Innovative technologies in the study of mechanical properties of materials
DOI:
https://doi.org/10.63341/vjmet/2.2024.130Keywords:
universal breaking machines, machine vision, pulse loading, prediction of the behaviour of materials, optical measurement systems, machine learning algorithms, visualisation of deformationsAbstract
The article provides an overview of modern innovative technologies used to study the mechanical properties
of materials using universal breaking machines. The focus is on the integration of machine vision technologies, machine
learning algorithms and high-speed stereoscopy, which provide new capabilities for analysing the behaviour of materials
during static and dynamic loads. An important aspect of the research is the improvement of traditional test methods
through the introduction of innovative components: high-speed cameras that allow recording material deformations with
microsecond precision; stereoscopic systems that create three-dimensional models of material behaviour under load; as well
as lighting devices that provide uniform illumination of the test object. These technologies are synchronized with powerful
computing modules capable of analysing large amounts of data in real time. The authors emphasise that the integration
of computer vision and machine learning algorithms can significantly reduce the impact of the human factor on research
results. Automated analysis systems are able to accurately detect and classify defects, simulate types of failures and predict
the behaviour of materials under various loading conditions. Examples of the use of such systems in the study of complex
composites, metal alloys and the latest polymers are also given. Additionally, innovative approaches to the creation of
dynamic loads that allow testing for impact strength and endurance are considered. The article shows how automated test
process management systems increase research efficiency by providing greater accuracy, repeatability of results, and faster
data processing. The practical significance of the described developments lies in their wide application in industries where
the study of the mechanical properties of materials is critical, such as aircraft construction, mechanical engineering, energy
and construction. A high level of automation and accuracy of tests, provided by the introduction of modern technologies,
allows setting new standards for the quality of research and creates prospects for the further development of materials
science. Thus, the presented approach to improving universal breaking machines contributes to increasing the accuracy of
measurements, expanding the functionality of traditional test systems and creating more efficient methods for studying
materials
References
García-Collado, A., Dorado-Vicente, R., Romero, P.E., & Gupta, M.K. (2023). Recent trends on the mechanical properties of additive manufacturing. Applied Sciences, 13(12), article number 7067. doi: 10.3390/app13127067.
Jiang, S., Dong, T., Zhan, Y., Dai, W., & Zhan, M. (2021). Experimental study on improving the mechanical properties of material extrusion rapid prototyping polylactic acid parts by applied vibration. Applied Sciences, 11(4), article number 1820. doi: 10.3390/app11041820.
Mashiwa, N., Furushima, T., & Manabe, K. (2017). Novel non-contact evaluation of strain distribution using digital image correlation with laser speckle pattern of low carbon steel sheet. Procedia Engineering, 184, 16-21. doi: 10.1016/J. PROENG.2017.04.065.
Amini, A., & Haghpanahi, M. (2020). Machine learning for material design and engineering applications. Hoboken: Wiley-Blackwell.
Singh, B., & Chattopadhyay, S. (2022). Advanced materials and technologies in industry. Berlin: Springer.
Chien, C.F., & Li, W.L. (2021). Artificial intelligence in materials science and engineering. Amsterdam: Elsevier.
Wu, P., & Liu, Y. (2020). Artificial intelligence for materials science and engineering. Amsterdam: Elsevier.
Suryawanshi, R.D., & Patel, V.P. (2021). Machine learning in materials science: Fundamentals and applications. Boca Raton: CRC Press.
Zhu, Y., & Liang, Y. (2019). Computational materials science: From basic principles to state-of-the-art applications. Weinheim: Wiley-VCH.
Hoffmann, M.J., & Dieringa, H. (2018). Materials science and technology: The key to innovation. Weinheim: Wiley-VCH.
Jha, S.K., & Sharma, P. (2022). Advanced smart materials for energy and environmental sustainability. Amsterdam: Elsevier.
Evans, J.R., & Oliver, A.C. (2021). Emerging materials science and technologies. Cambridge: Cambridge University Press.
Kumar, R., & Singh, R. (2023). Applications of artificial intelligence in materials science and engineering. Berlin: Springer Nature.
Downloads
-
PDF
Downloads: 41
