Process fault detection using time-explicit Kiviat diagrams

摘要: Significant amounts of data are collected and stored during chemical process operations. The corresponding datasets typically difficult to represent analyze using traditional visualization methods. This article introduces time-explicit Kiviat diagrams as a means visualize the multidimensional time series acquired from plant framework is then used build multivariate control charts for large scale datasets, develop fault detection mechanism that lends itself real-time implementation. proposed methodology applied an industrial case study well obtained Tennessee Eastman simulator, showing very good performance. © 2015 American Institute Chemical Engineers AIChE J, 61: 4277–4293,