The configuration and the reference frame of the four-axis wire-electric discharge machining （WEDM） machine tool are introduced. Based on the motion analysis of the four-axis WEDM machine tool, an algorithm for cont...The configuration and the reference frame of the four-axis wire-electric discharge machining （WEDM） machine tool are introduced. Based on the motion analysis of the four-axis WEDM machine tool, an algorithm for controlling the four-axis motion is proposed. The algorithm is applicable to both the invariable and variable taper machining. Motion loci of the machining platform and the wire guiding head are deduced by the algorithm according to the bottom surface locus of the workpiece and the taper angle. The algorithm is used in the CNC system of the four-axis WEDM machine tool and confirmed to be effective.展开更多
The high porosity and tunable chemical functionality of metal-organic frameworks(MOFs)make it a promising catalyst design platform.High-throughput screening of catalytic performance is feasible since the large MOF str...The high porosity and tunable chemical functionality of metal-organic frameworks(MOFs)make it a promising catalyst design platform.High-throughput screening of catalytic performance is feasible since the large MOF structure database is available.In this study,we report a machine learning model for high-throughput screening of MOF catalysts for the CO_(2) cycloaddition reaction.The descriptors for model training were judiciously chosen according to the reaction mechanism,which leads to high accuracy up to 97%for the 75%quantile of the training set as the classification criterion.The feature contribution was further evaluated with SHAP and PDP analysis to provide a certain physical understanding.12,415 hypothetical MOF structures and 100 reported MOFs were evaluated under 100℃ and 1 bar within one day using the model,and 239 potentially efficient catalysts were discovered.Among them,MOF-76(Y)achieved the top performance experimentally among reported MOFs,in good agreement with the prediction.展开更多
The unique long-range disordered atomic arrangement inherent in amorphous materials endows them with a range of superior properties,rendering them highly promising for applications in catalysis,medicine,and battery te...The unique long-range disordered atomic arrangement inherent in amorphous materials endows them with a range of superior properties,rendering them highly promising for applications in catalysis,medicine,and battery technology,among other fields.Since not all materials can be synthesized into an amorphous structure,the composition design of amorphous materials holds significant importance.Machine learning offers a valuable alternative to traditional“trial-anderror”methods by predicting properties through experimental data,thus providing efficient guidance in material design.In this study,we develop a machine learning workflow to predict the critical casting diameter,glass transition temperature,and Young's modulus for 45 ternary reported amorphous alloy systems.The predicted results have been organized into a database,enabling direct retrieval of predicted values based on compositional information.Furthermore,the applications of high glass forming ability region screening for specified system,multi-property target system screening and high glass forming ability region search through iteration are also demonstrated.By utilizing machine learning predictions,researchers can effectively narrow the experimental scope and expedite the exploration of compositions.展开更多
BACKGROUND:Rapid and accurate identification of high-risk patients in the emergency departments(EDs)is crucial for optimizing resource allocation and improving patient outcomes.This study aimed to develop an early pre...BACKGROUND:Rapid and accurate identification of high-risk patients in the emergency departments(EDs)is crucial for optimizing resource allocation and improving patient outcomes.This study aimed to develop an early prediction model for identifying high-risk patients in EDs using initial vital sign measurements.METHODS:This retrospective cohort study analyzed initial vital signs from the Chinese Emergency Triage,Assessment,and Treatment(CETAT)database,which was collected between January 1^(st),2020,and June 25^(th),2023.The primary outcome was the identification of high-risk patients needing immediate treatment.Various machine learning methods,including a deep-learningbased multilayer perceptron(MLP)classifier were evaluated.Model performance was assessed using the area under the receiver operating characteristic curve(AUC-ROC).AUC-ROC values were reported for three scenarios:a default case,a scenario requiring sensitivity greater than 0.8(Scenario I),and a scenario requiring specificity greater than 0.8(Scenario II).SHAP values were calculated to determine the importance of each predictor within the MLP model.RESULTS:A total of 38,797 patients were analyzed,of whom 18.2%were identified as high-risk.Comparative analysis of the predictive models for high-risk patients showed AUC-ROC values ranging from 0.717 to 0.738,with the MLP model outperforming logistic regression(LR),Gaussian Naive Bayes(GNB),and the National Early Warning Score(NEWS).SHAP value analysis identified coma state,peripheral capillary oxygen saturation(SpO_(2)),and systolic blood pressure as the top three predictive factors in the MLP model,with coma state exerting the most contribution.CONCLUSION:Compared with other methods,the MLP model with initial vital signs demonstrated optimal prediction accuracy,highlighting its potential to enhance clinical decision-making in triage in the EDs.展开更多
