Abstract
A data fusion system based on Independent Component Analysis (ICA) has been applied to remove the negative effects produced by the lift-off variations of Eddy Current (EC) sensors, in the context of crack detection and recognition. Due to the sensor drift effect, EC magnitude and phase measurements are unavoidably affected by the lift-off noise that, in some cases, has a power content whose level is most than comparable to the defect related signal level. A set of measurements carried out on the specimen under inspection are sent as input to a neural network trained to perform the Independent Component Analysis of the input data: each sample measurement can be interpreted as a linear combination of quasi- independent signals related to measurement noise, lift-off noise and flaw presence. The basic work hypothesis is that the lift-off signal is present in multiple “views” of the specimen in the form of correlated noise. Therefore, the ICA will be able to fuse the knowledge provided by magnitude and phase signals in different measuring contexts, in order to extract the lift-off noise from the input signals and to separate it from the signal related to the crack.