Metal-halide hybrid perovskite materials are excellent candidates for solar cells and photoelectric devices.In recent years,machine learning(ML)techniques have developed rapidly in many fields and provided ideas for m...Metal-halide hybrid perovskite materials are excellent candidates for solar cells and photoelectric devices.In recent years,machine learning(ML)techniques have developed rapidly in many fields and provided ideas for material discovery and design.ML can be applied to discover new materials quickly and effectively,with significant savings in resources and time compared with traditional experiments and density functional theory(DFT)calculations.In this review,we present the application of ML in per-ovskites and briefly review the recent works in the field of ML-assisted perovskite design.Firstly,the advantages of perovskites in solar cells and the merits of ML applied to perovskites are discussed.Secondly,the workflow of ML in perovskite design and some basic ML algorithms are introduced.Thirdly,the applications of ML in predicting various properties of perovskite materials and devices are reviewed.Finally,we propose some prospects for the future development of this field.The rapid devel-opment of ML technology will largely promote the process of materials science,and ML will become an increasingly popular method for predicting the target properties of materials and devices.展开更多
We investigate the impact of different numbers of positive and negative examples on machine learning for sapphire crystals defects prediction. We obtain the models of crystal growth parameters influence on the sapphir...We investigate the impact of different numbers of positive and negative examples on machine learning for sapphire crystals defects prediction. We obtain the models of crystal growth parameters influence on the sapphire crystal growth. For example, these models allow predicting the defects that occur due to local overcooling of crucible walls in the thermal node leading to the accelerated crystal growth. We also develop the prediction models for obtaining the crystal weight, blocks, cracks, bubbles formation, and total defect characteristics. The models were trained on all data sets and later tested for generalization on testing sets, which did not overlap the training set.During training and testing, we find the recall and precision of prediction, and analyze the correlation among the features. The results have shown that the precision of the neural network method for predicting defects formed by local overcooling of the crucible reached 0.94.展开更多
Growth of high-quality single crystals is of great significance for research of condensed matter physics. The exploration of suitable growing conditions for single crystals is expensive and time-consuming, especially ...Growth of high-quality single crystals is of great significance for research of condensed matter physics. The exploration of suitable growing conditions for single crystals is expensive and time-consuming, especially for ternary compounds because of the lack of ternary phase diagram. Here we use machine learning(ML) trained on our experimental data to predict and instruct the growth. Four kinds of ML methods, including support vector machine(SVM), decision tree, random forest and gradient boosting decision tree, are adopted. The SVM method is relatively stable and works well, with an accuracy of 81% in predicting experimental results. By comparison,the accuracy of laboratory reaches 36%. The decision tree model is also used to reveal which features will take critical roles in growing processes.展开更多
A large database is desired for machine learning(ML) technology to make accurate predictions of materials physicochemical properties based on their molecular structure.When a large database is not available,the develo...A large database is desired for machine learning(ML) technology to make accurate predictions of materials physicochemical properties based on their molecular structure.When a large database is not available,the development of proper featurization method based on physicochemical nature of target proprieties can improve the predictive power of ML models with a smaller database.In this work,we show that two new featurization methods,volume occupation spatial matrix and heat contribution spatial matrix,can improve the accuracy in predicting energetic materials' crystal density(ρ_(crystal)) and solid phase enthalpy of formation(H_(f,solid)) using a database containing 451 energetic molecules.Their mean absolute errors are reduced from 0.048 g/cm~3 and 24.67 kcal/mol to 0.035 g/cm~3 and 9.66 kcal/mol,respectively.By leave-one-out-cross-validation,the newly developed ML models can be used to determine the performance of most kinds of energetic materials except cubanes.Our ML models are applied to predict ρ_(crystal) and H_(f,solid) of CHON-based molecules of the 150 million sized PubChem database,and screened out 56 candidates with competitive detonation performance and reasonable chemical structures.With further improvement in future,spatial matrices have the potential of becoming multifunctional ML simulation tools that could provide even better predictions in wider fields of materials science.展开更多
The discovery of novel materials with desired properties is essential to the advancements of energy-related technologies.Despite the rapid development of computational infrastructures and theoretical approaches,progre...The discovery of novel materials with desired properties is essential to the advancements of energy-related technologies.Despite the rapid development of computational infrastructures and theoretical approaches,progress so far has been limited by the empirical and serial nature of experimental work.Fortunately,the situation is changing thanks to the maturation of theoretical tools such as density functional theory,high-throughput screening,crystal structure prediction,and emerging approaches based on machine learning.Together these recent innovations in computational chemistry,data informatics,and machine learning have acted as catalysts for revolutionizing material design and hopefully will lead to faster kinetics in the development of energy-related industries.In this report,recent advances in material discovery methods are reviewed for energy devices.Three paradigms based on empiricism-driven experiments,database-driven high-throughput screening,and data informatics-driven machine learning are discussed critically.Key methodological advancements involved are reviewed including high-throughput screening,crystal structure prediction,and generative models for target material design.Their applications in energy-related devices such as batteries,catalysts,and photovoltaics are selectively showcased.展开更多
