论文部分内容阅读
针对现有机理建模算法普遍存在计算电磁脉冲响应过程过于复杂的问题,为能够给电子设备静电放电电磁脉冲响应计算提供一种简便有效的能量耦合建模方法,设计了脉冲场强测试仪的静电放电辐射实验。用NARX神经网络代替传统NARX网络,依靠遗传算法对网络的初始权值、阈值进行优化,以3.5 kV静电放电实验数据作为建模数据对系统进行非线性辨识,并对4.5 kV静电放电电磁脉冲响应进行预测。建模结果表明,两种模型均能准确预测响应波形,但优化后的NARX神经网络模型精度更高。该建模方法计算过程简单。该方法同样适用于其他电磁脉冲响应建模。
Aiming at the problem that the existing algorithms for modeling the mechanism are too complex to calculate the electromagnetic impulse response process, a simple and effective energy coupling modeling method is provided for calculating the electromagnetic impulse response of the electrostatic discharge of the electronic device. The pulse field strength tester Electrostatic discharge radiation experiment. The NARX neural network is used to replace the traditional NARX network. Genetic algorithms are used to optimize the initial weights and thresholds of the network. Non-linear identification of the system is made using experimental data of 3.5 kV electrostatic discharge as modeling data. The 4.5 kV electrostatic discharge electromagnetic pulse response Make a prediction The modeling results show that both models can accurately predict the response waveforms, but the optimized NARX neural network model has higher accuracy. The modeling method is simple to calculate. This method is equally applicable to other electromagnetic impulse response modeling.