摘要
为解决非线性系统Wiener模型参数辨识问题,提出了一种基于改进人工蜂群算法(NLJ-artificial bee colony algorithm,NABC)的分步辨识方法。NABC算法融合了人工蜂群算法的简洁性和随机搜索算法的高精度优势,有较快的收敛速度、较强的局部求精和全局搜索能力。通过对经典测试函数的寻优,验证了NABC算法较其他改进方法的优势。分步辨识法解决了Wiener模型辨识过程中容易造成的误差累积问题,实现其线性和非线性部分的独立辨识。通过pH中和反应过程建模仿真验证了分步辨识法的有效性。
A two-step method is proposed to solve the parameter identification problem of nonlinear Wiener system based on a no-vel artificial bee colony algorithm (NABC).NABC took advantages of simplicity of artificial bee colony algorithm and random search algorithm to improve the global optimization ability and convergence speed.It uses NABC to test two classical functions to show the advantages.The two-step method identifies the linear part and nonlinear part of Wiener system respectively to avoid er-ror accumulation.The experiment study of pH neutralization process shows that the two-step identification procedure is effective.
出处
《中国科技论文》
CAS
北大核心
2015年第14期1671-1676,共6页
China Sciencepaper
基金
国家自然科学基金资助项目(61273132)
国家重点基础研究发展计划(973计划)资助项目(2007CB714300)
