Non-Destructive Test by the Hopfield Network

The aim of this 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.

• Type: Conference
• Year: 2000
• Where: IJCNN
• Authors: S. Barcherini, L. Cipiccia, M. Maggi, Simone Fiori, Pietro Burrascano
• Keywords: Hopfield Associative Memory, IJCNN 2000, Metallic Components, Neural Networks, Remote-Field Eddy-Current Technique