Activated sludge plant is usually difficult to operate and control because
of its complex operational behaviour and usual significant process disturba
nces. To increase safety and improve operating performance of this biologic
al wastewater treatment process, it is important to develop computer operat
ional decision support systems. This intelligent computing system is able t
o assist ordinary operators to work at the level of a domain expert in dail
y operation. Neural network techniques and fuzzy logic methods have become
important and effective tools to help build such intelligent system. The ar
tificial neural network technique is powerful because it can learn to repre
sent complicated data patterns or data relationships between input and outp
ut variables of the system being studied. Nevertheless, it has limitations
in performing heuristic reasoning of the domain problem. On the other hand,
expert systems are good at performing heuristic reasoning by making use of
logic rules. It is, however, generally weak for knowledge acquisition. In
this study, a fuzzy neural model is developed for addressing the operating
problems of activated sludge processes, relating to prediction and heuristi
c understanding of the sludge age. Neural network techniques and fuzzy logi
c are used in model development. Simulation studies show that this fuzzy-ne
ural network model obtained is able to extract fuzzy rules from a set of nu
merical data that can be used to carry out heuristic reasoning, (C) 1999 El
sevier Science Ltd. All rights reserved.