Automated Design Of Fuzzy Non-Destructive Testing System By A Genetic Algorithms

Kouki Nagamune, Syoji Kobashi, Yutaka Hata, Kazuhiko Taniguchi(1

*)Kinden Corp.

Proceedings of Third International Forum on Multimedia & Image Processing
IFMIP054, (2002)

This paper proposes an application of a Genetic Algorithms (GA) to Fuzzy Non-Destructive Testing (NDT) System. We are concerned here with the system extracts embedded tubes from pulse-radar images. The system usually uses several fixed parameters to analyze input data. The optimal values of the parameters depend on the environment (e.g. permittivity of concrete, pulse-radar device, and so on). Therefore, the system often fails extract embedded tubes when the fixed parameters are not optimal in the environment. No work deals with this problem. This paper attempts to optimize them by a simple GA in order to solve the problem. We applied the system with the GA to two data sets obtained by various environments. As the result, the system with the GA was able to adapt each environment.