In this paper, an efficient methodology for synthesizing the indirect work exchange networks(WEN) considering isothermal process and adiabatic process respectively based on transshipment model is first proposed. In co...In this paper, an efficient methodology for synthesizing the indirect work exchange networks(WEN) considering isothermal process and adiabatic process respectively based on transshipment model is first proposed. In contrast with superstructure method, the transshipment model is easier to obtain the minimum utility consumption taken as the objective function and more convenient for us to attain the optimal network configuration for further minimizing the number of units. Different from division of temperature intervals in heat exchange networks,different pressure intervals are gained according to the maximum compression/expansion ratio in consideration of operating principles of indirect work exchangers and the characteristics of no pressure constraints for stream matches. The presented approach for WEN synthesis is a linear programming model applied to the isothermal process, but for indirect work exchange networks with adiabatic process, a nonlinear programming model needs establishing. Additionally, temperatures should be regarded as decision variables limited to the range between inlet and outlet temperatures in each sub-network. The constructed transshipment model can be solved first to get the minimum utility consumption and further to determine the minimum number of units by merging the adjacent pressure intervals on the basis of the proposed merging methods, which is proved to be effective through exergy analysis at the level of units structures. Finally, two cases are calculated to confirm it is dramatically feasible and effective that the optimal WEN configuration can be gained by the proposed method.展开更多
Due to the deterioration of serious energy dilemma,energy-conservation and emission–reduction have been the strategic target in the past decades,thus people have identified the vital importance of higher energy effic...Due to the deterioration of serious energy dilemma,energy-conservation and emission–reduction have been the strategic target in the past decades,thus people have identified the vital importance of higher energy efficiency and the influence of lower carbon development.Since work exchange network is a significant part of energy recovery system,its optima design will have dramatically significant effect on energy consumption reduction in chemical process system.With an extension of the developed transshipment model in isothermal process,a novel step-wise methodology for synthesis of direct work exchange network(WEN)in adiabatic process involving heat integration is first proposed in this paper,where a nonlinear programming(NLP)model is formulated by regarding the minimum utility consumption as objective function and optimizing the initial WEN in accordance with the presented matching rules to get the optimized WEN configuration at first.Furthermore,we focus on the work exchange network synthesis with heat integration to attain the minimal total annual cost(TAC)with the introduction of heat-exchange equipment that is achieved by the following strategies in sequence:introducing heat-exchange equipment directly,adjusting the work quantity of the adjacent utility compressors or expanders,and approximating upper/lower pressure limits consequently to obtain considerable cost savings of expanders or compressors and work utility.Finally,a case taken from the literature is studied to illustrate the feasibility and effectiveness of the proposed method.展开更多
Binding kinetic properties of protein–ligand complexes are crucial factors affecting the drug potency.Nevertheless,the current in silico techniques are insufficient in providing accurate and robust predictions for bi...Binding kinetic properties of protein–ligand complexes are crucial factors affecting the drug potency.Nevertheless,the current in silico techniques are insufficient in providing accurate and robust predictions for binding kinetic properties.To this end,this work develops a variety of binding kinetic models for predicting a critical binding kinetic property,dissociation rate constant,using eight machine learning(ML)methods(Bayesian Neural Network(BNN),partial least squares regression,Bayesian ridge,Gaussian process regression,principal component regression,random forest,support vector machine,extreme gradient boosting)and the descriptors of the van der Waals/electrostatic interaction energies.These eight models are applied to two case studies involving the HSP90 and RIP1 kinase inhibitors.Both regression results of two case studies indicate that the BNN model has the state-of-the-art prediction accuracy(HSP90:R^(2)_(test)=0:947,MAE_(test)=0.184,rtest=0.976,RMSE_(test)=0.220;RIP1 kinase:R^(2)_(test)=0:745,MAE_(test)=0.188,rtest=0.961,RMSE_(test)=0.290)in comparison with other seven ML models.展开更多