Organic solar cells(OSCs) hold great potential as a photovoltaic technology for practical applications.However, the traditional experimental trial-and-error method for designing and engineering OSCs can be complex, ex...Organic solar cells(OSCs) hold great potential as a photovoltaic technology for practical applications.However, the traditional experimental trial-and-error method for designing and engineering OSCs can be complex, expensive, and time-consuming. Machine learning(ML) techniques enable the proficient extraction of information from datasets, allowing the development of realistic models that are capable of predicting the efficacy of materials with commendable accuracy. The PM6 donor has great potential for high-performance OSCs. However, it is crucial for the rational design of a ternary blend to accurately forecast the power conversion efficiency(PCE) of ternary OSCs(TOSCs) based on a PM6 donor.Accordingly, we collected the device parameters of PM6-based TOSCs and evaluated the feature importance of their molecule descriptors to develop predictive models. In this study, we used five different ML algorithms for analysis and prediction. For the analysis, the classification and regression tree provided different rules, heuristics, and patterns from the heterogeneous dataset. The random forest algorithm outperforms other prediction ML algorithms in predicting the output performance of PM6-based TOSCs. Finally, we validated the ML outcomes by fabricating PM6-based TOSCs. Our study presents a rapid strategy for assessing a high PCE while elucidating the substantial influence of diverse descriptors.展开更多
Perovskite solar cells(PSCs)have developed rapidly,positioning them as potential candidates for nextgeneration renewable energy sources.However,conventional trial-and-error approaches and the vast compositional parame...Perovskite solar cells(PSCs)have developed rapidly,positioning them as potential candidates for nextgeneration renewable energy sources.However,conventional trial-and-error approaches and the vast compositional parameter space continue to pose challenges in the pursuit of exceptional performance and high stability of perovskite-based optoelectronics.The increasing demand for novel materials in optoelectronic devices and establishment of substantial databases has enabled data-driven machinelearning(ML)approaches to swiftly advance in the materials field.This review succinctly outlines the fundamental ML procedures,techniques,and recent breakthroughs,particularly in predicting the physical characteristics of perovskite materials.Moreover,it highlights research endeavors aimed at optimizing and screening materials to enhance the efficiency and stability of PSCs.Additionally,this review highlights recent efforts in using characterization data for ML,exploring their correlations with material properties and device performance,which are actively being researched,but they have yet to receive significant attention.Lastly,we provide future perspectives,such as leveraging Large Language Models(LLMs)and text-mining,to expedite the discovery of novel perovskite materials and expand their utilization across various optoelectronic fields.展开更多
LiFePO_(4) is a cathode material with good thermal stability,but low thermal conductivity is a critical problem.In this study,we employ a machine learning potential approach based on first-principles methods combined ...LiFePO_(4) is a cathode material with good thermal stability,but low thermal conductivity is a critical problem.In this study,we employ a machine learning potential approach based on first-principles methods combined with the Boltzmann transport theory to investigate the influence of Na substitution on the thermal conductivity of LiFePO_(4) and the impact of Li-ion de-embedding on the thermal conductivity of Li_(3/4)Na_(1/4)FePO_(4),with the aim of enhancing heat dissipation in Li-ion batteries.The results show a significant increase in thermal conductivity due to an increase in phonon group velocity and a decrease in phonon anharmonic scattering by Na substitution.In addition,the thermal conductivity increases significantly with decreasing Li-ion concentration due to the increase in phonon lifetime.Our work guides the improvement of the thermal conductivity of Li FePO_4,emphasizing the crucial roles of both substitution and Li-ion detachment/intercalation for the thermal management of electrochemical energy storage devices.展开更多
The first 2^(+)excited states of the nucleus directly reflect the interaction between the shell structure and the nucleus,providing insights into the validity of the shell model and nuclear structure characteristics.A...The first 2^(+)excited states of the nucleus directly reflect the interaction between the shell structure and the nucleus,providing insights into the validity of the shell model and nuclear structure characteristics.Although the features of the first 2^(+)excited states can be measured for stable nuclei and calculated using nuclear models,significant uncertainty remains.This study employs a machine learning model based on a light gradient boosting machine(LightGBM)to investigate the first 2^(+)excited states.Specifically,the training of the LightGBM algorithm and the prediction of the first 2^(+)properties of 642 nuclei are presented.Furthermore,detailed comparisons of the LightGBM predictions were performed with available experimental data,shell model calculations,and Bayesian neural network predictions.The results revealed that the average difference between the LightGBM predictions and the experimental data was 18 times smaller than that obtained by the shell model and only 70%of the BNN prediction results.Considering Mg,Ca,Kr,Sm,and Pb isotopes as examples,it was also observed that LightGBM can effectively reproduce the magic number mutation caused by shell effects,with the energy being as low as 0.04 MeV due to shape coexistence.Therefore,we believe that leveraging LightGBM-based machine learning can profoundly enhance our insights into nuclear structures and provide new avenues for nuclear physics research.展开更多
Accurately estimating protein–ligand binding free energy is crucial for drug design and biophysics, yet remains a challenging task. In this study, we applied the screening molecular mechanics/Poisson–Boltzmann surfa...Accurately estimating protein–ligand binding free energy is crucial for drug design and biophysics, yet remains a challenging task. In this study, we applied the screening molecular mechanics/Poisson–Boltzmann surface area(MM/PBSA)method in combination with various machine learning techniques to compute the binding free energies of protein–ligand interactions. Our results demonstrate that machine learning outperforms direct screening MM/PBSA calculations in predicting protein–ligand binding free energies. Notably, the random forest(RF) method exhibited the best predictive performance,with a Pearson correlation coefficient(rp) of 0.702 and a mean absolute error(MAE) of 1.379 kcal/mol. Furthermore, we analyzed feature importance rankings in the gradient boosting(GB), adaptive boosting(Ada Boost), and RF methods, and found that feature selection significantly impacted predictive performance. In particular, molecular weight(MW) and van der Waals(VDW) energies played a decisive role in the prediction. Overall, this study highlights the potential of combining machine learning methods with screening MM/PBSA for accurately predicting binding free energies in biosystems.展开更多
