Advanced Pattern Recognition Techniques for Fast and Reliable E-nose Response Analysis in NDTs Scenarios

摘要: Non Destructive Tests (NDT) technologies have strong requirements in terms of fast response and reliability, these constraints are particularly stressed aerospace industry, for safety efficiency reasons. Composite panels bonding, essential to green aircraft concept, is still lacking a validated NDT technique that can guarantee the bond quality. E-noses appear be promising choice but they adapted surface analysis task, furthermore may require significant amount time acquire complete pattern slowing testing large panels. In this paper, we present results obtained by combining real classifiers on an e-nose platform obtain rapid while keeping possibility maximize accuracy awaiting end measurement cycle. A reject option casted base combined perceived reliability nullify high costs false negatives low positive rate.