ID 原文 译文
12764 根据锰锌铁氧体低频磁导率高，镣锌铁氧体高频磁导率稳定的特点，提出双磁芯共模电感的设计方法,实现共模电感宽频率和小体积。 Based on the characteristics that Mn-：n ferrite has high magnetc conductivity at low frequency and N i-：n ferrite has stable magnetc conductivity at high frequency, the design of using common mode inductor with dual magnetc core is proposed, and it makes the common mode inductor achieve a wider frequency and a smaller volume.
12765 实测结果证明输入电磁干扰滤 波器可使电源变换器符合GJB 151中CE102要求。 Finally, the experimental results verify that the power supply converter adoptng the des gned nput EMI flter can meet the requrements of CE102 in GJB 151.
12766 针对人工提取雷达辐射源信号特征存在提取周期长、特征描述不完备等局限性，提出了一种基于深度学习栈式自编码机和模糊函数主脊的雷达信号识别方法。 Aiming at the limitation of artiticial extraction of radar emitter signa l features, such as long extraction period and incomplete feature description, a radar emitter signal recognition method is proposed based on ambiguity function main ridge and stacked autcencoder of deep learning.
12767 该方法根据信号模糊函数主脊包含丰富的内在调制信息的特点，从信号中提取用于分类识别的抽象特征。 According to the ambiguity function main ridge contains rich intrinsic modulation information; the method of this paper extracts abstract features for classification recognition from radar emitter signals.
12768 通过对六种雷达辐射源信号进行实验，并对比人工特征提取及其他深度学习方法,结果表明,本文所提方法在信噪比(signal-noise ratio, SNR)为2 dB 以上时均能保持100%的识别准确率,SNR为-6 dB时识别准确率仍能保持82.S3%以上,明显高于其他方法。 We experiment with s ix radar emitter sgnals and comparesthe proposed method with other artificia l features and deep learning methods. The experimental results show that the proposed method can mamtain 100% recognition accuracy when the signal-noise ratio i s above 2 dB. And the s ignal-noise ratio is -6 dB, the recognition accuracy can st i ll be maintained above 82. 83% , which is significantly higher than other methods.
12769 即使在包含相同调制类型不同参数的信号环境中,当SNR大于0 dB时识别率均稳定在95.0%以上, SNR降低到一4 dB时识别率也能达到79.0%。 Even though in the sgnal en- vronment that contans the same modulaton type but dfferent modulaton parameters, when the sgnal-to-noise ratio is greater than 0 dB, the recognition accuracy is stable above 95%. The recognition accuracy can reach 79% when the s ignal-noise ratio is reduced to—4 dB.
12770 证明该方法能有效提取到信号的深层特征,且具有良好的抗噪性能,基本满足实际战场的需求。 It is proved that the method can effectively extract the deep features of the signal and has good anti-noise performance, which bascally meets the requirements of the actual battlefield.
12771 针对现有能量收集装置存在易受天气影响、安装复杂、寿命短、绝缘要求高等问题,文中提出采用电容收集高压输电线路来感应电场能量的方法。 Aiming at the problems that existing energy harvesting devices are susceptible to weather, complcated installation, short life and high insulation requirements, the paper proposes a method for harvest ng Jnduced electric Held energy oH hgh voltage transmisson line by using capacitor.
12772 这种与高压输电线路无直接电器连接的方法,具有供能 稳定、能源清洁、操作简便等特点。 This method of isolated electrical connection with high-voltage transmisson lines has the characterstics of stable energy supply, clean energy and easy operation.
12773 根据该方法收集能量的原理，建立了相应的等效电路，分析了该方法收集 能量的特点。 According to the prmciple of harvesting energy by the method, the paper establishes the corresponding equivalent circuit and analyzes the characteristics of the energy harvested by the method.