The selection of chemical reactions is directly related to the quality of synthesis pathways,so a reasonable reaction evaluation metric plays a crucial role in the design and planning of synthesis pathways.Since react...The selection of chemical reactions is directly related to the quality of synthesis pathways,so a reasonable reaction evaluation metric plays a crucial role in the design and planning of synthesis pathways.Since reaction conditions also need to be considered in synthesis pathway design,a reaction metric that combines reaction time,temperature,and yield is required for chemical reactions of different reaction agents.In this study,a chemical reaction graph descriptor which includes the atom-atom mapping relationship is proposed to effectively describe reactions.Then,through pre-training using graph contrastive learning and fine-tuning through supervised learning,we establish a model for generating the probability of reaction superiority(RSscore).Finally,to validate the effectiveness of the current evaluation index,RSscore is applied in two applications,namely reaction evaluation and synthesis routes analysis,which proves that the RSscore provides an important agents-considered evaluation criterion for computer-aided synthesis planning(CASP).展开更多
Small-molecule drugs are essential for maintaining human health. The objective of this study is to identify a molecule that can inhibit the Factor Xa protein and be easily procured. An optimization-based de novo drug ...Small-molecule drugs are essential for maintaining human health. The objective of this study is to identify a molecule that can inhibit the Factor Xa protein and be easily procured. An optimization-based de novo drug design framework, Drug CAMD, that integrates a deep learning model with a mixed-integer nonlinear programming model is used for designing drug candidates. Within this framework, a virtual chemical library is specifically tailored to inhibit Factor Xa. To further filter and narrow down the lead compounds from the designed compounds, comprehensive approaches involving molecular docking,binding pose metadynamics(BPMD), binding free energy calculations, and enzyme activity inhibition analysis are utilized. To maximize efficiency in terms of time and resources, molecules for in vitro activity testing are initially selected from commercially available portions of customized virtual chemical libraries. In vitro studies assessing inhibitor activities have confirmed that the compound EN300-331859shows potential Factor Xa inhibition, with an IC_(50)value of 34.57 μmol·L^(-1). Through in silico molecular docking and BPMD, the most plausible binding pose for the EN300-331859-Factor Xa complex are identified. The estimated binding free energy values correlate well with the results obtained from biological assays. Consequently, EN300-331859 is identified as a novel and effective sub-micromolar inhibitor of Factor Xa.展开更多
Over the last three decades,flexibility and controllability considerations for heat exchanger networks(HENs)have received great attention,respectively.However,they should be simultaneously incorporated in HEN synthesi...Over the last three decades,flexibility and controllability considerations for heat exchanger networks(HENs)have received great attention,respectively.However,they should be simultaneously incorporated in HEN synthesis to allow the economic performance to be achievable in a practical operating environment.This paper proposes a method for simultaneous synthesis of flexible and controllable HEN by considering their coupling.The key idea is to add the bypasses with optimized initial fractions and positions to explore such coupling,and consequently enabling HENs to be operated successfully over a range of disturbance variations.These are implemented by identifying and quantifying disturbance propagations,and then examining the sensitivity of bypasses to the entire HEN.In this way,the superstructurebased mixed integer non-linear programming(MINLP)with objective function of minimizing the total annual cost is formulated.A case study is used to demonstrate the application of the proposed method.Quantitative measures and dynamic simulation show the ability to provide the satisfactory flexibility and controllability of the obtained HEN.展开更多
Because of its paramount importance in the successful industrial control strategy of a given heat exchanger network(HEN),the control structure designs for providing appropriate manipulated variable(MV)and controlled v...Because of its paramount importance in the successful industrial control strategy of a given heat exchanger network(HEN),the control structure designs for providing appropriate manipulated variable(MV)and controlled variable pairings have received considerable attention.However,quite frequently HENs with such control structures face the problem of hard constraints,typically holding the HENs at less controlled operating space.So both the MV pairings and the above control pairings should be considered to design a control structure.This paper investigates the systematic incorporation of the two pairings,and presents a methodology for designing such two-tier control structure.This is developed based on the sequential strategy,coupling an indirect-tier with direct-tier control structure design,wherein the intention is realized in the former