Two types of aluminium-based composites reinforced respectively with 20 vol short fibre alumina and with a hybrid of 15 vol SiC particle and 5 vol short alumina fibre are machined with different tool materials:cemente...Two types of aluminium-based composites reinforced respectively with 20 vol short fibre alumina and with a hybrid of 15 vol SiC particle and 5 vol short alumina fibre are machined with different tool materials:cemented carbide,ceramic,cubic boron nitride(CBN)and polycrystalline diamond(PCD).The analysis on tool wear shows that the various tool materials exhibite different tool wear behaviours,and the tool wear mechanisma are discussed.Apparently,PCD tools do not necessarily guarantee dimensional stability but they can provide the most economic means for machining all sorts of composites.Consequently,a suitable tool material is suggested for machining each metal matrix composite(MMC) from the standpoints of tool wear and machined surface finish.展开更多
The theory and its method of machining parameter optimization for high-speed machining are studied. The machining data collected from workshops, labs and references are analyzed. An optimization method based on the ge...The theory and its method of machining parameter optimization for high-speed machining are studied. The machining data collected from workshops, labs and references are analyzed. An optimization method based on the genetic algorithm (GA) is investigated. Its calculation speed is faster than that of traditional optimization methods, and it is suitable for the machining parameter optimization in the automatic manufacturing system. Based on the theoretical studies, a system of machining parameter management and optimization is developed. The system can improve productivity of the high-speed machining centers.展开更多
Based on the theory of elastic mechanics and material mechanics, the orientation precision of the hohl schaft kegel（HSK） tooling system in static and dynamic states is theoretically and experimentally studied. The r...Based on the theory of elastic mechanics and material mechanics, the orientation precision of the hohl schaft kegel（HSK） tooling system in static and dynamic states is theoretically and experimentally studied. The relation between the clamping force and the shank taper is obtained. And a proper clamping force is found to be essential to assure the axial and radial orientation precisions of the HSK tooling system in high speed machining （HSM）. Analytical results show that the reason why the HSK tooling system can keep high precision at the high rotational speed is that the actual axial clamping force keeps the two surfaces of the shank and the spindle in contact all the time.展开更多
NC machining path of sculptured surfaces in CAD/CAM system plays an important role on manufacture. This paper describes a new algorithm for 5 axis machining of sculptured surfaces and the algorithm is interference fr...NC machining path of sculptured surfaces in CAD/CAM system plays an important role on manufacture. This paper describes a new algorithm for 5 axis machining of sculptured surfaces and the algorithm is interference free. The approach includes: (1) the tesselation of the parametric surfaces into triangles; (2) building topological relations among triangles;(3) 5 axis tool path generation; (4) interference detection and tool position correction.展开更多
In the verification of wire electrical discharge machining （EDM）, the motion and the performance of the wire-EDM system are analyzed. The maximum inclining angle of the wire is calculated. The relevant judgment meth...In the verification of wire electrical discharge machining （EDM）, the motion and the performance of the wire-EDM system are analyzed. The maximum inclining angle of the wire is calculated. The relevant judgment methods are used for the collision between the wire, the fixture, and the machining table. In the wire-EDM simulation, the generated solid model can he used to investigate programming results and to check the machining accuracy. The generation algorithm for the solid model in the simulation is solved based on Boolean operations. The wire swept volume for each cutting step is united to form the entire wire swept volume. Through Boolean subtraction between the stock model and the entire wire swept volume, the solid model in the wire-EDM simulation is generated. The method is also suitable for the wire path intersection occurred in cutting cone-shaped models. Finally, experiments are given to prove the method.展开更多
The planning method of tool orientation in the five-axis NC machining is studied. The problem of the existing method is analyzed and a new method for generating the global smoothing tool orientation is proposed by int...The planning method of tool orientation in the five-axis NC machining is studied. The problem of the existing method is analyzed and a new method for generating the global smoothing tool orientation is proposed by introducing the key frame idea in the animation-making. According to the feature of the part, several key tool orientations are set without interference between the tool and the part. Then, these key tool orientations are inter- polated by the spline function. By mapping the surface parameter to the spline parameter, the spline function value is obtained and taken as the tool orientation when generating the CL file. The machining result shows that the proposed method realizes the global smoothing of the tool orientation and the continuity of the rotational speed and the rotational acceleration. It also avoids the shake of the machine tool and improves the machining quality.展开更多
