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...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 mod-els 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.展开更多
In September 2018,we proposed the cutting-edge concept of“Beyond Limits Manufacturing”(BLM).BLM technology is based on the three-dimensional inner engraving or precise outer engraving of ultra-fast laser,to invent m...In September 2018,we proposed the cutting-edge concept of“Beyond Limits Manufacturing”(BLM).BLM technology is based on the three-dimensional inner engraving or precise outer engraving of ultra-fast laser,to invent micro/nano scale flow chips or devices,which makes it possible for the microform,integration,economy,safety,high efficiency,green and intelligence of research,development and manufacturing process,so as to realize transformational manufacturing in the era of Industry 4.0.In this paper,we reviewed the representative results we made in the field of micro/nano flow chemistry during the implementation of the BLM major project(December 2019 to August 2023),and discussed its application prospects in micro/nano flow chemistry.展开更多
In this study,a continuous-flow procedure containing four steps has been developed to synthesize Pigment Red 53 and modify its crystal structure.This process avoided the problems of conveying highly insoluble reaction...In this study,a continuous-flow procedure containing four steps has been developed to synthesize Pigment Red 53 and modify its crystal structure.This process avoided the problems of conveying highly insoluble reaction intermediates by removing intermediate operating steps.After optimization,the overall yield of Pigment Red 53:1 reached 97.1%in the total residence time of 80 s by this diazotizationcoupling-laking-crystal transition process.From batch to continuous flow,the purity of products increased from 97.1%to 98.2%and the median diameter of pigment particles decreased from 14μm to 1.9μm.This process achieved a similar crystal transition effect in 18 s as in batch,producingα,δandνcrystals of Pigment Red 53:2 as expected.In conclusion,this continuous-flow procedure displays advantages in both synthesis and crystal transition,indicating another potential use for industrial application.展开更多
Prediction of creep rupture life of high-temperature titanium alloys is crucial for their practical applications.The efficient representations(features)of the information encoded in the data are essential to achieve a...Prediction of creep rupture life of high-temperature titanium alloys is crucial for their practical applications.The efficient representations(features)of the information encoded in the data are essential to achieve an accurate prediction model.Here,using convolutional neural networks(CNN)enhanced features,we obtain largely improved prediction models for creep rupture life.Comparison of CNNbased features with the original features in describing different samples reveals that the former,by assigning more individualized labels,outperforms the latter and underpins improved prediction models.This work suggests that beyond images,CNN is also suitable for numerical data to obtain enhanced features and surrogate models.展开更多
基金National Key Research and Development Program of China(No.2021YFB3702604)National Natural Science Foundation of China(No.52002326).
文摘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 mod-els 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.
文摘In September 2018,we proposed the cutting-edge concept of“Beyond Limits Manufacturing”(BLM).BLM technology is based on the three-dimensional inner engraving or precise outer engraving of ultra-fast laser,to invent micro/nano scale flow chips or devices,which makes it possible for the microform,integration,economy,safety,high efficiency,green and intelligence of research,development and manufacturing process,so as to realize transformational manufacturing in the era of Industry 4.0.In this paper,we reviewed the representative results we made in the field of micro/nano flow chemistry during the implementation of the BLM major project(December 2019 to August 2023),and discussed its application prospects in micro/nano flow chemistry.
基金financial support from Shanghai Municipal Science and Technology Commission (No.21520761100)the Open Project of State Key Laboratory of Chemical Engineering (No. SKL-Ch E-21C07)+1 种基金the Fundamental Research Funds for the Central Universitiesthe Program of Leading Talents (2013)
文摘In this study,a continuous-flow procedure containing four steps has been developed to synthesize Pigment Red 53 and modify its crystal structure.This process avoided the problems of conveying highly insoluble reaction intermediates by removing intermediate operating steps.After optimization,the overall yield of Pigment Red 53:1 reached 97.1%in the total residence time of 80 s by this diazotizationcoupling-laking-crystal transition process.From batch to continuous flow,the purity of products increased from 97.1%to 98.2%and the median diameter of pigment particles decreased from 14μm to 1.9μm.This process achieved a similar crystal transition effect in 18 s as in batch,producingα,δandνcrystals of Pigment Red 53:2 as expected.In conclusion,this continuous-flow procedure displays advantages in both synthesis and crystal transition,indicating another potential use for industrial application.
基金supported by the National Key Research and Development Program of China(No.2021YFB3702601).
文摘Prediction of creep rupture life of high-temperature titanium alloys is crucial for their practical applications.The efficient representations(features)of the information encoded in the data are essential to achieve an accurate prediction model.Here,using convolutional neural networks(CNN)enhanced features,we obtain largely improved prediction models for creep rupture life.Comparison of CNNbased features with the original features in describing different samples reveals that the former,by assigning more individualized labels,outperforms the latter and underpins improved prediction models.This work suggests that beyond images,CNN is also suitable for numerical data to obtain enhanced features and surrogate models.
