Solar energy will be a great alternative to fossil fuels since it is clean and renewable.The photovoltaic(PV)mechanism produces sunbeams’green energy without noise or pollution.The PV mechanism seems simple,seldom ma...Solar energy will be a great alternative to fossil fuels since it is clean and renewable.The photovoltaic(PV)mechanism produces sunbeams’green energy without noise or pollution.The PV mechanism seems simple,seldom malfunctioning,and easy to install.PV energy productivity significantly contributes to smart grids through many small PV mechanisms.Precise solar radiation(SR)prediction could substantially reduce the impact and cost relating to the advancement of solar energy.In recent times,several SR predictive mechanism was formulated,namely artificial neural network(ANN),autoregressive moving average,and support vector machine(SVM).Therefore,this article develops an optimal Modified Bidirectional Gated Recurrent Unit Driven Solar Radiation Prediction(OMBGRU-SRP)for energy management.The presented OMBGRU-SRP technique mainly aims to accomplish an accurate and time SR prediction process.To accomplish this,the presented OMBGRU-SRP technique performs data preprocessing to normalize the solar data.Next,the MBGRU model is derived using BGRU with an attention mechanism and skip connections.At last,the hyperparameter tuning of the MBGRU model is carried out using the satin bowerbird optimization(SBO)algorithm to attain maximum prediction with minimum error values.The SBO algorithm is an intelligent optimization algorithm that simulates the breeding behavior of an adult male Satin Bowerbird in the wild.Many experiments were conducted to demonstrate the enhanced SR prediction performance.The experimental values highlighted the supremacy of the OMBGRU-SRP algorithm over other existing models.展开更多
Multifaceted asymmetric radiation from the edge(MARFE) movement which can cause density limit disruption is often encountered during high density operation on many tokamaks. Therefore, identifying and predicting MARFE...Multifaceted asymmetric radiation from the edge(MARFE) movement which can cause density limit disruption is often encountered during high density operation on many tokamaks. Therefore, identifying and predicting MARFE movement is meaningful to mitigate or avoid density limit disruption for the steady-state high-density plasma operation. A machine learning method named random forest(RF) has been used to predict the MARFE movement based on the density ramp-up experiment in the 2022’s first campaign of Experimental Advanced Superconducting Tokamak(EAST). The RF model shows that besides Greenwald fraction which is the ratio of plasma density and Greenwald density limit, dβp/dt,H98and d Wmhd/dt are relatively important parameters for MARFE-movement prediction. Applying the RF model on test discharges, the test results show that the successful alarm rate for MARFE movement causing density limit disruption reaches ~ 85% with a minimum alarm time of ~ 40 ms and mean alarm time of ~ 700 ms. At the same time, the false alarm rate for non-disruptive and non-density-limit disruptive discharges can be kept below 5%. These results provide a reference to the prediction of MARFE movement in high density plasmas, which can help the avoidance or mitigation of density limit disruption in future fusion reactors.展开更多
Solar energy represents one of themost important renewable energy sources contributing to the energy transition process.Considering that the observation of daily global solar radiation(GSR)is not affordable in some pa...Solar energy represents one of themost important renewable energy sources contributing to the energy transition process.Considering that the observation of daily global solar radiation(GSR)is not affordable in some parts of the globe,there is an imperative need to develop alternative ways to predict it.Therefore,the main objective of this study is to evaluate the performance of different hybrid data-driven techniques in predicting daily GSR in semi-arid regions,such as the majority of Spanish territory.Here,four ensemble-based hybrid models were developed by hybridizing Additive Regression(AR)with Random Forest(RF),Locally Weighted Linear Regression(LWLR),Random Subspace(RS),and M5P.The base algorithms of the developed models are scarcely applied in previous studies to predict solar radiation.The testing phase outcomes demonstrated that the ARRF models outperform all other hybrid models.The provided models were validated by statisticalmetrics,such as the correlation coefficient(R)and root mean square error(RMSE).The results proved that Scenario#6,utilizing extraterrestrial solar radiation,relative humidity,wind speed,and mean,maximum,and minimum ambient air temperatures as the model inputs,leads to the most accurate predictions among all scenarios(R=0.968–0.988 and RMSE=1.274–1.403 MJ/m^(2)・d).Also,Scenario#3 stood in the next rank of accuracy for predicting the solar radiation in both validating stations.The AD-RF model was the best predictive,followed by AD-RS and AD-LWLR.Hence,this study recommends new effective methods to predict GSR in semiarid regions.展开更多
