【作者】 向婕； 吴敏； 郑红燕； 谌晓文；

【Author】 Xiang Jie, Wu Min, Zheng Hongyan, Shen Xiaowen School of Information Science and Engineering, Central South University, Changsha 410083

【机构】 中南大学信息科学与工程学院；

【摘要】 针对烧结过程的强非线性、强耦合性及时变时滞特性,融合自适应控制、神经网络和模糊控制的优点,提出了一种模糊神经网络自适应控制方法,并应用于烧结过程终点控制。本文将模糊控制映射到一类神经网络结构中,从而将模糊规则的自组织问题,转化为神经网络的自学习问题;采用辨识模型对烧结过程动态特性进行在线辨识,提高了控制精度和自适应能力。应用结果表明,这种方法能较为准确、快速的反映烧结终点状态,具有较好的自适应控制性能。更多还原

【Abstract】 The sintering process possesses strong nonlinear, strong coupling, time-varying and time-delay characters. In this paper, an adaptive control method based on fuzzy neural network is proposed by integrating adaptive control, neural networks and fuzzy control, and has been used to control the burning through point in the sintering process. The fuzzy control rules are reflected in the neural network, and can be obtained by self-learning of neural network. An identification model is used to identify the dynamic characters of the sintering process on-line, and improves the ability of control precision and self-adaptability. The results of actual runs show the effectiveness of the proposed method.更多还原