In order to accurately describe the dynamic characteristics of flight vehicles through aerodynamic modeling, an adaptive wavelet neural network (AWNN) aerodynamic modeling method is proposed, based on subset kernel pr...In order to accurately describe the dynamic characteristics of flight vehicles through aerodynamic modeling, an adaptive wavelet neural network (AWNN) aerodynamic modeling method is proposed, based on subset kernel principal components analysis (SKPCA) feature extraction. Firstly, by fuzzy C-means clustering, some samples are selected from the training sample set to constitute a sample subset. Then, the obtained samples subset is used to execute SKPCA for extracting basic features of the training samples. Finally, using the extracted basic features, the AWNN aerodynamic model is established. The experimental results show that, in 50 times repetitive modeling, the modeling ability of the method proposed is better than that of other six methods. It only needs about half the modeling time of KPCA-AWNN under a close prediction accuracy, and can easily determine the model parameters. This enables it to be effective and feasible to construct the aerodynamic modeling for flight vehicles.展开更多
Due to people’s increasing dependence on social networks,it is essential to develop a consensus model considering not only their own factors but also the interaction between people.Both external trust relationship am...Due to people’s increasing dependence on social networks,it is essential to develop a consensus model considering not only their own factors but also the interaction between people.Both external trust relationship among experts and the internal reliability of experts are important factors in decision-making.This paper focuses on improving the scientificity and effectiveness of decision-making and presents a consensus model combining trust relationship among experts and expert reliability in social network group decision-making(SN-GDM).A concept named matching degree is proposed to measure expert reliability.Meanwhile,linguistic information is applied to manage the imprecise and vague information.Matching degree is expressed by a 2-tuple linguistic model,and experts’preferences are measured by a probabilistic linguistic term set(PLTS).Subsequently,a hybrid weight is explored to weigh experts’importance in a group.Then a consensus measure is introduced and a feedback mechanism is developed to produce some personalized recommendations with higher group consensus.Finally,a comparative example is provided to prove the scientificity and effectiveness of the proposed consensus model.展开更多
Enantioselective extraction of hydrophobic clorprenaline （CPE） enantiomers from organic phase to aqueous phases with sulfobutylether-β-cyclodextrin （SBE-β-CD） as the selector was investigated with insight into a...Enantioselective extraction of hydrophobic clorprenaline （CPE） enantiomers from organic phase to aqueous phases with sulfobutylether-β-cyclodextrin （SBE-β-CD） as the selector was investigated with insight into a number of important process variables, such as the type of organic solvent, concentration of selector, pH, and temperature. Equilibrium of the extraction system was modeled using a reactive extraction modcl with a homogeneous aqueous phase reaction. The important parameters of this model were determined experimentally. The physical distribution coefficients for molecular and ionic CPE were determined as 0.3 and 8.93, respectively. The equilibrium constants of the complexation reaction with SBE-β-CD were determined as 152 and 110 L/mol for R- and S-CPE, respectively. Results show that the experimental data agree with the model predictions perfectly. Comprehensively considering the experiment and model, the extraction conditions are optimized and the best extraction conditions are： pH of 6.0, SBE-β-CD concentration of 0.04 tool/L, and temperature of 5 ℃, providing the enantioselectivity （a） of 1.25, the fraction of R-CPE （φR） in aqueous phase of 0.71 and performance factor （pf） of 0.025.展开更多
[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-base...[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.展开更多
The tunnel field-effect transistor(TFET) is a potential candidate for the post-CMOS era.As one of the most important electrical parameters of a device,double gate TFET(DG-TFET) gate threshold voltage was studied.First...The tunnel field-effect transistor(TFET) is a potential candidate for the post-CMOS era.As one of the most important electrical parameters of a device,double gate TFET(DG-TFET) gate threshold voltage was studied.First,a numerical simulation study of transfer characteristic and gate threshold voltage in DG-TFET was reported.Then,a simple analytical model for DG-TFET gate threshold voltage VTG was built by solving quasi-two-dimensional Poisson equation in Si film.The model as a function of the drain voltage,the Si layer thickness,the gate length and the gate dielectric was discussed.It is shown that the proposed model is consistent with the simulation results.This model should be useful for further investigation of performance of circuits containing TFETs.展开更多
