R.R. Leitch

Heriot-Watt University, Edinburgh, Scotland, United Kingdom

Are you R.R. Leitch?

Claim your profile

Publications (27)13.49 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: The authors consider models to be executable descriptions of the real world, that is a model can be used to predict or analyse properties of the system. Simulation and reasoning systems, which may be derived from traditional or AI approaches, are used to execute these models. Given the plethora of modelling techniques available which cope well with certain, but not other, contexts, it is evident that there is no `best model' covering all situations: a model is correct if it satisfies its purpose no less and no more. The desires of the user of a modelling system are always moderated by the availability of techniques permitting these desires to be met. To alleviate the difficulties associated with this requires a methodology to guide the user to the best model and simulation technique to meet his needs. A primary requirement in the construction of such a methodology is a comprehensive and understandable classification of the choices inherent in the construction of a model
    IEE Proceedings - Control Theory and Applications 10/1999; DOI:10.1049/ip-cta:19990503 · 2.11 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The desires of the user of a modelling system are always moderated by the availability of techniques permitting these desires to be met. To alleviate the difficulties associated with this requires a methodology to guide the user to the best model and simulation technique to meet his needs. A primary requirement in the construction of such a methodology is a comprehensive and understandable classification of the choices inherent in the construction of a model and a categorisation of existing techniques in the light of this classification. This paper has presented such a classification. The modelling process was presented as consisting of three modelling choices involving the definition or adjustment of a number of model properties
    Physical Modelling as a Basis for Control (Digest No: 1996/042), IEE Colloquium on; 03/1996
  • G.J Wyatt, R.R Leitch, A.D Steele
    [Show abstract] [Hide abstract]
    ABSTRACT: Traditional quantitative methods of analysis and simulation are compared with recently developed techniques in qualitative simulation by using as a case-study a simple dynamic model of the interacting markets for housing and mortgages. Analysis by the different techniques shows that while the qualitative simulation requires less detailed models, of the precision normally available in practice, it results in ambiguous descriptions of behaviour that for certain initial conditions can obscure the true behaviour. By contrast, quantitative simulation produces a unique precise behaviour, but in requiring excessively specific information of the modeller it may produce an inaccurate if precise outcome.
    Decision Support Systems 10/1995; 15(2):105-113. DOI:10.1016/0167-9236(94)00030-V · 2.04 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The development of application systems for fault diagnosis has attracted worldwide interest in many different research areas. In particular, advanced techniques for finding faults through the use of explicit structural and/or behavioural models of the physical system to be diagnosed have been developed both in the area of control engineering and in the field of artificial intelligence. Although many approaches to creating model-based diagnostic systems (MBDS) exist, as yet, no clear methodology is available for the selection of an appropriate approach to solve individual given diagnostic problems. We have therefore been developing a specification methodology that essentially comprises a taxonomy of diagnostic tasks, a taxonomy of model-based systems, and a set of guidelines that provides a mapping from the former to the latter, Our aim is to provide a method by which existing MBDS tools and techniques may be combined within a generic architecture in a principled manner to produce effective diagnostic systems for given applications. The structure of the methodology has been derived in part from the top level architectural design of ARTIST, a generic model-based diagnostic toolkit that combines a wide variety of model based diagnostic (MBD) tools. This architecture is based upon the three main types of knowledge that are necessary for the construction of model based diagnostic systems
    Real-Time Knowledge Based Systems, IEE Colloquium on; 03/1995
  • Q. Shen, R.R. Leitch, A.D. Steele
    [Show abstract] [Hide abstract]
    ABSTRACT: Utilising multiple-model descriptions requires that the relationships between the various models be well-defined and can be generated systematically from a reference model. We present a generic model harness, for component-based models, that is based on a set of fundamental representational primitives that are directly related to a classification of basic model properties. This supports the customisation of the harness for a particular model and also the systematic generation of multiple models. Examples of the resulting models and their corresponding behaviours are presented for a laboratory-scale system rig
    Intelligent Systems Engineering, 1994., Second International Conference on; 10/1994
  • R.R. Leitch, Q. Shen
    [Show abstract] [Hide abstract]
    ABSTRACT: The motivations for qualitative modelling and fuzzy modelling are almost identical: to cope with the complexities in the modelling of real systems. However, their developments have been independent, distinct and complementary. The synthesis of these techniques has required a re-appraisal of exactly what model properties are used in these techniques. We argue that precision and uncertainty are distinct concepts. Qualitative modelling deals with abstract imprecise models whilst fuzzy modelling copes with uncertain imprecise or precise models, With this clarification we have developed a fuzzy qualitative simulation system, an outline of which is given in this paper. We believe that such combinations of fuzzy and qualitative methods are the natural development of Zadeh's original proposal for intelligent reasoning about complex systems
    Fuzzy Systems, 1994. IEEE World Congress on Computational Intelligence., Proceedings of the Third IEEE Conference on; 07/1994
  • Julie-Ann Sime, R.R. Leitch
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper describes the basis of a specification methodology for building Intelligent Training Systems in Industrial Environments (ESPRIT project 2615, ITSIE). The specification methodology determines the mapping of specific training requirements onto tools and techniques for implementation based upon an analysis of the training requirements and of the nature of the domain knowledge.A task analysis is carried out on the training requirements to determine a number of specific training objectives. These objectives are described in terms of the required level of behaviour and knowledge necessary to achieve the objective. This description leads to the determination of a primitive mode of instruction, which promotes: rote, inductive or deductive learning. This decomposition is used to identify relevant tools and techniques for domain knowledge representations and for didactics and diagnosis within the tutor of the training system.
    Computers & Education 02/1993; 20(1):73–80. DOI:10.1016/0360-1315(93)90072-Q · 2.63 Impact Factor
  • R R Leitch, Yiu Kwong Wong, G J Wyatt
    [Show abstract] [Hide abstract]
    ABSTRACT: For many tasks, it may be more appropriate to reason with qualitative models which are an inexact representation of the real world than to use the more powerful classical tools of differential or difference equations. Qualitative methods allow us to build models which do not necessarily incorporate assumptions, such a linearity or constancy over time. Even with such imprecise knowledge, there is enough information in a qualitative description to support qualitative simulation, which predicts the possible qualitative behaviours of an economic system. Copyright 1993 by Taylor and Francis Group
    Economic Systems Research 02/1993; 5(4):377-93. DOI:10.1080/09535319300000030 · 2.43 Impact Factor
  • Q. Shen, R.R. Leitch, G.M. Coghill
    [Show abstract] [Hide abstract]
    ABSTRACT: The theory of fuzzy sets and the development of qualitative modelling have had similar motivations: coping with complexity in reasoning about the behaviour of physical systems. The paper presents a synthesis of these techniques, providing a fuzzy qualitative modelling method for performing qualitative simulation that offers significant advantages over existing qualitative simulation methods. The resulting simulation algorithm is termed FuSim hereafter. This development makes a significant contribution towards the full-scale industrial applications of qualitative modelling. The paper shows a typical example of utilising fuzzy qualitative models in fault diagnosis of continuous dynamic systems, based on an iterative search technique
    Two Decades of Fuzzy Control - Part 2, IEE Colloquium on; 02/1993
  • Q. Shen, R.R. Leitch
    [Show abstract] [Hide abstract]
    ABSTRACT: The paper presents several innovations in the development of techniques for diagnosing continuous dynamic systems based on qualitative models. It argues that, to diagnose such physical systems, a mechanism for modelling and simulating continuous dynamic behaviours, a method for synchronous tracking of the dynamic behaviours, a metric for detecting degradation of the continuous behaviours and for matching predictions with observations must be developed. The paper provides a particular realisation of these techniques, following a proposal for iteratively searching for fault models against possible modelling dimensions. The process of how such a diagnostic system finds faults is demonstrated by a simple example
    Intelligent Systems Engineering, 1992., First International Conference on (Conf. Publ. No. 360); 09/1992
  • R.R. Leitch, P. Ponnapalli, A.F. Slater
    [Show abstract] [Hide abstract]
    ABSTRACT: The ESPRIT project 2615 ITSIE, aims to utilise ITS techniques to develop a generic framework for the development of training systems. A major aspect of this project is the use of the qualitative modelling techniques to meet the needs of current training systems. The project has recognised the importance of clearly establishing the types of skills and `expertise' required of the trainee. The authors believe that this expertise exists in various forms and should be supported by appropriate representational tools. A systematic classification of domain knowledge for intelligent training is presented as used within the ITSIE project. Based on earlier studies on the classification of the behaviour of humans in industrial environments, it is proposed that the domain knowledge be classified into two main categories: domain expertise and domain simulation. The proposed classification and tools provide a coherent way of representing domain knowledge in ITS and allow the use of multiple models in a model switching framework for effective training
    Intelligent Systems Engineering, 1992., First International Conference on (Conf. Publ. No. 360); 09/1992
  • M.O. Tokhi, R.R. Leitch
    [Show abstract] [Hide abstract]
    ABSTRACT: An analysis of the process of field cancellation in a three-dimensional non-dispersive propagation medium is given. This analysis is presented from the perspective of the design of active noise control (ANC) systems for broadband noise emanating from compact sources. The analysis of cancellation is presented in parametric terms, both in time and in frequency, leading to a three-dimensional description of cancellation that is suitable for determining the geometrical arrangement for a given degree of cancellation, and consequently can be used for the design of ANC systems. Such parameters can also be used to determine the performance of the resulting ANC system.
    Journal of Sound and Vibration 06/1992; 155(3):497–514. DOI:10.1016/0022-460X(92)90714-9 · 1.86 Impact Factor
  • Q. Shen, R. R. Leitch
