Use of case-based reasoning for interpretation of data from NDT

NDT inspection provides us with data in the form of signals, images, or sequences of these. The data has to be analyzed in order to determine if it contains any indications of defects. This analysis is often complex due to reasons such as invertibility of the data, presence of noise, and a large number of possible interactions of the objects' features, defects and noise. in the past, systems have been built which used neural networks (or other classifiers) as well as expert systems to interpret data however successful uses of these systems in inspection practice are rare. This article presents how the case-based reasoning (CBR) methodology can be used to tackle the problem of NDT data interpretation. The article presents the characteristics of CBR which make it interesting for NDT Suitability of CBR for NDT data interpretation is illustrated by an example of a CBR system for eddy current inspection of heat exchangers.