Non-design roll system crossing seriously affects the plate shape and rolling mill performance.The problem of roll system crossing caused by liner wear was studied.The finite element model of rolling mill was establis...Non-design roll system crossing seriously affects the plate shape and rolling mill performance.The problem of roll system crossing caused by liner wear was studied.The finite element model of rolling mill was established to analyze the relationship between roll system crossing and liner wear.The wear of liner was measured by laser tracker.The range of roll system crossing angle was calculated by considering the amount of stand clearance obtained by numerical simulation.The wear surface morphology of liner was observed and the wear mechanism was analyzed.The liner wear experiment was carried out to analyze the wear amount of the liner.Finally,based on the Archard wear theory,the prediction model of the cross angle of the roll system and the wear amount of the liner was established.Because there are more uncertain factors in the field production,the prediction model cannot be considered one by one.Therefore,the predicted value is smaller than the actual wear value,but it still has great reference.展开更多
The severe environmental problems and the demand for energy urgently require electrocatalysis to replace Haber-Bosch for the nitrogen reduction reaction(NRR).The descriptors and important properties of single-atom and...The severe environmental problems and the demand for energy urgently require electrocatalysis to replace Haber-Bosch for the nitrogen reduction reaction(NRR).The descriptors and important properties of single-atom and homonuclear double-atom catalysts have been preliminarily explored,but the relationship between the inherent properties and catalytic activity of heteronuclear double-atom catalysts with better performance remains unclear.Therefore,it is very significant to explore the prediction expressions of catalytic activity of heteronuclear double-atom catalysts based on their inherent properties and find the rule for selecting catalytic centers.Herein,by summarizing the free energy for the key steps of NRR on 55 catalysts calculated through the first-principle,the expressions of predicting the free energy and the corresponding descriptors are deduced by the machine learning,and the strategy for selecting the appropriate catalytic center is proposed.The selection strategy for the central atom of heteronuclear double-atom catalysts is that the atomic number of central B atom should be between group VB and VIIIB,and the electron difference between central A atom and B atom should be large enough,and the selectivity of NRR or hydrogen evolution reaction(HER)could be calculated through the prediction formula.Moreover,five catalysts are screened to have low limiting potential and excellent selectivity,and are further analyzed by electron transfer.This work explores the relationship between the inherent properties of heteronuclear double-atom catalysts and the catalytic activity,and puts forward the rules for selecting the heteronuclear double-atom catalytic center,which has guiding significance for the experiment.展开更多
Data-driven approach has emerged as a powerful strategy in the construction of structure-performance relationships in organic synthesis.To close the gap between mechanistic understanding and synthetic prediction,we ha...Data-driven approach has emerged as a powerful strategy in the construction of structure-performance relationships in organic synthesis.To close the gap between mechanistic understanding and synthetic prediction,we have made efforts to implement mechanistic knowledge in machine learning modelling of organic transformation,as a way to achieve accurate predictions of reactivity,regio-and stereoselectivity.We have constructed a comprehensive and balanced computational database for target radical transformations(arene C—H functionalization and HAT reaction),which laid the foundation for the reactivity and selectivity prediction.Furthermore,we found that the combination of computational statistics and physical organic descriptors offers a practical solution to build machine learning structure-performance models for reactivity and regioselectivity.To allow machine learning modelling of stereoselectivity,a structured database of asymmetric hydrogenation of olefins was built,and we designed a chemical heuristics-based hierarchical learning approach to effectively use the big data in the early stage of catalysis screening.Our studies reflect a tiny portion of the exciting developments of machine learning in organic chemistry.The synergy between mechanistic knowledge and machine learning will continue to generate a strong momentum to push the limit of reaction performance prediction in organic chemistry.展开更多
Extreme learning machine(ELM)allows for fast learning and better generalization performance than conventional gradient-based learning.However,the possible inclusion of non-optimal weight and bias due to random selecti...Extreme learning machine(ELM)allows for fast learning and better generalization performance than conventional gradient-based learning.However,the possible inclusion of non-optimal weight and bias due to random selection and the need for more hidden neurons adversely influence network usability.Further,choosing the optimal number of hidden nodes for a network usually requires intensive human intervention,which may lead to an ill-conditioned situation.In this context,chemical reaction optimization(CRO)is a meta-heuristic paradigm with increased success in a large number of application areas.It is characterized by faster convergence capability and requires fewer tunable parameters.This study develops a learning framework combining the advantages of ELM and CRO,called extreme learning with chemical reaction optimization(ELCRO).ELCRO simultaneously optimizes the weight and bias vector and number of hidden neurons of a single layer feed-forward neural network without compromising prediction accuracy.We evaluate its performance by predicting the daily volatility and closing prices of BSE indices.Additionally,its performance is compared with three other similarly developed models—ELM based on particle swarm optimization,genetic algorithm,and gradient descent—and find the performance of the proposed algorithm superior.Wilcoxon signed-rank and Diebold–Mariano tests are then conducted to verify the statistical significance of the proposed model.Hence,this model can be used as a promising tool for financial forecasting.展开更多
