摘要
为消除普遍存在于流程工业的各变量之间的时滞对于数据分析和使用等的影响,研究了工业过程实时数据的复杂特性,设计出了一种时滞计算方法。先对过程数据进行误差消除、缺失值补偿等数据预处理,再通过计算最大交叉相关性来确定变量间的时滞,最后分析了流程中流量大小对于时滞的影响。在加氢裂化装置中的应用,表明了该方法的准确性、有效性和灵活性。
To eliminate the impact oftime-delay which is widespread in various variables in process industry in analysis and use ofprocess industry data, the complex features of industry process real-time data is studied, a new method of calculating time-delay is designed, some data preprocessing, such as omission of abnormal points, imputation of missing data and data filter, are proposed to improve the precision of the process data, and the time-delay is determined by calculating the max cross-correlation between tags, and then, the impact of flow in process to the time-delay is analyzed. The method gets a successful application in the hydrogenation units, and the application result demonstrates the accuracy and reliability of the method.
出处
《计算机工程与设计》
CSCD
北大核心
2010年第18期4120-4123,共4页
Computer Engineering and Design
关键词
时滞
交叉相关性
线性平滑
缺失值补偿
数据预处理
time-delay
cross-correlation
linear smoothing
imputation ofmissingdata
data preprocessing
