Methylcyclohexane Continuous Distillation Column Fault Detection Using Stationary Wavelet Transform and K-Means

摘要

It is extremely difficult to develop fault detection and diagnosis approaches for systems composed of several complex processes. This work is placed in the context of detection and diagnosis of the operating faults of an industrial installation. Indeed, the installation in this study is a Methylcyclohexane continuous column from a mixture of toluene/methylcyclohexane in which the mass composition was defined to 23% of methylcyclohexane. The studied system, allows the separation of the more volatile component which is methylcyclohexane contained in the liquid mixture. We use K-means clustering technique combined with wavelet transform for noise reduction in order to determine precisely data mapping to different classes of faults in the distillation column. This approach is compared with the exclusive use of K-means and its classification accuracy is proved. The developed technique is implemented and tested against a dataset, which covers two modes of operation of the distillation column: the normal mode, and the abnormal mode. The latter mode is represented by the four most common dysfunctions of the distillation column.