Abstract | ||
---|---|---|
The aim of the work is to propose and discuss a technique which allows for classifying the defects found in metallic components on the basis of a non-destructive remote-field eddy-current technique experimental test (RFEC). To this aim, we propose to employ a Hopfield associative memory as a neural classifier. The performances of the proposed approach are evaluated on real-world data |
Year | DOI | Venue |
---|---|---|
2000 | 10.1109/IJCNN.2000.859425 | IJCNN (6) |
Keywords | Field | DocType |
non-destructive test,flaw detection,hopfield neural nets,metallic component,real-world data,pattern classification,structural engineering computing,metallic components,neural classifier,hopfield associative memory,experimental test,eddy current testing,content-addressable storage,hopfield network,defects classification,non-destructive remote-field eddy-current technique,nondestructive remote-field eddy-current technique experimental test,corrosion,microstructure,industrial engineering,associative memory,nondestructive testing,prototypes,voltage,non destructive testing | Eddy-current testing,Content-addressable memory,Pattern recognition,Computer science,Nondestructive testing,Content-addressable storage,Artificial intelligence,Classifier (linguistics),Hopfield network,Machine learning | Conference |
Volume | ISSN | ISBN |
6 | 1098-7576 | 0-7695-0619-4 |
Citations | PageRank | References |
2 | 0.55 | 1 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
s barcherini | 1 | 2 | 0.55 |
l cipiccia | 2 | 2 | 0.55 |
marco maurizio maggi | 3 | 2 | 0.55 |
Simone Fiori | 4 | 85 | 7.38 |
P. Burrascano | 5 | 17 | 7.64 |