Prediction of stress concentration factor of corrosion pits on buried pipes by least squares support vector machine

Published on Sep 1, 2015in Engineering Failure Analysis2.897
· DOI :10.1016/J.ENGFAILANAL.2015.05.010
Jian Ji15
Estimated H-index: 15
(Monash University, Clayton campus),
Chunshun Zhang13
Estimated H-index: 13
(Monash University, Clayton campus)
+ 1 AuthorsSheng-Qi Yang38
Estimated H-index: 38
(CUMT: China University of Mining and Technology)
Concentrated working stress of a corrosion pit is known to be an important factor inducing the deterioration and consequently the breakage of a buried pipe. In this paper, we investigate the stress concentration factors (SCFs) of isolated elliptical corrosion pits using 3-D finite element analyses. The elliptical pits are fully characterized by their 3-D geometries, i.e., major and minor diameters and pit depth via a series of parametric studies of finite element pipe models. This is to quantify the effect of geometric variations of the pits on SCF. Realizing the fact that the 3-D finite element analysis is computationally intensive, efficient statistically predictive models have been developed based on least squares support vector machine (LS-SVM) realized in a ubiquitous spreadsheet platform. This approach shows very close predictions of SCF to the numerical findings for elliptical corrosion patterns on buried pipes. Particularly, two typical kernel functions have been adopted to cross validate the excellent performance of the LS-SVM method in SCF prediction of corroded pipes.
📖 Papers frequently viewed together
43 Citations
51 Citations
25 Citations
#1Yanfei Chen (China University of Petroleum)H-Index: 8
#2Hong Zhang (China University of Petroleum)H-Index: 11
Last. Jing Zhou (DUT: Dalian University of Technology)H-Index: 7
view all 6 authors...
Abstract Corrosion defects may compromise the safety of oil and gas pipelines. This paper investigates the failure behavior and failure pressure of X80 pipelines with longitudinally and circumferentially aligned interacting corrosion defects based on nonlinear finite element method, X80 pipeline with single corrosion defect is studied as well. On the basis of proposed failure pressure regression equations for X80 pipeline with single corrosion defect, this paper develops an assessment procedure ...
47 CitationsSource
#1Hongbo ZhaoH-Index: 8
#2Zhongliang RuH-Index: 9
Last. Shaojun Li (CAS: Chinese Academy of Sciences)H-Index: 30
view all 5 authors...
Abstract In the reliability analysis of tunnels, the limited state function is implicit and nonlinear, and is difficult to apply based on the traditional reliability method, especially for large-scale projects. Least squares support vector machines (LS-SVM) are capable of approximating the limited state function without the need for additional assumptions regarding the function form, in comparison to traditional polynomial response surfaces. In the present work, the LS-SVM method was adapted to ...
59 CitationsSource
13 CitationsSource
#1Alan Turnbull (National Physical Laboratory)H-Index: 27
#2Louise Wright (National Physical Laboratory)H-Index: 9
Last. Louise Crocker (National Physical Laboratory)H-Index: 4
view all 3 authors...
A finite element (FE) analysis has been undertaken to evaluate the stress and strain distribution associated with a single corrosion pit in a cylindrical steel specimen stressed remotely in tension. A key observation was the localisation of plastic strain to the pit walls (just below the surface of the specimen). Simulation of a growing pit in a static stress field indicated corresponding plastic strain rates that were commensurate with values associated with stress corrosion cracking. This obse...
105 CitationsSource
#1M. Cerit (Sakarya University)H-Index: 3
#2Kenan Genel (Sakarya University)H-Index: 15
Last. S. Eksi (Sakarya University)H-Index: 1
view all 3 authors...
Localized (pitting) corrosion has been observed in steel and high-strength aluminium alloys in aqueous environments and has been identified as a potential origin for fatigue crack nucleation. In the present study, under uniaxial tension loading, stress distribution at the semi-elliptical corrosion pits has been investigated by conducting a series of three-dimensional semi-elliptical pitted models, systematically. Based on the finite element analyses, it is concluded that pit aspect ratio (a/2c) ...
