This work presents three data-driven models based on process data, to estimate different indicators related to process performance in a steel production process. The generated models allow the optimization of the process parameters to achieve optimal performance and quality levels. A new approach based on ensembles has been developed with feature selection methods and four state-of-the-art regression approximations (random forest, gradient boosting, xgboost and neural networks). The results show that the proposed approach makes the prediction more stable reducing the variance for all cases, even in one case, slightly reducing the bias. Furthermore, from the four machine learning paradigms presented, random forest is the one with the best results in a quantitative way, obtaining a coefficient of determination of 0.98 as a maximum, depending on the target sub-process.

In this work, four low carbon steels with different contents of Mn and Ni were heat treated by quenching and partitioning (Q&P) cycles where high partitioning temperatures, in the range of 550 °C–650 °C, were applied. In order to elucidate the effect of applying these high partitioning temperatures with respect to more common Q&P cycles, the materials were also heat treated considering a partitioning temperature of 400 °C. The microstructure evolution during the Q&P cycles was studied by means of dilatometry tests. The microstructural characterization of the treated materials revealed that austenite retention strongly depended on the alloy content and partitioning conditions. It was shown that the occurrence of austenite reverse transformation (ART) in the partitioning stage in some of the alloys and conditions was a very effective mechanism to increase the austenite content in the final microstructure. However, the enhancement of tensile properties achieved by the application of high partitioning temperature cycles was not significant.

In the last decades, low-density steels for forging have increasing interest in the automotive industry, and good mechanical properties are required for their real application. This paper describes the results obtained for a 0.66C11.4Mn9.9Al duplex austenitic low-density steel after applying a set of isothermal treatments at different combinations of time and temperature, aimed to promote kappa carbide precipitation, and improve the mechanical properties obtained with a water quenching treatment. The effects of the different isothermal treatments on the microstructure and on the mechanical properties have been analyzed and compared to those obtained from a quenching heat treatment. We found that isothermal treatments in the range temperature between 550–750 °C promoted the profuse precipitation of coarse kappa carbides at grain boundaries, which dramatically reduced the ductility of the alloy, whereas a traditional quenching treatment resulted in a better combination of ductility and mechanical strength.