...
首页> 外文期刊>Fuzzy sets and systems >A new fuzzy neural network with fast learning algorithm and guaranteed stability for anufacturing process control
【24h】

A new fuzzy neural network with fast learning algorithm and guaranteed stability for anufacturing process control

机译:具有快速学习算法和保证稳定性的新型模糊神经网络,用于制造过程控制

获取原文
获取原文并翻译 | 示例
           

摘要

In this paper, a new fuzzy neural network (FNN) is presented for manufacturing process control. It is different from the conventional FNN in its structure, learning algorithm and stability analysis method. Firstly, it utilizes the input and output layer to on-line fine-tune scaling factors. It can also use the hidden layers to realize the fuzzification, fuzzy inference, defuzzification and tune parameters such as membership functions, fuzzy control rales dynamically. Secondly, a new combining learning algorithm (CL) which combines the gradient-based error back-propagation algorithm (EBP) with similar Newton (SN) algorithm is proposed in order to improve the convergence speed and release computational burden during the learning process. Lastly, a convergence condition for determining the stability of FNN is established. Physical experiments for manufacturing process control are implemented to evaluate the effectiveness of the proposed scheme.
机译:在本文中,提出了一种用于制造过程控制的新型模糊神经网络(FNN)。它与传统FNN的结构,学习算法和稳定性分析方法不同。首先,它利用输入和输出层在线微调比例因子。它还可以使用隐藏层来实现模糊化,模糊推理,去模糊化以及动态调整隶属函数,模糊控制规则等参数。其次,提出了一种新的组合学习算法(CL),该算法将基于梯度的误差反向传播算法(EBP)与类似的牛顿算法(SN)相结合,以提高收敛速度并减轻学习过程中的计算负担。最后,建立了确定神经网络稳定性的收敛条件。进行了用于制造过程控制的物理实验,以评估所提出方案的有效性。

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