变焦遗传算法优化变增益模糊ARX模型研究  被引量:1

Research on Optimization of Variable Gain Fuzzy ARX Model by Zooming Genetic Algorithm

在线阅读下载全文

作  者:刘冲[1] 宋智星 刘彬[2] LIU Chong;SONG Zhixing;LIU Bin(Department of Information Engineering,Hebei Chemical&Pharmaceutical College,Hebei 050026,China;School of Electrical Engineering,Yanshan University,Hebei 066004,China)

机构地区:[1]河北化工医药职业技术学院信息工程系,河北石家庄050026 [2]燕山大学电气工程学院,河北秦皇岛066004

出  处:《自动化仪表》2020年第2期42-46,共5页Process Automation Instrumentation

摘  要:针对传统ARX模型对非线性系统模型辨识精度比较低的问题,进行了模糊模型和ARX模型相关优化算法的调查,介绍了遗传算法优化模糊模型的现状,提出采用改进变焦遗传算法优化变增益模糊ARX模型参数的方法以提高模型的辨识精度。改进的变焦遗传算法能在不同前代种群情况下更新不同数量基因,以提高搜索速度;用不同的概率选择交叉位置,可避免早熟现象,并能在较短时间内达到最优或次优解。变增益模糊ARX模型可根据非线性系统的变化改变其增益,使模型的辨识精度提高。利用改进变焦遗传算法的优点,对变增益模糊ARX模型的参数进行优化,并通过两入两出多时滞离散非线性系统进行试验仿真。试验结果证明了改进变焦遗传算法优化变增益模糊ARX模型参数的方法能提高模型辨识精度,表明了提出的优化方法的有效性,为变焦遗传算法与模糊模型的结合提供了一种途径。Aiming at the problem of low identification accuracy of traditional ARX model for non-linear system model,the related optimization algorithms of fuzzy model and ARX model were investigated,the current situation of optimizing fuzzy model by genetic algorithm was introduced,and an improved zooming genetic algorithm was proposed for optimizing the parameters of variable gain fuzzy ARX model to improve the identification accuracy of the model.The improved zooming genetic algorithm could update different quantities of genes in different predecessor populations to improve search speed,and select crossover positions with different probabilities to avoid premature phenomena and achieve optimal or sub-optimal solutions in a relatively short time.Variable gain fuzzy ARX model could change its gain according to the change of the non-linear systemto improve the identification accuracy of the model.By using the advantages of improved zooming genetic algorithm,the parameters of variable gain fuzzy ARX model were optimized,and the experimental simulation was carried out by two-in-two-out multi-delay discrete nonlinear system.Experimental results proved the effectiveness of the proposed optimization method,which provided a way for the combination of the zooming genetic algorithm and the fuzzy model.

关 键 词:变焦遗传算法 模糊模型 ARX模型 变增益 辨识精度 参数优化 非线性系统 

分 类 号:TH-39[机械工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象