改进鸽群优化算法在SVD-UKF参数整定中的应用  

Application of improved pigeon-inspired optimization algorithm in SVD-UKF parameter setting

作　　者：周延锋 李宁洲 卫晓娟 王卫红 ZHOU Yanfeng;LI Ningzhou;WEI Xiaojuan;WANG Weihong(School of Electromechanical,Lanzhou Jiaotong University,Lanzhou 730070,China;School of Railway Transportation,Shanghai Institute of Technology,Shanghai 201418,China;Zhuzhou Gofront Equipment Co Ltd,Zhuzhou,412001,China)

机构地区：[1]兰州交通大学机电工程学院,甘肃兰州730070 [2]上海应用技术大学轨道交通学院,上海201418 [3]株洲九方装备股份有限公司,湖南株洲412001

出　　处：《传感器与微系统》2022年第2期153-156,160,共5页Transducer and Microsystem Technologies

基　　金：国家自然科学基金资助项目(51665027);甘肃省高等学校创新能力提升项目(2019B—059);甘肃省自然科学基金资助项目(20JR5RA406)。

摘　　要：为解决鸽群优化(PIO)算法易陷入局部最优、收敛速度慢的问题,提出了一种改进的鸽群优化(IPIO)算法。将全局搜索能力较强的天牛须搜索(BAS)算法融入到指南针算子中,在地标算子中引入混沌扰动策略来提高算法的局部搜索精度。利用测试函数对改进算法进行性能测试,并提出奇异值分解—无迹卡尔曼滤波(SVD-UKF)参数整定的适应度函数,将经改进算法优化后的参数应用到机车黏着控制系统中。仿真结果表明:改进算法具有更强的全局搜索能力和更高的搜索精度,经参数整定后的SVD-UKF具有良好的滤波估计效果。In order to address the problem that the pigeon-inspired optimization(PIO)algorithm is easy to fall into the local optimum and the convergence rate is slow, an improved pigeon-inspired optimization(IPIO)algorithm is proposed.The beetle antennae search(BAS)algorithm with strong global search ability is integrated into the compass operator.The chaos disturbance strategy is introduced into the landmark operator to improve the local search accuracy of the algorithm.The performance of the improved algorithm is tested by using standard test function, and the fitness function of singular value decomposition unscented Kalman filtering(SVD-UKF)parameter tuning is proposed, and the parameters optimized by the improved algorithm are applied to the locomotive adhesion control system.The simulation results show that the improved algorithm has stronger global search ability and higher search precision, and the SVD-UKF after parameter setting has a good filtering estimation effect.

关 键 词：鸽群优化算法 天牛须算法 混沌扰动 全局寻优 参数整定 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]