To overcome the challenges of limited experimental data and improve the accuracy of empirical formulas,we propose a low-cycle fatigue(LCF)life prediction model for nickel-based superalloys using a data augmentation me...To overcome the challenges of limited experimental data and improve the accuracy of empirical formulas,we propose a low-cycle fatigue(LCF)life prediction model for nickel-based superalloys using a data augmentation method.This method utilizes a variational autoencoder(VAE)to generate low-cycle fatigue data and form an augmented dataset.The Pearson correlation coefficient(PCC)is employed to verify the similarity of feature distributions between the original and augmented datasets.Six machine learning models,namely random forest(RF),artificial neural network(ANN),support vector machine(SVM),gradient-boosted decision tree(GBDT),eXtreme Gradient Boosting(XGBoost),and Categorical Boosting(CatBoost),are utilized to predict the LCF life of nickel-based superalloys.Results indicate that the proposed data augmentation method based on VAE can effectively expand the dataset,and the mean absolute error(MAE),root mean square error(RMSE),and R-squared(R^(2))values achieved using the CatBoost model,with respective values of 0.0242,0.0391,and 0.9538,are superior to those of the other models.The proposed method reduces the cost and time associated with LCF experiments and accurately establishes the relationship between fatigue characteristics and LCF life of nickel-based superalloys.展开更多
Two water cooled toroidal limiters were used in HT-7 to exhaust power effectively since the spring campaign of 2004. The heat flux deposition pattern on their surfaces both in steady state and transient state, caused ...Two water cooled toroidal limiters were used in HT-7 to exhaust power effectively since the spring campaign of 2004. The heat flux deposition pattern on their surfaces both in steady state and transient state, caused only by plasma displacement, were studied with ANSYS code. The ripple of the toroidal magnetic field was taken into account. The heat flux deposition appeared to be periodic. The ripple and the relative location of the limiter to the toroidal field （TF） coils, as well as the shift of the center of the last closed flux surface （LCFS）, had a vital influence upon the heat flux profile. The location with maximum temperature didn＇t coincide with that for the maximum heat flux in a transient state. The shift of the center of LCFS, caused by plasma displacement, made the heat flux on the limiter more uneven. The heat flux deposition pattern concerning the real shift of the center of LCFS at a transient state calls for further research.展开更多
Cold-stretched pressure vessels from austenitic stainless steels （ASS） are widely used for storage and transportation of liquefied gases, and have such advantages as thin wall and light weight. Fatigue is an importa...Cold-stretched pressure vessels from austenitic stainless steels （ASS） are widely used for storage and transportation of liquefied gases, and have such advantages as thin wall and light weight. Fatigue is an important concern in these pressure vessels, which are subjected to alternative loads. Even though several codes and standards have guidelines on these pressure vessels, there are no relevant design methods on fatigue failure. To understand the fatigue properties of ASS 1.4301 （equivalents include UNS $30400 and AISI 304） in solution-annealed （SA） and cold-stretched conditions （9% strain level） and the response of fatigue properties to cold stretching （CS）, low-cycle fatigue （LCF） tests were performed at room temperature, with total strain amplitudes ranging from ：~0.4% to ＂0.8%. Martensite transformations were measured during the tests. Comparisons on cyclic stress response, cyclic stress-strain behavior, and fatigue life were carried out between SA and CS materials. Results show that CS reduces the initial hardening stage, but prolongs the softening period in the cyclic stress response. Martensite transformation helps form a stable regime and subsequent secondary hardening. The stresses of monotonic and cyclic stress-strain curves are improved by CS, which leads to a lower plastic strain and a much higher elastic strain. The fatigue resistance of the CS material is better than that of the SA material, which is approximately 1 - 103 to 2 - 104 cycles. The S-N curve of the ASME standard for ASS is compared with the fatigue data and is justified to be suitable for the fatigue design of cold-stretched pressure vessels. However, considering the CS material has a better fatigue resistance, the S-N curve will be more conservative. The present study would be helpful in making full use of the advantages of CS to develop a new S-N curve for fatigue design of cold-stretched pressure vessels.展开更多
基金Financial support from the Fundamental Research Funds for the Central Universities(ZJ2022-003,JG2022-27,J2020-060,and J2021-060)Sichuan Province Engineering Technology Research Center of General Aircraft Maintenance(GAMRC2021YB08)the Young Scientists Fund of the National Natural Science Foundation of China(No.52105417)is acknowledged.
