摘要
针对难以建立精确数学模型时的碰撞振动系统混沌运动控制问题,提出一种采用QPSO算法优化RBFNN的参数反馈混沌控制方法。利用分岔图、Lyapunov指数谱图、Poincaré截面图和相图分析了混沌运动与系统特定参数条件间的关联关系及表现特征,基于RBFNN设计了参数反馈混沌控制器,并将最大Lyapunov指数作为加权项构建适应度函数,以引导QPSO算法优化控制器的参数并量化评价混沌控制效果。仿真研究中,进一步分析了QPSO算法的控制参数(即收缩扩张系数)对混沌控制效果的影响。
Aiming at the chaos control problem for a single-degree-of-freedom vibro-impact system with clearance,a parameter feedback control method of chaotic motion based on RBFNN(radial basis function neural network)optimized by QPSO(quantum particle swarm optimization)algorithm is proposed in this paper.The correlation relationship and its characteristics between the chaotic motion and specific parameters of the system were analyzed by using bifurcation diagram,Lyapunov exponential spectrum diagram,Poincare cross section diagram and phase diagram.A parameter feedback chaos controller was designed based on RBFNN,and the maximum Lyapunov exponent was used as a weighted term to construct a fitness function,so as to guide the QPSO algorithm to optimize the parameters of the controller and quantitatively evaluate the chaos control effect.In the simulation experiment,the influence of QPSO control parameters(i.e.,shrinkage and expansion coefficient)on chaos control effect is further analyzed and studied.
作者
卫晓娟
周方伟
李宁洲
丁旺才
WEI Xiaojuan;ZHOU Fangwei;LI Ningzhou;DING Wangcai(School of Railway Transportation,Shanghai Institute of Technology,Shanghai 201418,China;School of Mechatronic Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China)
出处
《机械科学与技术》
CSCD
北大核心
2023年第6期842-849,共8页
Mechanical Science and Technology for Aerospace Engineering
基金
国家自然科学基金项目(51665027,11962013)
甘肃省自然科学基金项目(20JR5RA406)
甘肃省高等学校创新能力提升项目(2019B-059)。