This paper is concerned with the work involved in improving the machining accuracy of a cantilever boring bar by on line compensation with a piezoelectric actuator. A boring bar is made into lever structure, with str...This paper is concerned with the work involved in improving the machining accuracy of a cantilever boring bar by on line compensation with a piezoelectric actuator. A boring bar is made into lever structure, with strain gauges attached to the bar for measuring its force induced deflections. The piezoelectric actuator is employed to compensate the deflections of the boring bar for accuracy improvement. Due to the mechanical advantage of the structure, the boring bar can be made into smaller size. The diameter of the bar implemented is 10 mm and the ratio of length to diameter (L/D) is larger than 8. It is found that the machining accuracy is improved considerably by using the piezoelectric actuator compensation system.展开更多
In this study, a newly developed titanium superalloy, i.e., the Ti-5553 alloy has used for hot machining. This material replaced Ti-grade-5 alloy in the application of aerospace, automobile, and biomedical sector. How...In this study, a newly developed titanium superalloy, i.e., the Ti-5553 alloy has used for hot machining. This material replaced Ti-grade-5 alloy in the application of aerospace, automobile, and biomedical sector. However, similar to Ti-grade-5 alloy, the Ti-5553 alloy has a low thermal conductivity which makes it difficult-to-cut material categories hence, high tool wear, cutting force and bad surface finish. Hot machining of Ti-5553 has been studied at different machining condition (room and hot) using Deform-2D finite element analysis. The result from the simulation test was compared with the experimental value and reduction of cutting and thrust forces was observed. The experiment was carried out with the same input parameters as simulation, and good coherence between them observed. Additionally, cutting zone temperature, effective stress, etc. for both room and elevated the temperature are also discussed.展开更多
We focus on the electrochemical dissolution characteristics of new titanium alloys such as near-αtitanium alloy Ti60,α+βtitanium alloy TC4andβtitanium alloy Ti40 which are often used for aerospace industry.The exp...We focus on the electrochemical dissolution characteristics of new titanium alloys such as near-αtitanium alloy Ti60,α+βtitanium alloy TC4andβtitanium alloy Ti40 which are often used for aerospace industry.The experiments are carried out by electrochemical machining tool,and the surface morphology of the specimens is observed by the scanning electron microscope(SEM)and three-dimensional video microscope(DVM).The appropriate electrolyte is selected and the relationships between surface roughness and current density are achieved.The results show that the single-phase titanium alloy Ti40 has a better surface roughness after ECM compared with theα+βtitanium alloy TC4 and the near-αtitanium alloy Ti60.The best surface roughness is Ra 0.28μm when the current density is 75A/cm2.Furthermore,the surface roughness of the near-αtitanium alloy Ti60 is the most sensitive with the current density because of the different electrochemical equivalents of substitutional elements and larger grains than TC4.Finally,the suitable current density for each titanium alloy is achieved.展开更多
Transparent brittle materials such as glass and sapphire are widely concerned and applied in consumer electronics, optoelectronic devices, etc. due to their excellent physical and chemical stability and good transpare...Transparent brittle materials such as glass and sapphire are widely concerned and applied in consumer electronics, optoelectronic devices, etc. due to their excellent physical and chemical stability and good transparency. Growing research attention has been paid to developing novel methods for high-precision and high-quality machining of transparent brittle materials in the past few decades. Among the various techniques, laser machining has been proved to be an effective and flexible way to process all kinds of transparent brittle materials. In this review, a series of laser machining methods, e.g. laser full cutting, laser scribing, laser stealth dicing, laser filament, laser induced backside dry etching (LIBDE), and laser induced backside wet etching (LIBWE) are summarized. Additionally, applications of these techniques in micromachining, drilling and cutting, and patterning are introduced in detail. Current challenges and future prospects in this field are also discussed.展开更多
In laser milling assisted with jet electrochemical machining(LMAJECM),the source of energy is a pulsed laser beam aligned coaxially with a jet of electrolyte,which focuses optical energy on the surface of workpiece.Th...In laser milling assisted with jet electrochemical machining(LMAJECM),the source of energy is a pulsed laser beam aligned coaxially with a jet of electrolyte,which focuses optical energy on the surface of workpiece.The impact of jet of electrolyte develops a state-of-art work to perform operations such as electrolytic etching,effective cooling,and transportation of debris.Therefore,a special jet cell is designed to obtain stable jet as to be a kind of noncontact tool,i.e.,electrode.According to the theoretical model of on-off pulse time process,laser machining and electrolytic anodization are simulated by finite element analysis(FEA)method.Grooves on a 0.5mm thick 321 stainless steel sheet produced by LMAJECM is performed with pulsed Nd:YAG laser at the second harmonic wavelength.Compared with laser milling under ambient atmosphere conditions,the recast layer and burrs are effectively diminished.And the accuracy of depth is dedicated to laser milling,whilst that of width is dominated by jet electrochemical machining.It is demonstrated that LMAJECM can be a highly potential approach for fabricating 3-D micro components.展开更多
文摘The configuration and the reference frame of the four-axis wire-electric discharge machining （WEDM） machine tool are introduced. Based on the motion analysis of the four-axis WEDM machine tool, an algorithm for controlling the four-axis motion is proposed. The algorithm is applicable to both the invariable and variable taper machining. Motion loci of the machining platform and the wire guiding head are deduced by the algorithm according to the bottom surface locus of the workpiece and the taper angle. The algorithm is used in the CNC system of the four-axis WEDM machine tool and confirmed to be effective.
