Modeling light olefin production was one of the main concerns in chemical engineering field.In this paper,machine learning model based on artificial neural networks(ANN)was established to describe the effects of tempe...Modeling light olefin production was one of the main concerns in chemical engineering field.In this paper,machine learning model based on artificial neural networks(ANN)was established to describe the effects of temperature and catalyst on ethylene and propene formation in n-pentane cracking.The establishment procedure included data pretreatment,model design,training process and testing process,and the mean square error(MSE)and regression coefficient(R2)indexes were employed to evaluate model performance.It was found that the learning algorithm and ANN topology affected the calculation accuracy.GD24223,CGB2423,and LM24223 models were established by optimally matching the learning algorithm with ANN topology,and achieved excellent calculation accuracy.Furthermore,the stability of GD24223,CGB2423 and LM24223 models was investigated by gradually decreasing training data and simultaneously transforming data distribution.Compared with GD24223 and LM24223 models,CGB2423 model was more stable against the variations of training data,and the MSE values were always maintained at the magnitude of 10^-3-10^-4,confirming its applicability for simulating light olefin production in n-pentane cracking.展开更多
The Permanent Magnet Torque Motor(PMTM)is the key electro-mechanical conversion device in an Electro-Hydraulic Servo Valve(EHSV).In this work,a refined model of a PMTM is developed,considering the non-working air-gaps...The Permanent Magnet Torque Motor(PMTM)is the key electro-mechanical conversion device in an Electro-Hydraulic Servo Valve(EHSV).In this work,a refined model of a PMTM is developed,considering the non-working air-gaps between the upper or lower yoke and the armature,the fringing effect at the limiting holes,and the nonlinear permeability of soft magnetic material.Based on the refined model,the influences of various factors on the calculation accuracy of the magnetic flux at the pole surfaces of the armature and the output torque are investigated.For verifying the validity of the refined model,a Finite Element Analysis(FEA)of the PMTM is conducted,and a test platform is constructed.Compared with existing models,the refined model can better reveal the intrinsic mechanism of the PMTM,and its calculations are more consistent with the FEA results.The experimental results of the armature deflection displacement show that the refined model can accurately describe the output characteristics of the PMTM.展开更多
Porosity is a key parameter in shale gas reservoir evaluation and reserve calculation and its accurate test is the basis for calculating geological reserves of shale gas and determining development plans.In order to c...Porosity is a key parameter in shale gas reservoir evaluation and reserve calculation and its accurate test is the basis for calculating geological reserves of shale gas and determining development plans.In order to clarify the differences between different porosity test methods and their influences on the calculation results of shale gas reserves,we collected 65 shale samples of Lower Silurian Longmaxi Formation from six shale gas wells in the Zhaotong National Shale Gas Demonstration Area of the southern Sichuan Basin for comparative experiments using three porosity test method,including gas injection porosimetry(GIP)method,water immersion porosimetry(WIP)method and nuclear magnetic resonance(NMR)method.Then,these three methods were comparatively analyzed based on the test results.Finally,it was proposed to optimize the key parameters of these three shale porosity test methods.And the following research results were obtained.First,in terms of the GIP method,the particle size of shale sample shall be in the range of 20–60 mesh and the helium saturation equilibrium time shall be over 1800 s.Second,in terms of the WIP method,the sample shall be dried for at least 48 h under 110°C and saturated for 24 h under the confining pressure of 15 MPa.Third,in terms of the NMR method,NMR porosity calculation shall not be conducted until the NMR signal of the dried sample is deducted,on the basis of echo time and waiting time optimization.Fourth,porosity average and median value obtained by these three shale porosity test methods follow the relationship of WIP porosity>NMR porosity>particle GIP porosity>plunger GIP porosity.Fifth,different shale porosity test methods have greater influences on the calculation results of shale gas geological reserves,whose difference can reach 20%.In conclusion,during the application of NMR method and WIP method,fluid is introduced for saturation,which may damage the shale pores.However,the particle GIP porosity can reflect the entire space of shale more comprehensively and is not influenced by the properties of the applied fluid.Therefore,it is suggested to adopt the particle GIP method to calculate shale gas geological reserves.展开更多
Computational fluid dynamics(CFD)methods are being increasingly used for predicting airflow fields around buildings,but personal computers can still take tens of hours to create a single design using traditional compu...Computational fluid dynamics(CFD)methods are being increasingly used for predicting airflow fields around buildings,but personal computers can still take tens of hours to create a single design using traditional computing models.Considering both accuracy and efficiency,this study compared the performances of the conventional algorithm PIMPLE,fast fluid dynamics(FFD),semi-Lagrangian PISO(SLPISO),and implicit fast fluid dynamics(IFFD)in OpenFOAM for simulating wind flow around buildings.The effects of calculation parameters,including grid resolution,discrete-time step,and calculation time for these methods are analyzed.The results of the simulations are compared with wind tunnel tests.It is found that IFFD and FFD have the fastest calculation speeds,but also have the largest discrepancies with test data.The PIMPLE algorithm has the highest accuracy,but with the slowest calculation speed.The calculation speeds of the FFD,SLPISO,and IFFD models are 6.3,3 and 13.3 times faster than the PIMPLE model,respectively.The calculation accuracy and speed of the SLPISO model are in between those of the IFFD,FFD and PIMPLE models.An appropriate algorithm for a project may be chosen based on the requirements of the project.展开更多
基金financial support from the National Natural Science Foundation of China(Grant No.21908010)the Education Department of Jilin Province(Grant No.JJKH20191314KJ)Changchun University of Technology。
文摘Modeling light olefin production was one of the main concerns in chemical engineering field.In this paper,machine learning model based on artificial neural networks(ANN)was established to describe the effects of temperature and catalyst on ethylene and propene formation in n-pentane cracking.The establishment procedure included data pretreatment,model design,training process and testing process,and the mean square error(MSE)and regression coefficient(R2)indexes were employed to evaluate model performance.It was found that the learning algorithm and ANN topology affected the calculation accuracy.GD24223,CGB2423,and LM24223 models were established by optimally matching the learning algorithm with ANN topology,and achieved excellent calculation accuracy.Furthermore,the stability of GD24223,CGB2423 and LM24223 models was investigated by gradually decreasing training data and simultaneously transforming data distribution.Compared with GD24223 and LM24223 models,CGB2423 model was more stable against the variations of training data,and the MSE values were always maintained at the magnitude of 10^-3-10^-4,confirming its applicability for simulating light olefin production in n-pentane cracking.