158 CitationsSource
#1Hsu Chih-WeiH-Index: 17
#2Chih-Chung Chang (NTU: National Taiwan University)H-Index: 8
Last. Chih-Jen LinH-Index: 64
view all 3 authors...
Support vector machine (SVM) is a popular technique for classication. However, beginners who are not familiar with SVM often get unsatisfactory results since they miss some easy but signicant steps. In this guide, we propose a simple procedure, which usually gives reasonable results.
5,219 Citations
#1Chongmin She (NUAA: Nanjing University of Aeronautics and Astronautics)H-Index: 10
#2Wanlin Guo (NUAA: Nanjing University of Aeronautics and Astronautics)H-Index: 68
Abstract The through-thickness variations of stress concentration factors along the wall of elliptic holes in finite thickness plates of isotropic materials subjected to remote tensile stress have been systematically analyzed using the finite element method. The three-dimensional stress concentration factor K t is found to be a function of the thickness to root radius ratio B / ρ and the aspect ratio t (short to long axial length) of the elliptic hole under tensile loading. It is found that the ...
64 CitationsSource
Based on detailed three-dimensional elastic FE analysis, the present work compiles the elastic stress concentration factor for a pipe with local wall thinning. To cover practically interesting cases, a wide range of pipe and defect geometries are considered, and both internal pressure and global bending are considered. Resulting values of stress concentration factors are tabulated for practical use, and the effects of relevant parameters such as pipe and defect geometries on stress concentration...
19 CitationsSource
#1Johan A. K. Suykens (Katholieke Universiteit Leuven)H-Index: 89
#2J. De Brabanter (Katholieke Universiteit Leuven)H-Index: 12
Last. Joos Vandewalle (Katholieke Universiteit Leuven)H-Index: 87
view all 4 authors...
Least squares support vector machines (LS-SVM) is an SVM version which involves equality instead of inequality constraints and works with a least squares cost function. In this way, the solution follows from a linear Karush–Kuhn–Tucker system instead of a quadratic programming problem. However, sparseness is lost in the LS-SVM case and the estimation of the support values is only optimal in the case of a Gaussian distribution of the error variables. In this paper, we discuss a method which can o...
1,013 CitationsSource
#1Kristin P. Bennett (RPI: Rensselaer Polytechnic Institute)H-Index: 60
#2Colin Campbell (UoB: University of Bristol)H-Index: 54
Support Vector Machines (SVMs) and related kernel methods have become increasingly popular tools for data mining tasks such as classification, regression, and novelty detection. The goal of this tutorial is to provide an intuitive explanation of SVMs from a geometric perspective. The classification problem is used to investigate the basic concepts behind SVMs and to examine their strengths and weaknesses from a data mining perspective. While this overview is not comprehensive, it does provide re...
561 CitationsSource
Cited By47
#1Jian Ji (Hohai University)H-Index: 15
#2Jiacheng Xia (Hohai University)
Last. Jayantha Kodikara (Monash University)H-Index: 30
view all 5 authors...
Abstract null null In recent years, underground pipeline leakage occurs frequently in urban regions, which seriously reduces the soil-structure stability in the vicinity of the leakage. In this paper, a numerical study about pipeline leakage-induced instability of adjacent excavation earth retaining wall (EERW) is carried out. To reflect the phenomenon of soil strength degradation when encountering leakage water, the relationship between soil strength parameters and saturation is established by ...
#1Chao ChenH-Index: 1
#2Zhiyu Jie (NBU: Ningbo University)H-Index: 2
Last. Kainan WangH-Index: 1
view all 0 authors...
#1Frederick Appoh (University of Manchester)H-Index: 2
#2Akilu Yunusa-Kaltungo (University of Manchester)H-Index: 10
Last. Jyoti K. Sinha (University of Manchester)H-Index: 22
view all 3 authors...
