A novel generalization ability-enhanced approach for corrosion fatigue life prediction of marine welded structures

Feng, Chao; Su, Molin; Xu, Longhua; Zhao, Lei; Han, Yongdian; Peng, Chentao

doi:10.1016/j.ijfatigue.2022.107222

Cited by 23 publications

(6 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method enables probabilistic estimation of the SCF. Feng et al 91 propose an enhanced approach for predicting corrosion fatigue life using Borderline-SMOTE and XGBoost algorithms, demonstrating excellent prediction accuracy and generalization under various factors. It…”

Section: Data-driven Methodsmentioning

confidence: 99%

Corrosion fatigue mechanisms and evaluation methods of high‐strength steel wires: A state‐of‐the‐art review

Jie,

Zhang,

Susmel

et al. 2024

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

Corrosion significantly degrades the fatigue performance of high‐strength steel wires. This study conducts an extensive review of corrosion fatigue in corroded steel wires based on relevant literature. It outlines corrosion fatigue evolution mechanisms and discusses various test methodologies. Six distinct approaches are employed to assess corrosion fatigue life. A three‐stage multiscale corrosion fatigue evolution process involves pitting formation and growth, short crack propagation, and long crack propagation. Advanced fatigue assessment methods like the theory of critical distances (TCD) and the strain energy density (SED) are explored for predicting the corrosion fatigue life for corroded steel wires. A model utilizes an elastoplastic corrosion fatigue damage framework to comprehensively represent the complex interactions. The physics‐data‐driven method has garnered increasing attention due to its requirement of fewer sample data and good robustness. Moreover, the reliability method underscores its pivotal role in guaranteeing the longevity of suspenders and cables in practical settings.

show abstract

Section: Data-driven Methodsmentioning

confidence: 99%

Corrosion fatigue mechanisms and evaluation methods of high‐strength steel wires: A state‐of‐the‐art review

Jie,

Zhang,

Susmel

et al. 2024

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

show abstract

“…[4,10,110] Therefore, in order to improve the accuracy of fatigue life prediction of welded joints, more IFs should be considered to fully reflect the relationship between fatigue performance and IFs. [111,112] Therefore, the polynomial regression and time series models were integrated to quantify the relationship between the total IFs and fatigue properties. [113] Several studies [4][5][6][7]23,114] are conducted to better describe the fatigue behavior.…”

Section: Comprehensive Consideration Of Influencing Factorsmentioning

confidence: 99%

“…Correlation between multiple IFs and fatigue life. [90] www.advancedsciencenews.com www.aem-journal.com SVM, [56,[143][144][145] GA-ANN, [146] GA-BPNN, [146,147] RF, [89,137,148,149] DNN, [112,[150][151][152] convolution neural network (CNN), [153][154][155] long short-term memory (LSTM), [156][157][158] radial basis function neural network (RBFNN), [53,88,159,160] etc.) were developed to realize the fatigue performance prediction of welded joints.…”

Section: Progress In Prediction Approachesmentioning

confidence: 99%

“…[ 23,131–134 ] After the establishment of the database and the analysis of the IFs, different data‐driven algorithms were used to predict the fatigue performance. Specifically, several effectively approaches (Bayesian model, [ 135–137 ] ANN, [ 67,129,138–141 ] particle swarm optimization (PSO)‐BPNN, [ 75,142 ] Ant colony optimization‐BPNN, [ 39,55 ] SVM, [ 56,143–145 ] GA‐ANN, [ 146 ] GA‐BPNN, [ 146,147 ] RF, [ 89,137,148,149 ] DNN, [ 112,150–152 ] convolution neural network (CNN), [ 153–155 ] long short‐term memory (LSTM), [ 156–158 ] radial basis function neural network (RBFNN), [ 53,88,159,160 ] etc.) were developed to realize the fatigue performance prediction of welded joints.…”

Section: Progress In Prediction Approachesmentioning

confidence: 99%

See 1 more Smart Citation

A State‐of‐Art Review on Prediction Model for Fatigue Performance of Welded Joints via Data‐Driven Method

Feng

Zhao

et al. 2023

Adv Eng Mater

Self Cite

View full text Add to dashboard Cite

Fatigue fracture of welded joints is an important cause for engineering accidents. Due to the coexistence of so many influencing factors, the current prediction model of fatigue behavior cannot be used for all service conditions. The progress of each module (database establishment, data processing, data augmentation, dimension reduction, and comprehensive consideration of influencing factors) during the process of constructing a prediction model is summarized herein. Specifically, the state‐of‐art prediction models of fatigue strength, fatigue crack growth rate, fatigue life, and fatigue reliability are introduced. Moreover, suggestions for future work are given at the end of each section. Finally, according to the influential prediction methods, the establishment of fatigue performance prediction methods of welded joints via data‐driven method is summarized.

show abstract

“…Welded structures are widely applied in marine, automobile, transportation, nuclear, petrochemical, and offshore industries. [1][2][3] After a particular time of service, these structures often experience fatigue problems at welded joints, resulting from repeated or fluctuating stresses.…”

Section: Introductionmentioning

confidence: 99%

A post‐processing procedure for predicting high‐ and low‐cycle fatigue life of welded structures based on the master E–N curve

Liu

Lei

Xing

et al. 2023

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

This work provides a post‐processing procedure to predict the high‐ and low‐cycle fatigue life of welded structures. The post‐processor calculates the equivalent structural strain range, given the traction stress state at the weld notch, by enforcing the equilibrium condition and Navier's hypothesis. The return mapping algorithm is applied to deal with the low‐cycle fatigue condition in which through‐thickness plastic deformation develops. The proposed method predicts the fatigue life of 793 welded joints of different configurations made from steel, magnesium, titanium, and aluminum alloy. The predicted high‐ and low‐cycle fatigue lives agree equally well with the experimental result.

show abstract

A novel generalization ability-enhanced approach for corrosion fatigue life prediction of marine welded structures

Cited by 23 publications

References 71 publications

Corrosion fatigue mechanisms and evaluation methods of high‐strength steel wires: A state‐of‐the‐art review

Corrosion fatigue mechanisms and evaluation methods of high‐strength steel wires: A state‐of‐the‐art review

A State‐of‐Art Review on Prediction Model for Fatigue Performance of Welded Joints via Data‐Driven Method

A post‐processing procedure for predicting high‐ and low‐cycle fatigue life of welded structures based on the master E–N curve

Contact Info

Product

Resources

About