EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Assessment of Anisotropic Acoustic Properties in Additively Manufactured Materials: Experimental, Computational, and Deep Learning Approaches

Ivan Malashin iD, Vadim Tynchenko iD, Dmitry Martysyuk iD, Nikita Shchipakov iD, Nikolay Krysko iD, Maxim Degtyarev, Vladimir Nelyub iD, Andrei Gantimurov, Aleksei Borodulin iD, Andrey Galinovsky

Sensors · 11.07.2024 · 24 (14) · 4488

DOI: 10.3390/s24144488 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 11.07.2024. Verfasst von Ivan Malashin und 9 weiteren Autor:innen. Beteiligte Einrichtung: Bauman Moscow State Technical University, Moscow 105005, Russia. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 100 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 A13 (the ratio between the velocities of ultrasonic transverse waves with vertical and horizontal polarizations at a 45-degree angle to the growth direction), A3 (the ratio for waves at a 90-degree angle), and Ag (the modulus of the difference between A13 and A3) 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 Ag and the amplitude changes. Threshold values of Ag were introduced to classify anisotropic materials based on observed amplitude changes in defect echo signals. In addition, a method leveraging deep learning to predict Ag 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.

Schlagwörter

Stichwörter der Autor:innen

additive technologiesanisotropydeep learningselective laser meltingultrasonic inspection

Autor:innen und Institutionen

  • Bauman Moscow State Technical University, Moscow 105005, Russia.
  • Far Eastern Federal University, Vladivostok 690922, Russia.

ORCID-Profile: Ivan Malashin, Vadim Tynchenko, Dmitry Martysyuk, Nikita Shchipakov, Nikolay Krysko, Vladimir Nelyub, Aleksei Borodulin

Zitieren

APA

Malashin, I., Tynchenko, V., Martysyuk, D., Shchipakov, N., Krysko, N., Degtyarev, M., Nelyub, V., Gantimurov, A., Borodulin, A., & Galinovsky, A. (2024). Assessment of Anisotropic Acoustic Properties in Additively Manufactured Materials: Experimental, Computational, and Deep Learning Approaches. Sensors, 24(14), 4488. https://doi.org/10.3390/s24144488

Vancouver

Malashin I, Tynchenko V, Martysyuk D, Shchipakov N, Krysko N, Degtyarev M, et al. Assessment of Anisotropic Acoustic Properties in Additively Manufactured Materials: Experimental, Computational, and Deep Learning Approaches. Sensors. 2024;24(14):4488. doi:10.3390/s24144488

BibTeX
@article{Malashin2024,
  author = {Malashin, Ivan and Tynchenko, Vadim and Martysyuk, Dmitry and Shchipakov, Nikita and Krysko, Nikolay and Degtyarev, Maxim and Nelyub, Vladimir and Gantimurov, Andrei and Borodulin, Aleksei and Galinovsky, Andrey},
  title = {Assessment of Anisotropic Acoustic Properties in Additively Manufactured Materials: Experimental, Computational, and Deep Learning Approaches},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {14},
  pages = {4488},
  doi = {10.3390/s24144488}
}
Kostenlos starten →