基金financial support from the National Key Research and Development Program of China(2021YFB 3501501)the National Natural Science Foundation of China(No.22225803,22038001,22108007 and 22278011)+1 种基金Beijing Natural Science Foundation(No.Z230023)Beijing Science and Technology Commission(No.Z211100004321001).
文摘The high porosity and tunable chemical functionality of metal-organic frameworks(MOFs)make it a promising catalyst design platform.High-throughput screening of catalytic performance is feasible since the large MOF structure database is available.In this study,we report a machine learning model for high-throughput screening of MOF catalysts for the CO_(2) cycloaddition reaction.The descriptors for model training were judiciously chosen according to the reaction mechanism,which leads to high accuracy up to 97%for the 75%quantile of the training set as the classification criterion.The feature contribution was further evaluated with SHAP and PDP analysis to provide a certain physical understanding.12,415 hypothetical MOF structures and 100 reported MOFs were evaluated under 100℃ and 1 bar within one day using the model,and 239 potentially efficient catalysts were discovered.Among them,MOF-76(Y)achieved the top performance experimentally among reported MOFs,in good agreement with the prediction.
基金Project supported by funding from the National Natural Science Foundation of China(Grant Nos.52172258,52473227 and 52171150)the Strategic Priority Research Program of Chinese Academy of Sciences(Grant No.XDB0500200)。
文摘The unique long-range disordered atomic arrangement inherent in amorphous materials endows them with a range of superior properties,rendering them highly promising for applications in catalysis,medicine,and battery technology,among other fields.Since not all materials can be synthesized into an amorphous structure,the composition design of amorphous materials holds significant importance.Machine learning offers a valuable alternative to traditional“trial-anderror”methods by predicting properties through experimental data,thus providing efficient guidance in material design.In this study,we develop a machine learning workflow to predict the critical casting diameter,glass transition temperature,and Young's modulus for 45 ternary reported amorphous alloy systems.The predicted results have been organized into a database,enabling direct retrieval of predicted values based on compositional information.Furthermore,the applications of high glass forming ability region screening for specified system,multi-property target system screening and high glass forming ability region search through iteration are also demonstrated.By utilizing machine learning predictions,researchers can effectively narrow the experimental scope and expedite the exploration of compositions.
基金Applicable Funding Source University of Science and Technology of China(to YLL)National Natural Science Foundation of China(12126604)(to MPZ)+1 种基金R&D project of Pazhou Lab(Huangpu)(2023K0609)(to MPZ)Anhui Provincial Natural Science(grant number 2208085MH235)(to KJ)。
文摘BACKGROUND:Rapid and accurate identification of high-risk patients in the emergency departments(EDs)is crucial for optimizing resource allocation and improving patient outcomes.This study aimed to develop an early prediction model for identifying high-risk patients in EDs using initial vital sign measurements.METHODS:This retrospective cohort study analyzed initial vital signs from the Chinese Emergency Triage,Assessment,and Treatment(CETAT)database,which was collected between January 1^(st),2020,and June 25^(th),2023.The primary outcome was the identification of high-risk patients needing immediate treatment.Various machine learning methods,including a deep-learningbased multilayer perceptron(MLP)classifier were evaluated.Model performance was assessed using the area under the receiver operating characteristic curve(AUC-ROC).AUC-ROC values were reported for three scenarios:a default case,a scenario requiring sensitivity greater than 0.8(Scenario I),and a scenario requiring specificity greater than 0.8(Scenario II).SHAP values were calculated to determine the importance of each predictor within the MLP model.RESULTS:A total of 38,797 patients were analyzed,of whom 18.2%were identified as high-risk.Comparative analysis of the predictive models for high-risk patients showed AUC-ROC values ranging from 0.717 to 0.738,with the MLP model outperforming logistic regression(LR),Gaussian Naive Bayes(GNB),and the National Early Warning Score(NEWS).SHAP value analysis identified coma state,peripheral capillary oxygen saturation(SpO_(2)),and systolic blood pressure as the top three predictive factors in the MLP model,with coma state exerting the most contribution.CONCLUSION:Compared with other methods,the MLP model with initial vital signs demonstrated optimal prediction accuracy,highlighting its potential to enhance clinical decision-making in triage in the EDs.
