scholarly journals Application of classification neural networks for identification of damage stages of degraded low alloy steel based on acoustic emission data analysis

2020 ◽  
Vol 20 (4) ◽  
Author(s):  
Joanna Krajewska-Śpiewak ◽  
Igor Lasota ◽  
Barbara Kozub

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.

Author(s):  
A. F. C. Brown ◽  
R. Edmonds

A comparison has been made between the dynamic and static tensile yield strengths of eight steels varying from mild steel to a heat-treated low-alloy steel, the rate of loading in the dynamic tests being such as would occur in a ship under the action of an underwater explosion. The dynamic yield strength of the steels with low static strength was 20–30 per cent greater than their static yield strength but, for the stronger steels, the increase was less, being negligible in the case of the heat-treated low-alloy steel. This result conforms with the findings of other investigators, and shows that any increase in strength under the dynamic loading considered is too small to be of importance in design.


Metal Science ◽  
1979 ◽  
Vol 13 (8) ◽  
pp. 451-462 ◽  
Author(s):  
H. N. G. Wadley ◽  
D. C. Furze ◽  
C. B. Scruby ◽  
B. L. Eyre

2013 ◽  
Vol 9 (1) ◽  
pp. 100-115 ◽  
Author(s):  
I. Ben Ammar ◽  
A. El Mahi ◽  
C. Karra ◽  
R. El Guerjouma ◽  
M. Haddar

PurposeThe aim of the present study is to investigate the mechanical behaviour of cross‐ply laminates under static tensile and buckling loading. Different cross‐ply laminates constituting of carbon fibers (CFRP), hybrid fibers (HFRP) and glass fibers (GFRP) in an epoxy matrix were considered. This work is also interested in identifying and characterizing the local damage in the composites with the use of acoustic emission method (AE).Design/methodology/approachThe cross‐ply laminates are differentiated by the stacking sequences, thickness of 90° oriented layers and reinforcement. They are subjected to the static tensile and buckling load. The damage investigation is reached by the analysis of acoustic emission signals collected from static buckling tests.FindingsThe results show the effects of reinforcement type, stacking sequences and thicknesses ratio of 90° and 0° layers on the stiffness, failure load and displacement. A cluster analysis of acoustic emission data is achieved and the results are correlated to the damage mechanism of specimens under buckling tests.Originality/valueThe analysis of acoustic emission signals collected from static buckling tests under loading levels of 40, 60 and 100 per cent of the static failure load allows the damage investigation in cross‐ply laminates.


Sign in / Sign up

Export Citation Format

Share Document