equipment. The automatic learning of fuzzy rules is a key techniq
ue in fuzzy control. In this paper, a software development system for fuzzy
control is presented. Since the learning of fuzzy rules can be seen as fin
ding the best classifications of fuzzy memberships of input-output variable
s in a fuzzy controller, it can also be seen as the combination optimizatio
n of input-output fuzzy memberships. Multi-layer feedforward network and ge
netic algorithms (GA) can be used for the automatic learning of fuzzy rules
. The algorithms and their characteristics are described. The software deve
lopment system has been successfully used for the design of some fuzzy cont
rollers.