Deep quality-related stacked isomorphic autoencoder for batch process quality prediction

Abstract

Abstract Batch processes play an important role in modern chemical industrial and manufacturing production, while the control of product quality relies largely on online quality prediction. However, the complex nonlinearity of batch process and the dispersion of quality-related features may affect the quality prediction performance. In this paper, a deep quality-related stacked isomorphic autoencoder for batch process quality prediction is proposed. Firstly, the raw input data are reconstructed layer-by-layer by isomorphic autoencoder and the raw data features are obtained. Secondly, the quality-related information is enhanced by analyzing the correlation between the isomorphic feature of each layer of the network and the output target, and constructing a correlation loss function. Thirdly, a deep quality-related prediction model is constructed to predict the batch process quality variables. Finally, experimental validation was carried out in penicillin fermentation simulation platform and strip hot rolling process, and the experimental results demonstrated the feasibility and effectiveness of the model proposed in this paper for the quality prediction of the batch process.