基金National Research Foundation of Korea (NRF) grant (No. 2016R1A3B 1908249) funded by the Korean government。
文摘Organic solar cells(OSCs) hold great potential as a photovoltaic technology for practical applications.However, the traditional experimental trial-and-error method for designing and engineering OSCs can be complex, expensive, and time-consuming. Machine learning(ML) techniques enable the proficient extraction of information from datasets, allowing the development of realistic models that are capable of predicting the efficacy of materials with commendable accuracy. The PM6 donor has great potential for high-performance OSCs. However, it is crucial for the rational design of a ternary blend to accurately forecast the power conversion efficiency(PCE) of ternary OSCs(TOSCs) based on a PM6 donor.Accordingly, we collected the device parameters of PM6-based TOSCs and evaluated the feature importance of their molecule descriptors to develop predictive models. In this study, we used five different ML algorithms for analysis and prediction. For the analysis, the classification and regression tree provided different rules, heuristics, and patterns from the heterogeneous dataset. The random forest algorithm outperforms other prediction ML algorithms in predicting the output performance of PM6-based TOSCs. Finally, we validated the ML outcomes by fabricating PM6-based TOSCs. Our study presents a rapid strategy for assessing a high PCE while elucidating the substantial influence of diverse descriptors.
基金supported by the Ministry of Science and ICT(MSIT)of the Republic of Korea(00302646)supported by the National Research Foundation of Korea grant funded by the Korean Government(MSIT)(NRF-2022R1A4A1019296,1345374646,2022M3J1A1064315).
文摘Perovskite solar cells(PSCs)have developed rapidly,positioning them as potential candidates for nextgeneration renewable energy sources.However,conventional trial-and-error approaches and the vast compositional parameter space continue to pose challenges in the pursuit of exceptional performance and high stability of perovskite-based optoelectronics.The increasing demand for novel materials in optoelectronic devices and establishment of substantial databases has enabled data-driven machinelearning(ML)approaches to swiftly advance in the materials field.This review succinctly outlines the fundamental ML procedures,techniques,and recent breakthroughs,particularly in predicting the physical characteristics of perovskite materials.Moreover,it highlights research endeavors aimed at optimizing and screening materials to enhance the efficiency and stability of PSCs.Additionally,this review highlights recent efforts in using characterization data for ML,exploring their correlations with material properties and device performance,which are actively being researched,but they have yet to receive significant attention.Lastly,we provide future perspectives,such as leveraging Large Language Models(LLMs)and text-mining,to expedite the discovery of novel perovskite materials and expand their utilization across various optoelectronic fields.
基金supported by the National Natural Science Foundation of China(Grant No.12074115)the Science and Technology Innovation Program of Hunan Province(Grant No.2023RC3176)。
文摘LiFePO_(4) is a cathode material with good thermal stability,but low thermal conductivity is a critical problem.In this study,we employ a machine learning potential approach based on first-principles methods combined with the Boltzmann transport theory to investigate the influence of Na substitution on the thermal conductivity of LiFePO_(4) and the impact of Li-ion de-embedding on the thermal conductivity of Li_(3/4)Na_(1/4)FePO_(4),with the aim of enhancing heat dissipation in Li-ion batteries.The results show a significant increase in thermal conductivity due to an increase in phonon group velocity and a decrease in phonon anharmonic scattering by Na substitution.In addition,the thermal conductivity increases significantly with decreasing Li-ion concentration due to the increase in phonon lifetime.Our work guides the improvement of the thermal conductivity of Li FePO_4,emphasizing the crucial roles of both substitution and Li-ion detachment/intercalation for the thermal management of electrochemical energy storage devices.
基金supported by the National Key R&D Program of China (No. 2022YFA1603300)the Romanian Ministry of Research,Innovation and Digitalization under Contract PN 23.21.01.06+1 种基金The ELI-RO project with Contract ELI-RORDI-2024-008 (AMAP)a grant from the Romanian Ministry of Research,Innovation and Digitization,CNCS-UEFIS-CDI,with project numbers PN-Ⅲ-P4-PCE-2021-1014, PN-Ⅲ-P4-PCE-2021-0595, and PN-Ⅲ-P1-1.1-TE2021-1464 within PNCDI Ⅲ
文摘The first 2^(+)excited states of the nucleus directly reflect the interaction between the shell structure and the nucleus,providing insights into the validity of the shell model and nuclear structure characteristics.Although the features of the first 2^(+)excited states can be measured for stable nuclei and calculated using nuclear models,significant uncertainty remains.This study employs a machine learning model based on a light gradient boosting machine(LightGBM)to investigate the first 2^(+)excited states.Specifically,the training of the LightGBM algorithm and the prediction of the first 2^(+)properties of 642 nuclei are presented.Furthermore,detailed comparisons of the LightGBM predictions were performed with available experimental data,shell model calculations,and Bayesian neural network predictions.The results revealed that the average difference between the LightGBM predictions and the experimental data was 18 times smaller than that obtained by the shell model and only 70%of the BNN prediction results.Considering Mg,Ca,Kr,Sm,and Pb isotopes as examples,it was also observed that LightGBM can effectively reproduce the magic number mutation caused by shell effects,with the energy being as low as 0.04 MeV due to shape coexistence.Therefore,we believe that leveraging LightGBM-based machine learning can profoundly enhance our insights into nuclear structures and provide new avenues for nuclear physics research.
