Quality Prediction in Complex Batch Processes with Just-in-Time Learning Model Based on Non-Gaussian Dissimilarity Measure

Abstract

In modern batch processes, soft sensors have been widely used for estimating quality variables. However, they do not show superior prediction performance owing to the self-limitations of these methods and the unique characteristics of batch processes such as time-varying dynamics, nonlinearity, non-Gaussianity, multiphases and batch-to-batch variations. To cope with these issues, a novel just-in-time learning (JITL) soft sensor based on non-Gaussian dissimilarity measure is developed in this paper. Unlike the traditional JITL model which uses the distance-based dissimilarity measure for local modeling, the proposed method uses the non-Gaussian dissimilarity measure to evaluate the statistical dependency of the extracted independent components to construct the local model, which can well capture the non-Gaussian features in the process data. Furthermore, a novel relevant samples search strategy is introduced into the JITL framework for local modeling, which searches the relevant samples not only along the ...