# ProMix-DGNet: A Process-Aware Spatiotemporal Network for Sintering System Prediction

## TL;DR

This paper introduces ProMix-DGNet, a new spatiotemporal network that improves predictions in the iron ore sintering process by handling delays and complex interactions.

## Contribution

ProMix-DGNet introduces a novel process-aware architecture combining dynamic graphs and global mixers for robust sintering system prediction.

## Key findings

- ProMix-DGNet outperforms existing models on real-world datasets Sinter-A and Sinter-B.
- The model achieves lower Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) in multistep-ahead predictions.
- The architecture effectively captures long-range coupling and aligns future control setpoints with spatial topology.

## Abstract

Multistep-ahead prediction of critical states in the iron ore sintering process is essential for maintaining production stability, enhancing energy efficiency, and reducing industrial emissions. However, large time delays, strong coupling, and condition drifts challenge existing spatiotemporal graph neural networks (STGNNs). This paper proposes Process-aware Mixed Dynamic Graph Network (ProMix-DGNet), which integrates a Decoupled Two-Stream Topology Learning mechanism—fusing Adaptive Static Graph with a Radial Basis Function (RBF)-driven Dynamic Graph Constructor—to ensure robust spatial modeling under high-noise conditions. Furthermore, Process-View Global Mixer explicitly captures long-range process coupling across the entire sintering strand, overcoming the receptive field limitations of traditional graph convolutions. In the decoding phase, a future control-informed module utilizes a bidirectional Long Short-Term Memory (BiLSTM) and a global mixer to align known future control setpoints with the system’s spatial topology. These features are integrated via a gated residual mechanism that dynamically modulates the interaction between control intents and historical representations. Extensive experiments conducted on two real-world industrial datasets, Sinter-A and Sinter-B, demonstrate that ProMix-DGNet consistently outperforms mainstream baselines across multiple metrics, including Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The results verify the model’s higher accuracy and robustness in complex large-time-delay systems, offering a reliable framework for the intelligent monitoring and closed-loop optimization of sintering process.