一种新的模糊神经网络及在化工过程控制系统的应用研究

Research on a new fuzzy neural network and its application to chemical process control systems

本文提出一种新的采用补偿模糊算子的神经网络 ,它使控制系统具有更强的适应性和鲁棒性。该系统不仅能够自适应地调整隶属度函数 ,而且能够动态优化模糊规则 ,将其应用于化学反应器 (CSTR)的控制中。

This paper presents a new neurofuzzy controller. It makes a control system more adaptive and robust. This neurofuzzy controller can not only adjust the fuzzy membership functions adaptively, but also optimize the fuzzy rule dynamically by using compensatory learning algorithm. This approach has been applied to the control of a simulated CSTR plant. The simulation experiment shows that this fuzzy neural entwork is provided with good performance.