According to the phenomenon of "four more"and"four low "problems in the observation stations,the surface-based meteorological observing system can't adapt to the change of the adaptive observat...According to the phenomenon of "four more"and"four low "problems in the observation stations,the surface-based meteorological observing system can't adapt to the change of the adaptive observation equipment and reduce of business intensification. A station integrated system is proposed,w hich can be configured,connected and extended to all kinds of observation equipment. And the integrated processor is designed,supporting a variety of communication interface standards. Flexible configuration,connection and expansion betw een conventional and new type of meteorological observation equipment are supported. It is capable for online calibration and maintenance of observation equipment. The effectiveness of automatic observation equipment is totally achieved to provide basic information support for disaster prevention and mitigation and national economic development.展开更多
A genetic neural net work m odel about design of Mg content in the alloy , based on tested databetw een Mg and tensile intensity or elongation in Zn 27 % Al alloy , has been established . Theresult has sho w n th...A genetic neural net work m odel about design of Mg content in the alloy , based on tested databetw een Mg and tensile intensity or elongation in Zn 27 % Al alloy , has been established . Theresult has sho w n that the genetic neural netw ork is a better an d m ore applied method for m a terials design than the regress analysis .展开更多
The task of achieving high-accuracy full-field reconstruction in the realm of water waves is widely acknowledged as a challenge,primarily due to the sparsity and incompleteness of data measurement in both temporal and...The task of achieving high-accuracy full-field reconstruction in the realm of water waves is widely acknowledged as a challenge,primarily due to the sparsity and incompleteness of data measurement in both temporal and spatial dimensions.We develop a full-field velocity and pressure reconstruction approach for non-linear water waves based on physics-informed neural networks from the free surface measurement.The fully non-linear highly dispersive Boussinesq model is integrated to reduce the training cost by representing the three dimensional water wave problems in the horizontal two-dimensional plane with the inherent veloc-ity distribution along water depth.A series of test cases,including the solitary waves,fifth-order Stokes waves,standing waves,and superimposed waves,are employed to evaluate the performance of the algorithm.The proposed novel neural networks are capable of accurately reconstructing the flow fields even when assimilating the limited and sparse free surface deformation data,which facilitates the development of detecting the flow characteristics in real ocean waves.展开更多
基金supported by Meteorological Industry Research Projects ( 2013 ) : Development and Application of Key Integration Technologies for Surface-based Meteorological Observation
文摘According to the phenomenon of "four more"and"four low "problems in the observation stations,the surface-based meteorological observing system can't adapt to the change of the adaptive observation equipment and reduce of business intensification. A station integrated system is proposed,w hich can be configured,connected and extended to all kinds of observation equipment. And the integrated processor is designed,supporting a variety of communication interface standards. Flexible configuration,connection and expansion betw een conventional and new type of meteorological observation equipment are supported. It is capable for online calibration and maintenance of observation equipment. The effectiveness of automatic observation equipment is totally achieved to provide basic information support for disaster prevention and mitigation and national economic development.
文摘A genetic neural net work m odel about design of Mg content in the alloy , based on tested databetw een Mg and tensile intensity or elongation in Zn 27 % Al alloy , has been established . Theresult has sho w n that the genetic neural netw ork is a better an d m ore applied method for m a terials design than the regress analysis .
基金supported by the Narional Nanre Science Foundarion of China(Grand Nos 12202272 and U22B6010)。
文摘The task of achieving high-accuracy full-field reconstruction in the realm of water waves is widely acknowledged as a challenge,primarily due to the sparsity and incompleteness of data measurement in both temporal and spatial dimensions.We develop a full-field velocity and pressure reconstruction approach for non-linear water waves based on physics-informed neural networks from the free surface measurement.The fully non-linear highly dispersive Boussinesq model is integrated to reduce the training cost by representing the three dimensional water wave problems in the horizontal two-dimensional plane with the inherent veloc-ity distribution along water depth.A series of test cases,including the solitary waves,fifth-order Stokes waves,standing waves,and superimposed waves,are employed to evaluate the performance of the algorithm.The proposed novel neural networks are capable of accurately reconstructing the flow fields even when assimilating the limited and sparse free surface deformation data,which facilitates the development of detecting the flow characteristics in real ocean waves.
