Features of the microstructural and mechanical degradation of long term operated mild steel

Krechkovska, Halyna; Student, О. Z.; Lesiuk, Grzegorz; Correia, José A.F.O.

doi:10.1108/ijsi-10-2017-0056

Cited by 29 publications

(13 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We particularly used a convolutional neutral network (CNN), which displays high performance in terms of image analysis, even for deep learning. Although the input to the CNN was surface morphology converted to images, the output was an effective thickness as defined in Equation (1). Thus, analyses can be performed without removing necessary features through manual selection.…”

Section: Maximum Tensile Load Effective Thicknessmentioning

confidence: 99%

“…Maximum tensile load Width × Tensile strength of steel member with smooth surfaces (1) Thus, this study proposes a method that precisely estimates the effective thickness of the shell element from measurements of surface morphology. Although several methods have been proposed to obtain effective thickness from measurements of surface morphology [7,15,16], such thicknesses were estimated by manually selecting features such as the average thickness and standard deviation of thickness.…”

Section: Maximum Tensile Load Effective Thicknessmentioning

confidence: 99%

“…Corrosion of steel structures causes geometrical changes on the surface of structural members because of corrosion defects [1,2], which in turn lowers their load-bearing capacity. In the field of civil engineering, the corrosion of steel structures majorly contributes to deterioration of structural performance, together with fatigue cracks [3,4].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Evaluation of Tensile Performance of Steel Members by Analysis of Corroded Steel Surface Using Deep Learning

Chun

Yamane

Izumi

et al. 2019

Metals

View full text Add to dashboard Cite

To conduct safety checks of corroded steel structures and formulate appropriate maintenance strategies, the residual strength of steel structural members must be assessed with high accuracy. Finite element method (FEM) analyses that precisely recreate the morphology of corroded surfaces using solid elements are expected to accurately assess the strength; however, the cost of conducting these calculations is extremely high. Therefore, a model that uses mean thickness as the thickness of the shell element is widely used but this method has precision issues, particularly regarding overestimation of risk. Thus, this study proposes a method of structural analysis in which the effective thickness of a shell element is assessed using the convolutional neural network (CNN), a type of deep learning performed on tensile structural members. An FEM model is then built based on the shell element that uses this effective thickness. We cross-validated this method by adding a feature extraction layer that reflects the domain knowledge, together with convolutional and pooling layers that are commonly used for CNN and found that a high level of accuracy could be achieved. Furthermore, regarding corroded steel plates and H-section steel, our method demonstrated results that were extremely close to those of models that used solid elements.

show abstract

Section: Maximum Tensile Load Effective Thicknessmentioning

confidence: 99%

Section: Maximum Tensile Load Effective Thicknessmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of Tensile Performance of Steel Members by Analysis of Corroded Steel Surface Using Deep Learning

Chun

Yamane

Izumi

et al. 2019

Metals

View full text Add to dashboard Cite

show abstract

“…Amongst others, European studies have already looked into this subject related to fatigue pathologies of metallic assemblies, as shown for instance in Switzerland, 19 Sweden, 20 Portugal, 21 Italy, 22 Germany, 5 Poland, 23,24 and Ukraine. 25 In order to describe the fatigue behaviour of riveted connections, the classification of constructive details proposed in the Eurocode 3 can be applied. 26 This classification is made by considering the S-N or Wöhler curves of experimental fatigue data.…”

Section: Introductionmentioning

confidence: 99%

Contribution to the study of the influence of the stress ratio on the high cycle fatigue behaviour of riveted joints

Sire

Caiza

Espion

et al. 2020

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

Old riveted railway bridges are part of the cultural and technological heritage in many countries. The assessment of the actual behaviour and the remaining life of these structures is a key economical factor in the management of these bridges. This evaluation should take into account the evolution of the traffic loads, which have constantly increased since their construction, and a realistic estimation of the fatigue life derived from representative experimental tests. This study deals with the fatigue behaviour of riveted assemblies with specimens prepared from materials sampled in two old bridges: a railway bridge over the Adour river (France) built in 1862-1864 and the Stahringer bridge (Germany), constructed in 1895. Because all assemblies are not subjected to the same loads, this research concentrates on the influence of the stress ratio R on the fatigue behaviour. In order to quantify this influence, a comparison between the Basquin linear model and the Weibull model is performed. It is shown that a formula proposed in a recent study to determine the fatigue strength for an arbitrary value of R is not suitable in the high-cycle fatigue regime.

show abstract

“…• comparison of theoretical factors with real factors -determination of factors that can cause limit states and degradation processes of TO, • evaluation of TO degradation -TO analysis using microscopy methods, destructive and NDT tests, • processing results, determining the causes of TO degradation, • conclusions to prevent the formation of degradation processes of TO, resp. reduction of TO degradation [8][9][10][11][12][13][14].…”

Section: Introductionmentioning

confidence: 99%

Example of using complex system approach methodology by degradation of selected technical object

Kuśmierczak

Martin

2019

Engineering for Rural Development

View full text Add to dashboard Cite

Every graduate of engineering fields in his technical practice will encounter manifestations of limit states and degradation of technical objects. The consequences of these processes must be solved so as to ensure the required quality and safety, while ensuring the economic viability of the manufactured technical object. The consequences of the degradation processes of the technical objects lead not only to undesirable changes of properties and consequent shortening of the life cycle of a technical object, but also to economic losses and endangering the safety of the user of this object. Therefore, it is necessary to apply such a system approach for the evaluation of degradation processes, which will be repeatable for different types of TO and will lead to the detection of causes of degradation of TO. The methodology of a comprehensive approach to the degradation processes of TO has these main steps: localization and description of TO degradation manifestations; theoretical analysis of internal and external TO factors; description of the actual status of the TO and the actual conditions under which it was issued; determination of the factors that may cause boundary states and degradation processes TO; assessment of TO degradation-TO analysis using microscopic, destructive and non-destructive tests; processing results, determining causes of TO degradation; concluding conclusions to avoid the development of degradation processes of TO, resp. limitation of TO degradation. This methodology will be applied when dealing with a particular case from technical manufacturing practice. It is part of Shaft Throttle, which was made of 11SMnPb30 automatic steel according to CSN EN 10027-1. On this component during the manufacturing process on the surface unwanted corrosion products appeared. The aim of this article is to demonstrate to students of technical fields the application of a complex system approach methodology to solve a particular problem.

show abstract

Features of the microstructural and mechanical degradation of long term operated mild steel

Cited by 29 publications

References 19 publications

Evaluation of Tensile Performance of Steel Members by Analysis of Corroded Steel Surface Using Deep Learning

Evaluation of Tensile Performance of Steel Members by Analysis of Corroded Steel Surface Using Deep Learning

Contribution to the study of the influence of the stress ratio on the high cycle fatigue behaviour of riveted joints

Example of using complex system approach methodology by degradation of selected technical object

Contact Info

Product

Resources

About