基于NSGA-Ⅱ算法的低通滤波器优化  

Low pass filter optimization based on NSGA-Ⅱ

作　　者：袁爱霞[1,2] 房少军[1] 刘浩然 段云梦 YUAN Aixia;FANG Shaojun;LIU haoran;DUAN Yunmeng(School of Information Science and Technology, Dalian Maritime University, Dalian 116026, China;School of Information Science and Engineering, Dalian Polytechnic University, Dalian 116034, China)

机构地区：[1]大连海事大学信息科学技术学院,辽宁大连116026 [2]大连工业大学信息科学与工程学院,辽宁大连116034

出　　处：《大连工业大学学报》2021年第3期230-234,共5页Journal of Dalian Polytechnic University

基　　金：国家自然科学基金项目(61571075).

摘　　要：为满足滤波器多个性能参数优化的需求,提出了一种基于NSGA-Ⅱ算法的滤波器多目标优化方法,并对算法中群体的多样性和全局搜索能力进行了改进。通过对5阶定K型低通滤波器进行仿真,截止频率与设计目标有较大偏差。针对这个滤波器利用NSGA-Ⅱ算法将插入损耗、反射损耗以及群时延作为目标函数按照不同要求进行优化,并对优化后的滤波器及实际模型进行了设计和仿真。将插入损耗作为优化目标,不考虑其他两个目标,优化后的结果与优化前的滤波器性能比较,截止频率和设计目标间的偏差明显降低。优化出插入损耗、反射损耗以及群时延均有要求时的最优解,此结果可用于设计各项性能均衡的滤波器。In order to meet the requirements of optimizing multiple performance parameters of filters,a multi-objective filter optimization method based on NSGA-Ⅱalgorithm was proposed,and the group diversity and global search ability of the algorithm were improved.The cut-off frequency deviated greatly from the design objective through the simulation of the 5th-order fixed K-type low-pass filter.For this filter,NSGA-Ⅱalgorithm was used to optimize the insertion loss,reflection loss and group delay as the objective function according to different requirements,and the optimized filter and its actual model were designed and simulated.Taking insertion loss as the optimization objective and ignoring the other two objectives,the deviation between the cut-off frequency and the design objective was significantly reduced by comparing the optimized results with the performance of the filter before optimization.The optimal solution is obtained when the insertion loss,reflection loss and group delay are all required,and the results can be used to design filters with balanced performance.

关 键 词：NSGA-Ⅱ 滤波器优化 多目标 群体的多样性 全局搜索能力 

分 类 号：TP23[自动化与计算机技术—检测技术与自动化装置]