| 基于共轭梯度迭代算法受控AR模型的参数辨识 |
| |
| 引用本文： | 胡志增,梁开福.基于共轭梯度迭代算法受控AR模型的参数辨识[J].吉首大学学报(自然科学版),2016,37(6):29-33. |
| |
| 作者姓名： | 胡志增 梁开福 |
| |
| 作者单位： | (湘潭大学数学与计算科学学院，湖南 湘潭 411105) |
| |
| 基金项目： | 湖南省自然科学基金面上项目（2015JJ2134） |
| |
| 摘 要： | 推导了单输入单输出系统的辅助模型，它有助于减少计算量和提高共轭梯度迭代算法（新算法）的收敛速度.相比于受控移动平均模型中所提出的交互式随机梯度算法，新算法用更少的迭代步骤就可求出模型的参数估计.另外，新算法能避免出现矩阵的逆矩阵形式.对新算法与双共轭梯度算法进行比较，并给出数值实例检验新算法的有效性.
|
| 关 键 词： | 参数估计 辅助模型 共轭梯度迭代算法 受控AR模型 |
Parameter Estimation Based a Conjugate Gradient Iteration Algorithm for Controlled Autoregressive Models |
| |
| HU Zhizeng,LIANG Kaifu.Parameter Estimation Based a Conjugate Gradient Iteration Algorithm for Controlled Autoregressive Models[J].Journal of Jishou University(Natural Science Edition),2016,37(6):29-33. |
| |
| Authors: | HU Zhizeng LIANG Kaifu |
| |
| Institution: | (School of Mathematics and Computational Science，Xiangtan University，Xiangtan 411105，Hunan China) |
| |
| Abstract: | The auxiliary model is derived for the single-input single-output (SISO) system to reduce computational burden and improve the convergence rate of the new iteration algorithm based on the conjugate gradient.Compared with the interactive stochastic gradient algorithm for controlled moving average models，the proposed new iteration algorithm can give parameter estimates in less steps.In addition，the new algorithm can avoid the inverse of a matrix.The new algorithm is also compared with the biconjugate gradient algorithm.The simulation example shows that the proposed algorithm works quite well. |
| |
| Keywords: | parameter estimation auxiliary model conjugate gradient iterative algorithm controlled autoregressive model |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《吉首大学学报(自然科学版)》浏览原始摘要信息 |
| 点击此处可从《吉首大学学报(自然科学版)》下载免费的PDF全文 |
