Process monitoring and diagnosis: a model-based approach

A framework for process monitoring and diagnosis, called Mimic, is described. Mimic is based on the observation that the key cognitive skill for process operators is the formation of a mental model that not only accounts for current observations but also lets them predict near-term behavior as well as the effect of possible control actions. Mimic exploits three relatively new technologies: semiquantitative simulation, measurement interpretation (tracking), and model-based diagnosis. These technologies work together in a hypothesize-build-simulate-match cycle. Each of these technologies is discussed. To illustrate Mimic at work, an electric water heater modeled and tested with Mimic is considered. The advantages and limitations of Mimic, as seen by this example, are examined. Related work is discussed.<<ETX>>

[1]  Paul M. Frank,et al.  Fault diagnosis in dynamic systems: theory and application , 1989 .

[2]  Kenneth D. Forbus.  Qualitative Process Theory , 1984, Artif. Intell..

[3]  Benjamin Kuipers,et al.  Higher Order Derivative Constraints in Qualitative Simulation , 1991, Artif. Intell..

[4]  Dennis DeCoste,et al.  Dynamic Across-Time Measurement Interpretation , 1990, Artif. Intell..

[5]  Benjamin Kuipers,et al.  Bridging the Gap from Qualitative to Numerical Simulation , 1991 .

[6]  Randall Davis,et al.  Model-based reasoning: troubleshooting , 1988 .

[7]  Benjamin Kuipers,et al.  Reasoning about energy in qualitative simulation , 1992, IEEE Trans. Syst. Man Cybern..

[8]  Benjamin Kuipers,et al.  Qualitative Simulation , 1986, Artificial Intelligence.

[9]  D. Mccormick.  Normal Accidents , 1991, Bio/Technology.

[10]  T. Edgar,et al.  Qualitative simulation of dynamic chemical processes , 1989 .

[11]  Venkat Venkatasubramanian,et al.  An object-oriented two-tier architecture for integrating compiled and deep-level knowledge for process diagnosis , 1988 .

[12]  Benjamin Kuipers,et al.  Non-Intersection of Trajectories in Qualitative Phase Space: A Global Constraint for Qualitative Simulation , 1988, AAAI.

[13]  Reid G. Simmons,et al.  Generate, Test and Debug: Combining Associational Rules and Causal Models , 1987, IJCAI.

[14]  Kenneth D. Forbus.  Interpreting Measurements of Physical Systems , 1986, AAAI.

[15]  L. Steinberg,et al.  Robust fault diagnosis of physical systems in operation , 1990 .

[16]  Benjamin Kuipers,et al.  Using Incomplete Quantitative Knowledge In Qualitative Reasoning , 1988, AAAI.

[17]  Benjamin Kuipers,et al.  Numerical Behavior Envelopes for Qualitative Models , 1993, AAAI.

[18]  Johan de Kleer,et al.  A Qualitative Physics Based on Confluences , 1984, Artif. Intell..

[19]  O. O. Oyeleye,et al.  Qualitative simulation of chemical process systems: Steady‐state analysis , 1988 .

[20]  Benjamin Kuipers,et al.  Model-Based Monitoring of Dynamic Systems , 1989, IJCAI.

[21]  Benjamin Kuipers,et al.  QPC: A Compiler from Physical Models into Qualitative Differential Equations , 1990, AAAI.

[22]  D Dvorak,et al.  Expert Systems for Monitoring and Control , 1987 .

[23]  P. A. Sachs,et al.  Escort — an expert system for complex operations in real time , 1986 .

[24]  Benjamin J. Kaipers,et al.  Qualitative Simulation , 1989, Artif. Intell..

[25]  Thomas J. Laffey,et al.  Real-Time Knowledge-Based Systems , 1988, AI Mag..

[26]  Peter J. Denning,et al.  Towards a Science of Expert Systems , 1991, IEEE Expert.