Model-based Diagnostic Systems Research Articles

Graph of a Process—A New Tool for Finding Model Structures in a Model-Based Diagnosis

In this paper, graph of a process (GP) is introduced as a new formalization of causal graph useful in fault diagnosis. Faults are directly incorporated into the model. In this paper, we propose the concept of model structure (MS), which can be used for building fuzzy and neural models for fault detection. Algorithms for finding all MSs and methods for determining faults-symptoms relation are developed. This method is applicable to the design of model-based diagnostic systems, when only basic knowledge of the process to be diagnosed is available. No mathematical model is needed. This paper shows that GP can be constructed on the basis of process diagrams and expert knowledge. Models for fault detection can be built automatically from process measurements. Ideas are explained on a three-tank system example. In the last section, our proposed method is compared in detail with other existing approaches using qualitative models.

A framework for reasoning under uncertainty based on non-deterministic distance semantics

In this paper, we introduce a general and modular framework for formalizing reasoning with incomplete and inconsistent information. Our framework is composed of non-deterministic semantic structures and distance-based considerations. This combination leads to a variety of entailment relations that can be used for reasoning about non-deterministic phenomena and are inconsistency-tolerant. We investigate the basic properties of these entailments, as well as some of their computational aspects, and demonstrate their usefulness in the context of model-based diagnostic systems.

Fault diagnosis of electronic system using artificial intelligence

With increasing system complexity, shorter product life cycles, lower production costs, and changing technologies, the need for intelligent tools for all stages of a product's lifecycle is becoming increasingly important. The purpose of this article is to give a brief review how AI has been used in the field of electronic fault diagnosis. Topics discussed include: rule-based diagnostic systems; model-based diagnostic systems; case-based reasoning (CBR); fuzzy reasoning and artificial neural networks (ANN); hybrid approaches; IEEE diagnostic standards and automated diagnostic tool future developments.

A Taxonomy of User Requirements for Model-Based Diagnostic Systems

This paper highlights some of the important issues associated with the development of model-based diagnostic systems. These concern user requirements, modelling, instrumentation, and technology selection. The main focus, is however, on the user requirements taxonomy which comprises two parts. The first part describes what the application system is required to do, and the second concerns the constraints within which the application system must be developed and operated. The first type are normally explicitly developed and documented. We refer to these as “Capability Requirements”. The second type are often only implicit during the design process and stem from the economic realities of system development — thus the characteristics of the plant, its documentation, existing models and databases, and plant instrumentation all form a set of implicit constraints. We refer to these types of requirements as “Constraint Requirements”.

Selecting tools and techniques for model-based diagnosis

We present a methodology for the selection of candidate generation and prediction techniques for model-based diagnostic systems (MBDS). We start by describing our taxonomy of the solution space based upon the three main functional blocks of a top-level MBDS architecture (the predictor, the candidate generator and the diagnostic strategist). We divide the corresponding problem space into user requirements and system constraints which are further subdivided into task and fault requirements, and plant and domain knowledge constraints respectively. Finally we propose a set of guidelines for selecting tools and techniques in the solution space given descriptions of diagnostic tasks in the problem space.

Model-based analysis of protection system performance

Following a power system fault, protection engineers have to analyse the protection scheme activity to ensure correct operation. To aid them in this task, data gathering systems are increasingly being fitted to power systems. However, during extreme operating conditions, the volume of data made available by these systems can be overwhelming. To help overcome this, knowledge-based systems have been developed and installed at ScottishPower's corporate headquarters to extract the relevant `information' from the supervisory control and data acquisition (SCADA) system `data'. The paper reports on the next stage of decision support for the protection engineers which builds upon the diagnosis provided by the knowledge-based systems. This enhanced support is provided by a model-based diagnostic system which provides automatic analysis of the available fault recorder data. This system utilises the most appropriate techniques employed by existing model-based diagnostic systems. A novel approach for handling tolerances associated with the operating times of protection scheme components is introduced, thus enabling modelling measurement inaccuracies to be dealt with

Model Partitioning for Model-Based Diagnosis

Model-based diagnostic systems (MBDSs) are increasingly being applied to real industrial problems. Often this results in the development of large models which must be partitioned into a number of subsystems in order that the MBDSs may be applied to problems of practical size. For other MBDSs the model's equations must be causally ordered, and in dependency-based MBDSs (e.g. GDE, De Kleer and Williams. 1987) groups of simultaneous equations must be identified and solved so that a local "constraint propagation" algorithms may be employed. This paper presents the implementation, use, and extension, of a model partitioning algorithm due to Portè et al. (1988). As well as outlining its design, and its extensions, this paper also presents the results obtained by applying the algorithm to a chemical plant model.

