Stacked Spatial–Temporal Autoencoder for Quality Prediction in Industrial Processes

Abstract

Nowadays, data-driven soft sensors have become a mainstream for the key performance indicators prediction, which guarantees the safety and stability of the industrial process. The typical autoencoder (AE) has been widely used to extract potential features through unsupervised pretraining and supervised fine-tuning. However, most existing studies fail to consider both the time-varying features of the process and the differences in the contributions of the hidden features to the target variable. Therefore, in this paper, a stacked spatial-temporal autoencoder (S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> TAE) is proposed to enhance the representation learning capability for soft sensor modeling by taking the spatial-temporal correlations into consideration. Specifically, in order to effectively model the temporal dependence from nearby times, a temporal autoencoder (TAE) is proposed, in which a memory module is devised and integrated to learn valuable historical information. Moreover, a “feature recalibration” block is developed and embedded into the spatial-temporal autoencoder (STAE) to selectively capture more informative features and suppress the less useful ones in a supervised way. Then, multiple STAEs are stacked to construct the S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> TAE network to extract more robust high-level features. Finally, the experimental results on two real-world datasets of an SDS desulphurization process and a high–low transformer demonstrate that the S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> TAE-based soft sensor is effective and feasible.