改进的布谷鸟算法优化粒子滤波研究  

Research on Optimized Particle Filtering by Improved Cuckoo Algorithm

作　　者：王晓华[1] 聂腾腾 WANG Xiaohua;NIE Tengteng(School of Electronics and Information,Xi’an Polytechnic University,Xi’an 710048,China)

机构地区：[1]西安工程大学电子信息学院,西安710048

出　　处：《计算机工程与应用》2020年第12期60-65,共6页Computer Engineering and Applications

基　　金：国家自然科学基金(No.51607133);教育部工程科技人才培养研究项目(No.18JDGC029);陕西省科技厅工业攻关项目(No.2016GY-136);纺织工业联合会科技指导性计划(No.2018098);西安工程大学博士科研启动基金(No.107020384)。

摘　　要：针对布谷鸟算法易限于局部最优的问题,通过对布谷鸟算法的搜索步长值α和发现外来鸟卵的物种的概率pα进行改进,来平衡布谷鸟算法局部寻优与全局寻优的能力。改进的布谷鸟算法与粒子滤波结合,代替粒子滤波的重采样过程,解决粒子贫化和估计精度低的问题。实验结果表明,改进的布谷鸟优化粒子滤波算法中,粒子的多样性提高,从而保证了估计精度的提高。For the problem that the cuckoo algorithm is easily limited to the local optimum,the ability of the cuckoo algorithm to local optimization and global optimization is balanced by improving the search step valueαof the cuckoo algorithm and the probability pαof the species of an exotic bird in this paper.Combined with particle filtering the improved cuckoo algorithm replaces the resampling process of particle filtering to solve the problem of particle depletion and low estimation accuracy.The experimental results show that the particle diversity of the improved cuckoo optimized particle filter algorithm is improved,which ensures the estimation accuracy.

关 键 词：粒子滤波 粒子贫化 布谷鸟算法 重采样 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]