Data‐driven prediction of the probability of creep–fatigue crack initiation in 316H stainless steel

Chavoshi, Saeed Zare; Tagarielli, V.L.

doi:10.1111/ffe.13858

Cited by 8 publications

(5 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many supervised learning algorithms have been applied to crack initiation prediction, fatigue life prediction, and other engineering fields. Chavoshi and Tagarielli 115 propose a data‐driven approach to determine probabilistic surrogate models of stainless steel components creep–fatigue crack initiation in advanced gas‐cooled reactors at high temperatures. Numerous supervised learning algorithms have been employed, and it has been observed that the gradient tree boosting algorithm yields the highest accuracy.…”

Section: Ml‐based Methods For Fatigue Life Prediction Of Am Metalsmentioning

confidence: 99%

Recent developments and future trends in fatigue life assessment of additively manufactured metals with particular emphasis on machine learning modeling

Zhan,

He,

Tang

et al. 2023

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

Additive manufacturing (AM) has emerged as a very promising technology for producing complex metallic components with enhanced design flexibility. However, the mechanical properties and fatigue behavior of AM metals differ significantly from conventionally manufactured materials, thereby presenting challenges in accurately predicting their fatigue life. This study provides a comprehensive overview of recent developments and future trends in fatigue life prediction of AM metals, with a particular emphasis on machine learning (ML) modeling techniques. This review recalls recent developments and achievements in fatigue characteristics of AM metals, ML‐based approaches for fatigue life prediction of AM metals, and non‐ML‐based methodologies for the same purpose. In particular, some commonly used regression and classification techniques for fatigue evaluation of AM metals are summarized and elaborated. The study intends to furnish researchers, engineers, and practitioners in the field of AM with a guidance for the accurate and efficient prediction of fatigue life in AM metal components.

show abstract

Section: Ml‐based Methods For Fatigue Life Prediction Of Am Metalsmentioning

confidence: 99%

Recent developments and future trends in fatigue life assessment of additively manufactured metals with particular emphasis on machine learning modeling

Zhan,

He,

Tang

et al. 2023

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

show abstract

“…[19][20][21] Moreover, the critical location of creepfatigue failure will shift from the surface to the subsurface as the fraction of creep damage increases in the creep-fatigue interactions. [22][23][24][25][26] Therefore, a full-time description of stress/strain response and evaluation of damage accumulation is necessary for the blades under actual loading conditions, which can be performed by the combination of constitutive modeling and damage evaluation method. A unified viscoplasticity constitutive model (UVCM) for describing the deformation behavior has been widely used in the field of materials science and engineering.…”

Section: Introductionmentioning

confidence: 99%

“…It is difficult to obtain the real‐time stress/strain distribution and damage accumulation of the blades under actual loading conditions 19–21 . Moreover, the critical location of creep–fatigue failure will shift from the surface to the subsurface as the fraction of creep damage increases in the creep–fatigue interactions 22–26 . Therefore, a full‐time description of stress/strain response and evaluation of damage accumulation is necessary for the blades under actual loading conditions, which can be performed by the combination of constitutive modeling and damage evaluation method.…”

Section: Introductionmentioning

confidence: 99%

Multiaxial creep–fatigue failure mechanism and life prediction of a turbine blade based on a unified numerical solution approach

Zhang,

Xu,

Wang

et al. 2024

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

Exposure of turbine blades to cyclic torsional loading at high temperature, stemming from pre‐torque installation and the aerodynamic forces during operation, has the potential to induce substantial creep–fatigue damage, thereby contributing to the likelihood of premature failure. Investigating the deformation mechanisms and proposing a reliable life prediction method aiming at torsional loading is critical to ensure the structural integrity of turbine blades. This study conducted strain‐controlled fatigue and creep–fatigue tests on Inconel 718 superalloy, employing a multiaxial servo‐hydraulic testing machine. Electron backscattering diffraction elucidated deformation and damage mechanisms, forming a basis for subsequent constitutive modeling and life prediction. The lack of creep–fatigue mechanical behavior and microscopic failure mechanism when stress triaxiality equal to 0 is filled, which provides the theoretical basis and data support for the life design and damage assessment of this material under extreme service conditions. The unified viscoplasticity constitutive model effectively characterized macroscopic deformation under torsional loading. Prediction of creep–fatigue life under torsional loading, utilizing the multiaxial ductility factor‐modified strain energy density exhaustion model, demonstrated excellent alignment with experimental findings. Finally, parametric analyses of stress distribution and damage assessment under different conditions were carried out for the example of a turbine blade with relatively rarely considered aerodynamic loading as a variable. It is expected to be popularized and applied in life design and damage assessment of high‐temperature structures under multiaxial loading in engineering.

show abstract

“…surface roughness, manufacturing tolerances, heat treatment and cutting-tool wear) is of great importance to structural integrity assessments of turbine bladed disks. Generally, deterministic approaches together with safety factor accounting for uncertainties often cause conservative results (Schijve, 2005;Niu et al, 2021a, b), while probabilistic structural integrity assessments (Narayanan, 2020;Chavoshi and Tagarielli, 2023) permit the uncertainties to be reflected in the quantification of reliability in fatigue design. It's worth mentioning that finite element analysis (FEA) together with probabilistic methods provides an efficient solution to evaluate the fatigue performance and reliability of turbine bladed disks under multisource uncertainties.…”

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

Data‐driven prediction of the probability of creep–fatigue crack initiation in 316H stainless steel

Cited by 8 publications

References 56 publications

Recent developments and future trends in fatigue life assessment of additively manufactured metals with particular emphasis on machine learning modeling

Recent developments and future trends in fatigue life assessment of additively manufactured metals with particular emphasis on machine learning modeling

Multiaxial creep–fatigue failure mechanism and life prediction of a turbine blade based on a unified numerical solution approach

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

Contact Info

Product

Resources

About