一种新型非线性系统模型参数辨识方法

摘要

关于非线性自动控制系统优化问题,为解决复杂非线性系统的辨识问题,提出了一种基于菌群优化算法的非线性系统辨识方法.结合菌群优化算法的特点,通过将待辨识参数设置为群体细菌在参数空间的位置,并利用细菌群体觅食的动态行为来实现对系统参数的辨识,有效地提高了参数辨识的精度和效率.通过对重油热解三集总模型进行了仿真研究,得到了较为精确的过程模型,模型输出与实际输出基本一致.仿真结果表明:菌群优化算法为非线性系统模型参数估计提供了一种有效的途径.%Nonlinear system identification is one of the most important topics of modem identification. A novel approach for complex nonlinear system identification was proposed based on the bacterial swarm foraging for optimization ( BSFO). By combining the bacterial swarm foraging for optimization, BSFO was used to simulate the social behavior of foraging bacteria, in which the bacteria positions in the parameter spaces were set as the parameters of NSM, and the precision and efficiency for parameters identification were improved. Applied to heavy oil thermal cracking model , the method obtained the precise process model, and the model's outputs coincide to the actual outputs. The simulation results show that the BSFO algorithm provides an attractive method to identify parameters of NSM.