文摘To overcome the challenges of limited experimental data and improve the accuracy of empirical formulas,we propose a low-cycle fatigue(LCF)life prediction model for nickel-based superalloys using a data augmentation method.This method utilizes a variational autoencoder(VAE)to generate low-cycle fatigue data and form an augmented dataset.The Pearson correlation coefficient(PCC)is employed to verify the similarity of feature distributions between the original and augmented datasets.Six machine learning models,namely random forest(RF),artificial neural network(ANN),support vector machine(SVM),gradient-boosted decision tree(GBDT),eXtreme Gradient Boosting(XGBoost),and Categorical Boosting(CatBoost),are utilized to predict the LCF life of nickel-based superalloys.Results indicate that the proposed data augmentation method based on VAE can effectively expand the dataset,and the mean absolute error(MAE),root mean square error(RMSE),and R-squared(R^(2))values achieved using the CatBoost model,with respective values of 0.0242,0.0391,and 0.9538,are superior to those of the other models.The proposed method reduces the cost and time associated with LCF experiments and accurately establishes the relationship between fatigue characteristics and LCF life of nickel-based superalloys.
基金supported by National Natural Science Foundation of China (No.10475080)Foundation of Hefei Institutes of Physical Science of China (No.2006 YZJJ-1)
文摘Two water cooled toroidal limiters were used in HT-7 to exhaust power effectively since the spring campaign of 2004. The heat flux deposition pattern on their surfaces both in steady state and transient state, caused only by plasma displacement, were studied with ANSYS code. The ripple of the toroidal magnetic field was taken into account. The heat flux deposition appeared to be periodic. The ripple and the relative location of the limiter to the toroidal field （TF） coils, as well as the shift of the center of the last closed flux surface （LCFS）, had a vital influence upon the heat flux profile. The location with maximum temperature didn＇t coincide with that for the maximum heat flux in a transient state. The shift of the center of LCFS, caused by plasma displacement, made the heat flux on the limiter more uneven. The heat flux deposition pattern concerning the real shift of the center of LCFS at a transient state calls for further research.
基金Project supported by the National Key Technology R&D Program (No.2011BAK06B0205)the International Science and Technology Cooperation Project (No. 2010DFB42960)the Key Technology Innovation Team of Zhejiang Province (No. 2010R50001),China
文摘Cold-stretched pressure vessels from austenitic stainless steels （ASS） are widely used for storage and transportation of liquefied gases, and have such advantages as thin wall and light weight. Fatigue is an important concern in these pressure vessels, which are subjected to alternative loads. Even though several codes and standards have guidelines on these pressure vessels, there are no relevant design methods on fatigue failure. To understand the fatigue properties of ASS 1.4301 （equivalents include UNS $30400 and AISI 304） in solution-annealed （SA） and cold-stretched conditions （9% strain level） and the response of fatigue properties to cold stretching （CS）, low-cycle fatigue （LCF） tests were performed at room temperature, with total strain amplitudes ranging from ：~0.4% to ＂0.8%. Martensite transformations were measured during the tests. Comparisons on cyclic stress response, cyclic stress-strain behavior, and fatigue life were carried out between SA and CS materials. Results show that CS reduces the initial hardening stage, but prolongs the softening period in the cyclic stress response. Martensite transformation helps form a stable regime and subsequent secondary hardening. The stresses of monotonic and cyclic stress-strain curves are improved by CS, which leads to a lower plastic strain and a much higher elastic strain. The fatigue resistance of the CS material is better than that of the SA material, which is approximately 1 - 103 to 2 - 104 cycles. The S-N curve of the ASME standard for ASS is compared with the fatigue data and is justified to be suitable for the fatigue design of cold-stretched pressure vessels. However, considering the CS material has a better fatigue resistance, the S-N curve will be more conservative. The present study would be helpful in making full use of the advantages of CS to develop a new S-N curve for fatigue design of cold-stretched pressure vessels.
