| 采用BP神经网络记忆模糊规则的控制 |
| |
| 引用本文： | 应行仁,曾南.采用BP神经网络记忆模糊规则的控制[J].自动化学报,1991,17(1):63-67. |
| |
| 作者姓名： | 应行仁 曾南 |
| |
| 作者单位： | 1.中国科学院自动化研究所,北京 |
| |
| 基金项目： | 国家自然科学基金 No.68974016 |
| |
| 摘 要： | 本文提供了一种比模糊推理更为自然的方式使用人们的经验知识,通过一组神经元不同
程度的兴奋表达一个抽象的概念值,由此将抽象的经验规则转化成多层神经网络的输入一输
出样本.通过Back-Propagation学习算法使得网络记忆这些样本.控制器以"联想记忆"方
式使用这些经验.本文介绍了控制器的构造方法,给出了控制仿真结果,并讨论了这种控制器
的特点和发展前途.
|
| 关 键 词： | 神经网络 智能控制 Back-Propagation 模糊控制 |
| 收稿时间： | 1990-6-12 |
A Controller Implemented by Recording the Fuzzy Rules by BP Neural Networks |
| |
| Ying Xingren,Zeng Nan.A Controller Implemented by Recording the Fuzzy Rules by BP Neural Networks[J].Acta Automatica Sinica,1991,17(1):63-67. |
| |
| Authors: | Ying Xingren Zeng Nan |
| |
| Affiliation: | 1.Institute of Automation,Chinese Academy of Sciences |
| |
| Abstract: | A more natural way of using the human experiences than the fuzzy reasoning is provided in this paper. An abstract concept is expressed by a set of neurons with different exciting degrees. So, the abstract experience rules are transformed to the input-output samples of multi layer neural network, and these samples are recorded in the network by Back-Propagation algorithm. The controller utilizes these experiences according to associative memory. The design, simulation result, feature and further development of this controller are also discussed. |
| |
| Keywords: | Neural network intelligent control back-propagation fuzzy control |
| 本文献已被 CNKI 维普 等数据库收录！ |
| 点击此处可从《自动化学报》浏览原始摘要信息 |
|
点击此处可从《自动化学报》下载全文 |
|