Reducing the radiated noise of a gearbox is a difficult problem in aviation,navigation,machinery,and other fields.Structural improvement is the main means of noise reduction for a gearbox,and it is realized primarily ...Reducing the radiated noise of a gearbox is a difficult problem in aviation,navigation,machinery,and other fields.Structural improvement is the main means of noise reduction for a gearbox,and it is realized primarily through contribution analysis and structure optimization.However,these approaches have certain limitations.In this study,a low-noise design method for a gearbox that combines the two approaches is proposed,and experimental verification is performed.First,a finite element/boundary element model is established using a single-stage herringbone gearbox.Considering the vibration excitation of the gear system,the radiation noise of a single-stage gearbox is predicted based on the modal acoustic transfer vector(MATV)method.Subsequently,the maximum field point of the radiated noise is determined,and the acoustic transfer vector(ATV)analysis and modal acoustic contribution(MAC)analysis are conducted to determine the region that contributes significantly to the radiated noise of the field point.The optimization region is selected through the panel acoustic contribution(PAC)analysis.Next,to reduce the normal speed in the optimization region,topology optimization is performed.According to the topology optimization results,four different noise reduction structures are added to the gearbox,and the low-noise optimization models are established respectively.Finally,by measuring the radiated noise of the gearbox before and after optimization under a given working condition,the validity of the radiated noise prediction method and the low-noise optimization design method are verified by comparing the simulation and experimental data.A comparison of the four optimization models proves that the noise reduction effect can be achieved only by adding a noise reduction structure to the center of the density nephogram.展开更多
In this paper,common mode(CM)and differential mode(DM)far-field radiation models of a typical digital inverter with cables are built up to predict electromagnetic field strength and analyze field characteristics.The C...In this paper,common mode(CM)and differential mode(DM)far-field radiation models of a typical digital inverter with cables are built up to predict electromagnetic field strength and analyze field characteristics.The CM current model and its analyses are based on the imbalance difference method.It is found out that the voltage between the drain and the source electrodes of upper transistor is the key equivalent source of electromagnetic interference(EMI).Far-field radiation strength of the digital inverter in free space is predicted by using the asymmetrical antenna radiation method and current loop radiation method.The accuracy of these methods is verified by the CST electromagnetic simulation results in the frequency range from 1 MHz to 400 MHz.Furthermore,the radiation models are improved by using the mirror method,which enables to include the reflection effect of the metal ground plane at the electromagnetic compatibility(EMC)test site.Both the results of measurements in a semi-anechoic chamber and the simulation results confirm the proposed electromagnetic radiation prediction method.展开更多
We investigate the role of clouds and radiation in the general circulation of the atmosphere using a model designed for 30-day predictions.Comprehensive verifications of 30-day predictions for the 500 hPa geo- potenti...We investigate the role of clouds and radiation in the general circulation of the atmosphere using a model designed for 30-day predictions.Comprehensive verifications of 30-day predictions for the 500 hPa geo- potential height field have been carried out,using the data from ECMWF objective analyses that cover the period from May 5 to June 3,1982.We perform three model simulations,including experiments with interac- tive cloud formation,without clouds,and without radiative heating.The latter two experiments allow us to study the effects of cloud/radiation interactions and feedbacks on the predicted vertical velocity,and the meridional and zonal wind profiles,averaged over a 30-day period. We demonstrate that the Hadley circulation is maintained by the presence of clouds.The radiative cooling in the atmosphere intensifies the vertical motion in low latitudes and,to some extent,also strengthens the overall meridional circulation.The meridional winds are correctly reproduced in the model if clouds are incorporated. The zonal winds are significantly affected by clouds and radiative cooling.Without an appropriate incor- poration of these physical elements,the model results would deviate significantly from observations.The presence of clouds strengthens the westerlies in middle and high levels.In May,the northerly movement of the jet stream over eastern Asia is,in part,associated with the presence of clouds.展开更多
