Machine Learning-Assisted probabilistic fatigue evaluation of Rib-to-Deck joints in orthotropic steel decks

Heng, Junlin; Zheng, Ke; Feng, Xiaoyang; Veljković, Milan; Zhou, Zhixiang

doi:10.1016/j.engstruct.2022.114496

Cited by 19 publications

(8 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…He et al [122] used the LEFM and random forest approach to conduct a machinelearning-centered assessment of the impact of defect/inclusion on the fatigue behavior of steels. Heng et al [123] performed a machine learning-assisted probabilistic fatigue assessment of RD joints in OSDs using the GPR surrogate model, DBN, and PFCG model in a subsequent study. The modified posterior model exhibits better concordance with the test data when compared to the old PFCG model.…”

Section: Random/hybrid Based Methodsmentioning

confidence: 99%

Advances in Machine Learning Techniques Used in Fatigue Life Prediction of Welded Structures

Gbagba,

Maccioni,

Concli

2023

Applied Sciences

View full text Add to dashboard Cite

In the shipbuilding, construction, automotive, and aerospace industries, welding is still a crucial manufacturing process because it can be utilized to create massive, intricate structures with exact dimensional specifications. These kinds of structures are essential for urbanization considering they are used in applications such as tanks, ships, and bridges. However, one of the most important types of structural damage in welding continues to be fatigue. Therefore, it is necessary to take this phenomenon into account when designing and to assess it while a structure is in use. Although traditional methodologies including strain life, linear elastic fracture mechanics, and stress-based procedures are useful for diagnosing fatigue failures, these techniques are typically geometry restricted, require a lot of computing time, are not self-improving, and have limited automation capabilities. Meanwhile, following the conception of machine learning, which can swiftly discover failure trends, cut costs, and time while also paving the way for automation, many damage problems have shown promise in receiving exceptional solutions. This study seeks to provide a thorough overview of how algorithms of machine learning are utilized to forecast the life span of structures joined with welding. It will also go through their drawbacks and advantages. Specifically, the perspectives examined are from the views of the material type, application, welding method, input parameters, and output parameters. It is seen that input parameters such as arc voltage, welding speed, stress intensity factor range, crack growth parameters, stress histories, thickness, and nugget size influence output parameters in the manner of residual stress, number of cycles to failure, impact strength, and stress concentration factors, amongst others. Steel (including high strength steel and stainless steel) accounted for the highest frequency of material usage, while bridges were the most desired area of application. Meanwhile, the predominant taxonomy of machine learning was the random/hybrid-based type. Thus, the selection of the most appropriate and reliable algorithm for any requisite matter in this area could ultimately be determined, opening new research and development opportunities for automation, testing, structural integrity, structural health monitoring, and damage-tolerant design of welded structures.

show abstract

Section: Random/hybrid Based Methodsmentioning

confidence: 99%

Advances in Machine Learning Techniques Used in Fatigue Life Prediction of Welded Structures

Gbagba,

Maccioni,

Concli

2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Finite-element method New data generation. [9,185,186,200] Synthetic minority oversampling technique Artificially synthesizing new samples. [201] Sample pairing method Average value superposition with relatively poor interpretability.…”

Section: Characteristics Referencesmentioning

confidence: 99%

“…[184] The hybrid model combining Gaussian regression and dynamic Bayesian network was established to estimate the probability S-N curve of welded joints. [185,186] As shown in Figure 33, the FEM model was integrated into the approximate Bayesian framework to realize the [178] Figure 30. Schematic diagram of the prediction model via deep learning regression algorithm.…”

Section: Prediction Of Fatigue Reliabilitymentioning

confidence: 99%

“…[ 184 ] The hybrid model combining Gaussian regression and dynamic Bayesian network was established to estimate the probability S–N curve of welded joints. [ 185,186 ] As shown in Figure , the FEM model was integrated into the approximate Bayesian framework to realize the accurate prediction of fatigue reliability. [ 187 ] Fatigue reliability analysis model can be constructed via Latin hypercube sampling technology, SVM, and Monte Carlo (MC) simulations, which exhibited good accuracy and universality.…”

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

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

“…However, the effects of the environment on natural structures were ignored. The high accuracy of SMFL detection technology, for instance, is easily affected by the external environment [ 40 , 41 ]. The cable undergoes continuous vibrations due to alternating loads, including the vibrations caused by bridge structures, vehicle loads, wind-induced vibrations [ 42 , 43 ], and rain-wind-induced vibrations [ 44 ].…”

Section: Introductionmentioning

confidence: 99%

Experimental Analysis of the Magnetic Leakage Detection of a Corroded Steel Strand Due to Vibration

Zhang

Ding

Yuan

et al. 2023

Sensors

View full text Add to dashboard Cite

The self-magnetic flux leakage (SMFL) detection technique has great potential in the corrosion detection of bridge stay cables due to its advantages of small testing equipment, high accuracy, and fast testing rate. However, the vibration effect in the cable’s SMFL detection is unclear. To address this, the influence of vibration on the magnetic field distribution of cable structure is analyzed theoretically. According to the theoretical model, the effect of vibration on SMFL detection primarily manifests as displacement changes (displacement-added magnetic field) and defect shape changes (deformation-added magnetic field). SMFL detection experiments are conducted on steel strands. The results demonstrate that the displacement-added magnetic field exhibits statistical characteristics in the form of a normal distribution, fluctuating around the zero value. The impact of the deformation-added magnetic field on SMFL is linearly correlated with the corrosion ratio c. Moreover, a corrosion characterization index A was proposed and has an excellent linear fit with the corrosion ratio c. The index A effectively improves the accuracy of corrosion detection and provides early warning for the maintenance of cable structures.

show abstract

Machine Learning-Assisted probabilistic fatigue evaluation of Rib-to-Deck joints in orthotropic steel decks

Cited by 19 publications

References 44 publications

Advances in Machine Learning Techniques Used in Fatigue Life Prediction of Welded Structures

Advances in Machine Learning Techniques Used in Fatigue Life Prediction of Welded Structures

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

Experimental Analysis of the Magnetic Leakage Detection of a Corroded Steel Strand Due to Vibration

Contact Info

Product

Resources

About