stage and the latter is implemented for further optimization.The MV identification and pairing are achieved through variations in heat load of heat exchangers to design the indirect-tier control structure.Then the direct-tier control structure is followed the relative gain array pairing rules.With the proposed methodology,on the one hand,it generates an explicit connection between the MV pairings and the HEN configuration,and the quantitative interaction measure is improved to avoid the multiple solutions to break the relationship among all the control pairings into individuals;on the other hand,a two-tier control structure reveals control potentials and control system design requirements,this may avoid complex and economically unfavourable control and HEN structures.The application of proposed framework is illustrated with two cases involving the dynamic simulation analysis,the quantitative assessment and the random test.展开更多
Integrating multiple systems into one has become an important trend in Process Systems Engineering research field since there is strong demand from the modern industries. In this study, a stage-wise superstructurebase...Integrating multiple systems into one has become an important trend in Process Systems Engineering research field since there is strong demand from the modern industries. In this study, a stage-wise superstructurebased method is proposed to synthesize a combined mass and heat exchange network(CM&HEN) which has two parts as the mass exchange network(MEN) and heat exchange network(HEN) involved. To express the possible heat exchange requirements resulted from mass exchange operations, a so called "indistinct HEN superstructure(IHS)", which can contain the all potential matches between streams, is constructed at first. Then, a non-linear programming(NLP) mathematical model is established for the simultaneous synthesis and optimization of networks. Therein, the interaction between mass exchange and heat exchange is modeling formulated.The NLP model has later been examined using an example from literature, and the effectiveness of the proposed method has been demonstrated with the results.展开更多
Chemical industry is always seeking opportunities to efficiently and economically convert raw materials to commodity chemicals and higher value-added chemicalbased products.The life cycles of chemical products involve...Chemical industry is always seeking opportunities to efficiently and economically convert raw materials to commodity chemicals and higher value-added chemicalbased products.The life cycles of chemical products involve the procedures of conceptual product designs,experimental investigations,sustainable manufactures through appropriate chemical processes and waste disposals.During these periods,one of the most important keys is the molecular property prediction models associating molecular structures with product properties.In this paper,a framework combining quantum mechanics and quantitative structure-property relationship is established for fast molecular property predictions,such as activity coefficient,and so forth.The workflow of framework consists of three steps.In the first step,a database is created for collections of basic molecular information;in the second step,quantum mechanics-based calculations are performed to predict quantum mechanics-based/derived molecular properties(pseudo experimental data),which are stored in a database and further provided for the developments of quantitative structure-property relationship methods for fast predictions of properties in the third step.The whole framework has been carried out within a molecular property prediction toolbox.Two case studies highlighting different aspects of the toolbox involving the predictions of heats of reaction and solid-liquid phase equilibriums are presented.展开更多
To study the dynamic behavior of a process,time-resolved data are collected at different time instants during each of a series of experiments,which are usually designed with the design of experiments or the design of ...To study the dynamic behavior of a process,time-resolved data are collected at different time instants during each of a series of experiments,which are usually designed with the design of experiments or the design of dynamic experiments methodologies.For utilizing such time-resolved data to model the dynamic behavior,dynamic response surface methodology(DRSM),a datadriven modeling method,has been proposed.Two approaches can be adopted in the estimation of the model parameters:stepwise regression,used in several of previous publications,and Lasso regression,which is newly incorporated in this paper for the estimation of DRSM models.Here,we show that both approaches yield similarly accurate models,while the computational time of Lasso is on average two magnitude smaller.Two case studies are performed to show the advantages of the proposed method.In the first case study,where the concentrations of different species are modeled directly,DRSM method provides more accurate models compared to the models in the literature.The second case study,where the reaction extents are modeled instead of the species concentrations,illustrates the versatility of the DRSM methodology.Therefore,DRSM with Lasso regression can provide faster and more accurate datadriven models for a variety of organic synthesis datasets.展开更多
