| Hierarchical Least Squares Identification and Its Convergence for Large Scale Multivariable Systems |
| |
| 作者姓名： | 丁锋 丁韬 |
| |
| 作者单位： | DING Feng，DING Tao Department of Automation，Tsinghua University，Beijing 100084，China |
| |
| 基金项目： | Supported by the National Natural Science Foundationof China (Nos.6 0 0 740 2 9and 6 9934 0 10 ) and theFoundation of Inform ation School of TsinghuaU niversity |
| |
| 摘 要： |
|
Hierarchical Least Squares Identification and Its Convergence for Large Scale Multivariable Systems |
| |
| DING Feng,DING Tao.Hierarchical Least Squares Identification and Its Convergence for Large Scale Multivariable Systems[J].Tsinghua Science and Technology,2002,7(3). |
| |
| Authors: | DING Feng DING Tao |
| |
| Institution: | DING Feng,DING Tao Department of Automation,Tsinghua University,Beijing 100084,China |
| |
| Abstract: | The recursive least squares identification algorithm (RLS) for large scale multivariable systems requires a large amount of calculations, therefore, the RLS algorithm is difficult to implement on a computer. The computational load of estimation algorithms can be reduced using the hierarchical least squares identification algorithm (HLS) for large scale multivariable systems. The convergence analysis using the Martingale Convergence Theorem indicates that the parameter estimation error (PEE) given by the HLS algorithm is uniformly bounded without a persistent excitation signal and that the PEE consistently converges to zero for the persistent excitation condition. The HLS algorithm has a much lower computational load than the RLS algorithm. |
| |
| Keywords: | large scale system identification parameter estimation hierarchical identification |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