Throught fusion of the mechanism modeling and the neural networks modeling,a compo- nent content soft-sensor,which is composed of the equilibrium calculation model for multi-component rare earth extraction and the err...Throught fusion of the mechanism modeling and the neural networks modeling,a compo- nent content soft-sensor,which is composed of the equilibrium calculation model for multi-component rare earth extraction and the error compensation model of fuzzy system,is proposed to solve the prob- lem that the component content in countercurrent rare-earth extraction process is hardly measured on-line.An industry experiment in the extraction Y process by HAB using this hybrid soft-sensor proves its effectiveness.展开更多
The understanding of crack propagation characteristics and law of rocks during the loading process is of great significance for the exploitation and support of rock engineering.In this study,the crack propagation beha...The understanding of crack propagation characteristics and law of rocks during the loading process is of great significance for the exploitation and support of rock engineering.In this study,the crack propagation behavior of rocks in triaxial compression tests was investigated in detail.The main conclusions were as follows:1)According to the evolution characteristics of crack axial strain,the differential stress?strain curve of rocks under triaxial compressive condition can be divided into three phases which are linear elastic phase,crack propagation phase,post peak phase,respectively;2)The proposed models are applied to comparison with the test data of rocks under triaxial compressive condition and different temperatures.The theoretical data calculated by the models are in good agreement with the laboratory data,indicating that the proposed model can be applied to describing the crack propagation behavior and the nonlinear properties of rocks under triaxial compressive condition;3)The inelastic compliance and crack initiation strain in the proposed model have a decrease trend with the increase of confining pressure and temperature.Peak crack axial strain increases nonlinearly with the inelastic compliance and the increase rate increases gradually.Crack initiation strain has a linear relation with peak crack axial strain.展开更多
Fetr6 is an underground mine using the stope-and-pillar mining method. As there was some evidence regarding pillar failure in this mine, improving works such as roof support and replacing existing pillars with concret...Fetr6 is an underground mine using the stope-and-pillar mining method. As there was some evidence regarding pillar failure in this mine, improving works such as roof support and replacing existing pillars with concrete pillars (CP) were carried out. During the construction of the second CP, in the space between the remaining pillars, one of the pillars failed leading to the progressive failure of other pillars until 4 000 m 2 of mine had collapsed within a few minutes. In this work, this phenomenon is described by applying both numerical and empirical methods and the respective results are compared. The results of numerical modelling are found to be closer to the actual condition than those of the empirical method. Also, a width-to-height (W/H) ratio less than 1, an inadequate support system and the absence of a detailed program for pillar recovery are shown to be the most important causes of the Domino failure in this mine.展开更多
In order to maintain vibration performances within the limits of the design, a vibration-based feature extraction method for dynamic characteristic using empirical mode decomposition （EMD） and wavelet analysis was p...In order to maintain vibration performances within the limits of the design, a vibration-based feature extraction method for dynamic characteristic using empirical mode decomposition （EMD） and wavelet analysis was proposed. The proposed method was verified experimentally and numerically by implementing the scheme on engine block. In the implementation process, the following steps were identified to be important： 1） EMD technique in order to solve the feature extraction of vibration signals; 2） Vibration measurement for the purpose of confirming the structural weak regions of engine block in experiment; 3） Finite element modeling for the purpose of determining dynamic characteristic in time region and frequency region to affirm the comparability of response character corresponding to improvement schemes; 4） Adopting a feature index oflMF for structural improvement based on EMD and wavelet analysis. The obtained results show that IMF of signal is more sensitive to response character corresponding to improvement schemes. Finally, examination of the results confirms that the proposed vibration-based feature extraction method is very robust, and focuses on the relative merits of modification and full-scale structural optimization of engine, together with the creation of new low-vibration designs.展开更多
