Prediction Of Creep Rupture Life Research Articles

Transfer learning enables the rapid design of single crystal superalloys with superior creep resistances at ultrahigh temperature

Accelerating the design of Ni-based single crystal (SX) superalloys with superior creep resistance at ultrahigh temperatures is a desirable goal but extremely challenging task. In the present work, a deep transfer learning neural network with physical constraints for creep rupture life prediction at ultrahigh temperatures is constructed. Transfer learning enables deep learning model breaks through the generalization performance barrier in the extrapolation space of ultrahigh temperature creep properties in the case of a very small dataset, which is the key to achieving the above design goal. Transfer learning is demonstrated to be effective in utilizing the prior compositional sensitivities information contained in the pre-trained model, and motivates the fine-tuned model to capture the particular relationship between composition and creep rupture life at ultrahigh temperature. Aiming to find advanced SX superalloys applied at 1200 °C, the proposed transfer learning-based model guides us to design a superalloy with a verified creep rupture life of ~170 h at 80 MPa, which exceeds the state-of-art value by 30%. The improved γ/γ′ interface strengthening, which is effectively regulated by the Mo/Ta ratio to form γ′ rafting with longer, flatter interfaces and achieve stronger interfacial bonding, is revealed as the dominant mechanism behind combining experiments and first-principles calculations. Moreover, the excellent extrapolation ability of the proposed model is further confirmed to enhance the efficiency of active learning by reducing its dependence on the initial dataset size. This study provides a pioneering AI-driven approach for the rapid development of Ni-based SX superalloys applied in advanced aero-engine blades.

Creep rupture life prediction methodology based on establishment of the correlations between creep properties of superalloy in virgin and degraded conditions

Creep rupture life prediction methodology based on establishment of the correlations between creep properties of superalloy in virgin and degraded conditions

Prediction of creep rupture life of ODS steels based on machine learning

Creep rupture life is a key material parameter for service life and mechanical properties of ODS steels. Therefore, accurately predicting the creep rupture life of ODS steels holds significant importance. This study aims to build quantitative models to predict the creep rupture life of ODS steels by ML techniques. Before the construction of models, the SFS and RF methods were used for input selection. Seven features were selected as inputs and used to predict creep rupture life. The ML algorithms including LR, SVR, MLP, KRR, RFR, and XGBoost are employed, among which XGBoost performs best in predicting the creep rupture life of ODS steels with high accuracy (RMSE of 0.78 h and 0.88 h, MAE of 0.62 h and 0.71 h, and R2 of 0.96 and 0.91 for training and testing sets, respectively). Feature importance coefficients of the XGBoost model were used to show the magnitude of the effect of descriptors on creep fracture life. For the chemical composition, the parameters that have a great influence on the creep rupture life are Ti, Cr, W and Y2O3 with the values of importance coefficients of 0.154, 0.04, 0.039 and 0.034, respectively. For the heat treatment process, the parameters that have a great influence on the creep rupture life are ST and FT with the values of importance coefficients of 0.127 and 0.025, respectively. For the test conditions, the parameters that have a great influence on the creep rupture life are CR and CS with the values of importance coefficients of 0.342 and 0.041, respectively. The findings of the feature importance of the XGBoost model are similar to those of the RFR model. This study developed an effective ML model to predict the creep rupture life of ODS steels, providing a strategy to predict the creep rupture life of ODS steels and significant insights as additional guidelines for the research and development of novel type ODS alloys with high performance.

Evaluating creep rupture life in austenitic and martensitic steels with soft-constrained machine learning

Machine learning is extensively utilized for predicting creep rupture of high-temperature steels. Recently, five soft-constrained machine learning algorithms (SCMLAs) have been developed to enhance the extrapolation capabilities of machine learning. These SCMLAs were applied to the austenitic steel Sanicro 25, showing their potential. To improve SCMLAs, this study has introduced new guidelines that address temperature culling within the input range and temperature extrapolation beyond the input range. Leveraging these guidelines, the SCMLAs were extended to various austenitic and martensitic stainless steels. The predicted results of TP316H, the data of which is representative of austenitic stainless steels, were validated through error estimates. Furthermore, notable agreement has been reached for temperature culling and temperature extrapolation, as demonstrated for TP91 and TP92 martensitic steels. The effects of single casts and the temperature dependence of the predictions have been analyzed for the studied materials. Consistent results can be readily achieved through systematic evaluations of SCMLAs for extrapolating up to 300,000 h or three times the maximum experimental rupture time for the studied materials. It is demonstrated that SCMLAs can provide reliable creep rupture life prediction across various high-temperature materials.

