ID 原文 译文
40956 进而，模型在解码器中设计降噪模块和预测模块，克服一般循环神经网络难以对带噪声数据进行预测的问题，使得模型能够对含有噪声的输入变量进行分析。 Furthermore, the model designs the denoising module and prediction module in the decoder to overcome the difficulty of predicting noisy data with traditional recurrent neural networks, enabling the model to analyze input variables containing noise.
40957 通过利用电力物联网所采集的数据进行实验，结果证明提出的方法能很好地对风电功率进行预测，达到较好的预测效果。 By using the data collected by the power Internet of things to conduct experiments, the results show that the proposed method can forecast the wind power well and achieve a better prediction effect.
40958 针对直流无刷电机驱动系统存在的模拟PWM技术控制难、PWM芯片少以及PWM死区时间精度低等问题，本文采用Verilog语言设计了一款纯数字电路实现的PWM波形生成器。 In view of the problems in the brushless DC motor drive system, such as the difficulty of analog PWM technology control, the lack of PWM chips and the low precision of PWM dead time, this paper designs a pure digital PWM waveform generator using Verilog language.
40959 文中简要介绍了PWM在直流无刷电机系统的控制原理、电机转子位置和电机相导通的关系及PWM调制方式，重点描述了采用纯数字方法实现PWM波形发生器的设计流程。 This paper briefly introduces the control principle of PWM in brushless DC motor system, the relationship between motor rotor position and motor phase conduction and the PWM modulation mode, and emphatically describes the design process of PWM waveform generator using pure digital method.
40960 通过增加时钟除频模块，死区计数时钟频率可提高到PWM计数器的16倍; By adding a clock divider module, the clock frequency of dead-time counter can be increased to 16 times that of PWM counter.
40961 两通道PWM共用一个死区计数器，节省了设计资源。 Two channels of PWM share a dead-time counter, saving design resources.
40962 设计的PWM波形生成器可通过SPI接口进行参数配置，实现可编程、方便控制等优点。 The designed PWM waveform generator can be configured through SPI interface to realize the advantages of programmable, convenient control and so on.
40963 侧信道攻击中，泄露区间的定位对进一步提升攻击效果和芯片防护产生至关重要的作用。 Locating leakage plays a vital role in further improving the attack success rate and countermeasure in side-channel attacks.
40964 对于基于神经网络的模板攻击，由于神经网络是黑盒模型，使得泄露区间定位成为难题。 For template attacks based on convolutional neural network, it is difficult to locate the leakage due to the invisibility of the network.
40965 本文通过改进加权梯度类激活映射(Grad-CAM)，提出一种新的可以定位功耗或电磁曲线泄露位置的方法WAvg-Grad-CAM。 This paper proposed a new method named WAvg-Grad-CAM to locate the leakage spot of side-channel traces, based on the ideal of Gradient-weighted Class Activation Mapping(Grad-CAM).