基于UKF的实时混合试验自适应时滞补偿方法  

Unscented Kalman filter-based adaptive delay compensation method by real-time hybrid simulation

作　　者：王涛 龚越峰 孟丽岩 浩杰敦 王贞 许国山[3] Wang Tao;Gong Yuefeng;Meng Liyan;Hao Jiedun;Wang Zhen;Xu Guoshan(School of Architecture&Civil Engineering,Heilongjiang University of Science&Technology,Harbin 150022,China;School of Civil Engineering&Architecture,Wuhan University of Technology,Wuhan 430070,China;School of Civil Engineering,Harbin Institute of Technology,Harbin 150090,China)

机构地区：[1]黑龙江科技大学建筑工程学院,哈尔滨150022 [2]武汉理工大学土木与建筑学院,武汉430070 [3]哈尔滨工业大学土木工程学院,哈尔滨150090

出　　处：《黑龙江科技大学学报》2023年第2期281-286,293,共7页Journal of Heilongjiang University of Science And Technology

基　　金：国家自然科学基金项目(52278173;52078398)。

摘　　要：为解决伺服加载系统的变时滞问题,提出了一种基于无迹卡尔曼滤波的自适应时滞补偿方法。针对Benchmark问题开展虚拟实时混合实验,分析系统时滞给实时混合实验带来的不利影响,利用UKF-ADC方法对系统时滞进行自适应补偿,验证UKF-ADC方法对伺服加载系统的补偿效果。结果表明,相比于经典多项式外插法,UKF-ADC方法在名义值和标准差两种统计算法下的评价指标最大值分别减少了28.25%、55.93%,UKF-ADC方法表现出良好的精度及鲁棒性。This paper proposes an adaptive time-delay compensation method based on the unscented Kalman filter to solve the time-varying delay problem in servo loading system.The study involves performing virtual real-time hybrid simulation for the Benchmark problem;analyzing the adverse effects of the system delay on the real-time hybrid simulation;carrying out adaptive compensation by using UKF-ADC method;and verifying the compensation effect of the UKF-ADC method on the servo loading system.The results show that compared with the classical polynomial extrapolation,the maximum of evaluation indexes with UKF-ADC method under the two statistical algorithms of nominal value and standard deviationare reduces by 28.25%and 55.93%,respectively,and the UKF-ADC method shows better accuracy and robustness.

关 键 词：无迹卡尔曼滤波 变时滞 自适应补偿 

分 类 号：TU317[建筑科学—结构工程]