Skip to main content Accessibility help

Machine learning in configuration design

  • Tim Murdoch (a1) and Nigel Ball (a1)


New methods of configuration analysis have recently emerged that are based on development trends characteristic of many technical systems. It has been found that though the development of any system aims to increase a combination of the performance, reliability and economy, actual design changes are frequently kept to a minimum to reduce the risk of failure. However, a strategy of risk reduction commits the designer to an existing configuration and an approved set of components and materials. Therefore, it is important to analyze the configurations, components, and materials of past designs so that good aspects may be reused and poor ones changed. A good configuration produces the required performance and reliability with maximum economy. These three evaluation criteria form the core of a configuration optimization tool called KATE, where known configurations are optimized producing a set of ranked trial solutions. The authors suggest that this solution set contains valuable design knowledge that can be reused. This paper briefly introduces a generic method of configuration evaluation and then describes the use of a self-organizing neural network, the Kohonen Feature Map, to analyze solution sets by performing an initial data reduction step, producing archetype solutions, and supporting qualitative clustering.



Hide All
Ball, N.R., & Murdoch, T.N.S. (1994). Analysing design configuration spaces using a self-organising neural network. Adaptive Computing in Engineering Design and Control – '94, 9096.
Byworth, S. (1987). Design and development of high temperature turbines. Turbomachinery Int. May/June.
Caudell, T.P., Smith, D.G., Escobedo, R., & Anderson, M. (1994). NIRS: Large scale ART-1 neural architectures for engineering design retrieval. Neural Networks 7(9), 13391350.
Coplin, J.F. (1989). Engineering design – A powerful influence on the business success of manufacturing industry. ICED-89, 132.
Duffy, A.H.B., & Kerr, S.M. (1993). Customised perspectives of past designs from automated group rationalisations. Artificial Intelligence in Engineering, 8, 183200.
Koh, J., Suk, M., & Bhandarkar, S.M. (1995). A multilayer self-organizing feature map for range image segmentation. Neural Networks 8(1), 6786.
Kohonen, T. (1984). Self-organisation and associative memory. Springer-Verlag, New York.
Kohonen, T., Torkkola, K., Shozakai, M., Kangas, J., & Vent, O. (1987). Microprocessor implementation of a large vocabulary speech recognizer and phonetic typewriter for Finnish and Japanese. Proc. Eur. Conf. Speech Technol. 377380.
Martinelli, G., Ricotti, L.P., & Ragazzini, S. (1990). Nonstationary lattice quantization by a self-organizing neural network. Neural Networks 3(4), 385393.
Matsuyama, Y. (1988). Vector quantization with optimized grouping and parallel distributed processing. Neural Networks 1, 3642.
Murdoch, T.N.S. (1994). Machine learning in configuration design: A case study in configuration analysis. Workshop on Machine Learning in Design, AID-94.
Murdoch, T.N.S. (1993). Configuration evaluation and optimisation of technical systems. Ph.D. Thesis, Cambridge University.
Murdoch, T.N.S., & Wallace, K.M. (1992). Configuration optimisation of technical systems. J. Eng. Design 3(2), 99116.
Murdoch, T.N.S., & Wallace, K.M. (1995). Design for technical merit, design for X: Concurrent engineering imperatives. Chapman & Hall, New York.
Pahl, G., & Beitz, W. (1984). Engineering design. Design Council, London.
Reich, Y., Konda, S.L., Levy, S.N., Monarch, I.A., & Subrahmanian, E. (1993). New roles for machine learning in design. Artif. Intell. Eng. 8(3), 165181.
Schraudolph, N. (1990). A user’s guide to GENESIS 1.2ucsd. University of California, San Diego, CA.
Statnikov, R.B., & Matusov, J.B. (1995). Multicriteria optimization and engineering. Chapman & Hall, New York.
Vercauteren, L., Sieben, G., Praet, M., Otte, G., Vingerhoeds, R., Boullart, L., Calliauw, L., & Roels, H. (1990). The classification of brain tumours by a topological map. Proc. Int. Conf. Neural Nets., 387391.


Related content

Powered by UNSILO

Machine learning in configuration design

  • Tim Murdoch (a1) and Nigel Ball (a1)


Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed.