The design of the poloidal field （PF） system includes the ohmic heating field system and the equilibrium （EQ） field system, and is the basis for the design of a magnetic confinement fusion device. A coupling betwe...The design of the poloidal field （PF） system includes the ohmic heating field system and the equilibrium （EQ） field system, and is the basis for the design of a magnetic confinement fusion device. A coupling between the poloidal and plasma currents, especially the eddy current in the stabilizing shell, yields design difficulties. The effects of the eddy current in the stabilizing shell on the poloidal magnetic field also cannot be ignored. A new PF system design is thus proposed. By using a low-μ material （μ = 0.001, ε = 1） instead of a conductive shell, an electromagnetic model is established that can provide a continuous eddy current distribution on the conductive shell. In this model, a 3D time-domain problem with shells translates into a 2D magnetostatic problem, and the accuracy of the calculation is improved. Based on these current distributions, we design the PF system and analyze how the EQ coils and conductive shell affect the plasma EQ when the plasma ramps up. To meet the mainframe design requirements and achieve an efficient power-supply design, the position and connection of the poloidal coils are optimized further.展开更多
Atmospheric gravity waves(AGWs)observed by the All-Sky Airglow Imager(ASAI)require accurate identification for the study of atmospheric coupling mechanisms and space weather prediction.However,the traditional manual s...Atmospheric gravity waves(AGWs)observed by the All-Sky Airglow Imager(ASAI)require accurate identification for the study of atmospheric coupling mechanisms and space weather prediction.However,the traditional manual screening methods and existing machine learning approaches do not meet the demands of practical station monitoring,which has significantly impeded climatological statistical research based on AGWs.Therefore,a real-time detection framework for ground-based airglow gravity waves that integrates transfer learning with adaptive image preprocessing has been proposed.By employing wavelength-adaptive median filtering and multiscale fusion,the framework effectively suppresses stellar noise while preserving weak gravity wave features.The model utilizes an EfficientNet-B3(convolutional neural network)backbone enhanced with a deformable convolutional layer,trained via a two-stage strategy:A frozen phase prevents overfitting by locking the lower level feature extractor,and a fine-tuning phase optimizes the deformable convolution through cosine annealing and layered optimization.This approach improves both feature transfer efficiency and gravity wave detection sensitivity.The resulting lightweight model achieves 91.2%accuracy with millisecond-level inference speed(23 ms per frame).展开更多
基金supported by the National Magnetic Confinement Fusion Research Program of China (2011GB106000)
文摘The design of the poloidal field （PF） system includes the ohmic heating field system and the equilibrium （EQ） field system, and is the basis for the design of a magnetic confinement fusion device. A coupling between the poloidal and plasma currents, especially the eddy current in the stabilizing shell, yields design difficulties. The effects of the eddy current in the stabilizing shell on the poloidal magnetic field also cannot be ignored. A new PF system design is thus proposed. By using a low-μ material （μ = 0.001, ε = 1） instead of a conductive shell, an electromagnetic model is established that can provide a continuous eddy current distribution on the conductive shell. In this model, a 3D time-domain problem with shells translates into a 2D magnetostatic problem, and the accuracy of the calculation is improved. Based on these current distributions, we design the PF system and analyze how the EQ coils and conductive shell affect the plasma EQ when the plasma ramps up. To meet the mainframe design requirements and achieve an efficient power-supply design, the position and connection of the poloidal coils are optimized further.
基金supported by the Strategic Priority Research Program of the Chinese Academy of Sciences(Grant No.XDA17010302)the National Natural Science Foundation of China(Grant Nos.12241101,42174192,and 11872128).
文摘Atmospheric gravity waves(AGWs)observed by the All-Sky Airglow Imager(ASAI)require accurate identification for the study of atmospheric coupling mechanisms and space weather prediction.However,the traditional manual screening methods and existing machine learning approaches do not meet the demands of practical station monitoring,which has significantly impeded climatological statistical research based on AGWs.Therefore,a real-time detection framework for ground-based airglow gravity waves that integrates transfer learning with adaptive image preprocessing has been proposed.By employing wavelength-adaptive median filtering and multiscale fusion,the framework effectively suppresses stellar noise while preserving weak gravity wave features.The model utilizes an EfficientNet-B3(convolutional neural network)backbone enhanced with a deformable convolutional layer,trained via a two-stage strategy:A frozen phase prevents overfitting by locking the lower level feature extractor,and a fine-tuning phase optimizes the deformable convolution through cosine annealing and layered optimization.This approach improves both feature transfer efficiency and gravity wave detection sensitivity.The resulting lightweight model achieves 91.2%accuracy with millisecond-level inference speed(23 ms per frame).
