Reducing waste in casting with a predictive neural model
- 41 Downloads
- 6 Citations
This paper describes an interactive neural network model that predicts the quality of cast ceramic products using multiple quantitative and qualitative inputs. This has been done to enable a major sanitary ware manufacturer to reduce product waste by better control of the slip casting process. The input variables describe the raw materials, ambient conditions and line settings for the ceramic casting process. The neural network predictive model assigns one of seven quality categories to the cast based on the input data. This prediction is used by the quality control engineer to make a priori adjustments to materials and line settings so that a good quality cast is produced without trial and error. The neural model can also be used to determine optimum settings of each adjustable input variable in the light of values of non-adjustable input variables.
Keywords
Neural networks ceramic casting quality control predictive modellingPreview
Unable to display preview. Download preview PDF.
References
- Andersen, K., Cook, G. E., Karsai, G. and Ramaswamy, K. (1990) Artificial neural networks applied to arc welding process modeling and control. IEEE Transactions on Industry Applications, 26, 824–830.Google Scholar
- Ben Brahim, S., Smith, A. E. and Bidanda, B. (1993) Relating product specifications and performance data with a neural network model for design improvement. Journal of Intelligent Manufacturing, 4, 367–374.Google Scholar
- Dinger, D. R. (1990) Expert systems for use in ceramic processing. Ceramic Engineering Science Proceedings, 11, 320–331.Google Scholar
- Funahashi, K. (1989) On the approximate realization of continuous mappings by neural networks. Neural Networks, 2, 183–192.Google Scholar
- Geman, S., Bienenstock, E. and Doursat, R. (1992) Neural networks and the bias/variance dilemma. Neural Computation, 4, 1–58.Google Scholar
- Hornik, K., Stinchcombe, M. and White, H. (1989) Multilayer feedforward networks are universal approximators. Neural Networks, 2, 359–366.Google Scholar
- Lambe, C. M. (1958) Preparation and use of plaster molds, in Ceramic Fabrication Processes, Kingery, W. D. (ed.), John Wiley & Sons, New York, ch. 3.Google Scholar
- Lapedes, A. and Farber, R. (1988) How neural nets work, in Neural Information Processing Systems, Anderson, D. Z. (ed.), American Institute of Physics, New York, pp. 442–456.Google Scholar
- Ikafor, A. C., Marcus, M. and Tipirneni, R. (1990) Multiplen sensor integration via neural networks for estimating surface roughness and bore tolerance in circular end milling. 1990 Transactions of NAMRI/SME, 128–137.Google Scholar
- Rumelhart, D. E., McClelland, J. L. and The PDP Research Group (1986) Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol 1, MIT Press, Cambridge, MA.Google Scholar
- Smith, A. E. (1993) Predicting product quality with backpropagation: a thermoplastic injection moulding case study. International journal of Advanced Manufacturing Technology, 8, 252–257.Google Scholar
- Smith, A. E. and Dagli, C. H. (1991a) Controlling industrial processes through supervised, feedforward neural networks. Computers & Industrial Engineering, 21, 247–251.Google Scholar
- Smith, A. E. and Dagli, C. H. (1991b) Relating binary and continuous problem entropy to backpropagation network architecture, in Applications of Artificial Neural Networks II, SPIE, Bellingham, pp. 551–562.Google Scholar
- Twomey, J. M. and Smith, A. E. (in press) Performance measures, consistency and power for artifical neural network models. Journal of Mathematical and Computer Modelling.Google Scholar
- Werbos, P. J. (1974) Beyond regression: new tools for prediction and analysis in the behavioral sciences, unpublished Ph.D. Thesis, Harvard University.Google Scholar
- White, H. (1989) Learning in artificial neural networks: a statistical perspective. Neural Computation, 1, 425–464.Google Scholar