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a systematic investigation of developing multiple models of a physical system through the use of Fuzzy Qualitative Modelling (FuSim) technique, essentially along with four basic modelling dimensions identified: abstraction, commitment, model resolution, and relation strength. Implications of multiple models for Model-Based Reasoning in general and Model-Based Diagnosis in particular are discussed. Examples for building up multiple models against different modelling dimensions are provided with respect to a simple physical system and experimental simulation results shown.
    Annual Review in Automatic Programming 01/1992; 17:365-370. DOI:10.1016/S0066-4138(09)91060-6
  • M.O. Tokhi, R.R. Leitch
    [Show abstract] [Hide abstract]
    ABSTRACT: A design method is presented for active noise control (ANC) systems, in a three-dimensional nondispersive propagation medium with compact broadband noise sources. The design and implementation of the controller as a digital filter with a fixed transfer function is presented and verified through a set of practical experiments. The concept of self-tuning control as a combination of system identification and control is developed within the ANC system framework. Moreover, as required by the application, a supervisory level of control based on a performance criterion is added that automatically activates self-tuning control. The algorithm is implemented on a high-speed digital signal processor and tested on the exhaust noise of a 100 cc motorcycle. The experimental results are presented and compared with those of a system employing a fixed digital filter controller
    Control Theory and Applications, IEE Proceedings D [see also IEE Proceedings-Control Theory and Applications] 10/1991; DOI:10.1049/ip-d.1991.0058
  • M. O. Tokhi, R. R. Leitch
    [Show abstract] [Hide abstract]
    ABSTRACT: A design method for Active Noise Control (ANC) systems operating in a three dimensional nondispersive propagation medium is presented. The method is based on analysis of the relative stability of the inherent feedback loop. For practical systems, the use of absolute stability is not useful. A system having an extremely long oscillatory response is unlikely to be accepted and is liable to instability under small parameter variations. Practical limitations in the design of the controller, owing to the geometric configuration of the system are discussed.
  • R.R. Leitch, H.C. Quek
    [Show abstract] [Hide abstract]
    ABSTRACT: The paper proposes a classification of system behaviours that allows the generic control methods to be identified and clearly related. It then presents a strategy for integrated process supervision that provides for controlled evolution through the different control regimes. The generality of the strategy is independent of a particular realisation of individual control regimes, thereby allowing AI methods and classical control techniques to co-exist within an integrated framework. The system has been fully implemented on a SUN 3/160 workstation and validated on a laboratory scale process rig. An overview of the results obtained from a scheme utilising a standard three-term controller, a simple adaptive system and fault diagnosis based on a qualitative model of the process rig is presented. The paper then presents the behaviour classification for continuous processes. These are then related to a set of generic control regimes i.e. primary control, adaptive control and fault diagnosis. The structure of the integrated process supervision scheme is given, and its realisation for the control of the process rig is briefly described. Experimental results are given. Remarks on the effectiveness of the scheme and its future extensions are presented
    Control 1991. Control '91., International Conference on; 04/1991
  • [Show abstract] [Hide abstract]
    ABSTRACT: A status report is given on Esprit Project p2615: intelligent training systems in industrial environment (ITSIE). This project, started in March 1990, aims to: investigate intelligent training systems based on ITS concepts; develop a set of generic tools for domain knowledge, tutoring and user modelling; develop a generic architecture and associated communication protocols for ITSIE; establish a methodology for matching training objectives to generic solutions; validate the tools and methodology through two realistic demonstrators. The two demonstrators of the project are complementary with respect to the training and the domains. They are: training of electrical distribution network personnel in the correct online maintenance procedures and training of operators of a fossil-fuel power station
    Intelligent Tutoring Systems, IEE Colloquium on; 12/1990
  • R.R. Leitch
    [Show abstract] [Hide abstract]
    ABSTRACT: Artificial intelligence, once regarded as a fringe activity by the control and systems engineering community, is set to play a crucial role in the development of future automated systems. The insights gained from previous work are already being incorporated within the specification of new systems, e.g. object-oriented programming. However, the author argues that much more fundamental changes in the way people perceive and design systems is afoot. This amounts to no less than a scientific evolution or paradigm shift, significantly extending the tools and methods available to the engineer. This shift can be classified into three main categories of development: extending the tools and methods for modelling and reasoning about (physical) systems; extending the range of automated tasks; and developing architectures for intelligent systems
    Strategic Research Issues in AI in Engineering, IEE Colloquium on; 11/1990
  • Intelligent Tutoring Systems, IEE Colloquium on; 11/1990
  • R. R. Leitch, M. E. Wiegand, H. C. Quek
    [Show abstract] [Hide abstract]
    ABSTRACT: An abstract is not available.
    Ai Communications 01/1990; 3(2):48-57. · 0.47 Impact Factor

Publication Stats

330 Citations
13.49 Total Impact Points

Institutions

  • 1987–1999
    • Heriot-Watt University
      • Department of Electrical, Electronic and Computer Engineering
      Edinburgh, Scotland, United Kingdom
  • 1989–1991
    • The University of Sheffield
      • Department of Automatic Control and Systems Engineering
      Sheffield, ENG, United Kingdom