Heatsinks have quasi-antenna behavior in many cases and cause interference both at the system level and at the PCB design level. Therefore, determination or prediction of both resonance frequencies and maximum radiated emission are crucial at any design step. In this paper, as a novelty, in 2–8 GHz band, a model based on deep learning is developed to predict resonance frequencies in parallel plate-fin type heatsinks. Parameters taken into account are the number of fins, the width, length, and height of the heatsinks. 3888 heatsinks with different sizes are modeled to prepare data set and the Grey Wolf Optimizer algorithm (GWO) is utilized to optimize the heatsink parameters. Consequently, while this model obtains outputs for certain inputs, the optimization algorithm procures certain inputs for these outputs. Furthermore, the predicted and optimized results are compared with the simulation and measurement results. The proposed model successfully works according to the measurement and the proposed model results since $R^2$ values are 0.96, 0.98, 0.97, and 0.99 for $f_1,f_2,{\mathit{RE}}_{\max 1}$, and ${\mathit{RE}}_{\max 2}$, respectively. The results are good agreement and R-squared values of resonances ($f_1,f_2$) and the maximum radiated emissions (${\mathit{RE}}_{\max 1},{\mathit{RE}}_{\max 2}$) are quite acceptable considering the sophisticate of the proposed model.

散热器在许多情况下具有准天线性能，并且会在系统级和PCB设计级产生干扰。因此，在任何设计步骤中，谐振频率和最大辐射发射的确定或预测都是至关重要的。在本文中，作为一种新颖性，在2-8 GHz频带中，开发了一个基于深度学习的模型来预测平行板翅式散热器的共振频率。要考虑的参数是散热片的数量，散热器的宽度，长度和高度。对具有不同尺寸的3888散热器进行建模以准备数据集，并使用Gray Wolf Optimizer算法（GWO）来优化散热器参数。因此，虽然此模型获得某些输入的输出，但优化算法会为这些输出获取某些输入。此外，将预测和优化结果与仿真和测量结果进行比较。提出的模型根据测量结果和提出的模型结果成功工作${\mathrm{[R}}^{\mathrm{2个}}$ 值分别为0.96、0.98、0.97和0.99 $F_{\mathrm{1个}}，F_{\mathrm{2个}}，{\mathit{关于}}_{\mathrm{最大限度}\mathrm{1个}}$， 和 ${\mathit{关于}}_{\mathrm{最大限度}\mathrm{2个}}$， 分别。结果是良好的一致性和共振的R平方值（$F_{\mathrm{1个}}，F_{\mathrm{2个}}$）和最大辐射发射量（${\mathit{关于}}_{\mathrm{最大限度}\mathrm{1个}}，{\mathit{关于}}_{\mathrm{最大限度}\mathrm{2个}}$考虑到所提出模型的复杂性，）是完全可以接受的。