DOI: 10.18503/1995-2732-2024-22-4-171-180
Abstract
Problem Statement (Relevance). Additive technologies such as 3D printing are becoming increasingly relevant in the modern world. They allow to create complex products that were previously difficult or even impossible to manufacture using traditional production methods. At the same time, WAAM technology represents an important direction in the development of additive manufacturing of metal products and is highly relevant in modern industry. When manufacturing parts using the WAAM method, it is extremely important to know their residual life, which is largely determined by the fatigue properties of the material. Objectives. It is required to develop a method for diagnosing structural steels obtained by 3D printing with electric arc surfacing. Methods Applied. Methods of non-destructive testing and machine learning. Originality. The proposed method for diagnosing structural degradation is a new approach to monitoring the condition of parts made of NP-30HGSA alloy. The use of neural network models for analyzing data on the alloy structure allows to obtain more accurate results compared with traditional diagnostic methods. This makes it possible to more effectively monitor the condition of parts made of NP-30HGSA alloy and timely identify signs of structural degradation. Result. In this paper, the processes of accumulation of structural damage in alloy 30HGSA during fatigue tests are investigated. The most pronounced structural transformations occur at values of relative elongation above 7%. Practical Relevance. Assessment and diagnostics of structural degradation of NP-30CrHSA alloy manufactured using WAAM technology and analyzed using a neural network model is a key tool to ensure high quality of manufactured parts. It also makes it possible to increase the reliability of structures and improve production processes.
Keywords
metals, mechanical properties, neural network modeling, NP-30HGSAalloy, 3D printing, WAAM, new metal structures, preset properties, fatigue properties
For citation
Anosov M.S., Mantserov S.A., Klochkova N.S., Mikhailov A.M. Assessment and Diagnosis of Structural Degradation of NP-30HGSA Alloy Obtained by Waam Using a Neural Network Model. Vestnik Magnitogorskogo Gosudarstvennogo Tekhnicheskogo Universiteta im. G.I. Nosova [Vestnik of Nosov Magnitogorsk State Technical University]. 2024, vol. 22, no. 4, pp. 171-180. https://doi.org/10.18503/1995-2732-2024-22-4-171-180
1. J.-W. Jang, K.-E. Min, C. Kim, J. Shin, J. Lee, S. Yi, Scaffold characteristics, fabrication methods, and biomaterials for the bone tissue engineering. Int. J. Precis. Eng. Manuf. 2023;24:511-529.
2. Zivkovic M., Zujovic M., Milosevic J. Architectural 3D-printed structures created using artificial intelligence: a review of techniques and applications. Appl. Sci. 2023;13(19):10671.
3. Kirichek A.V., Sergeev A.G., Fedonina S.O., Petreshin D.I. Technological provision of quality parameters of a part synthesized by the WAAM method by controlling the trajectory of the feedstock movement. Transportnoe mashinostroenie [Transport engineering], 2022;(4):66–68. (In Russ.)
4. Oskolkov A.A., Matveev E.V., Bezukladnikov I.I., Trushnikov D.N., Krotova E.L. Advanced technologies for additive manufacturing of metal product. Vestnik PNIPU. Mashinostroenie, materialovedenie [Bulletin PNRPU. Mechanical engineering, materials science], 2018;20(3):90-105. (In Russ.)
5. Khlybov A.A., Kabaldin Yu.G., Anosov M.S., Ryabov D.A., Shatagin D.A. Investigation of low-cycle fatigue of steel 12X18H10T based on the approaches of fractal analysis and artificial intelligence. Zavodskaya laboratoriya. Diagnostika materialov [Factory Laboratory. Diagnostics of materials], 2021;87(9):59-67. (In Russ.)
6. Kabaldin Y.G., Shatagin D.A., Anosov M.S., Kolchin P.V., Kiselev A.V. Diagnostics of 3D printing on a CNC machine by machine learning. Russian Engineering Research. 2021;41(4):320-324.
7. Anosov M.S., Shatagin D.A., Chernigin M.A., Mordovina Yu.S., Anosova E.S., Structure formation of Np-30HGSA alloy during additive electric arc cultivation. Izvestiya vysshih uchebnyh zavedenij. Chernaya metallurgiya [News of higher educational institutions. Ferrous metallurgy], 2023;66(3):294-301. (In Russ.)
8. Cooper M., Camprubi R., Koc E., Buckley R., Digital Destination Matching: Practices, Priorities and Predictions. Sustainability. 2021;13(19):10540.
9. Kim V.A., Mokritskii B.Y., Morozova A.V. Multifractal analysis of microstructures after laser treatment of steels. Solid state phenomena. 2020;299SS:926-932.
10. Hinojosa, M., Trejo, V., Ortiz, U. Fractal Analysis of the Microstructure of Aisi 304 Steel. MRS Proceedings. 1995;(407):411-416.
11. Manzerov S.A., Anosov M.S., Italians D.S. Diagnostics of structural damage of steel 09G2C obtained using WAAM technology for low-cycle fatigue based on neuro-fuzzy classification. Morskoj vestnik [The Marine Bulletin], 2023;2(86):32-36. (In Russ.)