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

2015 ◽  
Vol 55 ◽  
pp. 131-138 ◽  
Author(s):  
Jian Ji ◽  
Chunshun Zhang ◽  
Jayantha Kodikara ◽  
Sheng-Qi Yang
Keyword(s):  
Support Vector Machine ◽  
Stress Concentration ◽  
Least Squares ◽  
Stress Concentration Factor ◽  
Concentration Factor ◽  
Support Vector ◽  
Buried Pipes ◽  
Corrosion Pits

Finite Element Analysis on Stress Concentration of Well Casing With Corrosion Pits

2010 ◽  
Author(s):  
Jing Zhang ◽  
Jianchun Fan ◽  
Laibin Zhang ◽  
Dong Wen ◽  
Yumei Wang
Keyword(s):  
Finite Element Analysis ◽  
Finite Element ◽  
Stress Concentration ◽  
Stress Concentration Factor ◽  
Concentration Factor ◽  
Spherical Cavity ◽  
High Stress ◽  
Orifice Diameter ◽  
Element Analysis ◽  
Corrosion Pits

Corrosion-induced pits will disturb the original stress distribution of casing and appear local high stress area. Through 3-D finite element analysis on casing with spherical and cylindrical corrosion cavity, the stress concentration degree and the influences of cavity shape, size and orifice diameter on stress concentration factor are determined and analyzed. The results show that the depth and shape of corrosion cavities are major factors impacting the stress concentration factor. For the casing with corrosion pits, the smaller orifice diameter, the more obvious influence of hemisphere effect on stress concentration factor. With the transition from shallow-spherical cavity to exact hemispherical cavity or from exact hemispherical cavity to deep-spherical cavity or from exact hemispherical cavity to cylindrical cavity, the changes of stress concentration factor show different characteristics.

scholarly journals Numerical simulation of the double pits stress concentration in a curved casing inner surface

2017 ◽  
Vol 9 (1) ◽  
pp. 168781401668265 ◽  
Author(s):  
Wei Yan ◽  
Lei Guan ◽  
Yun Xu ◽  
Jin-Gen Deng
Keyword(s):  
Numerical Simulation ◽  
Stress Concentration ◽  
Stress Concentration Factor ◽  
Concentration Factor ◽  
Saline Water ◽  
Finite Element Software ◽  
Inner Surface ◽  
Casing Strength ◽  
Corrosion Pits ◽  
Predict Model

Sour or sweet oil fields development is common in recent years. Casing and tubing are usually subjected to pitting corrosion because of exposure to the strong corrosion species, such as CO2, H2S, and saline water. When the corrosion pits formed in the casing inner surface, localized stress concentration will occur and the casing strength will be degraded. Thus, it is essential to evaluate the degree of stress concentration factor accurately. This article performed a numerical simulation on double pits stress concentration factor in a curved inner surface using the finite element software ABAQUS. The results show that the stress concentration factor of double pits mainly depends on the ratio of two pits distance to the pit radius ( L/R). It should not be only assessed by the absolute distance between the two pits. When the two pits are close and tangent, the maximum stress concentration factor will appear on the inner tangential edges. Stress concentration increased by double pits in a curved casing inner surface is more serious than that in a flat surface. A correction factor of 1.9 was recommended in the curved inner surface double pits stress concentration factor predict model.

Research of Dimensionality Reduction for Fatigue Stress Concentration Factor Based on SVM by Linear Kernel

2014 ◽  
Vol 687-691 ◽  
pp. 1649-1652
Author(s):  
Jian Feng Yang ◽  
Zi Sheng Li ◽  
Gang Jiang ◽  
Jian Fei Chen
Keyword(s):  
Stress Concentration ◽  
Dimensionality Reduction ◽  
Stress Concentration Factor ◽  
Concentration Factor ◽  
Principal Component ◽  
Support Vector ◽  
Linear Kernel ◽  
Fatigue Stress ◽  
Vector Machines ◽  
Stress Fatigue

We collected fatigue stress concentration factor and used Support Vector Machines (SVM) by linear kernel to reduce dimension processing. In order to research the way of dimensionality reduction for data, we also processed the sample of stress fatigue concentration factor to compare with Principal Component Analysis(PCA). The results showed that the sample is processed by linear kernel could improve efficiency to train by SVM again.

The Stress Concentration Factor of Different Corrosion Pits Shape

2010 ◽  
Vol 152-153 ◽  
pp. 1115-1119 ◽  
Author(s):  
Zhi Tao Mu ◽  
Ding Hai Chen ◽  
Zuo Tao Zhu ◽  
Bin Ye
Keyword(s):  
Finite Element ◽  
Stress Concentration ◽  
Stress Concentration Factor ◽  
Concentration Factor ◽  
Concentration Effect ◽  
Concentration Factors ◽  
Stress Concentration Factors ◽  
Corrosion Pits ◽  
Stress Concentration Effect

The stress concentration effect of different corrosion pits is different, the shapes of corrosion pits can be seen as semi-ellipsoidal, the short half axes、long half axes and depth of corrosion are 、 and , through finite element analyze, we can see that the stress concentration factors increase with the increase of , but the stress concentration factors decrease with the increase of .

Q-learning System Based on Cooperative Least Squares Support Vector Machine

2009 ◽  
Vol 35 (2) ◽  
pp. 214-219 ◽  
Author(s):  
Xue-Song WANG ◽  
Xi-Lan TIAN ◽  
Yu-Hu CHENG ◽  
Jian-Qiang YI
Keyword(s):  
Support Vector Machine ◽  
Least Squares ◽  
Learning System ◽  
Support Vector ◽  
Q Learning

scholarly journals Predicting Ink Transfer Rate of 3D Additive Printing Using EGBO Optimized Least Squares Support Vector Machine Model

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Shengpu Li ◽  
Yize Sun
Keyword(s):  
Support Vector Machine ◽  
Prediction Model ◽  
Least Squares ◽  
Transfer Rate ◽  
Coefficient Of Determination ◽  
Percentage Error ◽  
Support Vector ◽  
Experimental Sample ◽  
Machine Model ◽  
Ink Transfer

Ink transfer rate (ITR) is a reference index to measure the quality of 3D additive printing. In this study, an ink transfer rate prediction model is proposed by applying the least squares support vector machine (LSSVM). In addition, enhanced garden balsam optimization (EGBO) is used for selection and optimization of hyperparameters that are embedded in the LSSVM model. 102 sets of experimental sample data have been collected from the production line to train and test the hybrid prediction model. Experimental results show that the coefficient of determination (R2) for the introduced model is equal to 0.8476, the root-mean-square error (RMSE) is 6.6 × 10 (−3), and the mean absolute percentage error (MAPE) is 1.6502 × 10 (−3) for the ink transfer rate of 3D additive printing.

Sign in / Sign up

Export Citation Format

Share Document