With the improvements in computer computing ability,data accumulation and rapid algorithm development,the integration of artificial intelligence(AI)and drug synthesis has been accelerated,significantly improving the d...With the improvements in computer computing ability,data accumulation and rapid algorithm development,the integration of artificial intelligence(AI)and drug synthesis has been accelerated,significantly improving the design and synthesis of drug molecules.Recently,data-driven computer-aided synthesis tools have been quickly and widely applied in retrosynthetic analysis,reaction prediction and automated synthesis,which can effectively accelerate the process of drug discovery and development and improve the quality of designed and synthesized drug molecules.Here,we review the development and applications of computer-aided synthesis technology and introduce recent advances in computer-aided drug development from three aspects:computer-aided drug design,computer-aided drug synthesis route design and computer-aided intelligent drug synthesis machines.Furthermore,the challenges and opportunities of computer-aided drug synthesis technology are discussed.展开更多
In order to explore the J^(π)=1+;T=1 states in ^(40)Ca between 11.0 and 12.0MeV,which have been predicted recently,the measurements of the ^(39)K(p,γ)^(40)Ca reaction have been taken.Nine resonances appeared in the ...In order to explore the J^(π)=1+;T=1 states in ^(40)Ca between 11.0 and 12.0MeV,which have been predicted recently,the measurements of the ^(39)K(p,γ)^(40)Ca reaction have been taken.Nine resonances appeared in the region E_(p)=2.7-3.8MeV,and six of them corresponding to E_(p)=2749,3085,3135,3202,3417 and 3708ke were observed for the first time with the(p,γ)reaction.The spin,parity and isospin of the 11.08SMeV state in ^(40)Ca are determined to be J^(π)=1^(+);T=1.The M1 transition strength B(M1)↑of this state from the ground state is 0.24μ_(0)^(2).The result is qualitatively in agreement with the the oretical prediction.展开更多
基金funded by Central Government Guide Local Science and Technology Development Fund Project(No.216Z1602G)Major Science and Technology Projects of Shanxi province,China(No.20191102009).
文摘Non-design roll system crossing seriously affects the plate shape and rolling mill performance.The problem of roll system crossing caused by liner wear was studied.The finite element model of rolling mill was established to analyze the relationship between roll system crossing and liner wear.The wear of liner was measured by laser tracker.The range of roll system crossing angle was calculated by considering the amount of stand clearance obtained by numerical simulation.The wear surface morphology of liner was observed and the wear mechanism was analyzed.The liner wear experiment was carried out to analyze the wear amount of the liner.Finally,based on the Archard wear theory,the prediction model of the cross angle of the roll system and the wear amount of the liner was established.Because there are more uncertain factors in the field production,the prediction model cannot be considered one by one.Therefore,the predicted value is smaller than the actual wear value,but it still has great reference.
基金supports by the National Natural Science Foundation of China(NSFC,52271113)the Natural Science Foundation of Shaanxi Province,China(2020JM 218)+1 种基金the Fundamental Research Funds for the Central Universities(CHD300102311405)HPC platform,Xi’an Jiaotong University。
文摘The severe environmental problems and the demand for energy urgently require electrocatalysis to replace Haber-Bosch for the nitrogen reduction reaction(NRR).The descriptors and important properties of single-atom and homonuclear double-atom catalysts have been preliminarily explored,but the relationship between the inherent properties and catalytic activity of heteronuclear double-atom catalysts with better performance remains unclear.Therefore,it is very significant to explore the prediction expressions of catalytic activity of heteronuclear double-atom catalysts based on their inherent properties and find the rule for selecting catalytic centers.Herein,by summarizing the free energy for the key steps of NRR on 55 catalysts calculated through the first-principle,the expressions of predicting the free energy and the corresponding descriptors are deduced by the machine learning,and the strategy for selecting the appropriate catalytic center is proposed.The selection strategy for the central atom of heteronuclear double-atom catalysts is that the atomic number of central B atom should be between group VB and VIIIB,and the electron difference between central A atom and B atom should be large enough,and the selectivity of NRR or hydrogen evolution reaction(HER)could be calculated through the prediction formula.Moreover,five catalysts are screened to have low limiting potential and excellent selectivity,and are further analyzed by electron transfer.This work explores the relationship between the inherent properties of heteronuclear double-atom catalysts and the catalytic activity,and puts forward the rules for selecting the heteronuclear double-atom catalytic center,which has guiding significance for the experiment.
