Defective Casting Diagnosing via an Enhanced Knowledge Hyper-Surface Method

Abstract:

Article Preview

The research on the analysis of cause and effect relationships in castings has always been a centre of attention in the manufacturing industry. An intelligent diagnosis system should be able to diagnose effectively the causal representation and also justify its diagnosis. Recently, a method, known as the Knowledge Hyper-surface method which used Lagrange Interpolation polynomials has gained more popularity in learning cause and effect analysis in casting processes. The current method show that the belief value of the occurrence of cause with respect to the change in the belief value in the occurrence of effect can be modelled by linear, quadratic or cubic relationships and the method retained the advantages of neural networks and overcomes their limitations in learning the input-output mapping function in the presence of noisy, limited and sparse data. However, the methodology was unable to model exponential increase/decrease in belief values in cause and effect relationships. This paper proposed an enhancement to the current Knowledge Hyper-surface method by introducing midpoints in the existing shape formulation which further constrains the shape of the Knowledge hyper-surfaces to model an exponential rise in belief values but without exposing the dataset to the limitations of ‘over fitting’. The ability of the proposed method to capture the exponential change in the belief variation of the cause when the belief in the effect is at its minimum is compared to the current method on real casting data.

Info:

Periodical:

Edited by:

Mohamed Othman

Pages:

684-689

Citation:

N. Mohd Nawi et al., "Defective Casting Diagnosing via an Enhanced Knowledge Hyper-Surface Method", Applied Mechanics and Materials, Vols. 229-231, pp. 684-689, 2012

Online since:

November 2012

Export:

Price:

$38.00

[1] Meghana R. Ransing, 2002, Issues in Learning Cause and Effect Relationships from Examples: With particularly emphasis on casting process, University of Wales Swansea, Swansea.

[2] B. Lally, L. T. Biegler, and H. Henein, 1991, Optimisation and Continous casting. 1. Problem Formulation and Solution Strategy: Metallurgical Transactions B - Process Metallugy, v. 22, pp.641-648.

DOI: https://doi.org/10.1007/bf02679019

[3] J. Grum, and J.M. Slabe, 2004, The use of factorial design and response surface methodology for fast determination of optimal heat treatment conditions of different Ni-Co-Mo surfaced layers: Journal of Materials Processing Technology, v. 155-156, p.2026-(2032).

DOI: https://doi.org/10.1016/j.jmatprotec.2004.04.220

[4] Bendall A., 1988, Introduction to Taguchi methodology: Proceedings of the 1988 European Conference, pp.1-14.

[5] Kackar R.N., 1985, Off-line quality control, parameter design and the Taguchi method: Journal of Quality Technology, v. 17, pp.176-88.

DOI: https://doi.org/10.1007/978-1-4684-1472-1_4

[6] Singh H., and Kumar P., 2005, Optimizing cutting force for turned parts using Taguchi's parameter design approach: Indian J. Eng. Mater. Sci., v. 12, pp.97-103.

[7] M. Perzyk, and A. Kochanski, 2003, Detection of cause of casting defetcs assisted by artificial neural netwroks: Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, v. 217, pp.1279-1284.

DOI: https://doi.org/10.1243/095440503322420205

[8] Wilson R. L., and Sharda R., 1994, Bankruptcy prediction using neural networks: Decision Support Systems, v. 11, pp.545-557.

DOI: https://doi.org/10.1016/0167-9236(94)90024-8

[9] Funahashi K., 1989, On the Approximate Realization of Continuous Mappings by Neural Networks: Neural Networks, v. 2, pp.183-192.

DOI: https://doi.org/10.1016/0893-6080(89)90003-8