Temporal graph convolutional network soft sensor for molecular weight distribution prediction

Abstract

In chemical processes with distributed outputs, characteristics of products are influenced by their distributions and significantly correlated with process variables. It is crucial for an accurate distribution characteristic prediction to adequately describe variable relationships and their temporal variations. For this purpose, a temporal graph convolutional network (TGCN) soft sensor is developed to describe the distribution of outputs. First, the variable relationships are represented in a topology subgraph based on prior knowledge. Then, the graph is supplemented based on variable screening results with the maximal information coefficient (MIC) as standard. Finally, the graph convolutional mechanism is used to model variable relationships, the gated recurrent unit to capture temporal dependencies, and GNNexplainer to provide a comprehensive explanation for the prediction. Results suggest that prediction accuracy and explainability is improved by the proposed TGCN soft sensor on the basis of prior knowledge, and verified in the case of molecular weight distribution (MWD) modeling.