Missing values in radionuclide diffusion datasets can undermine the predictive accuracy and robustness of the machine learning(ML)models.In this study,regression-based missing data imputation method using a light grad...Missing values in radionuclide diffusion datasets can undermine the predictive accuracy and robustness of the machine learning(ML)models.In this study,regression-based missing data imputation method using a light gradient boosting machine(LGBM)algorithm was employed to impute more than 60%of the missing data,establishing a radionuclide diffusion dataset containing 16 input features and 813 instances.The effective diffusion coefficient(D_(e))was predicted using ten ML models.The predictive accuracy of the ensemble meta-models,namely LGBM-extreme gradient boosting(XGB)and LGBM-categorical boosting(CatB),surpassed that of the other ML models,with R^(2)values of 0.94.The models were applied to predict the D_(e)values of EuEDTA^(−)and HCrO_(4)^(−)in saturated compacted bentonites at compactions ranging from 1200 to 1800 kg/m^(3),which were measured using a through-diffusion method.The generalization ability of the LGBM-XGB model surpassed that of LGB-CatB in predicting the D_(e)of HCrO_(4)^(−).Shapley additive explanations identified total porosity as the most significant influencing factor.Additionally,the partial dependence plot analysis technique yielded clearer results in the univariate correlation analysis.This study provides a regression imputation technique to refine radionuclide diffusion datasets,offering deeper insights into analyzing the diffusion mechanism of radionuclides and supporting the safety assessment of the geological disposal of high-level radioactive waste.展开更多
An appropriate flow mode of electrolyte has a positive effect on process efficiency, surface roughness, and machining accuracy in the electrochemical machining（ECM） process. In this study, a new dynamic lateral flow...An appropriate flow mode of electrolyte has a positive effect on process efficiency, surface roughness, and machining accuracy in the electrochemical machining（ECM） process. In this study, a new dynamic lateral flow mode, in which the electrolyte flows from the leading edge to the trailing edge, was proposed in trepanning ECM of a diffuser. Then a numerical model of the channel was set up and simulated by using computational fluid dynamics software. The result showed that the distribution of the flow field was comparatively uniform in the inter-electrode gap. Furthermore, a fixture was designed to realize this new flow mode and then corresponding experiments were carried out. The experimental results illustrated that the feeding rate of the cathode reached 2 mm/min, the best taper angle was about 0.4°, and the best surface roughness was up to Ra= 0.115 lm. It reflects that this flow mode is suitable and effective, and can also be applied to machining other complex structures in trepanning ECM.展开更多
Polyvinylpyrrolidone K-30(PVP) was introduced into the preparation of nanozero-valent iron(n ZVI) and the traditional liquid-phase reduction was improved. The introduction of PVP simplified the traditional method.The ...Polyvinylpyrrolidone K-30(PVP) was introduced into the preparation of nanozero-valent iron(n ZVI) and the traditional liquid-phase reduction was improved. The introduction of PVP simplified the traditional method.The n ZVI prepared with this new approach showed excellent surface characters and high performance on the removal of cadmium. TEM results showed that the aggregates of n ZVI can reach to several micrometers in length but less than 100 nm in diameter. The iron particles that were enclosed by a layer of oxide film that is less than10 nm, demonstrated that the n ZVI possesses a core–shell structure. BET results indicate that the specific surface area of the n ZVI was 20.3159 m^2g^(-1). A three factor and three level orthogonal experiment was employed to find out the dominant factor that affects the removal rate of cadmium by n ZVI. Based on the range values, the prominence order of each factor was: initial p H of the solution N initial concentration of cadmium N dosage of n ZVI, the range was 96.453, 3.294 and 1.747, respectively. A simulation was performed under the same condition and a same conclusion was derived, this consistence confirmed the validity of the conclusion that p H is the most significant factor that affects the adsorption efficiency.展开更多
This study guides the discovery of sustainable high-performance polymer membranes for organic binary solvent separations.We focus on solvent diffusivity in polymers,a key factor in quantifying solvent transport.Tradit...This study guides the discovery of sustainable high-performance polymer membranes for organic binary solvent separations.We focus on solvent diffusivity in polymers,a key factor in quantifying solvent transport.Traditional experimental and computational methods for determining diffusivity are time-and resource-intensive,while current machine learning(ML)models often lack accuracy outside their training domains.To overcome this,we fuse experimental and simulated diffusivity data to train physics-enforced multi-task ML models,achieving more robust predictions in unseen chemical spaces and outperforming single-task models in data-limited scenarios.Next,we address the challenge of identifying optimal membranes for a model toluene-heptane separation,identifying polyvinyl chloride(PVC)as the optimal membrane among 13,000 polymers,consistent with literature findings,thereby validating our methodology.Expanding our search,we screen 1 million publicly available and 7 million chemically recyclable polymers,identifying greener halogen-free alternatives to PVC.This capability is expected to advance membrane design for solvent separations.展开更多
The equilibrium and kinetic characteristics of the adsorption of erythromycin to Sepabeads SP825 were determined.The equilibrium data in a batch system was well described by a Langmuir isotherm.The separation performa...The equilibrium and kinetic characteristics of the adsorption of erythromycin to Sepabeads SP825 were determined.The equilibrium data in a batch system was well described by a Langmuir isotherm.The separation performance was investigated in a fixed-bed system with respect to the adsorption superficial velocity,ionic strength and pH.A mathematical model was used to simulate the mass transfer mechanism,taking film mass transfer,pore diffusion and axial dispersion into account.The model predictions were consistent with the experi-mental data and were consequently used to determine the mass transfer coefficients.展开更多
基金supported by the National Natural Science Foundation of China(No.12475340 and 12375350)Special Branch project of South Taihu Lakethe Scientific Research Fund of Zhejiang Provincial Education Department(No.Y202456326).
