An enhanced uniform simulation approach coupled with SVR for efficient structural reliability analysis

Luo, Changqi; Zhu, Shibai; Keshtegar, Behrooz; Taylan, Osman

doi:10.1016/j.ress.2023.109377

Cited by 41 publications

(8 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2022b) focused on developing a novel enhanced Monte Carlo simulation approach with an advanced machine learning method, namely hybrid enhanced Monte Carlo simulation, for achieving accurate approximation of failure probability with high efficiency computations. Furthermore, Luo et al . (2023) proposed a novel hybrid enhanced sampling method named as enhanced uniform importance sampling coupled with support vector regression for structural reliability analysis with low failure probability, which can provide a capability and stability for different structural reliability problems.…”

Section: Introductionmentioning

confidence: 99%

Research on fatigue life evaluation method of shaft parts based on small sample

Liu

Zhang

Zhu

et al. 2023

IJSI

View full text Add to dashboard Cite

PurposeDue to the limitation of experimental conditions and budget, fatigue data of mechanical components are often scarce in practical engineering, which leads to low reliability of fatigue data and reduces the accuracy of fatigue life prediction. Therefore, this study aims to expand the available fatigue data and verify its reliability, enabling the achievement of life prediction analysis at different stress levels.Design/methodology/approachFirst, the principle of fatigue life probability percentiles consistency and the perturbation optimization technique is used to realize the equivalent conversion of small samples fatigue life test data at different stress levels. Meanwhile, checking failure model by fitting the goodness of fit test and proposing a Monte Carlo method based on the data distribution characteristics and a numerical simulation strategy of directional sampling is used to extend equivalent data. Furthermore, the relationship between effective stress and characteristic life is analyzed using a combination of the Weibull distribution and the Stromeyer equation. An iterative sequence is established to obtain predicted life.FindingsThe TC4–DT titanium alloy is selected to assess the accuracy and reliability of the proposed method and the results show that predicted life obtained with the proposed method is within the double dispersion band, indicating high accuracy.Originality/valueThe purpose of this study is to provide a reference for the expansion of small sample fatigue test data, verification of data reliability and prediction of fatigue life data. In addition, the proposed method provides a theoretical basis for engineering applications.

show abstract

Section: Introductionmentioning

confidence: 99%

Research on fatigue life evaluation method of shaft parts based on small sample

Liu

Zhang

Zhu

et al. 2023

IJSI

View full text Add to dashboard Cite

show abstract

“…The rapid development of machine learning (ML) has led to the widespread application of datadriven methods in both science and industry. Owing to its powerful function approximation capability and big data analysis ability, ML provides potential solutions for solving problems where the physical mechanism is not fully understood [1][2][3][4][5][6] and improving the computational efficiency of numerical simulations [7][8][9][10][11][12]. To guarantee the structural integrity and performance requirements of industrial equipment and infrastructures under complex working conditions, several efforts has been made to apply ML to failure mechanism modelling and PHM.…”

Section: Introductionmentioning

confidence: 99%

Physics-informed machine learning and its structural integrity applications: state of the art

Zhu,

Wang,

Luo

et al. 2023

Phil. Trans. R. Soc. A.

Self Cite

View full text Add to dashboard Cite

The development of machine learning (ML) provides a promising solution to guarantee the structural integrity of critical components during service period. However, considering the lack of respect for the underlying physical laws, the data hungry nature and poor extrapolation performance, the further application of pure data-driven methods in structural integrity is challenged. An emerging ML paradigm, physics-informed machine learning (PIML), attempts to overcome these limitations by embedding physical information into ML models. This paper discusses different ways of embedding physical information into ML and reviews the developments of PIML in structural integrity including failure mechanism modelling and prognostic and health management (PHM). The exploration of the application of PIML to structural integrity demonstrates the potential of PIML for improving consistency with prior knowledge, extrapolation performance, prediction accuracy, interpretability and computational efficiency and reducing dependence on training data. The analysis and findings of this work outline the limitations at this stage and provide some potential research direction of PIML to develop advanced PIML for ensuring structural integrity of engineering systems/facilities. This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 1)'.

show abstract

“…However, the probability-based stochastic FEA with huge samples is exactly time-consuming. Considering this, modern mechanical design approaches require low-cost and high-accuracy characteristics, in which the machine learning approaches (Li et al, 2022a(Li et al, , 2023Li et al, 2023a, b;Luo et al, 2023) are useful tools being capable of balancing the accuracy and cost.…”

Section: Introductionmentioning

confidence: 99%

Machine learning-based probabilistic fatigue assessment of turbine bladed disks under multisource uncertainties

Zhu,

Niu,

Keshtegar

et al. 2023

IJSI

View full text Add to dashboard Cite

PurposeThe multisource uncertainties, including material dispersion, load fluctuation and geometrical tolerance, have crucial effects on fatigue performance of turbine bladed disks. In view of the aim of this paper, it is essential to develop an advanced approach to efficiently quantify their influences and evaluate the fatigue life of turbine bladed disks.Design/methodology/approachIn this study, a novel combined machine learning strategy is performed to fatigue assessment of turbine bladed disks. Proposed model consists of two modeling phases in terms of response surface method (RSM) and support vector regression (SVR), namely RSM-SVR. Two different input sets obtained from basic variables were used as the inputs of RSM, then the predicted results by RSM in first phase is used as inputs of SVR model by using a group data-handling strategy. By this way, the nonlinear flexibility of SVR inputs is improved and RSM-SVR model presents the high-tendency and efficiency characteristics.FindingsThe accuracy and tendency of the RSM-SVR model, applied to the fatigue life estimation of turbine bladed disks, are validated. The results indicate that the proposed model is capable of accurately simulating the nonlinear response of turbine bladed disks under multisource uncertainties, and SVR-RSM model provides an accurate prediction strategy compared to RSM and SVR for fatigue analysis of complex structures.Originality/valueThe results indicate that the proposed model is capable of accurately simulate the nonlinear response of turbine bladed disks under multisource uncertainties, and SVR-RSM model provides an accurate prediction compared to RSM and SVRE for fatigue analysis of turbine bladed disk.

show abstract

An enhanced uniform simulation approach coupled with SVR for efficient structural reliability analysis

Cited by 41 publications

References 73 publications

Research on fatigue life evaluation method of shaft parts based on small sample

Research on fatigue life evaluation method of shaft parts based on small sample

Physics-informed machine learning and its structural integrity applications: state of the art

Machine learning-based probabilistic fatigue assessment of turbine bladed disks under multisource uncertainties

Contact Info

Product

Resources

About