Submerged Entry Nozzle (SEN) clogging is a serious problem for continuous casting process and slab quality. In order to investigate the impact of the SEN clogging rate on the flow field and the optimization effect of electromagnetic stirring (EMS) on the asymmetrical flow due to the SEN clogging, a 1:5 scaled mercury model, with various SEN clogging rates and different electromagnetic stirring currents was established and the flow velocity was measured by means of Ultrasonic Doppler Velocimetry (UDV). S index is introduced to judge quantitatively whether the horizontal flow pattern is symmetrical or not. The results show that the symmetry of the flow pattern in the mold becomes broken with the increase of the SEN clogging rate. In this study, EMS is an effective method to increase S index and active the free surface flow when the SEN clogging rate is under 50%. However, the stirring current of EMS should be controlled to avoid the adverse surface flow which may induce slag entrapment.

Quality prediction in the continuous casting process is of great significance to the quality improvement of casting slabs. Due to the uncertainty and nonlinear relationship between the quality of continuous casting slabs (CCSs) and various factors, reliable prediction of CCS quality poses a challenge to the steel industry. However, traditional prediction models based on domain knowledge and expertise are difficult to adapt to the changes in multiple operating conditions and raw materials from various enterprises. To meet the challenge, we propose a framework with a multiscale convolutional and recurrent neural network (MCRNN) for reliable CCS quality prediction. The proposed framework outperforms conventional time series classification methods with better feature representation since the input is transformed at different scales and frequencies, which captures both long-term trends and short-term changes in time series. Moreover, we generate different category distributions based on the random undersampling (RUS) method to mitigate the impact of the skewed data distribution due to the natural imbalance of continuous casting data. The experimental results and comprehensive comparison with the state-of-the-art methods show the superiority of the proposed MCRNN framework, which has not only satisfactory prediction performance but also good potential to improve continuous casting process understanding and CCS quality.

The transient numerical model combined with the volume of fluid (VOF) approach is employed to investigate the steel/slag interface behavior under multifunction electromagnetic driving in a continuous casting slab mold. Here, electromagnetic stirring (EMS) and electromagnetic braking (EMBr), respectively, are chosen as flow multifunction control technologies in the upper and lower areas of the mold. The computational models are validated with measurement results. The results show that multifunction electromagnetic driving changes the flow pattern, which has the potential to simultaneously meet the requirements of the steel flow in the regions above and below the nozzle, ensuring the uniformity and activity of the molten steel in the upper region of the mold and avoiding the excessive depth of the impinging jet. After EMS, the steel forms a deflected circulation flow at the steel/slag interface, and the surface velocity distribution is more uniform. EMBr still has the function of stabilizing the meniscus when multifunction electromagnetic driving is applied. Taking wave height and wave amplitude as evaluation criteria, the influence of EMS and EMBr on the steel/slag interface can be evaluated and controlled to some extent by observing the key points.

A mathematical model coupled with electromagnetic field has been developed to simulate the transient turbulence flow and initial solidification in a slab continuous casting mold under different electromagnetic stirring (EMS) currents and casting speeds. Through comparing the magnetic flux density, flow field with measured results, the reliability of the mathematical model is proved. The uniform index of solidified shell thickness has been introduced to judge the uniformity of the solidified shell. The results show that a horizonal recirculation flow has been generated when EMS is applied, and either accelerated or decelerated regions of flow field are formed in the liquid pool. Large EMS current and low casting speed may cause the plug flow near the mold narrow face and a suitable EMS current can benefit to the uniform growth of solidified shell. Meanwhile, an industrial test exhibits that EMS can weaken the level fluctuation and number density of inclusion. Overall, a rational EMS current range is gained, when the casting speed is 1.2 m/min, the rational EMS current is 500–600 A.