论文部分内容阅读
针对基于主元分析(Principal Component Analysis,PCA)的统计过程性能监测法,尽管不依赖于精确的数学模型,然而却限制了其在故障诊断方面的能力问题,在故障重构技术的基础上,研究了基于统计量的故障诊断问题,获得了主元子空间中故障可重构性的理论条件,提出了故障识别指标和诊断算法。通过对双效蒸发过程的仿真监测,表明了所获得的结果能对故障(传感器故障和过程故障)进行有效地识别,证实了所获理论结果的有效性。
The statistical process performance monitoring method based on Principal Component Analysis (PCA), though it does not depend on accurate mathematical model, limits its capability in fault diagnosis. Based on the fault reconstruction technique, The problem of fault diagnosis based on statistics is studied, the theoretical conditions of fault reconfiguration in the principal meta-subspace are obtained, and the fault identification index and diagnosis algorithm are proposed. Through the simulation monitoring of the double-effect evaporation process, it is shown that the obtained results can effectively identify the faults (sensor failure and process failure), and prove the validity of the theoretical results obtained.