Exploiting Safety Constraints in Fuzzy Self-organising Maps for Safety Critical Applications
This paper defines a constrained Artificial Neural Network (ANN) that can be employed for highly-dependable roles in safety critical applications. The derived model is based upon the Fuzzy Self-Organising Map (FSOM) and enables behaviour to be described qualitatively and quantitatively. By harnessing these desirable features, behaviour is bounded through incorporation of safety constraints – derived from safety requirements and hazard analysis. The constrained FSOM has been termed a ’Safety Critical Artificial Neural Network’ (SCANN) and preserves valuable performance characteristics for non-linear function approximation problems. The SCANN enables construction of compelling (product-based) safety arguments for mitigation and control of identified failure modes. Illustrations of potential benefits for real-world applications are also presented.
KeywordsArtificial Neural Network Failure Mode Artificial Neural Network Model Fuzzy Rule Firing Strength
Unable to display preview. Download preview PDF.
- 1.Lisboa, P.: Industrial use of safety-related artificial neural networks. Health & Safety Executive 327 (2001)Google Scholar
- 2.Hull, J., Ward, D., Zakrzewski, R.: Verification and Validation of Neural Networks for Safety-Critical Applications, Barron Associates, Inc. and Goodrich Aerospace, Fuel and Utility Systems (2002)Google Scholar
- 3.Kurd, Z.: Artificial Neural Networks in Safety-critical Applications, First Year Dissertation, Department of Computer Science, University of York (2002)Google Scholar
- 6.Ojala, T.: Neuro-Fuzzy Systems in Control, Masters Thesis, Department of Electrical Engineering, Tampere University of Technology, Tampere (1994)Google Scholar
- 7.Kurd, Z., Kelly, T.P.: Establishing Safety Criteria for Artificial Neural Networks. In: Palade, V., Howlett, R.J., Jain, L. (eds.) KES 2003. LNCS, vol. 2774, Springer, Heidelberg (2003)Google Scholar
- 8.CISHEC, A Guide to Hazard and Operability Studies, The Chemical Industry Safety and Health Council of the Chemical Industries Association Ltd. (1977)Google Scholar
- 9.Bilgic, T., Turksen, I.B.: Measurement of membership functions: theoretical and empirical work. In: Handbook of fuzzy sets and systems, In Dubois and Prade (1997)Google Scholar
- 10.Chipperfield, A.J., Bica, B., Fleming, P.J.: Fuzzy Scheduling Control of a Gas Turbine Aero-Engine: A Multiobjective Approach. IEEE Trans. on Indus. Elec. 49(3) (2002)Google Scholar