Autor: |
Shyamsunder, M. T., Raj, Baldev, Rao, B. P. C., Jayakumar, T., Kalyanasundaram, P. |
Předmět: |
|
Zdroj: |
AIP Conference Proceedings; 2001, Vol. 557 Issue 1, p649, 7p, 3 Diagrams, 2 Graphs |
Abstrakt: |
Two neural network based approaches are highlighted for automated eddy current detection and characterization of defects in AISI type 316 stainless steel sheets/plates. In the first approach, neural networks are used for off-line quantitative characterization of artificial and natural defects. In the second approach, neural networks are used for on-line EC testing and their use in conjunction with raster scan imaging to realize a new intelligent imaging scheme to produce accurate three-dimensional pictures of defects. The details of the two approaches and the experimental results are discussed. © 2001 American Institute of Physics. [ABSTRACT FROM AUTHOR] |
Databáze: |
Complementary Index |
Externí odkaz: |
|