轧钢加热炉故障检测与诊断方法研究

RESEARCH ON TROUBLE SHOOTING AND DIAGNOSIS OF REHEATING FURNACE OF A HOT ROLLING MILL

基于多元统计投影技术 (如主元分析、PCA) ,连续生产过程故障检测与诊断研究已经得到了学术界和工业界的广泛重视。针对轧钢加热炉这类典型的工业生产过程 ,运用多元统计投影技术进行了故障检测与诊断的研究。在建立过程主元模型的基础上 ,对单故障源和多故障源两类问题进行了研究。结果表明 。

The trouble shooting and diagnosis based upon multivariate statistical projection methods (such as principal component analysis, PCA) have attracted more and more interest academically and industrially. In this paper, PCA and statistical control chart have been used to detect process operating faults on an industrial rolling mill reheating furnace. The diagnosing results to single (fuel gas pipe control valve failure or furnace temperature sensor failure alone) and multiple faults (control valve failure and temperature sensor failure simultaneously) were presented based on establishing the operating PCA model. The simulation indicates that the method is effective.