A physics-informed neural network for creep-fatigue life prediction of components at elevated temperatures

Zhang, Xiaocheng; Gong, Jing; Xuan, Fu‐Zhen

doi:10.1016/j.engfracmech.2021.108130

Cited by 77 publications

(22 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this way, data‐driven models can achieve a better prediction performance and also a lower requirement on the size of training datasets, thanks to the cooperation between different information sources for modeling. Several exploration works have been reported for the development of domain knowledge‐integrated data‐driven models 39–42 . For example, Read et al 41 explored encoding the principle of energy conservation into the loss function of ANNs for lake water temperature prediction, Masi et al 42 studied the fusion of principles of thermodynamics into the structure design of ANNs for material constitutive modeling, and Gan et al 39 recently developed a robust damage theory‐informed data‐driven model for remaining life prediction under stepwise loading.…”

Section: Domain Knowledge‐integrated Elm Ensemble Modelmentioning

confidence: 99%

“…Apart from ensemble learning, domain knowledge integration is also a useful approach to essentially improve the accuracy and stability of ANN‐based models. It has shown that incorporating domain knowledge as the restrictions or benchmarks for model training can inherently optimize the data‐driven process of model prediction 39,40 . As an emerging modeling methodology, domain knowledge‐integrated ANN‐based models are still in the exploration stage, and several successful applications have been reported in previous studies 39–42 …”

Section: Introductionmentioning

confidence: 99%

“…It has shown that incorporating domain knowledge as the restrictions or benchmarks for model training can inherently optimize the data-driven process of model prediction. 39,40 As an emerging modeling methodology, domain knowledgeintegrated ANN-based models are still in the exploration stage, and several successful applications have been reported in previous studies. [39][40][41][42] In the present work, to maximize the accuracy and stability for predicting the fatigue life affected by mean stresses, ensemble learning and domain knowledge are used integratedly, and an emerging variant of ANNs, called extreme learning machine (ELM), 43 is employed here as the base learner.…”

Section: Introductionmentioning

confidence: 99%

“…39,40 As an emerging modeling methodology, domain knowledgeintegrated ANN-based models are still in the exploration stage, and several successful applications have been reported in previous studies. [39][40][41][42] In the present work, to maximize the accuracy and stability for predicting the fatigue life affected by mean stresses, ensemble learning and domain knowledge are used integratedly, and an emerging variant of ANNs, called extreme learning machine (ELM), 43 is employed here as the base learner. ELM is a simple single hidden layer neural network whose input weights and hidden neuron parameters can be randomly assigned without needing iteratively tuning.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Fatigue life prediction in presence of mean stresses using domain knowledge‐integrated ensemble of extreme learning machines

Gan

Zhong

2022

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

An accurate and stable data-driven model is proposed in this work for fatigue life prediction in presence of mean stresses. Multiple independent extreme learning machines are integrated into the model with distinct neural network configurations to simulate the complex correlations among mean stress levels, material properties, and fatigue lives. Meanwhile, the theoretical prediction, as a representation of domain knowledge, is used to optimize the data-driven processes of model training and prediction. Extensive experimental data of 13 metallic materials with different mean stress levels are collected from the open literatures for model training and evaluation. The results demonstrate that the proposed model can achieve high accuracy and good stability in fatigue life prediction under mean stress loading conditions, even with a small training dataset, showing great applicability for fatigue life prediction.

show abstract

Section: Domain Knowledge‐integrated Elm Ensemble Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fatigue life prediction in presence of mean stresses using domain knowledge‐integrated ensemble of extreme learning machines

Gan

Zhong

2022

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

show abstract

“…The division ratio is related to the overall size of the data set. Based on the above, 80% of the data is used for training, and 20% is used for testing [44]. In the collected 450 sets of data sets, 360 sets of sample data are used for training, and 90 sets of sample data are used for testing.…”

Section: Optimization and Evaluation Of The Modelmentioning

confidence: 99%

Prediction of the Control Effect of Fractured Leakage in Unconventional Reservoirs Using Machine Learning Method

Song

et al. 2022

Geofluids

View full text Add to dashboard Cite

Bridging plugging is the most used method of plugging in unconventional oil reservoirs, and many factors affect the effect of bridging and plugging. Since the laboratory cannot simulate the actual leakage size of the lost formation and the corresponding leakage plugging process at the drilling site, the laboratory experiment results cannot reflect the actual leakage plugging construction effect. Aiming at the problem of frequent fracture leakage during drilling in Chepaizi block, Xinjiang, China, this paper proposes a set of machine learning methods based on a neural network. Three types of factors and 14 parameters with a strong correlation with the leakage control effect were screened out. Three categories of factors include construction parameters, choice of plugging material, and fluid properties of the carrier fluid. The training was carried out based on the collected field data, the appropriate activation function was set, and the deep well network structure was optimized. By improving the field plugging measures in the later period, the model was verified by these actual cases, and the results showed that the established model produced the highest R 2 of 0.974, has a good fit, and predicts well.

show abstract

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

A physics-informed neural network for creep-fatigue life prediction of components at elevated temperatures

Cited by 77 publications

References 40 publications

Fatigue life prediction in presence of mean stresses using domain knowledge‐integrated ensemble of extreme learning machines

Fatigue life prediction in presence of mean stresses using domain knowledge‐integrated ensemble of extreme learning machines

Prediction of the Control Effect of Fractured Leakage in Unconventional Reservoirs Using Machine Learning Method

A State‐of‐Art Review on Prediction Model for Fatigue Performance of Welded Joints via Data‐Driven Method

Contact Info

Product

Resources

About