摘要
针对在非线性、时变不确定系统中,常规PID控制器难以获得满意效果的问题,仿照传统PID控制器结构,设计了一种基于T-S模型的模糊神经网络PID控制器。该控制器基于T-S模糊模型,将PID结构融入模糊控制中,充分发挥了模糊系统非线性、可解释性的特点;然后又利用神经网络的学习算法,实现了对模糊控制器的参数调整,使控制器具有了适应时变、不确定系统的自学习和自组织能力。针对非线性、时变系统,将此控制器与传统PID控制器对比进行了仿真研究,并应用于啤酒发酵领域,其结果表明,该控制器取得了令人满意的效果。
To the problem that PID controller is difficult to achieve efficient control of time variable and nonlinear plants, a fuzzy neural network PID controller based on T-S model is designed by imitating the structure of the conventional digital PID controller. This structure with T-S fuzzy, model takes a good use of characteristics of nonlinear and interpretation of fuzzy theory. The abilities of self-study and self-organlze of neural network can regulate parameters of fuzzy structure. Simulations results of beer fementation shows that these performances and implementations can be applied to time variable and nonlinear plants.
出处
《控制工程》
CSCD
2006年第6期540-542,546,共4页
Control Engineering of China