In this paper, the modified slip/fracture activation model has been used in order to understand the mechanism of ductile-brittle transition on the R-plane of sapphire during ultra-precision machining by reflecting dir...In this paper, the modified slip/fracture activation model has been used in order to understand the mechanism of ductile-brittle transition on the R-plane of sapphire during ultra-precision machining by reflecting direction of resultant force. Anisotropic characteristics of crack morphology and ductility of machining depending on cutting direction were explained in detail with modified fracture cleavage and plastic deformation parameters. Through the analysis, it was concluded that crack morphologies were mainly determined by the interaction of multiple fracture systems activated while, critical depth of cut was determined by the dominant plastic deformation parameter. In addition to this, by using proportionality relationship between magnitude of resultant force and depth of cut in the ductile region, an empirical model for critical depth of cut was developed.展开更多
The object is to investigate the wear of an atomic force microscope (AFM) diamond tip when conducting micro/nano machining on single crystal silicon surface. The experimental research and theoretical analysis were car...The object is to investigate the wear of an atomic force microscope (AFM) diamond tip when conducting micro/nano machining on single crystal silicon surface. The experimental research and theoretical analysis were carried out on the worn tip in terms of wear rate, wear mechanism and the effect of the tip wear on micro machining process. The wear rate was calculated as 1.7(10～10mm 3/(N·m) by using a theoretical model combined with the experimental results. Through an integration of an AFM observation on the worn tip features with the FEM simulation of the stress distribution, in addition to the unit cutting force calculation on the AFM diamond tip, the wear mechanism of the AFM diamond tip was concluded as mainly chemical wear, and the wear process was also elaborated as well.展开更多
To understand the deformation and removal mechanism of material on nano-scale at ultralow loads,a systemic study on AFM micro/nano-machining on single crystal ailicon is conducted. The results indicate that AFM nano- ...To understand the deformation and removal mechanism of material on nano-scale at ultralow loads,a systemic study on AFM micro/nano-machining on single crystal ailicon is conducted. The results indicate that AFM nano- machining has a precisely dimensional controllability and a good surface quality on nanometer scale.A SEM is adopted to observe nano-machined region and chips,the results indicate that the material removal mechanisms change with the applied normal load. An XPS is used to analyze the changes of chemical composition inside and outside the nano-machined region respectively.The nano-indentation which is conducted with the same AFM diamond tip on the machined region shows a big discrepancy compared with that on the macro-scale. The calculated results show higher nano-hardness and elastic modulus than normal values .This phenomenon on be regarded as the indentation size effect(ISE).展开更多
基金funded by the Strategic Priority Research Program of the Chinese Academy of Sciences (Grant No.XDA17040506)the National Natural Science Foundation of China(62005148/12004235)+2 种基金The Open Competition Mechanism to Select The Best Candidates Project in Jinzhong Science and Technology Bureau (J202101)the DNL Cooperation Fund CAS(DNL180311)the 111 Project (B14041)
文摘Metal-halide hybrid perovskite materials are excellent candidates for solar cells and photoelectric devices.In recent years,machine learning(ML)techniques have developed rapidly in many fields and provided ideas for material discovery and design.ML can be applied to discover new materials quickly and effectively,with significant savings in resources and time compared with traditional experiments and density functional theory(DFT)calculations.In this review,we present the application of ML in per-ovskites and briefly review the recent works in the field of ML-assisted perovskite design.Firstly,the advantages of perovskites in solar cells and the merits of ML applied to perovskites are discussed.Secondly,the workflow of ML in perovskite design and some basic ML algorithms are introduced.Thirdly,the applications of ML in predicting various properties of perovskite materials and devices are reviewed.Finally,we propose some prospects for the future development of this field.The rapid devel-opment of ML technology will largely promote the process of materials science,and ML will become an increasingly popular method for predicting the target properties of materials and devices.
基金supported by the Russian Foundation for Basic Research Projects under Grant No.16-52-48016ИНД_оми(R.Kumar and A.V.Filimonov)。
文摘We investigate the impact of different numbers of positive and negative examples on machine learning for sapphire crystals defects prediction. We obtain the models of crystal growth parameters influence on the sapphire crystal growth. For example, these models allow predicting the defects that occur due to local overcooling of crucible walls in the thermal node leading to the accelerated crystal growth. We also develop the prediction models for obtaining the crystal weight, blocks, cracks, bubbles formation, and total defect characteristics. The models were trained on all data sets and later tested for generalization on testing sets, which did not overlap the training set.During training and testing, we find the recall and precision of prediction, and analyze the correlation among the features. The results have shown that the precision of the neural network method for predicting defects formed by local overcooling of the crucible reached 0.94.