基金Project supported by the National Natural Science Foundation of China (Grant Nos. 12222506, 12347102, 12447164, and 12174184)。
文摘Accurately estimating protein–ligand binding free energy is crucial for drug design and biophysics, yet remains a challenging task. In this study, we applied the screening molecular mechanics/Poisson–Boltzmann surface area(MM/PBSA)method in combination with various machine learning techniques to compute the binding free energies of protein–ligand interactions. Our results demonstrate that machine learning outperforms direct screening MM/PBSA calculations in predicting protein–ligand binding free energies. Notably, the random forest(RF) method exhibited the best predictive performance,with a Pearson correlation coefficient(rp) of 0.702 and a mean absolute error(MAE) of 1.379 kcal/mol. Furthermore, we analyzed feature importance rankings in the gradient boosting(GB), adaptive boosting(Ada Boost), and RF methods, and found that feature selection significantly impacted predictive performance. In particular, molecular weight(MW) and van der Waals(VDW) energies played a decisive role in the prediction. Overall, this study highlights the potential of combining machine learning methods with screening MM/PBSA for accurately predicting binding free energies in biosystems.
文摘Two types of aluminium-based composites reinforced respectively with 20 vol short fibre alumina and with a hybrid of 15 vol SiC particle and 5 vol short alumina fibre are machined with different tool materials:cemented carbide,ceramic,cubic boron nitride(CBN)and polycrystalline diamond(PCD).The analysis on tool wear shows that the various tool materials exhibite different tool wear behaviours,and the tool wear mechanisma are discussed.Apparently,PCD tools do not necessarily guarantee dimensional stability but they can provide the most economic means for machining all sorts of composites.Consequently,a suitable tool material is suggested for machining each metal matrix composite(MMC) from the standpoints of tool wear and machined surface finish.
文摘The theory and its method of machining parameter optimization for high-speed machining are studied. The machining data collected from workshops, labs and references are analyzed. An optimization method based on the genetic algorithm (GA) is investigated. Its calculation speed is faster than that of traditional optimization methods, and it is suitable for the machining parameter optimization in the automatic manufacturing system. Based on the theoretical studies, a system of machining parameter management and optimization is developed. The system can improve productivity of the high-speed machining centers.
文摘Based on the theory of elastic mechanics and material mechanics, the orientation precision of the hohl schaft kegel（HSK） tooling system in static and dynamic states is theoretically and experimentally studied. The relation between the clamping force and the shank taper is obtained. And a proper clamping force is found to be essential to assure the axial and radial orientation precisions of the HSK tooling system in high speed machining （HSM）. Analytical results show that the reason why the HSK tooling system can keep high precision at the high rotational speed is that the actual axial clamping force keeps the two surfaces of the shank and the spindle in contact all the time.
文摘NC machining path of sculptured surfaces in CAD/CAM system plays an important role on manufacture. This paper describes a new algorithm for 5 axis machining of sculptured surfaces and the algorithm is interference free. The approach includes: (1) the tesselation of the parametric surfaces into triangles; (2) building topological relations among triangles;(3) 5 axis tool path generation; (4) interference detection and tool position correction.
文摘In the verification of wire electrical discharge machining （EDM）, the motion and the performance of the wire-EDM system are analyzed. The maximum inclining angle of the wire is calculated. The relevant judgment methods are used for the collision between the wire, the fixture, and the machining table. In the wire-EDM simulation, the generated solid model can he used to investigate programming results and to check the machining accuracy. The generation algorithm for the solid model in the simulation is solved based on Boolean operations. The wire swept volume for each cutting step is united to form the entire wire swept volume. Through Boolean subtraction between the stock model and the entire wire swept volume, the solid model in the wire-EDM simulation is generated. The method is also suitable for the wire path intersection occurred in cutting cone-shaped models. Finally, experiments are given to prove the method.
文摘The planning method of tool orientation in the five-axis NC machining is studied. The problem of the existing method is analyzed and a new method for generating the global smoothing tool orientation is proposed by introducing the key frame idea in the animation-making. According to the feature of the part, several key tool orientations are set without interference between the tool and the part. Then, these key tool orientations are inter- polated by the spline function. By mapping the surface parameter to the spline parameter, the spline function value is obtained and taken as the tool orientation when generating the CL file. The machining result shows that the proposed method realizes the global smoothing of the tool orientation and the continuity of the rotational speed and the rotational acceleration. It also avoids the shake of the machine tool and improves the machining quality.
