| 引用本文: | 马晓敏.基于神经网络的动态系统逆模型辨识及闭环控制[J].控制理论与应用,1997,14(6):829~836.[点击复制] |
| MA Xiaomin.Inverse Identification and Closed-Loop Control of Dynamic Systems Using Neural Networks[J].Control Theory and Technology,1997,14(6):829~836.[点击复制] |
|
| 基于神经网络的动态系统逆模型辨识及闭环控制 |
| Inverse Identification and Closed-Loop Control of Dynamic Systems Using Neural Networks |
| 摘要点击 984 全文点击 396 投稿时间：1995-11-09 修订日期：1996-09-21 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 |
| 1997,14(6):829-836 |
| 中文关键词 神经网络 系统辨识 自适应控制 |
| 英文关键词 neural networks system identification adaptive control |
| 基金项目 |
|
| 中文摘要 |
| 本文提出一种动态线性或非线性系统的神经网络逆模型辨识结构．并引出两种PID与神经网络逆模型相结合的自适应控制方案．神经网络模型采用基于U－D分解卡尔曼滤波学习算法（UDK）的动态前向多层同．仿真结果表明了所述辨识方案的有效性及特点． |
| 英文摘要 |
| A structure for inverse identification of dynamic linear or non-linear system using neural network is presented. Two types of closed-loop control schemes that combine the neural network inverse model with PID are proposed. The dynamic feed forward multilayer network for identification and control is trained by a novel learning algorithm based on U-D factorization Kalman filter (UDK). The potentials of the proposed structure and schemes are demonstrated by simulation studies. |