Making manufacturing systems more robust (i.e., able to carry out thei
r function under the presence of faults) is an issue of paramount impo
rtance: It involves on-line and real-time detection of faults, diagnos
is of faults, and recovery from the faults. In this paper, we present
a system that is able to generate practical and efficient solutions fo
r these problem. This approach we present is available as part of IPCS
(Intelligent Process Control System), which is a model-based environm
ent-for generating monitoring, control, simulation, and diagnostics ap
plications for large-scale, continuous process plants. IPCS has been u
sed to generate practical real-time diagnostic and recovery applicatio
ns in chemical and cogenerator plants. (C) 1996 John Wiley & Sons, Inc
.