基于遗传算法的系统辨识方法研究

针对从样本数据进行系统辨识的问题,提出一种由典型数学模型相互组合构成系统模型的新的辨识方法,将系统结构辨识问题转化为组合优化问题,并采用遗传算法同时实现了系统的结构辨识与参数辨识,模拟仿真与实际系统辨识结果验证了系统辨识方法的合理性与求解算法的有效性.

Study on System Identification Method based on Genetic Algorithms

In terms of the system identification problem with sample data,a new identification method is proposed.The method employs a system model composed with classical mathematical models so as to transform the system structure identification problem into a combinational problem.A Genetic Algorithm is designed to implement the identification on the system structure and parameters.The results from the simulation and practical identification system testify the rationality of the new identification method and the effectiveness of the solving algorithm.