Development of a model selection method based on the reliability of a soft sensor model

Abstract

Soft sensors are widely used to realize highly efficient operation in chemical process because every important variablesuch as product quality is not measured online. By using soft sensors, such a difficult-to-measure variable y can be estimatedby other process variables which are measured online. In order to estimate values of y without degradation of a soft sensormodel, a time difference (TD) model was proposed previously. Though a TD model has high predictive ability, the model doesnot function well when process conditions have never been observed. To cope with this problem, a soft sensor model can beupdated with newest data. But updating a model needs time and effort for plant operators. We therefore developed an onlinemonitoring system to judge whether a TD model can predict values of y accurately or an updating model should be used forboth reducing maintenance cost and improving predictive accuracy of soft sensors. The monitoring system is based onsupport vector machine or standard deviation of y-values estimated from various intervals of time difference. We confirmedthat the proposed system has functioned successfully through the analysis of real industrial data of a distillation process.

Keywords

• soft sensor
• process control
• model selection
• time difference
• moving window