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

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.

Creep rupture life prediction of high-temperature titanium alloy using cross-material transfer learning

High-temperature titanium alloys are the key materials for the components in aerospace and their service life depends largely on creep deformation-induced failure. However, the prediction of creep rupture life remains a challenge due to the lack of available data with well-characterized target property. Here, we proposed two cross-materials transfer learning (TL) strategies to improve the prediction of creep rupture life of high-temperature titanium alloys. Both strategies effectively utilized the knowledge or information encoded in the large dataset (753 samples) of Fe-base, Ni-base, and Co-base superalloys to enhance the surrogate model for small dataset (88 samples) of high-temperature titanium alloys. The first strategy transferred the parameters of the convolutional neural network while the second strategy fused the two datasets. The performances of the TL models were demonstrated on different test datasets with varying sizes outside the training dataset. Our TL models improved the predictions greatly compared to the models obtained by straightly applying five commonly employed algorithms on high-temperature titanium alloys. This work may stimulate the use of TL-based models to accurately predict the service properties of structural materials where the available data is small and sparse.

Deep learning accelerates the development of Ni-based single crystal superalloys: A physical-constrained neural network for creep rupture life prediction

Creep rupture life is a key target for designing Ni-based single crystal (SX) superalloys. Machine learning (ML) has the potential to accelerate alloy design by accurately predicting the creep rupture life of potential superalloys. In this work, a physical-constrained neural network named Superalloy Transformer-based Network for Creep (SaTNC) is established, and the representation of superalloy is automatically learned based on deep representation learning. As core physical bias in the SaTNC model, the information associated with interaction among alloying elements achieved by Transformer-based neural network is introduced to constrain the representation of the superalloy. The SaTNC model exhibits competitive generalization performance and the results have verified the high capability of the SaTNC model to capture the sensitivities of creep rupture life on alloy composition and service conditions. Moreover, Transformer-based deep representation for superalloy with both effectiveness and interpretability is obtained. The material insights including the interactions among alloying elements and their combined effects on the creep rupture life of superalloy are extracted from this deep representation. Finally, with the aid of the SaTNC model, a potential alloy composition space with low density and excellent creep resistance at high temperatures is identified, which will be experimentally verified in the future.

A unified creep life prediction method and fracture mechanism of high-temperature alloys under multiaxial stress

In this paper, a unified creep rupture life prediction method based on continuum damage mechanics under multiaxial stress was proposed. By optimizing the traditional skeletal point stress method, the number of models that need to be computed during the simulation was reduced by 5/6, and the generality of the method for different notch sizes was significantly improved. Creep tests on Ni-based superalloy round bar specimens with different notch sizes, which verify the accuracy of the method, were conducted. Furthermore, creep rupture mechanism analyses were conducted for different notch sizes by combining finite element simulations with experiments, stress and damage were analyzed, and void growth was explained based on triaxial stress states.

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

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

Creep rupture life prediction of nickel-based superalloys based on data fusion

Creep rupture life is a key performance parameter of nickel-based superalloys, which directly affects the engineering service behavior of components. In this study, a machine learning method based on data fusion was proposed to predict the properties of new alloys with the properties of existing alloys, or to predict other related properties of the same alloy, so as to solve the problem of accurate prediction of creep rupture life caused by the lack of accumulated data. Using the existing nickel-based superalloy creep rupture life data accumulated in the NIMS database, a creep rupture life prediction model was established using key alloy factor screening and feature-based transfer learning strategy (FS-SVR). The performance of GH4169D alloy was successfully predicted by the properties of GH4169 alloy, and the high temperature creep rupture life was predicted by the low temperature creep rupture life of GH4169 and GH4169D alloys, and the prediction accuracy reached more than 90%. The research results not only provide a fast method for predicting the creep properties of novel nickel-based superalloys, but also provide a reference case for data fusion to assist the research and development of new materials.

