A Bayesian Supervisory Approach of Outlier Detection for Recursive Soft Sensor Update

Partial least squares (PLS) based soft sensors that predict the primary variables of a process by using the secondary measurements have drawn increased research interests recently. Such data-driven soft sensors are easy to develop and only require a good historical data set. As industrial processes often experience time-varying changes, it is desirable to update the soft sensor model with the new process data once the soft sensor is implemented online. Because the PLS algorithms are sensitive to outliers in the dataset, outlier detection and handling plays a critical role in the development of the PLS based soft sensors. In this work, we develop multivariate approaches for both off-line and online outlier detection. For online application, to differentiate outliers caused by erroneous readings from those caused by process changes, we propose a Bayesian supervisory approach to further analyze and classify the detected outliers. Both simulated and industrial case studies of the Kamyr digesters are used to demonstrate the effectiveness of the proposed approaches.