基金co-supported by the National Natural Science Foundation of China(No.51975275)Primary Research&Development Plan of Jiangsu Province,China(No.BE2021034)Postgraduate Research&Practice Innovation Program of NUAA,China(No.xcxjh20210502).
文摘The Permanent Magnet Torque Motor(PMTM)is the key electro-mechanical conversion device in an Electro-Hydraulic Servo Valve(EHSV).In this work,a refined model of a PMTM is developed,considering the non-working air-gaps between the upper or lower yoke and the armature,the fringing effect at the limiting holes,and the nonlinear permeability of soft magnetic material.Based on the refined model,the influences of various factors on the calculation accuracy of the magnetic flux at the pole surfaces of the armature and the output torque are investigated.For verifying the validity of the refined model,a Finite Element Analysis(FEA)of the PMTM is conducted,and a test platform is constructed.Compared with existing models,the refined model can better reveal the intrinsic mechanism of the PMTM,and its calculations are more consistent with the FEA results.The experimental results of the armature deflection displacement show that the refined model can accurately describe the output characteristics of the PMTM.
基金supported by the National Major Science and Technology Project“Quantitative characterization and evaluation of shale reservoirs”(No.2017ZX05035002-002).
文摘Porosity is a key parameter in shale gas reservoir evaluation and reserve calculation and its accurate test is the basis for calculating geological reserves of shale gas and determining development plans.In order to clarify the differences between different porosity test methods and their influences on the calculation results of shale gas reserves,we collected 65 shale samples of Lower Silurian Longmaxi Formation from six shale gas wells in the Zhaotong National Shale Gas Demonstration Area of the southern Sichuan Basin for comparative experiments using three porosity test method,including gas injection porosimetry(GIP)method,water immersion porosimetry(WIP)method and nuclear magnetic resonance(NMR)method.Then,these three methods were comparatively analyzed based on the test results.Finally,it was proposed to optimize the key parameters of these three shale porosity test methods.And the following research results were obtained.First,in terms of the GIP method,the particle size of shale sample shall be in the range of 20–60 mesh and the helium saturation equilibrium time shall be over 1800 s.Second,in terms of the WIP method,the sample shall be dried for at least 48 h under 110°C and saturated for 24 h under the confining pressure of 15 MPa.Third,in terms of the NMR method,NMR porosity calculation shall not be conducted until the NMR signal of the dried sample is deducted,on the basis of echo time and waiting time optimization.Fourth,porosity average and median value obtained by these three shale porosity test methods follow the relationship of WIP porosity>NMR porosity>particle GIP porosity>plunger GIP porosity.Fifth,different shale porosity test methods have greater influences on the calculation results of shale gas geological reserves,whose difference can reach 20%.In conclusion,during the application of NMR method and WIP method,fluid is introduced for saturation,which may damage the shale pores.However,the particle GIP porosity can reflect the entire space of shale more comprehensively and is not influenced by the properties of the applied fluid.Therefore,it is suggested to adopt the particle GIP method to calculate shale gas geological reserves.
基金supported by the National Key R&D Project“Research on key technologies for environmental protection and energy saving of industrial buildings with high pollution emission”(No.2018YFC0705300)the National Natural Science Foundation of China Youth Fund Project“Fast reverse identification of indoor multiple gaseous pollutant sources”(No.51708084)+1 种基金the joint research project of the Wind Engineering Research Center,Tokyo Polytechnic University(MEXT(Japan)Promotion of Distinctive Joint Research Center Program grant number:JPMXP0619217840,JURC grant number:192013).
文摘Computational fluid dynamics(CFD)methods are being increasingly used for predicting airflow fields around buildings,but personal computers can still take tens of hours to create a single design using traditional computing models.Considering both accuracy and efficiency,this study compared the performances of the conventional algorithm PIMPLE,fast fluid dynamics(FFD),semi-Lagrangian PISO(SLPISO),and implicit fast fluid dynamics(IFFD)in OpenFOAM for simulating wind flow around buildings.The effects of calculation parameters,including grid resolution,discrete-time step,and calculation time for these methods are analyzed.The results of the simulations are compared with wind tunnel tests.It is found that IFFD and FFD have the fastest calculation speeds,but also have the largest discrepancies with test data.The PIMPLE algorithm has the highest accuracy,but with the slowest calculation speed.The calculation speeds of the FFD,SLPISO,and IFFD models are 6.3,3 and 13.3 times faster than the PIMPLE model,respectively.The calculation accuracy and speed of the SLPISO model are in between those of the IFFD,FFD and PIMPLE models.An appropriate algorithm for a project may be chosen based on the requirements of the project.
