【作者】 渠晓东；

【导师】 邵诚；

【作者基本信息】 大连理工大学 ， 模式识别与智能系统， 2008， 硕士

【摘要】 氯乙烯单体(VCM)是生产聚氯乙烯的主要原料。氯乙烯单体生产过程反应机理复杂，反应过程具有非线性、不确定性和时变性，它具有一系列复杂化工反应过程的典型特性。目前我国氯乙烯生产的自动化水平很低，大多生产装置都处于手动控制和半自动控制状态，而对氯乙烯生产技术的研究大多着重于工艺性的研究，工艺研究和控制研究还没有有效地结合。如何提高控制水平，优化氯乙烯生产过程已经成为提高氯乙烯生产效率和产品质量的瓶颈。本文在对氯乙烯生产工艺流程、机理特性深入了解分析的基础上，根据生产的工艺要求和控制要求，提出了生产过程优化方案以及氯乙烯生产过程集成控制系统整体方案设计，采用IPC+PLC+现场总线模块的形式，利用工业以太网技术，组成三层分布式控制系统；针对氯乙烯生产过程四个阶段之一的乙炔生产过程存在的“气柜”问题，提出了PFC-PID串级控制策略解决方案；针对氯乙烯转化过程存在的模型难以建立，转化温度难以控制的问题，采用支持向量机对氯乙烯转化过程进行建模，并将得到的支持向量机模型应用于非线性系统的预测控制，提出了基于支持向量机模型的非线性预测控制算法；最后采用Rsview32组态软件对氯乙烯生产过程进行了上位机组态设计。仿真结果表明，文中所提出的先进控制解决方案有良好的控制品质，可以成功的解决氯乙烯生产过程现存的控制问题，实现了提质、降耗和提高生产效率的目的。更多还原

【Abstract】 Vinyl chloride monomer (VCM) is the main material of PVC produce. The produce process of VCM has complicated mechanism, it is nonlinear, uncertainty and time-varying, so it has typical character of a series of complex chemical reaction process. Currently, the automation level of VCM production is very low in China, most of device is in a manual or semi-automatic control, and most of research of VCM production technique focus on production technology, it has not been combined effectively with research of control. How to improve the level of control and optimize the production process have become the important methods of improving production efficiency and product quality.Based on understanding and analyzing the mechanics of VCM production process and production flow, according to the request of technology and control, the production process optimization solution and the project of the integrated control system of VCM production process are proposed. In this project, the 3-layer distributed control system is presented by assembling PLC, industrial PC, field bus I/O modules and the industrial Ethernet. Aimed at the "gas-tank" problem in acetylene station, the PFC-PID cascade control solution is designed. Aimed at the problems of building up model and controlling translation temperature difficulty, a modeling method of nonlinear systems using support vector machines is proposed. And the modeling of SVM is applied to nonlinear predictive control. A kind of nonlinear predictive control scheme based on the SVM model is gave out. Finally, the human machine interface of VCM production is designed based on Rsview32.The results of simulation show that the advanced control solutions have good control quality, it could revolved successfully the control problems of VCM production process, realize the purpose of improving produce quality, reducing consume and improving production efficiency.更多还原