• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Symposium on Knowledge and Systems Sciences amp; International Workshop on Meta-Synthesis and Complek System(KSS'2002 amp; MCS'2002); 20020807-08; Shanghai(CN) >A Controller Designed Based on Universal Learning Network
【24h】

A Controller Designed Based on Universal Learning Network

机译：基于通用学习网络的控制器设计

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

A new type of neural network-Universal learning networks (ULN's) and control system for pH neutralization process design are discussed. ULN's provide a generalized framework to model and control complex systems. They consist of a number of inter-connected nodes where the nodes may have any continuously differentiable nonlinear functions in them and each pair of nodes can be connected by multiple branches with arbitrary time-delay. ULN is a type of dynamical neural network and can overcome the shortcomings of the ever neural networks, and this type of network can predict the output of the system in the future time, so it can be easily used as predictor model. In order to verify the effect of the ULN, it is applied to a typical nonlinear process existing in many fields -pH neutralization process. Making good control of such process is very important for the factory and society. But the process has the strong nonlinear characteristics, uncertainty factors and also contains long time delay, it is very difficult for traditional methods to identify and control such process. In this paper, we will use the Universal Learning Networks to identify the pH neutralization process and get the neural network model, and then the model is used as predictor for the control system. From the result, we can see that the effect of the control result and the robusticity of the system is much better than the single PID method. So the ULN proposes a kind of simple and effective method of such process.
机译：讨论了一种新型的神经网络-通用学习网络（ULN）和用于pH中和过程设计的控制系统。 ULN提供了一个通用框架来建模和控制复杂的系统。它们由多个相互连接的节点组成，其中节点中可以具有任何可连续微分的非线性函数，并且每对节点都可以由具有任意时延的多个分支连接。 ULN是一种动态神经网络，可以克服以前的神经网络的缺点，并且这种网络可以预测将来的系统输出，因此可以很容易地用作预测器模型。为了验证ULN的效果，将其应用于许多领域中存在的典型非线性过程-pH中和过程。良好地控制这种过程对工厂和社会都非常重要。但是该过程具有很强的非线性特性，不确定性因素，并且还具有较长的时延，传统方法很难识别和控制这种过程。在本文中，我们将使用通用学习网络来识别pH中和过程并获得神经网络模型，然后将该模型用作控制系统的预测器。从结果可以看出，控制结果的效果和系统的鲁棒性比单一PID方法要好得多。因此，ULN提出了一种简单而有效的方法。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号