Abstract
This paper defines a type of constrained Artificial Neural Network (ANN) that enables analytical certification arguments whilst retaining valuable performance characteristics. Previous work has defined a safety lifecycle for ANNs without detailing a specific neural model. Building on this previous work, the underpinning of the devised model is based upon an existing neuro-fuzzy system called the Fuzzy Self-Organising Map (FSOM). The FSOM is type of ‘hybrid’ ANN which allows behaviour to be described qualitatively and quantitatively using meaningful expressions. Safety of the FSOM is argued through adherence to safety requirements – derived from hazard analysis and expressed using safety constraints. The approach enables the construction of compelling (product-based) arguments for mitigation of potential failure modes associated with the FSOM. The constrained FSOM has been termed a ‘Safety Critical Artificial Neural Network’ (SCANN). The SCANN can be used for nonlinear function approximation and allows certified learning and generalisation. A discussion of benefits for real-world applications is also presented within the paper.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Lisboa, P.: Industrial use of safety-related artificial neural networks. Health & Safety Executive 327 (2001)
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)
Kurd, Z., Kelly, T.P.: Safety Lifecycle for Developing Safety Critical Artificial Neural Networks. In: Anderson, S., Felici, M., Littlewood, B. (eds.) SAFECOMP 2003. LNCS, vol. 2788, pp. 77–91. Springer, Heidelberg (2003)
Nabney, I., et al.: Practical Assessment of Neural Network Applications. Aston University & Lloyd’s Register, UK (2000)
Vuorimaa, P.: Fuzzy self-organising map. Fuzzy Sets and Systems 66, 223–231 (1994)
Ojala, T.: Neuro-Fuzzy Systems in Control, Masters Thesis, Department of Electrical Engineering. Tampere University of Technology, Tampere (1994)
Kohonen, T.: Self-organisation and associative memory. Springer, Berlin (1984)
Jang, J.S.R.: ANFIS: adaptive-network-based fuzzy inference systems. IEEE Trans. Syst. Man. Cybern. 23(3), 665–685 (1993)
Takagi, H., et al.: Neural networks designed on approximate reasoning architecture and their applications. IEEE Trans. Neural Networks 3(5), 752–760 (1992)
Brown, M., Harris, C.: Neuro-fuzzy adaptive modelling and control. Prentice Hall, New York (1994)
Haykin, S.: Neural Networks: A Comprehensive Foundation. Prentice-Hall, Englewood Cliffs (1999)
Towell, G., Shavlik, J.W.: Knowledge-Based Artificial Neural Networks. Artificial Intelligence (70), 119–165 (1994)
Kurd, Z., Kelly, T.P.: Establishing Safety Criteria for Artificial Neural Networks. In: Seventh International Conference on Knowledge-Based Intelligent Information & Engineering Systems (KES 2003), Oxford, UK (2003)
Wen, W., Callahan, J., Napolitano, M.: Towards Developing Verifiable Neural Network Controller, Department of Aerospace Engineering, NASA/WVU Software Research Laboratory, West Virginia University, Morgantown, WV (1996)
Wang, L.X.: Fuzzy systems are universal approximators. IEEE Trans. Syst. Man. Cybern. SMC-7(10), 1163–1170 (1992)
Jackson, T.O., McDermid, J.: Certification of Neural Networks. ERA Technology Ltd., Report 97-0365, Project 13-01-4745 (1997)
CISHEC, A Guide to Hazard and Operability Studies, The Chemical Industry Safety and Health Council of the Chemical Industries Association Ltd. (1977)
Bilgic, T., Turksen, I.B.: Measurement of membership functions: theoretical and empirical. In: Dubois, Prade (eds.) Handbook of fuzzy sets and systems (1997)
Fox, J., Robertson, D.: Industrial use of Safety Related Expert Systems. Health & Safety Executive 296 (2000)
Oliveira, J.V.: Semantic Constraints for Membership Function Optimisation. IEEE Trans. Syst., Man., Cybern. Part A: Systems and Humans 29(1) (1999)
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)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kurd, Z., Kelly, T.P. (2004). Using Fuzzy Self-Organising Maps for Safety Critical Systems. In: Heisel, M., Liggesmeyer, P., Wittmann, S. (eds) Computer Safety, Reliability, and Security. SAFECOMP 2004. Lecture Notes in Computer Science, vol 3219. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30138-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-540-30138-7_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23176-9
Online ISBN: 978-3-540-30138-7
eBook Packages: Springer Book Archive