A kind of hybrid reliability model is presented to solve the fatigue reliability problems of steel bridges. The cumulative damage model is one kind of the models used in fatigue reliability analysis. The parameter cha...A kind of hybrid reliability model is presented to solve the fatigue reliability problems of steel bridges. The cumulative damage model is one kind of the models used in fatigue reliability analysis. The parameter characteristics of the model can be described as probabilistic and interval. The two-stage hybrid reliability model is given with a theoretical foundation and a solving algorithm to solve the hybrid reliability problems. The theoretical foundation is established by the consistency relationships of interval reliability model and probability reliability model with normally distributed variables in theory. The solving process is combined with the definition of interval reliability index and the probabilistic algorithm. With the consideration of the parameter characteristics of the S-N curve, the cumulative damage model with hybrid variables is given based on the standards from different countries. Lastly, a case of steel structure in the Neville Island Bridge is analyzed to verify the applicability of the hybrid reliability model in fatigue reliability analysis based on the AASHTO.展开更多
The dynamic transmission characteristics and the sensitivities of the three stage idler gear system of the new NC power turret are studied in the paper. Considering the strongly nonlinear factors such as the periodica...The dynamic transmission characteristics and the sensitivities of the three stage idler gear system of the new NC power turret are studied in the paper. Considering the strongly nonlinear factors such as the periodically time-varying mesh stiffness, the nonlinear tooth backlash, the lump-parameter model of the gear system is developed with one rotational and two translational freedoms of each gear. The eigen-values and eigenvectors are derived and analyzed on the basis of the real modal theory. The sensitivities of natural frequencies to design parameters including supporting and meshing stiffnesses, gear masses, and moments of inertia by the direct differential method are also calculated. The results show the quantitative and qualitative impact of the parameters to the natural characteristics of the gear system. Furthermore, the periodic steady state solutions are obtained by the numerical approach based on the nonlinear model. These results are employed to gain insights into the primary controlling parameters, to forecast the severity of the dynamic response, and to assess the acceptability of the gear design.展开更多
Juice extraction from chopped sweet sorghum is an example of flow through porous media. Darcy’s law is often used to express this type of phenomenon. However, using Darcy’s law to construct a mathematical model to p...Juice extraction from chopped sweet sorghum is an example of flow through porous media. Darcy’s law is often used to express this type of phenomenon. However, using Darcy’s law to construct a mathematical model to predict juice extraction from chopped sweet sorghum is difficult, because the volume of the porous media changes during the pressing operations. A mathematical model was developed from fundamental analysis to predict the juice extraction ratio of chopped sweet sorghum, and experiments were conducted to verify the model. An experimental piston-cylinder assembly was developed to conduct the validation experiments. The parameters in the developed model were estimated by using non-linear regression analysis from the experimental data. Plots of the mathematical model agreed well with experimental data. R^2（coefficient of determination） values for all the regressions studied were higher than 0.99. Results showed that the juice extraction ratio of chopped sweet sorghum approached an asymptote with a maximum value that depended on the physical form of the sample. The model could help in understanding the mechanics of juice extraction from chopped sweet sorghum.展开更多
中文电子病历实体关系抽取是构建医疗知识图谱,服务下游子任务的重要基础。目前,中文电子病例进行实体关系抽取仍存在因医疗文本关系复杂、实体密度大而造成医疗名词识别不准确的问题。针对这一问题,提出了基于对抗学习与多特征融合的...中文电子病历实体关系抽取是构建医疗知识图谱,服务下游子任务的重要基础。目前,中文电子病例进行实体关系抽取仍存在因医疗文本关系复杂、实体密度大而造成医疗名词识别不准确的问题。针对这一问题,提出了基于对抗学习与多特征融合的中文电子病历实体关系联合抽取模型AMFRel(adversarial learning and multi-feature fusion for relation triple extraction),提取电子病历的文本和词性特征,得到融合词性信息的编码向量;利用编码向量联合对抗训练产生的扰动生成对抗样本,抽取句子主语;利用信息融合模块丰富文本结构特征,并根据特定的关系信息抽取出相应的宾语,得到医疗文本的三元组。采用CHIP2020关系抽取数据集和糖尿病数据集进行实验验证,结果显示:AMFRel在CHIP2020关系抽取数据集上的Precision为63.922%,Recall为57.279%,F1值为60.418%;在糖尿病数据集上的Precision、Recall和F1值分别为83.914%,67.021%和74.522%,证明了该模型的三元组抽取性能优于其他基线模型。展开更多
基金Project(51209167) supported by Youth Project of the National Natural Science Foundation of ChinaProject(2012JM8026) supported by Shaanxi Provincial Natural Science Foundation, China
文摘In order to accurately describe the dynamic characteristics of flight vehicles through aerodynamic modeling, an adaptive wavelet neural network (AWNN) aerodynamic modeling method is proposed, based on subset kernel principal components analysis (SKPCA) feature extraction. Firstly, by fuzzy C-means clustering, some samples are selected from the training sample set to constitute a sample subset. Then, the obtained samples subset is used to execute SKPCA for extracting basic features of the training samples. Finally, using the extracted basic features, the AWNN aerodynamic model is established. The experimental results show that, in 50 times repetitive modeling, the modeling ability of the method proposed is better than that of other six methods. It only needs about half the modeling time of KPCA-AWNN under a close prediction accuracy, and can easily determine the model parameters. This enables it to be effective and feasible to construct the aerodynamic modeling for flight vehicles.
