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

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