| 基于多模型切换的智能主动容错控制方法研究 |
| |
| 引用本文： | 李炜,鲁保云. 基于多模型切换的智能主动容错控制方法研究[J]. 计算机仿真, 2008, 25(1): 328-331,343 |
| |
| 作者姓名： | 李炜 鲁保云 |
| |
| 作者单位： | 兰州理工大学电气工程与信息工程学院,甘肃兰州,730050 |
| |
| 摘 要： | 针对某些具有可能故障先验知识的非线性系统,采用主动容错控制方法,基于神经网络对系统正常及各种先验故障情形建模,并采用基于神经网络的PID控制方法离线整定出各种故障模式下的控制律,由此建立模型库;在系统实时运行时,依据系统性能容忍度指标和模型失配度指标的计算分析,判断系统所处运行模式,切换与该模式匹配的控制律,从而达到系统主动容错控制的目的.最后将所提出的主动容错控制方法应用于某一非线性系统和线性系统,仿真结果表明了方法的有效性.
|
| 关 键 词： | 非线性系统 神经网络 模型库 主动容错控制 |
| 文章编号： | 1006-9348（2008）01-0328-04 |
| 收稿时间： | 2006-12-18 |
| 修稿时间： | 2006-12-20 |
Intelligent Active Fault-tolerant Control Using Multiple Models Approach |
| |
| LI Wei,LU Bao-yun. Intelligent Active Fault-tolerant Control Using Multiple Models Approach[J]. Computer Simulation, 2008, 25(1): 328-331,343 |
| |
| Authors: | LI Wei LU Bao-yun |
| |
| Affiliation: | LI Wei LU Bao-yun (College of Electrical , Information Engineering,Lanzhou University of Technology,Lanzhou Gansu 730050,China) |
| |
| Abstract: | An active fault -tolerant control of nonlinear system is investigated based on model bank. The model bank is formed of the NN models and corresponding controller parameters aimed at various possible running modes. Based on neural networks method, the models and switchable controllers are trained offline respectively. The switch of controller parameters in running is according to the analysis of supervision indices. The approach is validated by simulations and has good availability for linear systems likewise. |
| |
| Keywords: | Nonlinear system Neural networks Model bank Active fault - tolerant control |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
