Application of classification neural networks for identification of damage stages of degraded low alloy steel based on a
- PDF / 5,296,224 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 94 Downloads / 161 Views
(2020) 20:109
REVIEW ARTICLE
Application of classification neural networks for identification of damage stages of degraded low alloy steel based on acoustic emission data analysis Joanna Krajewska‑Śpiewak1 · Igor Lasota2 · Barbara Kozub3 Received: 13 February 2020 / Revised: 27 August 2020 / Accepted: 31 August 2020 © The Author(s) 2020
Abstract The paper presents the influence of low alloy steel degradation on the acoustic emission (AE) generated during static tension of notched specimen. The material was cut from a technological pipeline long-term operated in the oil refinery industry. Comparative analysis of AE activity generated by damage process of degraded and new material has been carried out. The different AE parameters were used to detect different stages of fracture process of low alloy steel under quasi-static tensile test. Neural networks with three layers were created with Broyden–Fletcher–Goldfarb–Shanno learning algorithm for a database analysis. The different AE parameters were included in the input layer. Classification neural networks were created in order to determine the stages of material degradation. The results obtained from the carried out studies will be used as the basis for new methodology development of the assessment of the structural condition of in-service equipment.
1 Introduction Low alloy steels with different chemical composition are widely used in pressure vessels structures, operated in the oil refining and petrochemical processing. To work for decades, the pressure equipment needs to withstand extreme conditions such as high/low temperatures, time-varying pressure load and influence of aggressive media. Long-term application of equipment under extreme conditions can cause defects initiation and growth in the microstructure of the materials which can damage the equipment or cause the failure of the entire industrial unit. * Joanna Krajewska‑Śpiewak joanna.krajewska‑[email protected] Igor Lasota [email protected] Barbara Kozub [email protected] 1
Faculty of Mechanical Engineering, Production Engineering Institute, Cracow University of Technology, Al. Jana Pawła II 37, 31‑864 Kraków, Poland
2
PKN Orlen S.A., Chemików 7, 09‑411 Płock, Poland
3
Faculty of Materials Science and Physics, Institute of Material Engineering, Cracow University of Technology, Al. Jana Pawła II 37, 31‑864 Kraków, Poland
Therefore, the development of new, non-destructive methodologies which allow to assess the condition of materials after long-term use in the refinery industry is very important. Development of such methodologies is possible only by complex laboratory investigations. This research is aimed at using acoustic emission data analysis for the identification of plastic deformation and fracture processes in low alloy steel under quasi-static loading. The tested material came from the long-term operated seamless furnace coil pipe of the crude oil distillation unit. Tensile tests of notched flat specimens were performed with simultaneous registration of AE signal.
Data Loading...
