Artificial olfaction tool and techniques for safety controls in aerospace assembly and maintenance

Abstract

Fast response and reliability are mandatory requirements in non- destructive tests specifically in aerospace industry, for safety and efficiency reasons. Currently, the adoption of composite materials, a fundamental technology for the green aircraft concept, is limited by the lack of a validated NDT technique for the assessment of adhesive bonds quality. The latter is hampered by panels surface contamination. E-noses equipped with PARC algorithms appear a promising choice to obtain a rapid surface contamination state assessment but their dependability should be carefully analyzed. In this paper, combining real time classifiers, we show how to obtain a rapid first-hand response for the operator, retaining the possibility of increasing accuracy awaiting for the end of the e-nose measurement cycle. A reject option is casted on the base of classifier self-perceived reliability to nullify false negatives while keeping the false positive rate at minimum.