文摘Missing values in radionuclide diffusion datasets can undermine the predictive accuracy and robustness of the machine learning(ML)models.In this study,regression-based missing data imputation method using a light gradient boosting machine(LGBM)algorithm was employed to impute more than 60%of the missing data,establishing a radionuclide diffusion dataset containing 16 input features and 813 instances.The effective diffusion coefficient(D_(e))was predicted using ten ML models.The predictive accuracy of the ensemble meta-models,namely LGBM-extreme gradient boosting(XGB)and LGBM-categorical boosting(CatB),surpassed that of the other ML models,with R^(2)values of 0.94.The models were applied to predict the D_(e)values of EuEDTA^(−)and HCrO_(4)^(−)in saturated compacted bentonites at compactions ranging from 1200 to 1800 kg/m^(3),which were measured using a through-diffusion method.The generalization ability of the LGBM-XGB model surpassed that of LGB-CatB in predicting the D_(e)of HCrO_(4)^(−).Shapley additive explanations identified total porosity as the most significant influencing factor.Additionally,the partial dependence plot analysis technique yielded clearer results in the univariate correlation analysis.This study provides a regression imputation technique to refine radionuclide diffusion datasets,offering deeper insights into analyzing the diffusion mechanism of radionuclides and supporting the safety assessment of the geological disposal of high-level radioactive waste.
基金co-supported by the National Natural Science Foundation of China (51675271)–ChinaKey Project of Jiangsu Provincial Research and Development (BE2015160)–ChinaFundamental Research Funds for the Central Universities (NE 2017003)–China
文摘An appropriate flow mode of electrolyte has a positive effect on process efficiency, surface roughness, and machining accuracy in the electrochemical machining（ECM） process. In this study, a new dynamic lateral flow mode, in which the electrolyte flows from the leading edge to the trailing edge, was proposed in trepanning ECM of a diffuser. Then a numerical model of the channel was set up and simulated by using computational fluid dynamics software. The result showed that the distribution of the flow field was comparatively uniform in the inter-electrode gap. Furthermore, a fixture was designed to realize this new flow mode and then corresponding experiments were carried out. The experimental results illustrated that the feeding rate of the cathode reached 2 mm/min, the best taper angle was about 0.4°, and the best surface roughness was up to Ra= 0.115 lm. It reflects that this flow mode is suitable and effective, and can also be applied to machining other complex structures in trepanning ECM.
基金Supported by the National Natural Science Foundation of China(51278147)the Funds for Creative Research Groups of China(51121062)State Key Laboratory of Urban Water Resource and Environment(Harbin Institute of Technology)(2014TS02)
文摘Polyvinylpyrrolidone K-30(PVP) was introduced into the preparation of nanozero-valent iron(n ZVI) and the traditional liquid-phase reduction was improved. The introduction of PVP simplified the traditional method.The n ZVI prepared with this new approach showed excellent surface characters and high performance on the removal of cadmium. TEM results showed that the aggregates of n ZVI can reach to several micrometers in length but less than 100 nm in diameter. The iron particles that were enclosed by a layer of oxide film that is less than10 nm, demonstrated that the n ZVI possesses a core–shell structure. BET results indicate that the specific surface area of the n ZVI was 20.3159 m^2g^(-1). A three factor and three level orthogonal experiment was employed to find out the dominant factor that affects the removal rate of cadmium by n ZVI. Based on the range values, the prominence order of each factor was: initial p H of the solution N initial concentration of cadmium N dosage of n ZVI, the range was 96.453, 3.294 and 1.747, respectively. A simulation was performed under the same condition and a same conclusion was derived, this consistence confirmed the validity of the conclusion that p H is the most significant factor that affects the adsorption efficiency.
基金the Office of Naval Research through a multidisciplinary university research initiative(MURI)for their funding support,We would also like to acknowledge Dr.Kuan-Hsuan Shen for their valuable support in building the simulation pipeline.We also extend a thank you to Dr.Lihua Chen for her guidance in the initial stage of the work.This research is supported in part through research cyber-infrastructure resources and services provided by the Partnership for an Advanced Computing Environment(PACE)at the Georgia Institute of Technology and XSEDE/ACCESS for computational support through Grant No.TG-DMR080058N.
文摘This study guides the discovery of sustainable high-performance polymer membranes for organic binary solvent separations.We focus on solvent diffusivity in polymers,a key factor in quantifying solvent transport.Traditional experimental and computational methods for determining diffusivity are time-and resource-intensive,while current machine learning(ML)models often lack accuracy outside their training domains.To overcome this,we fuse experimental and simulated diffusivity data to train physics-enforced multi-task ML models,achieving more robust predictions in unseen chemical spaces and outperforming single-task models in data-limited scenarios.Next,we address the challenge of identifying optimal membranes for a model toluene-heptane separation,identifying polyvinyl chloride(PVC)as the optimal membrane among 13,000 polymers,consistent with literature findings,thereby validating our methodology.Expanding our search,we screen 1 million publicly available and 7 million chemically recyclable polymers,identifying greener halogen-free alternatives to PVC.This capability is expected to advance membrane design for solvent separations.
文摘The equilibrium and kinetic characteristics of the adsorption of erythromycin to Sepabeads SP825 were determined.The equilibrium data in a batch system was well described by a Langmuir isotherm.The separation performance was investigated in a fixed-bed system with respect to the adsorption superficial velocity,ionic strength and pH.A mathematical model was used to simulate the mass transfer mechanism,taking film mass transfer,pore diffusion and axial dispersion into account.The model predictions were consistent with the experi-mental data and were consequently used to determine the mass transfer coefficients.
