A qualitative modelling environment for design & diagnosis of automation

ABSTRACT

This paper describes a qualitative modelling toolbox for designing and developing application independent architectures.Developed out of a remote monitoring application, the toolbox uses object-oriented software and encapsulates knowledge-based information from a human expert to construct the model. Being object-oriented there is full inheritance between individual objects. It was considered feasible that the original work could be the basis of a design tool for automation architectures.Currently, application specific, hierarchically ordered architectures for automation are a barrier to progress. The present monolithic layering of such architectures means fault detection and monitoring remain the domain of the human expert. Here, we can produce the qualitative model in the form of an interactive user interface that can be used in fault monitoring and diagnosis and report faults. This modular, evolvable approach to designing architectures should aid in the reduction of their complexity particularly at the design stage.

REFERENCES

• 1: The computer integration organisation- some business and technology issues for osi-map/top solution. In ENE'88, Baltimore, USA, 1988.
• 2: Peter Clark and Tim Niblett. Induction in noisy domains. In I. Bratko and N. Lavrac, editors, Progress in Machine Learning (proceedings of the 2nd European Working Session on Learning), Sigma, Wilmslow, UK, 1987.
• 3: G.Moore. Manufacturing automation protocol. mapping the factory of the future. Electronics and Power, April, 1986.
• 4: R. S. Michalski and J. Larson. Incremental generation of VL1 hypotheses: the underlying methodology and the description of program A Q11. Technical Report ISG 83-5, The University of of Illinois at Urbana-Champaign, Department of Computer Science, Urbana, 1983.
• 5: I. Bratko , I. Mozetic , N. Lavrac, Automatic synthesis and compression of cardiological knowledge, Machine intelligence 11, Oxford University Press, Inc., New York, NY, 1988
• 6: D. Pearce. The induction of fault diagnosis systems from qualitative models. In AAAI88 The Seventh National Conference on Artificial Intelligence, Proceedings, pages 353-357, St. Paul Minnesota, 1988.
• 7: J. Ross Quinlan. Learning efficient classification procedures and their application to chess endgames. In J. G. Carbonell, R. S. Michalski, and T. M. Mitchell, editors, Machine Learning, vol. 1, Palo Alto, Ca, Tioga, 1983.
• 8: S.Tulip. Map- the icl way. Computer Manufacturing, Nov, 1987.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.6 SIMULATION AND MODELING

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.1 Applications and Expert Systems
          Subjects: Industrial automation
      I.2.5 Programming Languages and Software
          Subjects: Expert system tools and techniques
      I.2.6 Learning
          Subjects: Induction
      I.2.9 Robotics
          Subjects: Sensors; Manipulators

  K. Computing Milieux
  K.6 MANAGEMENT OF COMPUTING AND INFORMATION SYSTEMS
      K.6.1 Project and People Management
          Subjects: Systems analysis and design

General Terms:
Algorithms, Design, Management, Theory