By Topic

Second International Conference on Intelligent Systems Engineering, 1994

Date 5-9 Sep 1994

Filter Results

Displaying Results 1 - 25 of 71
  • The application of fuzzy logic to position control: optimisation, simulations and experiments

    Publication Year: 1994, Page(s):255 - 261
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (352 KB)

    In this paper fuzzy logic is applied to position control. Comparisons are made with other simple nonlinear controllers, and optimisation on a system with one degree of freedom has been carried out for these controllers using the same simulated annealing method. It is found that the full simulated annealing algorithm was not required for the idealised, mathematical model but in the real systems the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Predictive fuzzy controllers for drug delivery

    Publication Year: 1994, Page(s):262 - 267
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (392 KB)

    Deals with the design of intelligent controllers for drug delivery in long term treatment, where a partially closed-loop is necessary in order to assist patients and physicians in assessing and modifying drug protocols. The authors present the general characteristics of their proposed approach and an application of predictive fuzzy controllers for managing renal anaemia View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Control of a nonlinear pressure process in practice based on neural net models and exact-linearization

    Publication Year: 1994, Page(s):268 - 273
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (408 KB)

    This paper deals with exact-linearization of nonlinear processes which can be modeled by feedforward neural networks. The authors propose two approaches. The first one uses nonlinear control theory to linearize a feedforward neural model of the involved process. The latter approach uses a feedforward neural network to exact-linearize the process directly. Both are used in the control of a pilot pl... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Knowledge based monitoring and diagnosis in machine maintenance

    Publication Year: 1994, Page(s):448 - 454
    Cited by:  Patents (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (376 KB)

    Maximum availability of cost intensive machinery is highly dependant of minimizing downtime caused by maintenance. Software systems for monitoring and diagnosis can help to reduce downtime. Permanent monitoring of a machine guarantees a reliable detection of most faults. An interactive diagnosis system can guide the maintenance staff to accomplish their tasks. A system architecture which supports ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using causal ordering for explanation in model-based diagnosis of continuous dynamic systems

    Publication Year: 1994, Page(s):274 - 279
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (464 KB)

    This paper presents a preliminary approach to providing an explanation facility for model-based diagnostic systems by the use of causal ordering. An explanation algorithm is described that allows explanations to be automatically generated for diagnostic findings by searching through the causal graph derived from the structural and behavioural model of the physical system under diagnosis. Typical e... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic learning of decision trees to acquire knowledge for the diagnosis of dynamic systems

    Publication Year: 1994, Page(s):101 - 106
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (340 KB)

    Inductive learning methods became an essential part of knowledge acquisition tools for diagnosis components of expert systems. If dealing with dynamic systems, not only the current state variables are relevant to the classification process of technical system's states but also their histories. These requirements result in the fact, that the state space seems to be not finite. Up to now, the way ou... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Control system fault-toleration ensuring via self-organization

    Publication Year: 1994, Page(s):461 - 466
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (340 KB)

    A new approach of fault-toleration enhancement via self-reorganizing control, based on principles of three-level hierarchy, deep diagnosis and flexible fault counteraction is considered. Methods of solving the main problems of fault-toleration for technical plant's standard control system are described. The results of digital simulation of aircraft fault-tolerant control system are given View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The design and use of multiple models for time-constrained hierarchical diagnosis

    Publication Year: 1994, Page(s):280 - 285
    Cited by:  Patents (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (420 KB)

    This paper describes the design and use of multiple models for time-constrained diagnosis. Although model-based diagnosis provides benefits in terms of maintainability and fault coverage, when compared with rule-based diagnosis, it also requires more computation time. We propose in this paper, a hierarchical model representation of the system to be diagnosed, in order that the most precise and det... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Non-minimum phase plants in iterative learning control

    Publication Year: 1994, Page(s):107 - 112
    Cited by:  Papers (7)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (316 KB)

    Some problems of iterative learning control with non-minimum phase plants are studied. One specific algorithm (norm-optimal iterative learning control) and one specific plant structure (a stable, SISO, non-minimum phase plant) are considered exclusively. It is shown that a zero of the plant in the RHP causes very slow convergence of the input sequence and results in a non-zero error View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A generic harness for the systematic generation of multiple models

    Publication Year: 1994, Page(s):49 - 55
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (440 KB)

    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 custom... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Diagnosis using fault trees induced from simulated incipient fault case data

    Publication Year: 1994, Page(s):304 - 309
    Cited by:  Papers (3)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (424 KB)

    Fault tree analysis is widely used in industry for fault diagnosis. The diagnosis of incipient or `soft' faults is considerably more difficult than that of `hard' faults, which is the case considered normally. A detailed fault tree model reflecting signal variations over a wide range is required in the case of soft faults. This paper presents comprehensive results describing the diagnosis of incip... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Method of decomposition for diagnosing malfunctions in assumption-based model

    Publication Year: 1994, Page(s):286 - 291
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (412 KB)

    This paper presents a formal framework for diagnosis. We focus on diagnosis from first principles, and study how the measurements affect diagnosis set. We explore the idea that the measurements do not eliminate an actual diagnosis from Diag (a set of diagnoses of a system being modeled). The measurements reduce the total diagnosis set, but in the case of minimal or kernel diagnoses it proves to be... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Relative degree of recurrent neural networks

