Graphical representations for probabilistic relationships have recently received considerable attention in A1. Qualitative probabilistic networks abstract from the usual numeric representations by encoding only qualitative relationships, which are inequality constraints on the joint probability distribution over the variables. Although these constraints are insufficient to determine probabilities uniquely, they are designed to justify the deduction of a class of relative likelihood conclusions that imply useful decision-making properties. Two types of qualitative relationship are defined, each a probabilistic form of monotonicity constraint over a group of variables. Qualitative influences describe the direction of the relationship between two variables. Qualitative synergies describe interactions among influences. The probabilistic definitions chosen justify sound and efficient inference procedures based on graphical manipulations of the network. These procedures answer queries about qualitative relationships among variables separated in the network and determine structural properties of optimal assignments to decision variables.

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...

Incomplete knowledge of the structure of mechanisms is an important fact of life in reasoning, commonsense or expert, about the physical world. Qualitative simulation captures an important kind of incomplete, ordinal, knowledge, and predicts the set of qualitatively possible behaviors of a mechanism, given a qualitative description of its structure and initial state. However, one frequently has quantitative knowledge as well as qualitative, though seldom enough to specify a numerical simulation.

Shortcomings of qualitative simulation and of quantitative simulation motivate combining them to do simulations exhibiting strengths of both. The resulting class of techniques is called semi-quantitative simulation. One approach to semi-quantitative simulation is to use numeric intervals to represent incomplete quantitative information. In this research we demonstrate semiquantitative simulation using intervals in an implemented semi-quantitative simulator called Q3. Q3 progressively refines a qualitative simulation, providing increasingly specific quantitative predictions which can converge to a numerical simulation in the limit while retaining important correctness guarantees from qualitative and interval simulation techniques. Q3's simulations are based on a technique we call step size refinement. While a pure qualitative simulation has a very coarse step size, representing the state of a system trajectory at relatively few qualitatively distinct states, Q3 interpolates newly expl...

It is difficult to assess hypothetical models in poorly measured domains such as neuroendocrinology. Without a large library of observations to constrain inference, the execution of such incomplete models implies making assumptions. Mutually exclusive assumptions must be kept in separate worlds. We define a general abductive multiple-worlds engine that assesses such models by (i) generating the worlds and (ii) tests if these worlds contain known behaviour. World generation is constrained via the use of relevant envisionment. We describe QCM, a modeling language for compartmental models that can be processed by this inference engine. This tool has been used to nd faults in theories published in international refereed journals; i.e. QCM can detect faults which are invisible to other methods. The generality and computational limits of this approach are discussed. In short, this approach is applicable to any representation that can be compiled into an and-or graph, provided the graphs are not too big or too intricate (fanout<7).

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...

A general problem in qualitative physics is determining the consequences of assumptions about the behavior of a system. If the space of behaviors is represented by an envisionment, many such consequences can be represented by pruning states from the envisionment. This paper provides a formal logic of occurrence which justifies the algorithms involved and provides a language for relating specific histories to envisionments. The concepts and axioms are general enough to be applicable to any system of qualitative physics. We further propose the concept of transverse quantities as a general solution to qualitative versions of Zeno's paradox. The utility of these ideas is illustrated by a rational reconstruction of the pruning algorithms used in FROB, a working AI program. December, 1 Introduction A goal of qualitative physics is to predict the behavior of physical systems. One technique, envisioning, generates all possible behaviors of a system, relative to a particular set of backgroun...

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...

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...

v Table of Contents vii List of Tables xii List of Figures xiii 1. Introduction and Overview 1 1.1 Motivating Overview : : : : : : : : : : : : : : : : : : : : : : : : 1 1.2 Specific Benefits of Qualitative-Quantitative Simulation : : : : : 4 1.3 Previous work : : : : : : : : : : : : : : : : : : : : : : : : : : : : 7 1.3.1 Qualitative-quantitative work in VLSI : : : : : : : : : : 7 1.3.2 Qualitative-quantitative spatial reasoning : : : : : : : : : 8 1.3.3 Qualitative-Quantitative work in temporal ordering : : : 8 1.3.4 Interval and inequality reasoning : : : : : : : : : : : : : 9 1.3.5 Qualitative-quantitative simulation work : : : : : : : : : 10 1.4 Outline of Remaining Chapters : : : : : : : : : : : : : : : : : : 14 2. Q2: Adding Interval Information to Qualitative Simulation 15 2.1 Overview : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 15 2.2 Propagation of Incomplete Quantitative Information : : : : : : : 16 2.2.1 Types of quantitative propagation constrain...