Abstract null null In this paper, we propose a novel hybrid adaptive model (HAM) that integrates Gaussian mixture probabilistic machine learning (ML), Weibull time-to-failure feature, and value of information (VOI) techniques for complex engineering failure analysis. The objective is to establish an optimum components replacement intervention strategy for composite brake blocks of railway rolling stocks to better curtail failures and possible accidents. The HAM considers brake blocks as rudiment...
#1Xiang Li (UM: University of Macau)H-Index: 1
#2Kin Ho Lo (UM: University of Macau)H-Index: 17
Last. Hui Pan (UM: University of Macau)H-Index: 53
view all 4 authors...
AbstractThe present paper looks into the postfire residual mechanical and corrosion behavior of the 2205 duplex stainless steel (DSS) after exposure to 800°C and 700°C (about and under the nose tem...
Abstract null null A rapid image segmentation and correlation-based approach to investigating the local microstructural effects on pitting corrosion susceptibility is introduced. The impact of four different microstructural features, consisting of grain orientation, proximity to grain boundaries, proximity to intermetallic particles, and local geometrically necessary dislocation (GND) density, on pitting initiation in the 5083 aluminum alloy was directly investigated using automated pit detectio...
#1Frederick Appoh (University of Manchester)H-Index: 2
#2Akilu Yunusa-Kaltungo (University of Manchester)H-Index: 10
The railway-rolling stock wheel flange lubricator protects the wheels and railhead by lubricating their contacts. Failed or missing flange lubricators can lead to excessive wheel wear, wheel flats, wheel cracks, rolling contact fatigue, rail damage, and derailment accidents. In extreme cases, missing or worn flange lubricators due to nonlinear rail conditions may lead to fire hazards, particularly in underground rail infrastructure. In addition, the location of lubricators present accessibility ...
1 CitationsSource
#1Atika Hossain Akhi (MUN: Memorial University of Newfoundland)
#2Ashutosh Sutra Dhar (MUN: Memorial University of Newfoundland)H-Index: 9
Abstract The municipal water distribution systems across the world include a significant amount of cast-iron pipes. Many of the buried cast-iron pipes are over fifty years old and require rehabilitation. Municipalities decide on a rehabilitation solution between the replacement and re-use of the existing pipes based on the remaining strengths of the pipes. Fracture mechanics has appeared as the most viable tool for remaining strength assessment of the deteriorating pipes. However, a method of as...
1 CitationsSource
#1Hieu Chi Phan (Le Quy Don Technical University)H-Index: 5
#2Tien-Thinh LeH-Index: 18
Last. Tiep Duc Pham (Le Quy Don Technical University)H-Index: 1
view all 5 authors...
Abstract Buried pipes suffer from various natural and human-related phenomena leading to the bending forces on such structures. The analytical models face obstacles such as the complications in modeling material behavior and the local stress concentration due to the appearance of defects are combined. This causes the accumulative over and under-estimation of pipe capacity due to the idealizations of full plastic stress distribution and location of defects at the most dangerous area, respectively...
6 CitationsSource
Abstract Establishing an accurate model to predict burst pressure is desired, which has been developed for decades. Although various models have been developed, errors unavoidably appear in the prediction of burst pressures because of the uncertainty in both input variables and nonlinear relationship of such variables to the burst pressure. Consequently, machine learning models, which is a data-driven approach, are potential alternatives. In this paper, various machine learning models such as Ra...
1 CitationsSource
A finite element model was built to assess the combined effects of internal pressure and axial applied stress $\left( {\sigma_{A} } \right) on localized stress concentration and electrochemical corrosion at defects on pipelines under the mechano-electrochemical (M-E) interaction. When defect angle \alpha (i.e., included angle between the major axis of the defect and longitudinal direction of the pipe) is 90°, the maximum stress of the defect is enlarged remarkably with the increase in \...