An adaptive control system based on spatial–temporal graph convolutional and disentangled baseline-volatility prediction of bellows temperature for iron ore sintering process

Abstract

The temperature within the sintering furnace is a decisive factor influencing the quality of the sintered ore in the iron ore sintering process. In practical operations, the temperature at the bellows directly linked to the bed layer indirectly signifies the internal furnace temperature. Maintaining a stable temperature at the bellows, particularly at the burn-through point, is vital for minimizing gas emissions, improving carbon efficiency, and enhancing the quality of the sintered ore. This paper proposes an intelligent temperature control system based on Spatial–Temporal Graph Convolutional and Disentangled Baseline-Volatility (STGCDBV) prediction. The STGCDBV network comprises three parallel modules: Adaptive Graph Convolution Network (AGCN), Baseline and Volatility Disentangler (BVD), and a residual link, along with a Temporal–Nodal Encoder–Decoder (TNED) module. The AGCN constructs a graph reflecting the characteristics of bellows temperature, effectively merging static spatial data with dynamic thermal information. The BVD module captures the nonlinear trend data inherent in the sintering process. In contrast, the TNED synergizes the insights from the parallel modules using cross encoding and decoding functionalities. For controlling the sintering gas flow rate, a Model Reference Adaptive Control (MRAC) system is implemented, which utilizes a control scheme founded on a temperature reference model and iterative parameter adjustments. Extensive experiments using actual time-series data from a steel plant have been conducted. Moreover, comparisons between the performance of pre- and post-control interventions demonstrate that the STGCDBV-MRAC system can stabilize temperature fluctuations and exhibit exemplary control proficiency.