文摘Solar energy will be a great alternative to fossil fuels since it is clean and renewable.The photovoltaic(PV)mechanism produces sunbeams’green energy without noise or pollution.The PV mechanism seems simple,seldom malfunctioning,and easy to install.PV energy productivity significantly contributes to smart grids through many small PV mechanisms.Precise solar radiation(SR)prediction could substantially reduce the impact and cost relating to the advancement of solar energy.In recent times,several SR predictive mechanism was formulated,namely artificial neural network(ANN),autoregressive moving average,and support vector machine(SVM).Therefore,this article develops an optimal Modified Bidirectional Gated Recurrent Unit Driven Solar Radiation Prediction(OMBGRU-SRP)for energy management.The presented OMBGRU-SRP technique mainly aims to accomplish an accurate and time SR prediction process.To accomplish this,the presented OMBGRU-SRP technique performs data preprocessing to normalize the solar data.Next,the MBGRU model is derived using BGRU with an attention mechanism and skip connections.At last,the hyperparameter tuning of the MBGRU model is carried out using the satin bowerbird optimization(SBO)algorithm to attain maximum prediction with minimum error values.The SBO algorithm is an intelligent optimization algorithm that simulates the breeding behavior of an adult male Satin Bowerbird in the wild.Many experiments were conducted to demonstrate the enhanced SR prediction performance.The experimental values highlighted the supremacy of the OMBGRU-SRP algorithm over other existing models.
基金This work is supported by the National MCF Energy R&D Program of China(Grant Nos.2018YFE0302100 and 2019YFE03010003)the National Natural Science Foundation of China(Grant Nos.12005264,12105322,and 12075285)+3 种基金the National Magnetic Confinement Fusion Science Program of China(Grant No.2022YFE03100003)the Natural Science Foundation of Anhui Province of China(Grant No.2108085QA38)the Chinese Postdoctoral Science Found(Grant No.2021000278)the Presidential Foundation of Hefei institutes of Physical Science(Grant No.YZJJ2021QN12).
文摘Multifaceted asymmetric radiation from the edge(MARFE) movement which can cause density limit disruption is often encountered during high density operation on many tokamaks. Therefore, identifying and predicting MARFE movement is meaningful to mitigate or avoid density limit disruption for the steady-state high-density plasma operation. A machine learning method named random forest(RF) has been used to predict the MARFE movement based on the density ramp-up experiment in the 2022’s first campaign of Experimental Advanced Superconducting Tokamak(EAST). The RF model shows that besides Greenwald fraction which is the ratio of plasma density and Greenwald density limit, dβp/dt,H98and d Wmhd/dt are relatively important parameters for MARFE-movement prediction. Applying the RF model on test discharges, the test results show that the successful alarm rate for MARFE movement causing density limit disruption reaches ~ 85% with a minimum alarm time of ~ 40 ms and mean alarm time of ~ 700 ms. At the same time, the false alarm rate for non-disruptive and non-density-limit disruptive discharges can be kept below 5%. These results provide a reference to the prediction of MARFE movement in high density plasmas, which can help the avoidance or mitigation of density limit disruption in future fusion reactors.
基金supported by the Portuguese Foundation for Science and Technology(FCT)through the project PTDC/CTA-OHR/30561/2017(WinTherface).
文摘Solar energy represents one of themost important renewable energy sources contributing to the energy transition process.Considering that the observation of daily global solar radiation(GSR)is not affordable in some parts of the globe,there is an imperative need to develop alternative ways to predict it.Therefore,the main objective of this study is to evaluate the performance of different hybrid data-driven techniques in predicting daily GSR in semi-arid regions,such as the majority of Spanish territory.Here,four ensemble-based hybrid models were developed by hybridizing Additive Regression(AR)with Random Forest(RF),Locally Weighted Linear Regression(LWLR),Random Subspace(RS),and M5P.The base algorithms of the developed models are scarcely applied in previous studies to predict solar radiation.The testing phase outcomes demonstrated that the ARRF models outperform all other hybrid models.The provided models were validated by statisticalmetrics,such as the correlation coefficient(R)and root mean square error(RMSE).The results proved that Scenario#6,utilizing extraterrestrial solar radiation,relative humidity,wind speed,and mean,maximum,and minimum ambient air temperatures as the model inputs,leads to the most accurate predictions among all scenarios(R=0.968–0.988 and RMSE=1.274–1.403 MJ/m^(2)・d).Also,Scenario#3 stood in the next rank of accuracy for predicting the solar radiation in both validating stations.The AD-RF model was the best predictive,followed by AD-RS and AD-LWLR.Hence,this study recommends new effective methods to predict GSR in semiarid regions.
