基于遗传算法的太赫兹腔体滤波器辅助设计

Design of terahertz cavity filter based on genetic algorithm

太赫兹滤波器是太赫兹系统的重要器件,然而它的快速准确设计是难点。基于遗传算法(GA)和有限元法的联合仿真,实现了太赫兹滤波器的快速准确设计。采用HFSS-MATLABAPI脚本库,利用HFSS对于场仿真的精确性,同时在MATLAB中基于遗传算法对结果进一步优化,降低了试探性优化的盲目性。采用该方法设计了210~230GHz带通滤波器,测试结果表明,带内插损均小于0.6 dB,带外抑制度大于30 dB,验证了该方法的准确性。

The terahertz filter is an important component of the terahertz system,which is difficult to be designed quickly and accurately.Based on the co-simulation of Genetic Algorithm(GA)and finite element method,a fast and accurate design method of terahertz filter is realized.The HFSS-MATLABAPI script library is utilized in the design,which not only adopts the accuracy of HFSS for field simulation,but also reduces the blindness of tentative optimization by genetic algorithm in MATLAB.A 210-230 GHz band-pass filter is designed by this method.The measured results show that the in-band insertion loss is less than 0.6 dB and the out-of-band rejection is more than 30 dB.The accuracy of the method is verified.