基金Supported by the National Natural Science Foundation of China(21576036 and 21776035)
文摘In this paper, an efficient methodology for synthesizing the indirect work exchange networks(WEN) considering isothermal process and adiabatic process respectively based on transshipment model is first proposed. In contrast with superstructure method, the transshipment model is easier to obtain the minimum utility consumption taken as the objective function and more convenient for us to attain the optimal network configuration for further minimizing the number of units. Different from division of temperature intervals in heat exchange networks,different pressure intervals are gained according to the maximum compression/expansion ratio in consideration of operating principles of indirect work exchangers and the characteristics of no pressure constraints for stream matches. The presented approach for WEN synthesis is a linear programming model applied to the isothermal process, but for indirect work exchange networks with adiabatic process, a nonlinear programming model needs establishing. Additionally, temperatures should be regarded as decision variables limited to the range between inlet and outlet temperatures in each sub-network. The constructed transshipment model can be solved first to get the minimum utility consumption and further to determine the minimum number of units by merging the adjacent pressure intervals on the basis of the proposed merging methods, which is proved to be effective through exergy analysis at the level of units structures. Finally, two cases are calculated to confirm it is dramatically feasible and effective that the optimal WEN configuration can be gained by the proposed method.
基金Supported by the National Natural Science Foundation of China(21576036,21406026)
文摘Due to the deterioration of serious energy dilemma,energy-conservation and emission–reduction have been the strategic target in the past decades,thus people have identified the vital importance of higher energy efficiency and the influence of lower carbon development.Since work exchange network is a significant part of energy recovery system,its optima design will have dramatically significant effect on energy consumption reduction in chemical process system.With an extension of the developed transshipment model in isothermal process,a novel step-wise methodology for synthesis of direct work exchange network(WEN)in adiabatic process involving heat integration is first proposed in this paper,where a nonlinear programming(NLP)model is formulated by regarding the minimum utility consumption as objective function and optimizing the initial WEN in accordance with the presented matching rules to get the optimized WEN configuration at first.Furthermore,we focus on the work exchange network synthesis with heat integration to attain the minimal total annual cost(TAC)with the introduction of heat-exchange equipment that is achieved by the following strategies in sequence:introducing heat-exchange equipment directly,adjusting the work quantity of the adjacent utility compressors or expanders,and approximating upper/lower pressure limits consequently to obtain considerable cost savings of expanders or compressors and work utility.Finally,a case taken from the literature is studied to illustrate the feasibility and effectiveness of the proposed method.
基金financial supports of“the Fundamental Research Funds for the Central Universities”(DUT22YG218),NSFC(22278053,22078041)China Postdoctoral Science Foundation(2022M710578)“the Dalian High-level Talents Innovation Support Program”(2021RQ105).
文摘Binding kinetic properties of protein–ligand complexes are crucial factors affecting the drug potency.Nevertheless,the current in silico techniques are insufficient in providing accurate and robust predictions for binding kinetic properties.To this end,this work develops a variety of binding kinetic models for predicting a critical binding kinetic property,dissociation rate constant,using eight machine learning(ML)methods(Bayesian Neural Network(BNN),partial least squares regression,Bayesian ridge,Gaussian process regression,principal component regression,random forest,support vector machine,extreme gradient boosting)and the descriptors of the van der Waals/electrostatic interaction energies.These eight models are applied to two case studies involving the HSP90 and RIP1 kinase inhibitors.Both regression results of two case studies indicate that the BNN model has the state-of-the-art prediction accuracy(HSP90:R^(2)_(test)=0:947,MAE_(test)=0.184,rtest=0.976,RMSE_(test)=0.220;RIP1 kinase:R^(2)_(test)=0:745,MAE_(test)=0.188,rtest=0.961,RMSE_(test)=0.290)in comparison with other seven ML models.
基金the financial support of the National Natural Science Foundation of China(22078041,22278053)Dalian High-level Talents Innovation Support Program(2021RQ105)the Fundamental Research Funds for China Central Universities(DUT22QN209,DUT22LAB608).