Numerical Prediction of Creep Rupture Life of Ex-Service and As-Received Grade 91 Steel at 873 K

Infallible creep rupture life prediction of high temperature steel needs long hours of robust testing over a domain of stress and temperature. A substantial amount of effort has been made to develop alternative methods to reduce the time and cost of testing. This study presents a finite element analysis coupled with a ductility based damage model to predict creep rupture time under the influence of multiaxial stress state of ex-service and as-received Grade 91 steel at 873 K. Three notched bar samples with different acuity ratios of 2.28, 3.0 and 4.56 are modelled in commercial Finite Element (FE) software, ABAQUS v6.14 in order to induce different stress state levels at notch throat area and investigate its effect on rupture time. The strain-based ductility exhaustion damage approach is employed to quantify the damage state. The multiaxial ductility of the material that is required to determine the damage state is estimated using triaxiality-ductility Cock and Ashby relation. Further reduction of the ductility due to the different creep mechanisms over a short and long time is also accounted for in the prediction. To simulate the different material conditions: ex-service and as-received material, different creep coefficients (A) have been assigned in the numerical modelling. In the case of ex-service material, using mean best fit data of minimum creep strain rate gives a good life prediction, while for new material, the lower bound creep coefficient should be employed to yield a comparable result with experimental data. It is also notable that ex-service material deforms faster than as-received material at the same stress level. Moreover, higher acuity provokes damage to concentrate on the small area around the notch, which initiates higher rupture life expectancy. It also found out that, the stress triaxiality and the equivalent creep strain influence the location of damage initiation around the notch area.

Numerical schemes based on the stress compensation method framework for creep rupture assessment

Evaluation of creep rupture limit and prediction of creep rupture life are two significant issues for high-temperature devices under the action of cyclic thermo-mechanical loadings. In this paper, the shakedown solution procedure proposed recently by the authors, so-called stress compensation method (SCM), is extended for creep rupture assessment via an extended shakedown theory including creep. Two distinct numerical schemes based on the SCM framework are presented, where Scheme 1 is utilised for evaluation of creep rupture limit and Scheme 2 is utilised for prediction of creep rupture life. Instead of using the detailed creep constitutive equations, the present methods just need to know several material parameters including the creep rupture data. A holed plate is provided as a typical example to validate the reliability of two numerical schemes. Detailed cycle-by-cycle analyses are carried out to illustrate the good accuracy of these calculated creep rupture limits and reveal the failure mechanisms of the structure under different combinations of loads. A numerical study on a pipe junction is also conducted to show the engineering application of the methods. As a result, the two numerical schemes are proved to be effective and reliable for solving practical industrial problems.

Optimization of Creep Rupture Life Prediction for A231 T91 Alloy Steel Using Kriging Surrogate Model

Creep rupture life prediction for the A231 T91 alloy steel has been optimized using the Kriging surrogate model. Creep rupture data published by NIMS data sheet was used in this optimization, and isothermal creep rupture life-stress and TTP(Time-Temperature Parameter)-stress curves were optimized with Kriging model. The creep rupture data having the rupture life of less than 10,000 hours was interpolated with the K海ing surrogate model and theKriging extrapolation to the creep life of 100,000 hours was verified by comparing with experimental data. It was found that the Kriging model could fit to the data within 3% of relative error. Furthermore, the Kriging surrogate model was compared to Wilshire, Manson-Brown, Manson-Haferd, and MCX models. It can be found that the creep rupture stress extrapolated to 100,000 hours by Kriging surrogate showed a relatively good accuracy and uncertainty of 4% - 16%.

OS10-7 Prediction of Creep Rupture Life of Welded Circular Pipe Subject to Combined Internal Pressure and Axial Load(Structural damage assessment,OS10 Mechanics, informatics and materials engineering for damage/life assessment,STRENGTH OF MATERIALS)

OS10-7 Prediction of Creep Rupture Life of Welded Circular Pipe Subject to Combined Internal Pressure and Axial Load(Structural damage assessment,OS10 Mechanics, informatics and materials engineering for damage/life assessment,STRENGTH OF MATERIALS)

Prediction of creep rupture life of a V-notched bar in DD6 Ni-based single crystal superalloy

The circumferential V-type notched round bar has been designed to investigate the effect of multi-axial stress state on creep rupture behavior of DD6 Ni-based single crystal superalloys at 1100°C. Creep test on both smooth and notched specimens were carried out under 160MPa and 200MPa on the minimum net-section. Time to creep fracture was found to be higher in notched specimens than in smooth specimens. Finite element (FE) analysis coupled with continuum damage mechanics (CDM) was carried out to understand the stress distribution and the creep damage evolution under uniaxial and multi-axial stress states. The creep rupture life of the smooth specimen was successfully predicted by the classical Kachanov–Rabotnov damage law. The creep rupture life of the notched specimen predicted by finite element calculation incorporating a multi-axial creep CDM model was in good agreement with the experimental results. Both the fracture morphology and FE damage analysis indicate that rupture initiates first at the notch root in the notched specimen and finally towards to the center location.