文摘This paper is concerned with the work involved in improving the machining accuracy of a cantilever boring bar by on line compensation with a piezoelectric actuator. A boring bar is made into lever structure, with strain gauges attached to the bar for measuring its force induced deflections. The piezoelectric actuator is employed to compensate the deflections of the boring bar for accuracy improvement. Due to the mechanical advantage of the structure, the boring bar can be made into smaller size. The diameter of the bar implemented is 10 mm and the ratio of length to diameter (L/D) is larger than 8. It is found that the machining accuracy is improved considerably by using the piezoelectric actuator compensation system.
文摘In this study, a newly developed titanium superalloy, i.e., the Ti-5553 alloy has used for hot machining. This material replaced Ti-grade-5 alloy in the application of aerospace, automobile, and biomedical sector. However, similar to Ti-grade-5 alloy, the Ti-5553 alloy has a low thermal conductivity which makes it difficult-to-cut material categories hence, high tool wear, cutting force and bad surface finish. Hot machining of Ti-5553 has been studied at different machining condition (room and hot) using Deform-2D finite element analysis. The result from the simulation test was compared with the experimental value and reduction of cutting and thrust forces was observed. The experiment was carried out with the same input parameters as simulation, and good coherence between them observed. Additionally, cutting zone temperature, effective stress, etc. for both room and elevated the temperature are also discussed.
基金supported by the National Natural Science Foundation of China(No.51205199)the Program for New Century Excellent Talents in University (No.NCET12-0627)+1 种基金the Funding of Jiangsu Innovation Program for Graduate Education (No.CXLX13_141)the Fundamental Research Funds for the Central Universities
文摘We focus on the electrochemical dissolution characteristics of new titanium alloys such as near-αtitanium alloy Ti60,α+βtitanium alloy TC4andβtitanium alloy Ti40 which are often used for aerospace industry.The experiments are carried out by electrochemical machining tool,and the surface morphology of the specimens is observed by the scanning electron microscope(SEM)and three-dimensional video microscope(DVM).The appropriate electrolyte is selected and the relationships between surface roughness and current density are achieved.The results show that the single-phase titanium alloy Ti40 has a better surface roughness after ECM compared with theα+βtitanium alloy TC4 and the near-αtitanium alloy Ti60.The best surface roughness is Ra 0.28μm when the current density is 75A/cm2.Furthermore,the surface roughness of the near-αtitanium alloy Ti60 is the most sensitive with the current density because of the different electrochemical equivalents of substitutional elements and larger grains than TC4.Finally,the suitable current density for each titanium alloy is achieved.
基金National Natural Science Foundation of China (51575114 and 51805093)National Key R&D Program of China (2018YFB1107700)Guangzhou Science and Technology Project (201607010156).
文摘Transparent brittle materials such as glass and sapphire are widely concerned and applied in consumer electronics, optoelectronic devices, etc. due to their excellent physical and chemical stability and good transparency. Growing research attention has been paid to developing novel methods for high-precision and high-quality machining of transparent brittle materials in the past few decades. Among the various techniques, laser machining has been proved to be an effective and flexible way to process all kinds of transparent brittle materials. In this review, a series of laser machining methods, e.g. laser full cutting, laser scribing, laser stealth dicing, laser filament, laser induced backside dry etching (LIBDE), and laser induced backside wet etching (LIBWE) are summarized. Additionally, applications of these techniques in micromachining, drilling and cutting, and patterning are introduced in detail. Current challenges and future prospects in this field are also discussed.
基金Supported by the National Natural Science Foundation of China(51205212)the Natural ScienceFoundation of Jiangsu Province(BK2012233)
文摘In laser milling assisted with jet electrochemical machining(LMAJECM),the source of energy is a pulsed laser beam aligned coaxially with a jet of electrolyte,which focuses optical energy on the surface of workpiece.The impact of jet of electrolyte develops a state-of-art work to perform operations such as electrolytic etching,effective cooling,and transportation of debris.Therefore,a special jet cell is designed to obtain stable jet as to be a kind of noncontact tool,i.e.,electrode.According to the theoretical model of on-off pulse time process,laser machining and electrolytic anodization are simulated by finite element analysis(FEA)method.Grooves on a 0.5mm thick 321 stainless steel sheet produced by LMAJECM is performed with pulsed Nd:YAG laser at the second harmonic wavelength.Compared with laser milling under ambient atmosphere conditions,the recast layer and burrs are effectively diminished.And the accuracy of depth is dedicated to laser milling,whilst that of width is dominated by jet electrochemical machining.It is demonstrated that LMAJECM can be a highly potential approach for fabricating 3-D micro components.