基金National Key R&D Program of China(Grant No.2018YFB2001501)Key Program of National Natural Science Foundation of China(Grant No.51535009).
文摘Reducing the radiated noise of a gearbox is a difficult problem in aviation,navigation,machinery,and other fields.Structural improvement is the main means of noise reduction for a gearbox,and it is realized primarily through contribution analysis and structure optimization.However,these approaches have certain limitations.In this study,a low-noise design method for a gearbox that combines the two approaches is proposed,and experimental verification is performed.First,a finite element/boundary element model is established using a single-stage herringbone gearbox.Considering the vibration excitation of the gear system,the radiation noise of a single-stage gearbox is predicted based on the modal acoustic transfer vector(MATV)method.Subsequently,the maximum field point of the radiated noise is determined,and the acoustic transfer vector(ATV)analysis and modal acoustic contribution(MAC)analysis are conducted to determine the region that contributes significantly to the radiated noise of the field point.The optimization region is selected through the panel acoustic contribution(PAC)analysis.Next,to reduce the normal speed in the optimization region,topology optimization is performed.According to the topology optimization results,four different noise reduction structures are added to the gearbox,and the low-noise optimization models are established respectively.Finally,by measuring the radiated noise of the gearbox before and after optimization under a given working condition,the validity of the radiated noise prediction method and the low-noise optimization design method are verified by comparing the simulation and experimental data.A comparison of the four optimization models proves that the noise reduction effect can be achieved only by adding a noise reduction structure to the center of the density nephogram.
基金Supported by the National Natural Science Foundation of China(52077046)Guangdong Natural Science Foundation(2020A1515010913)Shenzhen Science Technology Plan(JSGG20201201100406017).
文摘In this paper,common mode(CM)and differential mode(DM)far-field radiation models of a typical digital inverter with cables are built up to predict electromagnetic field strength and analyze field characteristics.The CM current model and its analyses are based on the imbalance difference method.It is found out that the voltage between the drain and the source electrodes of upper transistor is the key equivalent source of electromagnetic interference(EMI).Far-field radiation strength of the digital inverter in free space is predicted by using the asymmetrical antenna radiation method and current loop radiation method.The accuracy of these methods is verified by the CST electromagnetic simulation results in the frequency range from 1 MHz to 400 MHz.Furthermore,the radiation models are improved by using the mirror method,which enables to include the reflection effect of the metal ground plane at the electromagnetic compatibility(EMC)test site.Both the results of measurements in a semi-anechoic chamber and the simulation results confirm the proposed electromagnetic radiation prediction method.
基金This research wes supported by the Air Force Office of Scientific Grant AFOSR-87-0294.
文摘We investigate the role of clouds and radiation in the general circulation of the atmosphere using a model designed for 30-day predictions.Comprehensive verifications of 30-day predictions for the 500 hPa geo- potential height field have been carried out,using the data from ECMWF objective analyses that cover the period from May 5 to June 3,1982.We perform three model simulations,including experiments with interac- tive cloud formation,without clouds,and without radiative heating.The latter two experiments allow us to study the effects of cloud/radiation interactions and feedbacks on the predicted vertical velocity,and the meridional and zonal wind profiles,averaged over a 30-day period. We demonstrate that the Hadley circulation is maintained by the presence of clouds.The radiative cooling in the atmosphere intensifies the vertical motion in low latitudes and,to some extent,also strengthens the overall meridional circulation.The meridional winds are correctly reproduced in the model if clouds are incorporated. The zonal winds are significantly affected by clouds and radiative cooling.Without an appropriate incor- poration of these physical elements,the model results would deviate significantly from observations.The presence of clouds strengthens the westerlies in middle and high levels.In May,the northerly movement of the jet stream over eastern Asia is,in part,associated with the presence of clouds.