A quantitative causal analysis and optimization framework for inclusions of steel products

Abstract

Inclusions generated during steelmaking and continuous casting processes could seriously reduce the mechanical properties of steel products and greatly increase the risk of corrosion failure. Much attention has been paid to perceiving the origin and classification of inclusions based on the process knowledge and mechanism model, while the value of industrial big data is underestimated. Machine learning (ML) methods have demonstrated potential in the processing of nonlinear and strong coupling relationships in industrial data. However, existing ML models are frequently unable to analyze causal relationships between manufacturing process, which is essential for the quality optimization. To address the limitation, this paper proposes a quantitative causal analysis and optimization framework. This framework starts with a feature selection module using propensity score matching (PSM) to measure the quantitative and reliable causal relationship between the process parameters and inclusions. Subsequently, a high-performance AutoML method, AutoGluon-Tabular (AGT), is applied to quantify the optimization range and verify the optimization effect. Specifically, AGT is used to estimate the inclusion level in each window of the process parameter to be optimized, choose the best window of which to determine adjustment strategies, and eventually verify the change of inclusion levels after optimization. The comparative experiments based on the real data collected from a steel company demonstrate that the proposed framework reduces the inclusion rate by 8.85%, which is effective, efficient and has guiding significance for the inclusions control of steel products.