Ultrasonic Assessment of Thickness and Bonding Quality of Coating Layer Based on Short-Time Fourier Transform and Convolutional Neural Networks

Abstract

Ultrasonic non-destructive analysis is a promising and effective method for the inspection of protective coating materials. Offshore coating exhibits a high attenuation rate of ultrasonic energy due to the absorption and ultrasonic pulse echo testing becomes difficult due to the small amplitude of the second echo from the back wall of the coating layer. In order to address these problems, an advanced ultrasonic signal analysis has been proposed. An ultrasonic delay line was applied due to the high attenuation of the coating layer. A short-time Fourier transform (STFT) of the waveform was implemented to measure the thickness and state of bonding of coating materials. The thickness of the coating material was estimated by the projection of the STFT into the time-domain. The bonding and debonding of the coating layers were distinguished using the ratio of the STFT magnitude peaks of the two subsequent wave echoes. In addition, the advantage of the STFT-based approach is that it can accurately and quickly estimate the time of flight (TOF) of a signal even at low signal-to-noise ratios. Finally, a convolutional neural network (CNN) was applied to automatically determine the bonding state of the coatings. The time–frequency representation of the waveform was used as the input to the CNN. The experimental results demonstrated that the proposed method automatically determines the bonding state of the coatings with high accuracy. The present approach is more efficient compared to the method of estimating bonding state using attenuation.

Interfacial Bond Properties of Underwater Concrete Coated with Bisphenol A Epoxy Resins

“…This expectation was confirmed under constant laboratory conditions, and the effect of the coating method on changes in coating thickness over the exposure period was relatively minimal. The decreasing trend in thickness observed only in the RS conditions can be attributed to surface abrasion issues; nonetheless, further investigation remains necessary, and nondestructive methods could be useful for determining the reason for this reduction [43][44][45][46]. However, it should be noted that the thickness did not exhibit a significant relationship with the strength within the range of this study.…”

Ultrasonic non-destructive evaluation study of molecular diffusion bonding of thin copper-aluminum electrode sheets

“…With the wide application of machine learning, P. S. Mantra et al used a full factorial design methodology for experimental planning by selecting several process parameters such as welding pressure and welding time, developed a regression model to predict and simulate the weld strength of copper-aluminum thin plates using Artificial Neural Networks (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS), and used tensile and peeling loads to validation to ensure the accuracy of the results [18][19][20]. Despite the results achieved by this method, there are significant application limitations in practical engineering testing as the welding quality is affected by numerous process parameters, and the chosen model inputs directly affect the training results.…”

Ultrasonic tomography imaging enhancement approach based on deep convolutional neural networks

“…Most of the significant improvements in ultrasonic tomographic detection have occurred in the industrial and medical fields in recent years (Malikov et al 2021 ). For instance, the application of the RAPID algorithm with variable shape functions for detecting multiple defects in space (Martucci et al 2021 ).…”