基金the National Natural Science Foundation of China(71871121).
文摘Due to people’s increasing dependence on social networks,it is essential to develop a consensus model considering not only their own factors but also the interaction between people.Both external trust relationship among experts and the internal reliability of experts are important factors in decision-making.This paper focuses on improving the scientificity and effectiveness of decision-making and presents a consensus model combining trust relationship among experts and expert reliability in social network group decision-making(SN-GDM).A concept named matching degree is proposed to measure expert reliability.Meanwhile,linguistic information is applied to manage the imprecise and vague information.Matching degree is expressed by a 2-tuple linguistic model,and experts’preferences are measured by a probabilistic linguistic term set(PLTS).Subsequently,a hybrid weight is explored to weigh experts’importance in a group.Then a consensus measure is introduced and a feedback mechanism is developed to produce some personalized recommendations with higher group consensus.Finally,a comparative example is provided to prove the scientificity and effectiveness of the proposed consensus model.
基金Projects(21176262,21071052) supported by the National Natural Science Foundation of ChinaProject supported by the Aid program for Technology Innovative Research Team in Higher Educational Institutions of Hunan Province,China
文摘Enantioselective extraction of hydrophobic clorprenaline （CPE） enantiomers from organic phase to aqueous phases with sulfobutylether-β-cyclodextrin （SBE-β-CD） as the selector was investigated with insight into a number of important process variables, such as the type of organic solvent, concentration of selector, pH, and temperature. Equilibrium of the extraction system was modeled using a reactive extraction modcl with a homogeneous aqueous phase reaction. The important parameters of this model were determined experimentally. The physical distribution coefficients for molecular and ionic CPE were determined as 0.3 and 8.93, respectively. The equilibrium constants of the complexation reaction with SBE-β-CD were determined as 152 and 110 L/mol for R- and S-CPE, respectively. Results show that the experimental data agree with the model predictions perfectly. Comprehensively considering the experiment and model, the extraction conditions are optimized and the best extraction conditions are： pH of 6.0, SBE-β-CD concentration of 0.04 tool/L, and temperature of 5 ℃, providing the enantioselectivity （a） of 1.25, the fraction of R-CPE （φR） in aqueous phase of 0.71 and performance factor （pf） of 0.025.
文摘[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.
基金Project(P140c090303110c0904)supported by NLAIC Research Fund,ChinaProject(JY0300122503)supported by the Research Fund for the Doctoral Program of Higher Education of China+1 种基金Projects(K5051225014,K5051225004)supported by the Fundamental Research Funds for the Central Universities,ChinaProject(2010JQ8008)supported by the Natural Science Basic Research Plan in Shaanxi Province of China
文摘The tunnel field-effect transistor(TFET) is a potential candidate for the post-CMOS era.As one of the most important electrical parameters of a device,double gate TFET(DG-TFET) gate threshold voltage was studied.First,a numerical simulation study of transfer characteristic and gate threshold voltage in DG-TFET was reported.Then,a simple analytical model for DG-TFET gate threshold voltage VTG was built by solving quasi-two-dimensional Poisson equation in Si film.The model as a function of the drain voltage,the Si layer thickness,the gate length and the gate dielectric was discussed.It is shown that the proposed model is consistent with the simulation results.This model should be useful for further investigation of performance of circuits containing TFETs.
