| 基于最小二乘算子的混合计算智能辨识算法 |
| |
| 引用本文： | 赵明旺.基于最小二乘算子的混合计算智能辨识算法[J].系统工程学报,1997,12(3):99-105. |
| |
| 作者姓名： | 赵明旺 |
| |
| 作者单位： | 武汉冶金科技大学自动化系 |
| |
| 基金项目： | 武汉市科委“晨光计划”资助 |
| |
| 摘 要： | 基于非线性最小二乘（ＮＬＬＳ）法和遗传算法（ＧＡ）思想，通过定义ＮＬＬＳ算子、适应度以及混合数据结构，得到非线性回归模型非线性参数的混合计算智能辨识算法，该算法结合ＧＡ和ＮＬＬＳ法两者长处，即有较快收敛性，又能以较大概率求得全局（一致收敛）估计。计算结果表明该方法显著优于ＧＡ和ＮＬＬＳ法。
|
| 关 键 词： | 计算智能 参数辨识 最小二乘算子 算法 |
A HYBRID COMPUTATIONAL INTELLIGENT IDENTIFICATION ALGORITHM BASED ON LEAST SQUARE OPERATOR |
| |
| Zhao Mingwang.A HYBRID COMPUTATIONAL INTELLIGENT IDENTIFICATION ALGORITHM BASED ON LEAST SQUARE OPERATOR[J].Journal of Systems Engineering,1997,12(3):99-105. |
| |
| Authors: | Zhao Mingwang |
| |
| Abstract: | Based on ideas of both nonlinear least square (NLLS) method and genetic algorithm(GA),a NLLS operator,a fitness function,and a mixed numerical structure are defined and then a hybrid computational intelligent identification algorithm for nonlinear paramaters of nonlinear regressive models is got in this paper.The new algorithm with the faster convergence and the greater probability for the global (consistently convergence) estimates combines the advances of both GA and NLLS method.Finally,the computing results show that the algorithm is distinctly superior to the GA and the NLLS method. |
| |
| Keywords: | computational intelligent genetic algorithm nonlinear least square method parameter identification nonlinear regressive models |
| 本文献已被 CNKI 维普 等数据库收录！ |
