采用BP神经网络记忆模糊规则的控制
A Controller Implemented by Recording the Fuzzy Rules by BP Neural Networks
-
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
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 multiplayer 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.-
Key words:
- Neural network /
- intelligent control /
- back-propagation /
- fuzzy control
计量
- 文章访问数: 3137
- HTML全文浏览量: 212
- PDF下载量: 1285
- 被引次数: 0