Data-driven modeling of multiaxial fatigue in frequency domain

Ravi, Sandipp Krishnan; Dong, Ping; Wei, Zhigang

doi:10.1016/j.marstruc.2022.103201

Cited by 20 publications

(7 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Figure , Ravi et al [ 107 ] reduced the dimension of the factors influencing fatigue behavior via PCA to verify the possibility and ability of the data‐driven method to simulate the multiaxial fatigue in frequency domain. As shown in Figure , the influence of chemical composition on fatigue performance was evaluated based on feature selection via dimension reduction of IFs, and the results illustrated that the contents of C, Si, P, Cr, Cu, and Mo were the key factors affecting the fatigue performance.…”

Section: Analysis Of Factors Influencing Fatigue Propertiesmentioning

confidence: 99%

“…Schematic of data generation. [107] Figure 11. Online fatigue performance prediction method based on integrated data mining.…”

Section: Comprehensive Consideration Of Influencing Factorsmentioning

confidence: 99%

“…As shown in Figure 10, Ravi et al [107] reduced the dimension of the factors influencing fatigue behavior via PCA to verify the possibility and ability of the data-driven method to simulate the Table 3. Processing methods for fatigue performance database.…”

Section: Dimension Reduction Of Influencing Factorsmentioning

confidence: 99%

“…MethodsApplication field Characteristics References PCA and spatial correlation quantification Multiaxial fatigue in frequency domain. Simple but difficult to identify multiple nonlinear relationships [107]. …”

mentioning

confidence: 99%

See 3 more Smart Citations

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

Section: Analysis Of Factors Influencing Fatigue Propertiesmentioning

confidence: 99%

“…Schematic of data generation. [107] Figure 11. Online fatigue performance prediction method based on integrated data mining.…”

Section: Comprehensive Consideration Of Influencing Factorsmentioning

confidence: 99%

Section: Dimension Reduction Of Influencing Factorsmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

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

show abstract

“…The predictive capabilities of trained AI\ML models are extensively used to evaluate properties of new material system and structures, getting insights on response surfaces [33]. One prominent example of the same is given for multi-axial fatigue analysis [34][35][36][37][38]. Though several strides have been made in applying ML framework in the material science domain, one strong limitation that has been pointed out (as mentioned in the previous section) is the black box nature of the ML models and lack of associated interpretability.…”

Section: Application Of Explainable Ai In Materials Sciencementioning

confidence: 99%

Elucidating Precipitation in FeCrAl Alloys through Explainable AI: A Case Study

Roy

Ravi

Roychowdhury

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Primary challenge of using FeCrAl in high temperature industrial setting is the formation of α’- precipitates that causes brittleness in the alloy, resulting in failure through fracture. The precipitation causes hardness change during thermal aging which is sensitive to both alloy composition and experimental condition (i.e., temperature and time of heat treatment). A Gaussian Process Regression (GPR) model is built on the hardness data collected at GE Research. Subsequently, for the first time, SHapley Additive exPlanations (SHAP) built upon the GPR is used as an Explainable Artificial Intelligence (XAI) tool to understand the effect of feature values in driving the hardness change. Several key insights are affirmed and obtained from a material science perspective.

show abstract