A Bayesian machine learning approach to rapidly quantifying the fatigue probability of failure for steel catenary risers

The posterior statistical distributions of fatigue strength are determined using Bayesian inferential statistics and the Metropolis Monte Carlo method.This study explores how structural heterogeneity affects ultrahigh cycle fatigue strength in additive manufacturing. Monte Carlo methods and procedures may assist estimate fatigue strength posteriors and scatter. The acceptable probability in Metropolis Monte Carlo relies on the Markov chain's random microstructure state. In addition to commonly studied variables, the proportion of chemical composition was demonstrated to substantially impact fatigue strength if fatigue lifetime in crack propagation did not prevail due to high threshold internal notches. The study utilizes an algorithm typically used for quantum mechanics to solve the complicated multifactorial fatigue problem. The inputs and outputs are modified by fitting the microstructural heterogeneities into the Metropolis Monte Carlo algorithm. The main advantage here is applying a general-purpose nonphenomenological model that can be applied to multiple influencing factors without high numerical penalty.

show abstract

“…The suggested technique could correctly and efficiently calculate the fatigue life of a sample riser. 51…”

Section: Comparative Aspects Of the Current Studymentioning

confidence: 99%

“…An approach for forecasting fatigue damage patterns inside the steel catenary risers was presented in addition to numerical simulation and a random sampling technique. The suggested technique could correctly and efficiently calculate the fatigue life of a sample riser 51 …”

Section: Introductionmentioning

confidence: 99%

Effect of microstructural heterogeneity on fatigue strength predicted by reinforcement machine learning

Awd

Münstermann

Walther

2022

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

show abstract

“…Chen et al [43] analyzed root cause of tubing and casing failures in low-temperature carbon dioxide injection well, and an optimal tubing-casing combination is proposed to prolong the operation life of tubing. Moreover, in view of the fatigue failure of the risers caused by VIV, the researchers have established a fatigue life prediction method for risers in deep-water [44,45]. However, in their method, the acquisition of alternating stress ignores the contact and collision factors between riser and test pipe, which makes it impossible to accurately simulate the fatigue life of riser under severe working conditions.…”

Section: Introductionmentioning

confidence: 99%

Three-dimensional nonlinear vibration model and fatigue failure mechanism of deepwater test pipe

Guo

Nie

et al. 2022

Nonlinear Dyn

View full text Add to dashboard Cite

In deep-water test conditions, the riser-test pipe system (RTS) is subject to the vortex induced effect on riser, flow induced effect on test pipe and longitudinal/transverse coupling effect, which is prone to buckling deformation, fatigue fracture and friction perforation. To resolve this, the three-dimensional (3D) nonlinear vibration model of deep-water RTS is established using the micro-finite method, energy method and Hamilton variational principle. Based on the elastic-plastic contact collision theory, the nonlinear contact load calculation method between riser and test pipe is proposed. Compared with experimental measurement results, calculation results of the proposed vibration model in this study and the single tubing vibration model in our recent work, the correctness and effectiveness of the proposed vibration model of the deep-water RTS are verified. Meanwhile, the cumulative damage theory is used to establish the fatigue life prediction method of test pipe. Based on that, the influences of outflow velocity, internal flow velocity, significant wave height, as well as top tension coefficient on the fatigue life of test pipe are systematically analyzed. The results demonstrate that, first, with the increase of outflow velocity, the maximum alternating stress, the annual fatigue damage rate increased and the service life decreased significantly. The locations where fatigue failure of the test tube is easy to occur are mainly distributed at the upper "one third" and the bottom of test pipe. Second, with the increase of internal flow velocity, the "one third effect" of the test pipe will decrease, and is shown "the bottom damage effect", which needs the attention of field operators. Third, during field operation, it is necessary to properly configure the top tension coefficient so that there can be a certain relaxation between the riser and the test pipe, so as to cause transverse vibration and consume some axial energy and load. The study led to the formulation of a theoretical method for safety evaluation and a practical approach for effectively improving the fatigue life of deep-water test pipe.

show abstract

“…Goodfellow et al [ 27 ] used fuzzy mathematical methods to identify horizontal and vertical displacements and displacement distributions of buildings. Hejazi et al [ 28 ] investigated the fuzzy relationship between various influencing factors and the displacement of offshore buildings. Di Napoli et al [ 29 ] proposed the use of CNNs in the fitting and prediction analysis of building landslide monitoring data.…”

Section: Introductionmentioning

confidence: 99%

Research on a Machine Learning-Based Method for Assessing the Safety State of Historic Buildings

Peng

Zhang

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Historic and protected buildings are increasingly valued due to their valuable historical and cultural value. The assessment of the safety state of historic buildings has received more attention. Emerging machine learning algorithms, with their excellent computational performance, provide new ideas and new means to solve practical problems in various fields. Therefore, this paper proposes a method for assessing the safety state of historic buildings based on machine learning techniques. Firstly, based on the analysis of the characteristics of historical buildings and common security problems, the application of wireless sensor networks to the security monitoring of historical buildings is proposed in order to improve the automation of monitoring. Then, in order to improve the accuracy of the assessment, a combination of kernel canonical correlation analysis (KCCA) and support vector machine (SVM) is used to establish the security monitoring model. The experimental results show that by choosing a suitable KCCA function, the redundant features of the data can be reduced while the comprehensiveness of the building structure identification features can be retained, thus effectively improving the prediction accuracy of the SVM. The KCCA-SVM model can accurately predict the physical quantities such as relative structural displacement of historical buildings with good reliability.

show abstract

A Bayesian machine learning approach to rapidly quantifying the fatigue probability of failure for steel catenary risers

Cited by 16 publications

References 14 publications

Effect of microstructural heterogeneity on fatigue strength predicted by reinforcement machine learning

Effect of microstructural heterogeneity on fatigue strength predicted by reinforcement machine learning

Three-dimensional nonlinear vibration model and fatigue failure mechanism of deepwater test pipe

Research on a Machine Learning-Based Method for Assessing the Safety State of Historic Buildings

Contact Info

Product

Resources

About