基于双混沌优化搜索的改进粒子群算法及应用  

Research on the Application of Particle Swarm Optimization Algorithm Based on Double Chaos Optimization Search

作　　者：张晓勇 王仲君[2] 闫军 杨忠保 ZHANG Xiao-yong;WANG Zhong-jun;YAN Jun;YANG Zhong-bao(Department of Public Basic Education,HEBI POLYTECHNIC,Hebi 458030,China;Department of Statistics in Faculty of Science,Wuhan University of Technology,Wuhan 430070,China;Hebi Huasheng Monitoring Equipment Manufacturing Co.Ltd,Hebi 458000,China;School of Mathematics and Statistics,Qiannan Normal University for Nationalities,Duyun 55800,China)

机构地区：[1]鹤壁职业技术学院公共基础教育学院,河南鹤壁458030 [2]武汉理工大学理学院统计系,湖北武汉430070 [3]鹤壁华盛监控设备制造有限公司,河南鹤壁458000 [4]黔南民族师范学院数学与统计学院,贵州都匀558000

出　　处：《数学的实践与认识》2024年第4期151-161,共11页Mathematics in Practice and Theory

基　　金：国家自然科学基金重点资助项目(61633011,混杂非线性系统的性能分析与控制设计及应用);河南省高等学校重点科研项目计划(23B110018);鹤壁职业技术学院校本科技类重点资助课题项目(2022-KJZD-011)。

摘　　要：针对现有算法在智能电阻箱动态误差校正方面存在的收敛速度慢、计算精度低,且易进入“局部最优”的陷阱等缺点,展开对智能电阻箱动态示数校正过程的重构及设计,并对动态误差校正优化算法进行研究.在双混沌优化系统中添加扰动因子与指数自适应学习方式改进搜索策略;在粒子群算法中将惯性权重因子修正为自适应权重因子,将学习因子修正为异步线性学习因子以优化算法,进而提出一种改进的粒子群优化算法(AL-DCPSO).利用8个经典函数对算法性能进行测试后,将这种算法应用在某型号智能电阻箱动态误差校正的过程中,研究结果表明:改进后的算法具有更高的计算精度(达到0.001)与更强的寻优能力,且在优化过程中呈现出较强的自适应学习能力,计算过程较为稳定,鲁棒性有效提升,耗时在阈值范围内有所增加.其创新性在于将双混沌优化机制的优点与粒子群算法相结合,应用到智能电阻箱动态误差校正的过程中,对动态误差校正方法进行了一定拓展,为粒子群优化算法在具体实际优化过程中的关键参数选取与策略设计,有效提升算法优化性能提供了一些借鉴.In response to the shortcomings of existing algorithms in the dynamic error correction of intelligent resistance boxes,such as slow convergence speed,low computational accuracy,and easy entry into the“local optimal”trap,the reconstruction and design of the dynamic indication correction process of intelligent resistance boxes are carried out,and the optimization algorithm for dynamic error correction is studied.Adding disturbance factors and exponential adaptive learning to improve the search strategy in a dual chaotic optimization system;In the particle swarm optimization algorithm,the inertia weight factor is modified to an adaptive weight factor,and the learning factor is modified to an asynchronous linear learning factor to optimize the algorithm.Therefore,an improved particle swarm optimization algorithm(AL-DCPSO)is proposed.After testing the performance of the algorithm using 8 classic functions,this algorithm was applied to the dynamic error correction process of a certain type of intelligent resistance box.The research results showed that the improved algorithms all had higher computational accuracy(up to 0.001)and stronger optimization ability,and showed strong adaptive learning ability during the optimization process.The calculation process was relatively stable,and the robustness was significantly reduced,The time consumption has slightly increased within the threshold range.Its innovation lies in combining the advantages of the dual chaos optimization mechanism with the particle swarm optimization algorithm,and applying it to the dynamic error correction process of intelligent resistance boxes.It has expanded the dynamic error correction method of instrument equipment to a certain extent,providing some reference for the selection of key parameters and strategy design of the particle swarm optimization algorithm in the specific practical optimization process,and effectively improving the optimization performance of the algorithm.

关 键 词：智能电阻箱 双混沌优化 扰动因子 自适应学习 粒子群算法 测试函数 寻优策略 动态误差校正 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]