A novel prediction method of creep rupture life of 9–12% chromium ferritic steel based on abductive network

The creep rupture life of 9–12% chromium ferritic steel is predicted as a function of alloy composition, creep stress, and creep temperature. A database is made up from data in previous publications. A novel abductive network is constructed to predict creep rupture life. With a four-layer architecture, the network shows a precise prediction of creep rupture life of 9–12% chromium ferritic steel. Performance is examined and compared with backpropagation algorithm (BP) neural network. Results indicate that the proposed approach is more accurate than Larson–Miller parametric method and more efficient than that of BP neural network. Automatic relevance determination reveals that the influence of Cr and W on creep rupture life of 9–12% chromium ferritic steel are the greatest amongst the alloying elements.

Creep rupture life prediction based on creep dissipation energy analysis

Structural materials used in sodium cooled fast reactors (SFRs) shall have good high temperature low cycle fatigue and creep properties, adequate weldability to fabricate large size components and shall be compatable with the liquid sodium environment in service. Austenitic stainless steels have been the natural choice for structural components of SFRs worldwide. The creep design life of SFR component is very long and is of the order of 40 years. This calls for robust creep life rediction models to convert short and medium term laboratory rupture data to design life. This paper discusses the application of creep dissipation energy concepts to predict creep rupture life of four nitrogen alloyed grades of 316 LN SS.

Building on knowledge base of sodium cooled fast spectrum reactors to develop materials technology for fusion reactors

The alloys 316L(N) and Mod. 9Cr–1Mo steel are the major structural materials for fabrication of structural components in sodium cooled fast reactors (SFRs). Various factors influencing the mechanical behaviour of these alloys and different modes of deformation and failure in SFR systems, their analysis and the simulated tests performed on components for assessment of structural integrity and the applicability of RCC-MR code for the design and validation of components are highlighted. The procedures followed for optimal design of die and punch for the near net shape forming of petals of main vessel of 500 MWe prototype fast breeder reactor (PFBR); the safe temperature and strain rate domains established using dynamic materials model for forming of 316L(N) and 9Cr–1Mo steels components by various industrial processes are illustrated. Weldability problems associated with 316L(N) and Mo. 9Cr–1Mo are briefly discussed. The utilization of artificial neural network models for prediction of creep rupture life and delta-ferrite in austenitic stainless steel welds is described. The usage of non-destructive examination techniques in characterization of deformation, fracture and various microstructural features in SFR materials is briefly discussed. Most of the experience gained on SFR systems could be utilized in developing science and technology for fusion reactors. Summary of the current status of knowledge on various aspects of fission and fusion systems with emphasis on cross fertilization of research is presented.

Damage characterization of a P91 steel weldment under uniaxial and multiaxial creep

Clarification of creep damage mechanism and establishment of remaining life assessment methods of boiler pipings of P91 steel with weldment are important subjects to maintain reliable operation of thermal power plants. In order to characterize the creep damage of a P91 steel weldment and to discuss creep rupture life prediction methods, uniaxial creep tests on a P91 steel cross weld and internal pressure creep tests on a longitudinal welded tube specimen were conducted. Three-dimensional finite-element creep analysis of the longitudinal welded tube specimen was conducted to identify stress and creep strain distribution within the specimen. Creep rupture time of the weld joints was reduced significantly from that of the base metal due to Type IV failure. It was found from an examination of creep damage in interrupted cross weld specimens that creep voids have already initiated around 20% creep damage, and that the number of voids inside the specimens was larger than those at the surface of the specimens. Creep analysis results indicated that triaxial tensile stress yielded at mid-thickness in the heat affected zone (HAZ) of the tube specimen due to differences of creep deformation properties of the base metal, the HAZ and the weld metal. It was suggested that triaxial stress states caused acceleration of creep damage evolution in the HAZ resulting in internal failure of the tube specimens. Rupture life of the longitudinal welded tube specimen under internal pressure creep is predicted from the circumferential steady-state creep strain rate at the HAZ obtained from creep analysis using a three-materials finite-element model of the tube specimen.

Compositional prediction of creep rupture life of single crystal Ni base superalloy by Bayesian neural network

The creep rupture lives of single crystal Ni base superalloys are predicted as a function of alloy composition, creep stress, and creep temperature. A database has been constructed from previous publications and the Rolls-Royce materials database. The Bayesian neural network technique was used for the modelling of creep rupture life. To obtain the posterior distribution and prediction which is of a high dimensional integral form, the Markov chain Monte Carlo method was applied . With a complex 13-31-1 architecture, the neural network shows a precise prediction of creep rupture life of superalloys. Automatic relevance determination reveals that the influences of Re and Cr on creep rupture life of single crystal superalloys are the greatest amongst the alloying elements.