Abstract
A quasi real-time inversion strategy is presented for groove characterization of a conductive non-ferromagnetic tube structure by exploiting eddy current testing (ECT) signal. Inversion problem has been formulated by non-iterative Learning-by-Examples (LBE) strategy. Within the framework of LBE, an efficient training strategy has been adopted with the combination of feature extraction and a customized version of output space filling (OSF) adaptive sampling in order to get optimal training set during offline phase. Partial Least Squares (PLS) and Support Vector Regression (SVR) have been exploited for feature extraction and prediction technique respectively to have robust and accurate real time inversion during online phase.
Highlights
Nowadays non-invasive inspection through non-destructive testing and evaluation (NDT-NDE) is becoming very popular area of research for different applications
Within the framework of LBE, an efficient training strategy has been adopted with the combination of feature extraction and a customized version of output space filling (OSF) adaptive sampling in order to get optimal training set during offline phase
In this work, we have shown an innovative real time inversion solution within the framework of Learning-by-Examples (LBE) for groove characterization in tube structure
Summary
Nowadays non-invasive inspection through non-destructive testing and evaluation (NDT-NDE) is becoming very popular area of research for different applications. A quasi real-time inversion strategy is presented for groove characterization of a conductive non-ferromagnetic tube structure by exploiting eddy current testing (ECT) signal. Partial Least Squares (PLS) and Support Vector Regression (SVR) have been exploited for feature extraction and prediction technique respectively to have robust and accurate real time inversion during online phase.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have