检索结果-内蒙古大学图书馆

Adaptive Fault-Tolerant Tracking Control for MIMO discrete-time systems via Reinforcement Learning Algorithm With Less Learning Parameters

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2017年第1期14卷 299-313页

作者： Liu, Lei Wang, Zhanshan Zhang, Huaguang Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Liaoning Peoples R China State Key Lab Synthet Automat Proc Ind Shenyang 110819 Liaoning Peoples R China

This paper is concerned with a reinforcement learning-based adaptive tracking control technique to tolerate faults for a class of unknown multiple-input multiple-output nonlinear discrete-time systems with less learning parameters. Not only abrupt faults are considered, but also incipient faults are taken into account. Based on the approximation ability of neural networks, action network and critic network are proposed to approximate the optimal signal and to generate the novel cost function, respectively. The remarkable feature of the proposed method is that it can reduce the cost in the procedure of tolerating fault and can decrease the number of learning parameters and thus reduce the computational burden. Stability analysis is given to ensure the uniform boundedness of adaptive control signals and tracking errors. Finally, three simulations are used to show the effectiveness of the present strategy. Note to Practitioners-As the practical engineering systems are becoming more and more complex, it is more likely to suffer from faults which can lead to unpredictable behaviors and serious damages. Therefore, adaptive fault tolerant control technique plays an important role in modern engineering systems. As a matter of fact, it is always desired to minimize the maintenance cost even when some faults occur in the systems, which can reduce the energy consumption in the industrial production process. One way is to integrate the adaptive reinforcement learning algorithm into the fault tolerant controller. Furthermore, a major restriction of the learning algorithm is that a large number of parameters should be tuned online, which directly increase the computational burden. In order to tackle this difficulty, by adjusting the estimated values of the network weight vectors instead of their weights, the number of adaptive learning parameters is decreased, and the computational burden is reduced dramatically.

关键词： Adaptive critic design fault tolerant control multiple-input multiple-output discrete-time systems neural networks reinforcement learning algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：