High-frequency(HF)and ultrahigh-frequency(UHF)dual-band radio frequency identification(RFID)tags with both near-field and farfield communication can meet different application scenarios.However,it is time-consuming to...High-frequency(HF)and ultrahigh-frequency(UHF)dual-band radio frequency identification(RFID)tags with both near-field and farfield communication can meet different application scenarios.However,it is time-consuming to calculate the return loss of a UHF antenna in a dualband tag antenna using electromagnetic(EM)simulators.To overcome this,the present work proposes a model of a multi-scale convolutional neural network stacked with long and short-term memory(MSCNN-LSTM)for predicting the return loss of UHF antennas instead of EM simulators.In the proposed MSCNN-LSTM,the MSCNN has three branches,which include three convolution layers with different kernel sizes and numbers.Therefore,MSCNN can extract fine-grain localized information of the antenna and overall features.The LSTM can effectively learn the EM characteristics of different structures of the antenna to improve the prediction accuracy of the model.Experimental results show that the mean absolute error(0.0073),mean square error(0.00032),and root mean square error(0.01814)of theMSCNNLSTM are better than those of other prediction methods.In predicting the return loss of 100UHFantennas,compared with the simulation time of 4800 s for High Frequency Structure Simulator(HFSS),MSCNN-LSTM takes only 0.927519 s under the premise of ensuring prediction accuracy,significantly reducing the calculation time,which provides a basis for the rapid design of HF-UHF RFID tag antenna.ThenMSCNN-LSTM is used to determine the dimensions of the UHF antenna quickly.The return loss of the designed dualband RFID tag antenna is−58.76 and−22.63 dB at 13.56 and 915 MHz,respectively,achieving the desired goal.展开更多
With Al2O3 and SiO2 as polishing medium, under different polishing conditions, e.g. with different polishing pressure, polishing time and polishing fluid, the influences of polishing treatment on the return loss of op...With Al2O3 and SiO2 as polishing medium, under different polishing conditions, e.g. with different polishing pressure, polishing time and polishing fluid, the influences of polishing treatment on the return loss of optical fiber connectors were investigated. The return loss of optical fiber connectors is 32CD*238dB before polishing. The results show that dry polishing（i.e. no polishing fluid） with Al2O3 has less influence on return loss of optical fiber connectors, while dry polishing with SiO2 reduces return loss to about 20dB because of the end-face of optical fiber contaminated. The wet polishing（i.e. using distilled water as polishing fluid） with Al2O3 or SiO2 can increase return loss to 45CD*250dB, but wet polishing with Al2O3 may produce optical fiber undercut depth of 80CD*2140nm. Wet polishing with SiO2 should be preferentially selected for optical fiber connectors and polishing time should be controlled within 20CD*230s.展开更多
基金The research work is carried out under the Beijing Natural Science Foundation-Beijing Education Commission Joint Project(KZ202210015020)Discipline Construction and Postgraduate Education Project of BIGC(No.21090122005)BIGC Project(Ee202204).
文摘High-frequency(HF)and ultrahigh-frequency(UHF)dual-band radio frequency identification(RFID)tags with both near-field and farfield communication can meet different application scenarios.However,it is time-consuming to calculate the return loss of a UHF antenna in a dualband tag antenna using electromagnetic(EM)simulators.To overcome this,the present work proposes a model of a multi-scale convolutional neural network stacked with long and short-term memory(MSCNN-LSTM)for predicting the return loss of UHF antennas instead of EM simulators.In the proposed MSCNN-LSTM,the MSCNN has three branches,which include three convolution layers with different kernel sizes and numbers.Therefore,MSCNN can extract fine-grain localized information of the antenna and overall features.The LSTM can effectively learn the EM characteristics of different structures of the antenna to improve the prediction accuracy of the model.Experimental results show that the mean absolute error(0.0073),mean square error(0.00032),and root mean square error(0.01814)of theMSCNNLSTM are better than those of other prediction methods.In predicting the return loss of 100UHFantennas,compared with the simulation time of 4800 s for High Frequency Structure Simulator(HFSS),MSCNN-LSTM takes only 0.927519 s under the premise of ensuring prediction accuracy,significantly reducing the calculation time,which provides a basis for the rapid design of HF-UHF RFID tag antenna.ThenMSCNN-LSTM is used to determine the dimensions of the UHF antenna quickly.The return loss of the designed dualband RFID tag antenna is−58.76 and−22.63 dB at 13.56 and 915 MHz,respectively,achieving the desired goal.
文摘With Al2O3 and SiO2 as polishing medium, under different polishing conditions, e.g. with different polishing pressure, polishing time and polishing fluid, the influences of polishing treatment on the return loss of optical fiber connectors were investigated. The return loss of optical fiber connectors is 32CD*238dB before polishing. The results show that dry polishing（i.e. no polishing fluid） with Al2O3 has less influence on return loss of optical fiber connectors, while dry polishing with SiO2 reduces return loss to about 20dB because of the end-face of optical fiber contaminated. The wet polishing（i.e. using distilled water as polishing fluid） with Al2O3 or SiO2 can increase return loss to 45CD*250dB, but wet polishing with Al2O3 may produce optical fiber undercut depth of 80CD*2140nm. Wet polishing with SiO2 should be preferentially selected for optical fiber connectors and polishing time should be controlled within 20CD*230s.
