论文部分内容阅读
故障诊断对于化工过程安稳运行有极其重要的作用。主元分析(PCA)方法作为一种基于信号处理的数据驱动方法,已广泛应用于工业过程故障诊断中。但该方法在故障类型识别方面,还存在着不足。本文引入CLIPS专家系统,提出了C-PCA方法,增强了故障识别能力。C-PCA方法结合了PCA和CLIPS专家系统2种方法的优点,与单一的方法相比,具有较强的创新性和优越性。并以田纳西伊斯曼过程为例,验证了C-PCA方法在化工过程故障识别和诊断中应用的有效性。
Fault diagnosis plays a very important role in the stable operation of the chemical process. As a data-driven method based on signal processing, Principal Component Analysis (PCA) method has been widely used in industrial process fault diagnosis. However, there are still some shortcomings in the method of fault type identification. In this paper, CLIPS expert system is introduced, and a C-PCA method is proposed to enhance fault recognition capability. The C-PCA method combines the advantages of the two methods of PCA and CLIPS expert systems, and is more innovative and superior than the single method. Taking the Tennessee Eastman process as an example, the validity of C-PCA method in chemical process fault identification and diagnosis is verified.