基于遗传算法混合有源滤波器参数的多目标优化  

Multi-object optimization of hybrid active power filter based on genetic algorithm

作　　者：陈峻岭[1] 姜新建[1] 朱东起[1] 邓礼宽[1] 

机构地区：[1]清华大学电机工程与应用电子技术系,北京100084

出　　处：《清华大学学报（自然科学版）》2006年第1期5-8,共4页Journal of Tsinghua University(Science and Technology)

摘　　要：为了解决混合有源滤波器(hybrid active pow erfilter,HAPF)参数匹配以及无源部分和有源部分容量的合理分配,提出一种基于小生境遗传算法的多目标满意优化设计方法,较为全面地考虑HAPF的容量、滤波效果、无功补偿等因素,使得多目标参数求解达到协调满意的效果。优化结果表明:有源部分容量仅为滤波器容量的6.4%,电流总畸变率降低到0.8%,同时满足系统无功功率需要,降低了HAPF系统的投资,提高性能价格比,达到HAPF实用化及谐波抑制的目的。A multi-object optimization approach was developed for the design of hybrid active power filters （HAPF） to give better mitigation of the harmonics and better reactive power compensation. The genetic algorithm was used with optimization theory to improve the algorithm preeislon and stability. The optimization is more effective since the performance goals and optimization parameters were optimized together. The HAPF design results show the effectiveness of the optimization approach with a HAPF design having a active power filter rating ratio of 6.4%, and a total harmonic distortion of the system current of below 0.8%.

关 键 词：多目标规划 混合有源滤波器 遗传算法 

分 类 号：O221.6[理学—运筹学与控制论] TM762[理学—数学]