Since chemical processes are often operated over a range of operating
conditions and some of the system parameters are only known to a certa
in degree, uncertainties exist in the process model. Interval types of
process models offer an attractive alternative for process descriptio
n in an operating environment. In terms of fault diagnosis, an interva
l process model based diagnostic system is robust as compared to conve
ntional quantitative model-based systems. In this work, an interval mo
del is incorporated into the deep model algorithm (DMA) for fault diag
nosis. A design procedure is given, and characteristics of interval DM
A are also discussed. One unique property is that the interval parity
equations generally give better diagnostic resolution than the crisp o
nes under the DMA framework. A CSTR example with interval coefficients
is used to illustrate the design and effectiveness of the interval DM
A. Results show that the proposed method is not only successful in han
dling wide range of operating conditions but also capable of identifyi
ng correct fault origins accurately.