一种有效的单回路模型预测控制算法的开发与应用  

Development and Application of An Efficient Single-loop Model Prediction Control Algorithm

作　　者：王长军[1] 夏飞[1] Wang Changjun;Xia Fei(Sinopec Yangzi Petrochemical Company Ltd.,Nanjing,210048,China)

机构地区：[1]中石化扬子石油化工有限公司,江苏南京210048

出　　处：《石油化工自动化》2020年第6期15-18,共4页Automation in Petro-chemical Industry

摘　　要：针对传统PID控制器存在被控变量难以直接测量、被测参数的测量存在时间滞后、PID整定依赖现场技术人员等问题,介绍了模型预测控制原理,描述了一种高效的单回路模型预测算法,与传统的PID算法相比具有优越的控制性能,参数整定比较简单,减少了因测量噪声等引起的阀门振荡。这些优点使得模型预测控制成为单回路控制的一个新选择,并已经集成在霍尼韦尔控制系统中,作为标准控制功能的一部分。In view of difficulty to directly measuring control variables,time lag for measured parameters,PID tuning depending on on-site technicians and other problems for traditional PID controller,the principle of model predictive control is introduced,an efficient single-loop model prediction algorithm is described.Compared with the traditional PID algorithm,the algorithm has the advantage of superior control performance,simple parameter tuning,and valve oscillation caused by measurement noise is reduced.Model predictive control has been made a new option for single-loop control with these advantages,and have been integrated into Honeywell control system as part of standard control functions.

关 键 词：PID控制 模型预测 常规控制 单回路 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]