The paper introduces a computer vision methodology for detecting pitting corrosion in gas pipelines. To achieve this, a dataset comprising 576,000 images of pipelines with and without pitting corrosion was curated. A custom-designed and optimized convolutional neural network (CNN) was employed for binary classification, distinguishing between corroded and non-corroded images. This CNN architecture, despite having relatively few parameters compared to existing CNN classifiers, achieved a notably high classification accuracy of 98.44%. The proposed CNN outperformed many contemporary classifiers in its efficacy. By leveraging deep learning, this approach effectively eliminates the need for manual inspection of pipelines for pitting corrosion, thus streamlining what was previously a time-consuming and cost-ineffective process.

The influence of acoustic anisotropy on ultrasonic testing reliability poses a challenge in evaluating products from additive technologies (AT). This study investigates how elasticity constants of anisotropic materials affect defect signal amplitudes in AT products. Experimental measurements on AT samples were conducted to determine elasticity constants. Using Computational Modeling and Simulation Software (CIVA), simulations explored echo signal changes across ultrasound propagation directions. The parameters $A_{13}$ (the ratio between the velocities of ultrasonic transverse waves with vertical and horizontal polarizations at a 45-degree angle to the growth direction), $A_3$ (the ratio for waves at a 90-degree angle), and $A_g$ (the modulus of the difference between $A_{13}$ and $A_3$) were derived from wave velocity relationships and used to characterize acoustic anisotropy. Comparative analysis revealed a strong correlation (0.97) between the proposed anisotropy coefficient $A_g$ and the amplitude changes. Threshold values of $A_g$ were introduced to classify anisotropic materials based on observed amplitude changes in defect echo signals. In addition, a method leveraging deep learning to predict $A_g$ based on data from other anisotropy constants through genetic algorithm (GA)-optimized neural network (NN) architectures is proposed, offering an approach that can reduce the computational costs associated with calculating such constants.

Possible causes of anisotropy of acoustic properties in additive manufacturing products are considered. Based on acoustic measurements, the type of elastic symmetry in an Inconel alloy sample prepared by selective laser melting (SLM) was determined. The analysis of the measurements has shown that the sample growер direction corresponds to the axis of symmetry of acoustic properties. The results of experimental studies and analytical modeling of the effect of anisotropy on the amplitude of a signal reflected from an artificial reflector in the form of a side drilled hole are presented.

The possibility of a rigorous theoretical solution of the three-dimensional problem of scattering of elastic waves at the tip of a vertical crack in a weld is analyzed. It is shown that in the general case of ultrasound scattering on a flat target, the three-dimensional problem can be reduced to a two-dimensional one. On this basis, for an arbitrary direction of sounding a crack in a weld, the dependence of the signal from the crack tip on the direction to the receiver was assessed. It is noted that the wave size of the crack tip is much smaller than the wave size of the end of the grooves that can be made to simulate defects in welded joints. As a result, it was found that the nature of the scattering of elastic waves by the tip of the crack differs from the nature of scattering on the grooves, including in cases where the opening of the grooves is minimal, based on the possibility of their manufacture. The results of an experimental verification of the obtained theoretical estimates on samples of steel and aluminum are presented. It is shown that at the ends of the grooves (in contrast to the crack tips), even with their minimal openings, conditions are created for the formation of a scattered field of the type of specular reflection from a volumetric cavity—a side-drilled hole.

In this work, a computer vision system is proposed, which allows the identification and localization of pitting corrosion on metallic surface of the gas pipelines made of low carbon and low alloy steels. For this purpose, a dataset of 5,760 images of pipeline surface with and without pitting corrosion was collected. The developed convolutional neural network (CNN) architecture was trained on this dataset. The hyperparameters of this architecture were optimized using Bayesian optimization. The developed and optimized CNN architecture does not have a large number of trainable parameters compared to existing CNN-based architectures. Also, the developed architecture showed significantly higher accuracy of 98.44 %, when classifying images into images without corrosion and with pitting corrosion. The developed CNN outperformed most existing classifiers in its parameters. A pitting corrosion localization system was also developed using the “sliding windows” and “image pyramid” methods, which made it possible to localize areas with identified pitting corrosion on the surface of pipelines made of low carbon and low alloy steels, using the developed CNN without additional labeling of the data set. The proposed deep learning approach will eliminate the need for the operator to visually inspect the pipeline for pitting corrosion, which is costly and time-consuming method. The research was carried out with financial support of the grant of Russian Scientific Fund No. 22-29-00524, https://rscf.ru/project/22-29-00524/.