Composing Model-Based Diagnostic Systems

We present a novel approach to developing model-based diagnostic systems based on composing a solution from a prespecified and predeveloped, and hence reusable, set of software modules identified from a functional analysis of the complete model-based

A framework for hypothesis generation in model-based diagnosis

This work in progress is aimed at providing a framework for model-based diagnostic expert systems, considering knowledge and strategies that are useful for diagnosing faults. As the first step to reach the goal, we provide a framework for hypothesis generation, one of the three subtasks of diagnosis, classifying information needed for diagnosing faults into three classes: the domain model, additional domain knowledge, and diagnostic strategy. Three sorts of knowledge belonging to the domain model, namely, device model, process model, and topological relative position are used to model the device being diagnosed. Heuristics and naive physics, which are classified in the additional domain knowledge, are used as additional information to diagnose faults. As strategies for diagnosing faults, the framework applies three sorts of diagnostic strategies: the qualitative value propagation, direct path of causality, and structural fault localization. An algorithm for coordinating the sorts of knowledge and the strategies in diagnosing faults is also provided. Furthermore, an example of diagnosing a structural fault in the domain of refrigeration plants is given to illustrate how the framework works.

Diagnosing continuous systems with qualitative dynamic models

This paper presents several innovations in the development of model-based diagnostic systems for diagnosing faults in continuous dynamic physical systems. The approach utilises recent developments in qualitative simulation techniques to cope with the inherent lack of modelling knowledge and to provide a qualitative description of the dynamic behaviour. In particular, techniques for the synchronous tracking of the model-based predictions and the evolution of the physical system between equilibria are developed. A discrepancy metric is defined that allows for the continuous degradation of the system behaviour from normal to faulty to be detected. And, most fundamentally, a method for iteratively searching through the space of possible model variations is presented. This provides explicit feedback from detected discrepancies to model adjustments and has the important advantage of reducing the sensitivity to modelling errors and approximate fault models. In the limit, no fault models are required. However, if available these can be used to initialise the search. An example is included which outlines the basic approach discussed in this paper.

A preliminary specification methodology for model-based diagnosis

This paper sets out to provide a basis for a specification methodology for modelbased diagnostic systems (MBDS). The purpose of the methodology is to provide a mapping from the problem space of possible diagnostic applications to the solution space provided by the various approaches to MBDS. Therefore, given the major characteristics of a diagnostic problem, the methodology should provide guide-lines by which the specification of a suitable MBDS may be determined. As a first stage in the development of this methodology we provide taxonomies of the problem and solution spaces. The former is characterised via a set ofProblem requirements, divided intoTask, Fault andModel requirements, while the latter is classified as a set ofSystem specifications, with reference to the major functional blocks of MBDS: namely theDiagnostic Strategist, thePredictor and theCandidate Proposer. The last part of this paper proposes a mapping between these two multi-dimensional spaces. This mapping is preliminary, and therefore neither exhaustive nor exclusive, but together with the taxonomies of the problem requirements and system specification will provide a catalyst for the development of a more extensive methodology.

GENERATING FAULT HYPOTHESES WITH A FUNCTIONAL MODEL IN MACHINE-FAULT DIAGNOSIS

Traditional experiential knowledge-based diagnostic systems have suffered in their application to real-world problems due to their inability to handle unanticipated situations. Subsequently, diagnostic reasoning approaches have been developed that rely on a model of the device's normal operation to mitigate these shortcomings; these systems are called model-based diagnostic systems. The models of model-based systems are primarily a representation of the actual components of the device, which each have a defined behavior, along with a description of the topology of the device. The behavior of the device is simulated by introducing values into the device's inputs and propagating their effects throughout the interconnected components. Model-based systems often require an excessive amount of computation and data to arrive at a solution, primarily because information about any component in the model can only be utilized to make additional inferences about the components which are physical proximal to it in the...

Integrating diagnostic knowledge

The use of artificial intelligence technique to access, analyze, and integrate different types of knowledge under a single diagnostic concept is described. Repair statistics and field experience are handled by an empirical knowledge (shallow reasoning) diagnostic system in order to retain the experience of expert test personnel. Computer-aided-design knowledge is handled by model-based (deep reasoning) diagnostic systems in order to extract diagnostics directly from design data. Combining these approaches overcomes limitations of the individual techniques and provides a more powerful diagnostic system. The Westinghouse expert diagnostic system is considered as an example.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>