    Publication Year: 1994, Page(s):113 - 117
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (180 KB)

    In the paper some tools from the differential geometry theory of single-input single-output nonlinear systems are applied to a recurrent neural network. It is shown that a change of coordinates and a state feedback can transform a recurrent neural network in to a linear system View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mechatronics and intelligent systems

    Publication Year: 1994, Page(s):395 - 400
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (340 KB)

    The development of intelligent autonomous and semi-autonomous systems capable of operating safely in unstructured environments such as those outlined above will to a significant degree be dependent on the achievement on the levels of system integration and the transfer of functionality between the mechanical, electronic and software domains suggested by mechauonics. In particular, the system must ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Second International Conference on `Intelligent Systems Engineering' (Conf. Publ. No.395)

    Publication Year: 1994
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (40 KB)

    The following topics were dealt with: qualitative modelling; quantitative modelling; learning and identification; artificial neural network theory; classification by neural networks; control by neural networks; temporal reasoning; fuzzy control design; qualitative feedback control; fuzzy control applications; model-based diagnosis; mobile robots and vehicles; intelligent robot control; intelligent... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neural network approach to the robot inverse calibration problem

    Publication Year: 1994, Page(s):342 - 347
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (428 KB)

    In this paper, methods for robot inverse calibration are described. The position and orientation in space of the end effector (pose) errors of a six degrees of freedom (DOF) Puma robot are measured, using a precision co-ordinate measuring machine (CMM), at discrete locations distributed in the calibration volume. The corresponding joint corrections are obtained to compensate the pose error using a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The notion of the state in systems theory and artificial intelligence

    Publication Year: 1994, Page(s):56 - 61
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (320 KB)

    This paper discusses the methodological analogies and differences of the systems theoretic and the knowledge-based approaches to modelling and simulation of dynamical systems. This comparison is based on the notion of the dynamical system as defined in systems theory, in particular on the concept of state. Two examples show that these notions are relevant for quantitative models as used in systems... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A high-level communication mechanism for intelligent cooperative systems

    Publication Year: 1994, Page(s):360 - 365
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (392 KB)

    In this paper we are concerned with inter-agent communication processes to support intelligent collaborative reasoning mechanisms, which are necessary for the implementation of computer supported concurrent engineering systems. Following a brief overview of the research efforts in inter-agent communication, this paper describes briefly the VirtualTeam system's architecture. A design example is use... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of neural networks for fault diagnosis in a power plant

    Publication Year: 1994, Page(s):292 - 297
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (344 KB)

    The paper deals with the diagnosis of an industrial plant about which the knowledge in the fault situations is incomplete. The approach is as follows: the intelligent system, whose main part consists of a number of artificial neural networks, makes use of the qualitative knowledge about the process flow in the fault-free case and in the presence of faults, and it concludes about the possible fault... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Petri-net representation of the qualitative behaviour of a dynamical continuous-time system

    Publication Year: 1994, Page(s):223 - 228
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (376 KB)

    In this paper an approach is presented how a qualitative model of a dynamical continuous-variable system can be set up. The method is based on Petri nets which have been successfully used so far to describe discrete-event systems. Places will be used to represent qualitative states whereas transitions model the qualitative state transitions of the system. The influence of input variables is reflec... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The event calculus at work: a case study in the medical domain

    Publication Year: 1994, Page(s):195 - 200
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (436 KB)

    Efficiency issues involved in temporal reasoning have often been ignored, and this is a major limiting factor to the application of temporal reasoning in realistic domains. In this paper we adopt the event calculus (EC) model of time and change, enriched with preconditions. The addition of preconditions, which is crucial to deal with real-world examples, heavily deteriorates the performance. There... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Condensed knowledge representation in BP-networks

    Publication Year: 1994, Page(s):118 - 123
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (340 KB)

    In the framework of NN-theory, a lot of research deals with designing self-organizing neural networks with an internal structure that seems to be appropriate for a particular task domain. The aim of this paper is to contribute to better understanding the behaviour of BP-networks, their knowledge extraction and generalization capabilities. This is the way along which neural networks and rule-based ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Interfacing geometric and physical models in a virtual manufacturing environment

    Publication Year: 1994, Page(s):401 - 406
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (348 KB)

    This paper sets out to describe the development, function and operation of a design by manufacturing simulation system. The construction of a geometric modeller with its attendant object indexing and interaction detection modules is described. An automatic finite element meshing system is reported which allows a physical model to be fully embedded within the system. An interaction rule base is dev... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Problems and progress in intelligent systems control

    Publication Year: 1994, Page(s):1 - 8
    Cited by:  Papers (4)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (496 KB)

    Research in intelligent control (IC) methods has enhanced the capability and flexibility of controllers at servo levels, at process design and at process management and coordination levels. The methods utilised employ techniques such as neural networks and fuzzy logic which interact and reason about the process and its environment by iterative learning. This paper reviews the requirements, progres... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Functional diagnosis and prescription of measurements

    Publication Year: 1994, Page(s):316 - 322
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (604 KB)

    This paper deals with diagnostic reasoning based on functional models. The purpose of this paper is twofold: (i) to present an approach to functional diagnosis with generalized efforts and flows (FDf ); and (ii) to discuss in detail how the traditional minimum entropy approach to test prescription can be instantiated in FDf . After a brief illustration of the functional role ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.