基金Supported by National Natural Science Foundation of P.R.China(50474020,60534010,60504006)
文摘Throught fusion of the mechanism modeling and the neural networks modeling,a compo- nent content soft-sensor,which is composed of the equilibrium calculation model for multi-component rare earth extraction and the error compensation model of fuzzy system,is proposed to solve the prob- lem that the component content in countercurrent rare-earth extraction process is hardly measured on-line.An industry experiment in the extraction Y process by HAB using this hybrid soft-sensor proves its effectiveness.
基金Project(51622404)supported by Outstanding Youth Science Foundation of the National Natural Science Foundation of ChinaProjects(51374215,11572343,51904092)supported by the National Natural Science Foundation of China+2 种基金Project(2016YFC0801404)supported by the State Key Research Development Program of ChinaProject(KCF201803)supported by Henan Key Laboratory for Green and Efficient Mining&Comprehensive Utilization of Mineral Resources,Henan Polytechnic University,ChinaProject supported by Beijing Excellent Young Scientists,China
文摘The understanding of crack propagation characteristics and law of rocks during the loading process is of great significance for the exploitation and support of rock engineering.In this study,the crack propagation behavior of rocks in triaxial compression tests was investigated in detail.The main conclusions were as follows:1)According to the evolution characteristics of crack axial strain,the differential stress?strain curve of rocks under triaxial compressive condition can be divided into three phases which are linear elastic phase,crack propagation phase,post peak phase,respectively;2)The proposed models are applied to comparison with the test data of rocks under triaxial compressive condition and different temperatures.The theoretical data calculated by the models are in good agreement with the laboratory data,indicating that the proposed model can be applied to describing the crack propagation behavior and the nonlinear properties of rocks under triaxial compressive condition;3)The inelastic compliance and crack initiation strain in the proposed model have a decrease trend with the increase of confining pressure and temperature.Peak crack axial strain increases nonlinearly with the inelastic compliance and the increase rate increases gradually.Crack initiation strain has a linear relation with peak crack axial strain.
文摘Fetr6 is an underground mine using the stope-and-pillar mining method. As there was some evidence regarding pillar failure in this mine, improving works such as roof support and replacing existing pillars with concrete pillars (CP) were carried out. During the construction of the second CP, in the space between the remaining pillars, one of the pillars failed leading to the progressive failure of other pillars until 4 000 m 2 of mine had collapsed within a few minutes. In this work, this phenomenon is described by applying both numerical and empirical methods and the respective results are compared. The results of numerical modelling are found to be closer to the actual condition than those of the empirical method. Also, a width-to-height (W/H) ratio less than 1, an inadequate support system and the absence of a detailed program for pillar recovery are shown to be the most important causes of the Domino failure in this mine.
基金Project(50975192) supported by the National Natural Science Foundation of ChinaProject(10YFJZJC14100) supported by Tianjin Municipal Natural Science Foundation of China
文摘In order to maintain vibration performances within the limits of the design, a vibration-based feature extraction method for dynamic characteristic using empirical mode decomposition （EMD） and wavelet analysis was proposed. The proposed method was verified experimentally and numerically by implementing the scheme on engine block. In the implementation process, the following steps were identified to be important： 1） EMD technique in order to solve the feature extraction of vibration signals; 2） Vibration measurement for the purpose of confirming the structural weak regions of engine block in experiment; 3） Finite element modeling for the purpose of determining dynamic characteristic in time region and frequency region to affirm the comparability of response character corresponding to improvement schemes; 4） Adopting a feature index oflMF for structural improvement based on EMD and wavelet analysis. The obtained results show that IMF of signal is more sensitive to response character corresponding to improvement schemes. Finally, examination of the results confirms that the proposed vibration-based feature extraction method is very robust, and focuses on the relative merits of modification and full-scale structural optimization of engine, together with the creation of new low-vibration designs.
