Industrial process plants such as chemical refineries and electric power generation are examples of continuous-variable dynamic systems (CVDS) whose operation is continuously monitored for abnormal behavior. CVDSs pose a challenging diagnostic problem in which values are continuous (not discrete), relatively few parameters are observable, parameter values keep changing, and diagnosis must be performed while the system operates. We present a novel method for monitoring CVDSs which exploits the system's dynamic behavior for diagnostic clues. The key techniques are: modeling the physical system with dynamic qualitative /quantitative models, inducing diagnostic knowledge from qualitative simulations, continuously comparing observations against fault-model predictions, and incrementally creating and testing multiple-fault hypotheses. The important result is that the diagnosis is refined as the physical system's dynamic behavior is revealed over time. Introduction Process monitoring is a c...

Qualitative simulation of behavior from structure is a valuable method for reasoning about partially known physical systems. Unfortunately, in many realistic situations, a qualitative description of structure is consistent with an intractibly large number of behavioral predictions. We present two complementary methods, representing different trade-offs between generality and power, for taming an important case of intractible branching. The first method applies to the most general case of the problem. It changes the level of the behavioral description to aggregate an exponentially exploding tree of behaviors into a few distinct possibilities The second method draws on additional mathematical knowledge, and assumptions about the smoothness of partially known functional relationships, to derive a correspondingly stronger result. Higher-order derivative constraints are automatically derived by manipulating the structural constraint model algebraically, and applied to eliminate impossible branches These methods have been implemented as extensions to QSIM and tested on a substantial number of examples They move us significantly closer to the goal of reasoning qualitatively about complex physical systems

This article describes a method for monitoring and diagnosis of process systems based on three foundational technologies: semi-quantitative simulation, measurement interpretation (tracking), and model-based diagnosis. Compared to existing methods based on fixed-threshold alarms, fault dictionaries, decision trees, and expert systems, several advantages accrue: ffl the physical system is represented in a semi-quantitative model which, unlike a pure numeric model, predicts all possible behaviors that are consistent with the incomplete/imprecise knowledge of the system's devices and processes, ensuring, for example, that a hazardous-but-infrequent behavior will not be overlooked; ffl imprecise knowledge of parameter values and functional relationships (both linear and non-linear) can be expressed in the semi-quantitative model and used during simulation, producing a valid range for each variable; ffl incremental simulation of the model in step with incoming sensor readings, with subseq...

We report on experiences in the design of the programming language XC. It is an extension of C++ and combines abstract data types with rule based programming. Our design decisions are validated by three application prototypes and by benchmarking XC and OPS83. The experiences raise some critique on the RETE algorithm and on C++ as a host language. However, most of the results are also applicable to other host languages that support data abstraction. XC has been designed specifically to be used in embedded real-time expert systems.

Many large-scale industrial processes and services are centrally monitored and controlled under the supervision of trained operators. Common examples are electrical power plants, chemical refineries, air-traffic control, and telephone networks --- all impressively complex systems that are challenging to understand and operate correctly. The task of the operator is one of continuous, real-time monitoring and control, with feedback. The job can be difficult when the physical system is complex (tight coupling and complex interactions). Also, there may be faults not only in the system but also in its sensors and controls. Deciding the correct control action during a crisis can be difficult; a bad decision can be disastrous. This paper surveys existing work in the field of knowledge-based systems that assist plant/process operators in the task of monitoring and control. The goal here is to better define the information processing problems and identify key requirements for an automated opera...

We address two issues which arise in the task of detecting anomalous behavior in complex systems with numerous sensor channels: how to adjust alarm thresholds dynamically, within the changing operating context of the system, and how to utilize sensors selectively, so that nominal operation can be verified reliably without processing a prohibitive amount of sensor data. Our approach involves simulation of a causal model of the system, which provides information on expected sensor values, and on dependencies between predicted events, useful in assessing the relative importance of events so that sensor resources can be allocated effectively. 1. The Monitoring Problem Timely detection of anomalous behavior is essential for the continuous safe operation and longevity of aerospace systems. The pilot of a jet aircraft must be aware of any conditions which may affect thrust during the critical moments of takeoff. The thermal environment onboard Space Station Freedom must be carefully controlled to provide uninterrupted life support for the crew. The Mars Rover must react quickly to an unpredictable environment or the mission may come to an abrupt conclusion. Monitoring a physical system involves a number of problem-solving tasks. Dvorak, in his survey of work on expert systems for monitoring and control [Dvorak 87], lists among these tasks recognizing abnormal conditions, combining sensory information into a picture of the global state of a system, isolating faults, predicting both normal and faulted behavior, and maintaining safe operation in the presence of faults. In addition, decisions

Qualitative simulation is a useful method for predicting the possible qualitatively distinct behaviors of an incompletely known mechanism described by a system of qualitative differential equations (QDEs). Under some circumstances, sparse information about the derivatives of variables can lead to intractable branching (or "chatter") representing uninteresting or even spurious distinctions among qualitative behaviors. The problem of chatter stands in the way of real applications such as qualitative simulation of models in the design or diagnosis of engineered systems. One solution to this problem is to exploit information about higherorder derivatives of the variables. We demonstrate automatic methods for identification of chattering variables, algebraic derivation of expressions for second-order derivatives, and evaluation and application of the sign of second- and third-order derivatives of variables, resulting in tractable simulation of important qualitative models. Caution is requir...

Abstract: On-line fault detection and isolation techniques have been developed for automated processes during the last few years. These methods include numerical methods, artificial intelligence methods or combinations of the two methodologies. This paper includes a reference to recent research work on numerical methods, an extensive presentation of artificial intelligence methods used for the fault detection process in technical systems and relevant survey material. Special reference is made to the on-line expert systems development where specific resent research work is illustrated.

We report on experiences of the ExBed project, specifically on adding a rule based expression mechanism to an existing procedural programming language (C++) and on designing and implementing a self-contained language (XE) -- and its programming environment -- supporting similar but more general capabilities.

We report on experiences on adding a rule based expression mechanism to an existing procedural programming language (C++) and on designing and implementing a self-contained language -- and its integrated programming environment -- supporting similar but more general capabilities. Both languages, XC and XE, are based on abstract data types and XE is a close relative of CLU. Its programming environment -- implemented on a LISP workstation -- contains facilities for editing and composing programs, browsing a program data base, debugging, version management, and cross-compilation to microprocessors, including the Intel 8086. Key words: Programming languages, Embedded systems, Expert systems Subject categories: Languages/tools 1. Background Embedded systems are claimed to be a promising industrial AI application. The ExBed project (expert system framework for embedded applications) was established to determine how expert system techniques can be applied within embedded systems running on ...