摘要
针对传统智能优化算法对混沌系统参数辨识精度低、速度慢的问题,以教学优化算法为基础,通过在其教授-学习阶段后加入反馈阶段,提出一种基于改进教学优化算法的混沌系统参数辨识方法。分别以Jerk系统和Sprott-J系统为模型,利用改进教学优化算法辨识混沌系统的未知参数。与传统的粒子群优化算法、量子粒子群优化算法及教学优化算法辨识做比较。仿真结果表明,改进教学优化算法明显提高了混沌系统参数辨识精度和速度,验证了该方法的可行性和有效性。
Aiming at the low precision and speed of traditional intelligent optimization algorithm for parameter identification in chaotic system,on the basis of teaching-learning-based optimization algorithm,the feedback stage was added after its teaching and learning stage,so a method for parameter identification in chaotic system based on improved teaching-learning-based optimization algorithm was proposed.Jerk system and Sprott-J system were taken as models respectively,and unknown parameters in chaotic system were identified using feedback teaching-learning-based optimization algorithm.It was compared to the identification based on traditional particle swarm optimization algorithm,quantum particle swarm optimization algorithm and teachinglearning-based optimization algorithm.The simulation results show that the improved teaching-learning-based optimization algorithm significantly improves the precision and speed of parameter identification in chaotic system.Meanwhile,the feasibility and effectiveness of this identification method are well demonstrated.
出处
《计算机工程与设计》
北大核心
2016年第1期195-200,共6页
Computer Engineering and Design
基金
国家自然科学基金项目(61463047)
关键词
教授阶段
学习阶段
反馈阶段
混沌系统
参数辨识
teaching stage
learning stage
feedback stage
chaotic system
parameter identification