文摘The selection of chemical reactions is directly related to the quality of synthesis pathways,so a reasonable reaction evaluation metric plays a crucial role in the design and planning of synthesis pathways.Since reaction conditions also need to be considered in synthesis pathway design,a reaction metric that combines reaction time,temperature,and yield is required for chemical reactions of different reaction agents.In this study,a chemical reaction graph descriptor which includes the atom-atom mapping relationship is proposed to effectively describe reactions.Then,through pre-training using graph contrastive learning and fine-tuning through supervised learning,we establish a model for generating the probability of reaction superiority(RSscore).Finally,to validate the effectiveness of the current evaluation index,RSscore is applied in two applications,namely reaction evaluation and synthesis routes analysis,which proves that the RSscore provides an important agents-considered evaluation criterion for computer-aided synthesis planning(CASP).
基金financial supports of the National Natural Science Foundation of China (22078041, 22278053,22208042)Dalian High-level Talents Innovation Support Program (2023RQ059)“the Fundamental Research Funds for the Central Universities (DUT20JC41, DUT22YG218)”。
文摘Small-molecule drugs are essential for maintaining human health. The objective of this study is to identify a molecule that can inhibit the Factor Xa protein and be easily procured. An optimization-based de novo drug design framework, Drug CAMD, that integrates a deep learning model with a mixed-integer nonlinear programming model is used for designing drug candidates. Within this framework, a virtual chemical library is specifically tailored to inhibit Factor Xa. To further filter and narrow down the lead compounds from the designed compounds, comprehensive approaches involving molecular docking,binding pose metadynamics(BPMD), binding free energy calculations, and enzyme activity inhibition analysis are utilized. To maximize efficiency in terms of time and resources, molecules for in vitro activity testing are initially selected from commercially available portions of customized virtual chemical libraries. In vitro studies assessing inhibitor activities have confirmed that the compound EN300-331859shows potential Factor Xa inhibition, with an IC_(50)value of 34.57 μmol·L^(-1). Through in silico molecular docking and BPMD, the most plausible binding pose for the EN300-331859-Factor Xa complex are identified. The estimated binding free energy values correlate well with the results obtained from biological assays. Consequently, EN300-331859 is identified as a novel and effective sub-micromolar inhibitor of Factor Xa.
基金Supported by the National Natural Science Foundation of China(21576036,21776035)
文摘Over the last three decades,flexibility and controllability considerations for heat exchanger networks(HENs)have received great attention,respectively.However,they should be simultaneously incorporated in HEN synthesis to allow the economic performance to be achievable in a practical operating environment.This paper proposes a method for simultaneous synthesis of flexible and controllable HEN by considering their coupling.The key idea is to add the bypasses with optimized initial fractions and positions to explore such coupling,and consequently enabling HENs to be operated successfully over a range of disturbance variations.These are implemented by identifying and quantifying disturbance propagations,and then examining the sensitivity of bypasses to the entire HEN.In this way,the superstructurebased mixed integer non-linear programming(MINLP)with objective function of minimizing the total annual cost is formulated.A case study is used to demonstrate the application of the proposed method.Quantitative measures and dynamic simulation show the ability to provide the satisfactory flexibility and controllability of the obtained HEN.
基金financial support from Jiangsu Collaborative Innovation Center for Cultural Creativity (XYN1911)the National Natural Science Foundation of China (22008023+1 种基金21776035)Natural Science Foundation of Jiangsu Education Department (20KJB510041)
文摘Because of its paramount importance in the successful industrial control strategy of a given heat exchanger network(HEN),the control structure designs for providing appropriate manipulated variable(MV)and controlled variable pairings have received considerable attention.However,quite frequently HENs with such control structures face the problem of hard constraints,typically holding the HENs at less controlled operating space.So both the MV pairings and the above control pairings should be considered to design a control structure.This paper investigates the systematic incorporation of the two pairings,and presents a methodology for designing such two-tier control structure.This is developed based on the sequential strategy,coupling an indirect-tier with direct-tier control structure design,wherein the intention is realized in the former stage and the latter is implemented for further optimization.The MV identification and pairing are achieved through variations in heat load of heat exchangers to design the indirect-tier control structure.Then the direct-tier control structure is followed the relative gain array pairing rules.With the proposed methodology,on the one hand,it generates an explicit connection between the MV pairings and the HEN configuration,and the quantitative interaction measure is improved to avoid the multiple solutions to break the relationship among all the control pairings into individuals;on the other hand,a two-tier control structure reveals control potentials and control system design requirements,this may avoid complex and economically unfavourable control and HEN structures.The application of proposed framework is illustrated with two cases involving the dynamic simulation analysis,the quantitative assessment and the random test.
