Barat V.A., Marchenkov A.Yu., Karpova M.V., Bardakov V.V., Lepsheev E.A., Ushanov S.V., Elizarov S.V. «Application of artificial neural networks for detection of defects in dissimilar welded joints by acoustic emission method» Контроль. Диагностика, 27, № 12, с. 4-13 (2024)

The paper considers the possibility of using artificial neural networks to detect hits in acoustic emission (AE) testing. A distinctive feature of the proposed method is that the training set of the neural network is formed using a complex technique based on the application of modeling technology, on the one hand, and on calibration measurements carried out in the field, on the other. In this paper, process pipelines with dissimilar welded joints were considered as a test structure. AE signals were modeled using a hybrid method: the signal waveform was determined based on a finite element model, and the AE hits amplitudes were determined on the basis of a physical experiment on cyclic stretching of samples of dissimilar welded joints. Acoustic signals measured on the process pipelines bodies in the field condition were used as noise. A multilayer perceptron was used to classify the data, the architecture of which was selected based on the minimization of the classification error. Keywords: dissimilar welded joints, acoustic emission, diffusion layers, neural networks in acoustic emission, classification of acoustic emission signals, waveguide modeling.

Danilov V.N. «On the change in the amplitude of the echo signal recorded by a normal probe from a reflector – an ax symmetrically located flat-bottom hole, depending on the ratio of the radii of the hole and the piezoelectric plate of the probe» Контроль. Диагностика, 27, № 12, с. 27-32 (2024)

Calculations of the amplitude of the echo signal recorded by a round direct converter from a reflector – an ax symmetrically located flat bottom hole in the form of an integral representation of the Fourier-Bessel type have been carried out. The calculation results, with an increase in the ratio of the radii of the piezoelectric plate of the probe and the hole, confirmed the previously established by Prof. I.N. Ermolov the presence of a maximum echo signal in the far zone of the transducer when it is located on the border of the near zone of the reflector. It was found that in the far zone of the transducer, a change in the wave parameter of the piezoelectric plate (the product of the wave number of the longitudinal wave by the radius of the piezoelectric plate) from 10 to 25 practically does not affect the dependence of the amplitude of the echo signal on the ratio of the radii of the hole and the piezoelectric plate of the probe. It is shown that an increase in the ratio of the amplitude of the echo signal at the maximum tends to the limit value – corresponding to the amplitude of the bottom echo for the radius of the hole, much larger than the radius of the piezoelectric plate with an increase in the relative range to the flat bottom hole. Keywords: echo signal maximum, reflector, flat bottom hole, far zone, near zone, normal probe, piezoelectric plate, wave parameter, bottom signal.

Grigoriev S.N., Kozochkin M.P., Volosova M.A., Okunkova A.A. «Acoustic monitoring of laser pulses in processing of metal-ceramic hard alloy» Контроль. Диагностика, 27, № 12, с. 33-41 (2024)

This work is devoted to studying the relationship between the factors of processing with laser pulses of T15K6 hard alloy, the parameters of acoustic emission, and process productivity. The laser source was a pulsed fiber laser with a wavelength of 1064 nm, a power of 20 to 60 W, and pulse duration of 250 to 500 ns. The main dependencies for the lower and upper frequency ranges (10–28 kHz and 32–70 kHz) were plotted. Acoustic emission signals provide insight into the effects of concentrated energy flows on material and can be used to understand hard-to-observe phenomena and ongoing processing performancence. Keywords: vibroacoustic emission, laser processing, control, productivity, cutting insert, spectral analysis, hard alloy T15K6.