Online Semi-supervised Quality Prediction Model for Batch Mixing Process

Abstract

Current soft sensors for the Mooney viscosity prediction in rubber mixing processes only utilized the limited labeled data. By exploring the unlabeled data, a novel soft sensor, namely just-in-time semi-supervised extreme learning machine (JSELM), is presented to online predict the Mooney viscosity with multiple recipes. It integrates the just-in-time learning, extreme learning machine (ELM), and the graph Laplacian regularization into a unified online modeling framework. When a test sample is inquired online, the useful information in both of similar labeled and unlabeled data is absorbed into the JSELM model to enhance its prediction performance. Moreover, an efficient model selection strategy is formulated for online construction of the JSELM prediction model. The superiority of JSELM is validated via the industrial Mooney viscosity prediction.