Slow Feature Analysis Based Quality Prediction for Slow Time-Varying Batch Processes

Abstract

Batch processes require effective quality analysis and prediction techniques to ensure product quality. In this paper, quality prediction work has been carried out for multiphase batch processes with slow time-varying characteristics based on the slow feature analysis (SFA) algorithm. To analyze the slow time-varying characteristics along the batch direction, sliding windows are constructed in the batch direction covering different batches, and accordingly a series of models are established using the SFA algorithm to capture the slow feature of the varying relationship between the process variables and the quality. At last, the proposed strategy is applied to the quality analysis and prediction of a typical slow time-varying batch process, the start-up process of the injection molding process, and the prediction results are compared with those obtained by the strategy using partial least squares (PLS) to build the regression models. The results verify the effectiveness of the proposed method in the quality prediction of slow time-varying batch processes.