基金Supported by the National Key Research and Development Program of China under Grant Nos 2016YFA0401000 and2017YFA0302901the National Basic Research Program of China under Grant No 2015CB921000+2 种基金the National Natural Science Foundation of China under Grant Nos 11574371,11774399 and 11774398the Beijing Natural Science Foundation(Z180008)the Strategic Priority Research Program of Chinese Academy of Sciences under Grant No XDB28000000
文摘Growth of high-quality single crystals is of great significance for research of condensed matter physics. The exploration of suitable growing conditions for single crystals is expensive and time-consuming, especially for ternary compounds because of the lack of ternary phase diagram. Here we use machine learning(ML) trained on our experimental data to predict and instruct the growth. Four kinds of ML methods, including support vector machine(SVM), decision tree, random forest and gradient boosting decision tree, are adopted. The SVM method is relatively stable and works well, with an accuracy of 81% in predicting experimental results. By comparison,the accuracy of laboratory reaches 36%. The decision tree model is also used to reveal which features will take critical roles in growing processes.
基金support from the Ministry of Education(MOE) Singapore Tier 1 (RG8/20)。
文摘A large database is desired for machine learning(ML) technology to make accurate predictions of materials physicochemical properties based on their molecular structure.When a large database is not available,the development of proper featurization method based on physicochemical nature of target proprieties can improve the predictive power of ML models with a smaller database.In this work,we show that two new featurization methods,volume occupation spatial matrix and heat contribution spatial matrix,can improve the accuracy in predicting energetic materials' crystal density(ρ_(crystal)) and solid phase enthalpy of formation(H_(f,solid)) using a database containing 451 energetic molecules.Their mean absolute errors are reduced from 0.048 g/cm~3 and 24.67 kcal/mol to 0.035 g/cm~3 and 9.66 kcal/mol,respectively.By leave-one-out-cross-validation,the newly developed ML models can be used to determine the performance of most kinds of energetic materials except cubanes.Our ML models are applied to predict ρ_(crystal) and H_(f,solid) of CHON-based molecules of the 150 million sized PubChem database,and screened out 56 candidates with competitive detonation performance and reasonable chemical structures.With further improvement in future,spatial matrices have the potential of becoming multifunctional ML simulation tools that could provide even better predictions in wider fields of materials science.
文摘The discovery of novel materials with desired properties is essential to the advancements of energy-related technologies.Despite the rapid development of computational infrastructures and theoretical approaches,progress so far has been limited by the empirical and serial nature of experimental work.Fortunately,the situation is changing thanks to the maturation of theoretical tools such as density functional theory,high-throughput screening,crystal structure prediction,and emerging approaches based on machine learning.Together these recent innovations in computational chemistry,data informatics,and machine learning have acted as catalysts for revolutionizing material design and hopefully will lead to faster kinetics in the development of energy-related industries.In this report,recent advances in material discovery methods are reviewed for energy devices.Three paradigms based on empiricism-driven experiments,database-driven high-throughput screening,and data informatics-driven machine learning are discussed critically.Key methodological advancements involved are reviewed including high-throughput screening,crystal structure prediction,and generative models for target material design.Their applications in energy-related devices such as batteries,catalysts,and photovoltaics are selectively showcased.
基金supported by the NSF under grant No. CMMI-1844821。
文摘In this paper, the modified slip/fracture activation model has been used in order to understand the mechanism of ductile-brittle transition on the R-plane of sapphire during ultra-precision machining by reflecting direction of resultant force. Anisotropic characteristics of crack morphology and ductility of machining depending on cutting direction were explained in detail with modified fracture cleavage and plastic deformation parameters. Through the analysis, it was concluded that crack morphologies were mainly determined by the interaction of multiple fracture systems activated while, critical depth of cut was determined by the dominant plastic deformation parameter. In addition to this, by using proportionality relationship between magnitude of resultant force and depth of cut in the ductile region, an empirical model for critical depth of cut was developed.
文摘The object is to investigate the wear of an atomic force microscope (AFM) diamond tip when conducting micro/nano machining on single crystal silicon surface. The experimental research and theoretical analysis were carried out on the worn tip in terms of wear rate, wear mechanism and the effect of the tip wear on micro machining process. The wear rate was calculated as 1.7(10～10mm 3/(N·m) by using a theoretical model combined with the experimental results. Through an integration of an AFM observation on the worn tip features with the FEM simulation of the stress distribution, in addition to the unit cutting force calculation on the AFM diamond tip, the wear mechanism of the AFM diamond tip was concluded as mainly chemical wear, and the wear process was also elaborated as well.
基金This project is supported by National Natural ScienceFoundation of China (No.59835180) and Science andTechnology Foundatio
文摘To understand the deformation and removal mechanism of material on nano-scale at ultralow loads,a systemic study on AFM micro/nano-machining on single crystal ailicon is conducted. The results indicate that AFM nano- machining has a precisely dimensional controllability and a good surface quality on nanometer scale.A SEM is adopted to observe nano-machined region and chips,the results indicate that the material removal mechanisms change with the applied normal load. An XPS is used to analyze the changes of chemical composition inside and outside the nano-machined region respectively.The nano-indentation which is conducted with the same AFM diamond tip on the machined region shows a big discrepancy compared with that on the macro-scale. The calculated results show higher nano-hardness and elastic modulus than normal values .This phenomenon on be regarded as the indentation size effect(ISE).