基金support fromthe National Natural Science Foundation of China(21873081and 22122109,X.H.,22103070,S.-Q.Z.)the Starry Night Science Fund of Zhejiang University Shanghai Institute for Advanced Study(SN-ZJU-SIAS-006,X.H.)+3 种基金Beijing National Laboratory for Molecular Sciences(BNLMS202102,X.H.)the Centerof Chemistry for Frontier Technologies and Key Laboratory of Precise Synthesis of Functional Molecules of Zhejiang Province(PSFM 2021-01,X.H.)the State Key Laboratory of Clean Energy Utilization(ZJUCEU2020007,X.H.)CAS Youth Interdisciplinary Team(JCTD-2021-11,X.H.)。
文摘Data-driven approach has emerged as a powerful strategy in the construction of structure-performance relationships in organic synthesis.To close the gap between mechanistic understanding and synthetic prediction,we have made efforts to implement mechanistic knowledge in machine learning modelling of organic transformation,as a way to achieve accurate predictions of reactivity,regio-and stereoselectivity.We have constructed a comprehensive and balanced computational database for target radical transformations(arene C—H functionalization and HAT reaction),which laid the foundation for the reactivity and selectivity prediction.Furthermore,we found that the combination of computational statistics and physical organic descriptors offers a practical solution to build machine learning structure-performance models for reactivity and regioselectivity.To allow machine learning modelling of stereoselectivity,a structured database of asymmetric hydrogenation of olefins was built,and we designed a chemical heuristics-based hierarchical learning approach to effectively use the big data in the early stage of catalysis screening.Our studies reflect a tiny portion of the exciting developments of machine learning in organic chemistry.The synergy between mechanistic knowledge and machine learning will continue to generate a strong momentum to push the limit of reaction performance prediction in organic chemistry.
文摘Extreme learning machine(ELM)allows for fast learning and better generalization performance than conventional gradient-based learning.However,the possible inclusion of non-optimal weight and bias due to random selection and the need for more hidden neurons adversely influence network usability.Further,choosing the optimal number of hidden nodes for a network usually requires intensive human intervention,which may lead to an ill-conditioned situation.In this context,chemical reaction optimization(CRO)is a meta-heuristic paradigm with increased success in a large number of application areas.It is characterized by faster convergence capability and requires fewer tunable parameters.This study develops a learning framework combining the advantages of ELM and CRO,called extreme learning with chemical reaction optimization(ELCRO).ELCRO simultaneously optimizes the weight and bias vector and number of hidden neurons of a single layer feed-forward neural network without compromising prediction accuracy.We evaluate its performance by predicting the daily volatility and closing prices of BSE indices.Additionally,its performance is compared with three other similarly developed models—ELM based on particle swarm optimization,genetic algorithm,and gradient descent—and find the performance of the proposed algorithm superior.Wilcoxon signed-rank and Diebold–Mariano tests are then conducted to verify the statistical significance of the proposed model.Hence,this model can be used as a promising tool for financial forecasting.
基金This work was supported by grants from the National Natural Science Foundation of China(Nos.81922064,22177083,81874290,81803755)Sichuan University Postdoctoral Interdisciplinary Innovation Fund,and West China Nursing Discipline Development Special Fund Project,Sichuan University(No.HXHL21011).
文摘With the improvements in computer computing ability,data accumulation and rapid algorithm development,the integration of artificial intelligence(AI)and drug synthesis has been accelerated,significantly improving the design and synthesis of drug molecules.Recently,data-driven computer-aided synthesis tools have been quickly and widely applied in retrosynthetic analysis,reaction prediction and automated synthesis,which can effectively accelerate the process of drug discovery and development and improve the quality of designed and synthesized drug molecules.Here,we review the development and applications of computer-aided synthesis technology and introduce recent advances in computer-aided drug development from three aspects:computer-aided drug design,computer-aided drug synthesis route design and computer-aided intelligent drug synthesis machines.Furthermore,the challenges and opportunities of computer-aided drug synthesis technology are discussed.
文摘In order to explore the J^(π)=1+;T=1 states in ^(40)Ca between 11.0 and 12.0MeV,which have been predicted recently,the measurements of the ^(39)K(p,γ)^(40)Ca reaction have been taken.Nine resonances appeared in the region E_(p)=2.7-3.8MeV,and six of them corresponding to E_(p)=2749,3085,3135,3202,3417 and 3708ke were observed for the first time with the(p,γ)reaction.The spin,parity and isospin of the 11.08SMeV state in ^(40)Ca are determined to be J^(π)=1^(+);T=1.The M1 transition strength B(M1)↑of this state from the ground state is 0.24μ_(0)^(2).The result is qualitatively in agreement with the the oretical prediction.
