结合屏蔽外壳的PCB辐射发射智能化预测方法

iming at the problem that it is not possible to effectively predict the radiation emission of Printed Circuit Board (PCB) data combined with shielding housing. In this paper, based on electromagnetic shielding theory, a unified form of shielding shell data and PCB modeling method are proposed. In the modeling process, multiple factors affecting radiation emission in the shielding shell were analyzed, and then these factors, including the material and hole information on each surface of the shielding shell, were numerically analyzed. The radiation simulation calculation of the combination of the shielding shell and PCB was completed in the simulation software HFSS, and the radiation emission data was combined with the shielding shell and PCB data to form a complete data set of the electronic device system. Then, an intelligent radiation emission prediction model based on DNN is used to complete the training prediction on the data set combined with the shielding shell. The results show that the average absolute error of the prediction is also low, about 0.0014, which shows that the prediction method proposed in this paper has the advantages of accurate prediction, wide application scenarios and easy expansion.