A hybrid identification model based on multilayer artificial neural networks(ANNs) and particle swarm optimization(PSO) algorithm is developed to improve the simultaneous identification efficiency of thermal conductiv...A hybrid identification model based on multilayer artificial neural networks(ANNs) and particle swarm optimization(PSO) algorithm is developed to improve the simultaneous identification efficiency of thermal conductivity and effective absorption coefficient of semitransparent materials.For the direct model,the spherical harmonic method and the finite volume method are used to solve the coupled conduction-radiation heat transfer problem in an absorbing,emitting,and non-scattering 2D axisymmetric gray medium in the background of laser flash method.For the identification part,firstly,the temperature field and the incident radiation field in different positions are chosen as observables.Then,a traditional identification model based on PSO algorithm is established.Finally,multilayer ANNs are built to fit and replace the direct model in the traditional identification model to speed up the identification process.The results show that compared with the traditional identification model,the time cost of the hybrid identification model is reduced by about 1 000 times.Besides,the hybrid identification model remains a high level of accuracy even with measurement errors.展开更多
Human body communication(HBC) is a promising near-field communication(NFC) method emerging in recent years. But existing theoretical models of HBC are too simple to simulate the wave propagation on human body. In this...Human body communication(HBC) is a promising near-field communication(NFC) method emerging in recent years. But existing theoretical models of HBC are too simple to simulate the wave propagation on human body. In this work, in order to clarify the propagation mechanism of electromagnetic wave on human body, a surface waveguide HBC theoretical model based on stratified media cylinder is presented. A numerical model analyzed by finite element method(FEM) is used for comparing and validating the theoretical model. Finally, results of theoretical and numerical models from 80 MHz to 200 MHz agree fairly well, which means that theoretical model can characterize accurate propagation mechanism of HBC signal. Meanwhile, attenuation constants derived from two kinds of models are within the range from 1.64 to 3.37, so that HBC signal can propagate effectively on human body. The propagation mechanism derived from the theoretical model is useful to provide design information for the transmitter and the modeling of the propagation channel in HBC.展开更多
基金supported by the Fundamental Research Funds for the Central Universities (No.3122020072)the Multi-investment Project of Tianjin Applied Basic Research(No.23JCQNJC00250)。
文摘A hybrid identification model based on multilayer artificial neural networks(ANNs) and particle swarm optimization(PSO) algorithm is developed to improve the simultaneous identification efficiency of thermal conductivity and effective absorption coefficient of semitransparent materials.For the direct model,the spherical harmonic method and the finite volume method are used to solve the coupled conduction-radiation heat transfer problem in an absorbing,emitting,and non-scattering 2D axisymmetric gray medium in the background of laser flash method.For the identification part,firstly,the temperature field and the incident radiation field in different positions are chosen as observables.Then,a traditional identification model based on PSO algorithm is established.Finally,multilayer ANNs are built to fit and replace the direct model in the traditional identification model to speed up the identification process.The results show that compared with the traditional identification model,the time cost of the hybrid identification model is reduced by about 1 000 times.Besides,the hybrid identification model remains a high level of accuracy even with measurement errors.
基金Project(2009ZX01031-001-007-2)supported by the National Science and Technology Major Project,China
文摘Human body communication(HBC) is a promising near-field communication(NFC) method emerging in recent years. But existing theoretical models of HBC are too simple to simulate the wave propagation on human body. In this work, in order to clarify the propagation mechanism of electromagnetic wave on human body, a surface waveguide HBC theoretical model based on stratified media cylinder is presented. A numerical model analyzed by finite element method(FEM) is used for comparing and validating the theoretical model. Finally, results of theoretical and numerical models from 80 MHz to 200 MHz agree fairly well, which means that theoretical model can characterize accurate propagation mechanism of HBC signal. Meanwhile, attenuation constants derived from two kinds of models are within the range from 1.64 to 3.37, so that HBC signal can propagate effectively on human body. The propagation mechanism derived from the theoretical model is useful to provide design information for the transmitter and the modeling of the propagation channel in HBC.
