论文部分内容阅读
矿渣微粉是一种新型绿色环保型建材,可以大大提高水泥混凝土的力学性能.本文以矿渣微粉生产过程为研究对象,针对该过程难以通过机理建模进行辨识和控制的特点,利用数据驱动的思想,建立矿渣微粉生产过程的递归神经网络模型.在此基础上,利用自适应动态规划,设计具有控制约束的跟踪控制器,并将其应用到矿渣微粉生产过程中.仿真分析表明,建立的数据驱动模型能够有效地辨识矿渣微粉生产过程,同时,本文提出的控制方法能够实现输入受限的微粉比表面积及磨内压差的最优跟踪控制.
The slag powder is a new type of green building materials, which can greatly improve the mechanical properties of cement concrete.In this paper, the production process of slag powder is taken as the research object. According to the characteristics of the process that it is difficult to identify and control by mechanism modeling, , To establish a recurrent neural network model of slag powder production process.On the basis of this, using adaptive dynamic programming, a tracking controller with control constraints is designed and applied to the process of slag powder production.The simulation analysis shows that the established data The driving model can effectively identify the production process of slag powder. At the same time, the control method proposed in this paper can realize the optimal tracking control of the limited specific surface area and the pressure difference within the mill.