基金Projects(51178042,51578047)supported by the National Natural Science Foundation of ChinaProject(C14JB00340)supported by the Innovative Research Fund in Beijing Jiaotong University,ChinaProject(2014-ZJKJ-03)supported by Science and Technology Research and Development Fund of the China Communications Construction Co.,LTD
文摘A kind of hybrid reliability model is presented to solve the fatigue reliability problems of steel bridges. The cumulative damage model is one kind of the models used in fatigue reliability analysis. The parameter characteristics of the model can be described as probabilistic and interval. The two-stage hybrid reliability model is given with a theoretical foundation and a solving algorithm to solve the hybrid reliability problems. The theoretical foundation is established by the consistency relationships of interval reliability model and probability reliability model with normally distributed variables in theory. The solving process is combined with the definition of interval reliability index and the probabilistic algorithm. With the consideration of the parameter characteristics of the S-N curve, the cumulative damage model with hybrid variables is given based on the standards from different countries. Lastly, a case of steel structure in the Neville Island Bridge is analyzed to verify the applicability of the hybrid reliability model in fatigue reliability analysis based on the AASHTO.
文摘The dynamic transmission characteristics and the sensitivities of the three stage idler gear system of the new NC power turret are studied in the paper. Considering the strongly nonlinear factors such as the periodically time-varying mesh stiffness, the nonlinear tooth backlash, the lump-parameter model of the gear system is developed with one rotational and two translational freedoms of each gear. The eigen-values and eigenvectors are derived and analyzed on the basis of the real modal theory. The sensitivities of natural frequencies to design parameters including supporting and meshing stiffnesses, gear masses, and moments of inertia by the direct differential method are also calculated. The results show the quantitative and qualitative impact of the parameters to the natural characteristics of the gear system. Furthermore, the periodic steady state solutions are obtained by the numerical approach based on the nonlinear model. These results are employed to gain insights into the primary controlling parameters, to forecast the severity of the dynamic response, and to assess the acceptability of the gear design.
文摘Juice extraction from chopped sweet sorghum is an example of flow through porous media. Darcy’s law is often used to express this type of phenomenon. However, using Darcy’s law to construct a mathematical model to predict juice extraction from chopped sweet sorghum is difficult, because the volume of the porous media changes during the pressing operations. A mathematical model was developed from fundamental analysis to predict the juice extraction ratio of chopped sweet sorghum, and experiments were conducted to verify the model. An experimental piston-cylinder assembly was developed to conduct the validation experiments. The parameters in the developed model were estimated by using non-linear regression analysis from the experimental data. Plots of the mathematical model agreed well with experimental data. R^2（coefficient of determination） values for all the regressions studied were higher than 0.99. Results showed that the juice extraction ratio of chopped sweet sorghum approached an asymptote with a maximum value that depended on the physical form of the sample. The model could help in understanding the mechanics of juice extraction from chopped sweet sorghum.
文摘中文电子病历实体关系抽取是构建医疗知识图谱,服务下游子任务的重要基础。目前,中文电子病例进行实体关系抽取仍存在因医疗文本关系复杂、实体密度大而造成医疗名词识别不准确的问题。针对这一问题,提出了基于对抗学习与多特征融合的中文电子病历实体关系联合抽取模型AMFRel(adversarial learning and multi-feature fusion for relation triple extraction),提取电子病历的文本和词性特征,得到融合词性信息的编码向量;利用编码向量联合对抗训练产生的扰动生成对抗样本,抽取句子主语;利用信息融合模块丰富文本结构特征,并根据特定的关系信息抽取出相应的宾语,得到医疗文本的三元组。采用CHIP2020关系抽取数据集和糖尿病数据集进行实验验证,结果显示:AMFRel在CHIP2020关系抽取数据集上的Precision为63.922%,Recall为57.279%,F1值为60.418%;在糖尿病数据集上的Precision、Recall和F1值分别为83.914%,67.021%和74.522%,证明了该模型的三元组抽取性能优于其他基线模型。