基金Supported by the Fundamental Research Funds for the Central Universities of China(DUT14RC(3)046)China Postdoctoral Science Foundation(2014M551091)the National Natural Science Foundation of China(21406026)
文摘Integrating multiple systems into one has become an important trend in Process Systems Engineering research field since there is strong demand from the modern industries. In this study, a stage-wise superstructurebased method is proposed to synthesize a combined mass and heat exchange network(CM&HEN) which has two parts as the mass exchange network(MEN) and heat exchange network(HEN) involved. To express the possible heat exchange requirements resulted from mass exchange operations, a so called "indistinct HEN superstructure(IHS)", which can contain the all potential matches between streams, is constructed at first. Then, a non-linear programming(NLP) mathematical model is established for the simultaneous synthesis and optimization of networks. Therein, the interaction between mass exchange and heat exchange is modeling formulated.The NLP model has later been examined using an example from literature, and the effectiveness of the proposed method has been demonstrated with the results.
基金The authors are grateful for the financial supports of the National Natural Science Foundation of China(Grant Nos.22078041 and 21808025)the Fundamental Research Funds for the Central Universities(Grant No.DUT20JC41).
文摘Chemical industry is always seeking opportunities to efficiently and economically convert raw materials to commodity chemicals and higher value-added chemicalbased products.The life cycles of chemical products involve the procedures of conceptual product designs,experimental investigations,sustainable manufactures through appropriate chemical processes and waste disposals.During these periods,one of the most important keys is the molecular property prediction models associating molecular structures with product properties.In this paper,a framework combining quantum mechanics and quantitative structure-property relationship is established for fast molecular property predictions,such as activity coefficient,and so forth.The workflow of framework consists of three steps.In the first step,a database is created for collections of basic molecular information;in the second step,quantum mechanics-based calculations are performed to predict quantum mechanics-based/derived molecular properties(pseudo experimental data),which are stored in a database and further provided for the developments of quantitative structure-property relationship methods for fast predictions of properties in the third step.The whole framework has been carried out within a molecular property prediction toolbox.Two case studies highlighting different aspects of the toolbox involving the predictions of heats of reaction and solid-liquid phase equilibriums are presented.
基金Yachao Dong is grateful for the financial support of Fundamental Research Funds for the Central Universities(Grant No.DUT20RC(3)070).
文摘To study the dynamic behavior of a process,time-resolved data are collected at different time instants during each of a series of experiments,which are usually designed with the design of experiments or the design of dynamic experiments methodologies.For utilizing such time-resolved data to model the dynamic behavior,dynamic response surface methodology(DRSM),a datadriven modeling method,has been proposed.Two approaches can be adopted in the estimation of the model parameters:stepwise regression,used in several of previous publications,and Lasso regression,which is newly incorporated in this paper for the estimation of DRSM models.Here,we show that both approaches yield similarly accurate models,while the computational time of Lasso is on average two magnitude smaller.Two case studies are performed to show the advantages of the proposed method.In the first case study,where the concentrations of different species are modeled directly,DRSM method provides more accurate models compared to the models in the literature.The second case study,where the reaction extents are modeled instead of the species concentrations,illustrates the versatility of the DRSM methodology.Therefore,DRSM with Lasso regression can provide faster and more accurate datadriven models for a variety of organic synthesis datasets.
