Simple Data Analytics Approach Coupled with Larson–Miller Parameter Analysis for Improved Prediction of Creep Rupture Life

Lee, Chang-Ho; Lee, Taejoo; Choi, Yoon Suk

doi:10.1007/s12540-023-01445-3

Cited by 3 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We found from Equations ( 13)-( 15) that, for L-M, M-S, and G-D models, if the values of the fitting coefficients a 3 , a 2 , a 1 , and a 0 and the value of constant c are all determined, it is possible to obtain equations for logarithmic stress lgσ, logarithmic creep fracture time lgt and temperature T. It can be found from Equation ( 16) that for the M-H model, if the values of the fitting coefficients a 3 , a 2 , a 1 , a 0 and the values of constants T 0 and lgt 0 are all determined, a cubic equation about logarithmic stress lgσ, logarithmic creep fracture time lgt and temperature T can be obtained. The equations of four models can be unified as Equation (17). For Equation (17), once the values of the logarithmic stress lgσ and temperature T are determined, the cubic equation of the logarithmic creep fracture time lgt can be obtained.…”

Section: Deep Belief Network (Dbn) [6061]mentioning

confidence: 99%

“…The equations of four models can be unified as Equation (17). For Equation (17), once the values of the logarithmic stress lgσ and temperature T are determined, the cubic equation of the logarithmic creep fracture time lgt can be obtained. By solving the roots of the cubic equation, the logarithmic creep fracture time lgt can be obtained.…”

Section: Deep Belief Network (Dbn) [6061]mentioning

confidence: 99%

“…The Larson-Miller model is a time-temperature parametric model based on data fitting. The Larson-Miller model is often used in engineering to predict the creep rupture life of materials [14][15][16][17][18][19][20][21][22][23]. Recently, some researchers used machine learning models to predict the creep rupture life of materials [24][25][26][27][28][29].…”

Section: Introductionmentioning

confidence: 99%

“…Loghman et al [16] calculated the creep damage of a thick-walled reactor made of 316 austenitic stainless steel using the Larson-Miller parametric model and evaluated its remaining life. Lee et al [17] combined the data analysis method with the Larson-Miller parametric model to predict the creep rupture life of 2.25 Cr and 9~12% Cr ferritic steels. Pavan et al [18] evaluated the creep rupture life of nickel-based superalloys from superheater coils in supercritical power plants using the Larson-Miller parametric model.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Method for Predicting the Creep Rupture Life of Small-Sample Materials Based on Parametric Models and Machine Learning Models

Zhang,

Yao,

et al. 2023

Materials

View full text Add to dashboard Cite

In view of the differences in the applicability and prediction ability of different creep rupture life prediction models, we propose a creep rupture life prediction method in this paper. Various time–temperature parametric models, machine learning models, and a new method combining time–temperature parametric models with machine learning models are used to predict the creep rupture life of a small-sample material. The prediction accuracy of each model is quantitatively compared using model evaluation indicators (RMSE, MAPE, R2), and the output values of the most accurate model are used as the output values of the prediction method. The prediction method not only improves the applicability and accuracy of creep rupture life predictions but also quantifies the influence of each input variable on creep rupture life through the machine learning model. A new method is proposed in order to effectively take advantage of both advanced machine learning models and classical time–temperature parametric models. Parametric equations of creep rupture life, stress, and temperature are obtained using different time–temperature parametric models; then, creep rupture life data, obtained via equations under other temperature and stress conditions, are used to expand the training set data of different machine learning models. By expanding the data of different intervals, the problem of the low accuracy of the machine learning model for the small-sample material is solved.

show abstract

Section: Deep Belief Network (Dbn) [6061]mentioning

confidence: 99%

Section: Deep Belief Network (Dbn) [6061]mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Method for Predicting the Creep Rupture Life of Small-Sample Materials Based on Parametric Models and Machine Learning Models

Zhang,

Yao,

et al. 2023

Materials

View full text Add to dashboard Cite

show abstract

Rapid assessment of the creep rupture life of metals: A model enabling experimental design

Joy,

Talapatra,

Hoang

et al. 2024

International Journal of Plasticity

View full text Add to dashboard Cite

Prediction of creep deformation based on the Z_c parameter method

Kang,

Cao,

Cheng

et al. 2023

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

The prediction method of creep curve based on Zc parameter is proposed. The Zc parameter method is capable of effectively predicting creep curves and parameters (creep rate, minimum creep rate, and creep rupture life) under various experimental conditions, even with limited data. The predicted results are in accordance with experimental data, and all predictions are entirely within a 95% confidence interval, demonstrating the predictive reliability of the Zc method. Furthermore, on the premise of ensuring the accuracy of prediction, the setting of creep rupture strain for predicting creep rupture time using the Zc parameter method has a considerable range of options.

show abstract

Simple Data Analytics Approach Coupled with Larson–Miller Parameter Analysis for Improved Prediction of Creep Rupture Life

Cited by 3 publications

References 35 publications

A Method for Predicting the Creep Rupture Life of Small-Sample Materials Based on Parametric Models and Machine Learning Models

A Method for Predicting the Creep Rupture Life of Small-Sample Materials Based on Parametric Models and Machine Learning Models

Rapid assessment of the creep rupture life of metals: A model enabling experimental design

Prediction of creep deformation based on the Z_c parameter method

Contact Info

Product

Resources

About

Simple Data Analytics Approach Coupled with Larson–Miller Parameter Analysis for Improved Prediction of Creep Rupture Life

Cited by 3 publications

References 35 publications

A Method for Predicting the Creep Rupture Life of Small-Sample Materials Based on Parametric Models and Machine Learning Models

A Method for Predicting the Creep Rupture Life of Small-Sample Materials Based on Parametric Models and Machine Learning Models

Rapid assessment of the creep rupture life of metals: A model enabling experimental design

Prediction of creep deformation based on the Zc parameter method

Contact Info

Product

Resources

About

Prediction of creep deformation based on the Z_c parameter method