Ultrasonic guided wave estimation of minimum remaining wall thickness using Gaussian process regression

Ultrasonic Guided Waves (UGW) offer the possibility of inspecting a strip across structure rather than just point under traditional bulk wave transducer. This can increase rate inspection and enable obstructions. paper investigates instantaneous phase characteristics shear horizontal guided waves for various defect depths widths. The Gaussian process regression is then evaluated estimating minimum remaining wall thickness between pair transducers. A model built using fusion large-scale simulated low-scale real experimental data. For this purpose, more precise an electromagnetic acoustic transducer initially by integrating both elastic fields. Then data set after having been calibrated genetic algorithm. examination unseen evaluation shows that 96 % has error during gauging less 10 per cent thickness. Finally, testing containing three different defects with 3.7, 5.7 9.2 mm was examined, resulting in good depth prediction large 1 wider one wavelength.