Search

Sulfur is considered as one of the main impurities in hot metal. Hot metal desulfurization is often carried out with pneumatic injection of a fine-grade desulfurization reagent using a submerged lance. The aim of this study was to develop a data-driven model for the process. The model selection algorithm carries out a simultaneous variable selection and optimization of number of hidden neurons with a combination of binary and integer coded Genetic Algorithm. The objective function applied in the search is repeated Leave-Multiple-Out cross-validation. The model considered is a feedforward neural network with a single hidden layer. In the inner loop of the algorithm, the computational load is reduced by making use of Extreme Learning Machine (ELM) architecture. The final model is trained using the Bayesian regularization. The results show that a well-generalizing data-driven model with good prediction performance can be repeatedly selected based on noisy industrial data with the help of a Genetic Algorithm, provided that the model is validated comprehensively with internal and external data sets.

Liquid steel is typically stirred in a vacuum tank using argon gas injection to achieve a homogeneous composition and high‐purity steel. The aim of this work is to study the effect of vessel vibration on the operational state monitoring of the gas stirring in a vacuum tank degasser. Following an extensive analysis of vibration features, the root mean square (RMS) of vertical velocity is found to be the best feature for the measurement of the stirring intensity caused by the volumetric gas injection rate into the ladle. Smoothing is conducted using a centered median filter with a window length of 21 s. In this work, the operational state monitoring of gas stirring is described using a ladle responsiveness value (LRV). This describes the ability of a ladle to generate the maximum amount of vibration with the minimum amount of argon gas. The LRV summarized for each ladle reveals significant differences between them. Correspondingly, a rolling ladle responsiveness value (rLRV) is used for online monitoring of possible gas leakages. The rLRV can also be used for the online monitoring of the stirring efficiency and as its comparison with the overall efficiency of a specific ladle or all ladles.

During ladle stirring, a gas is injected into the steel bath to generate a mixing of the liquid steel. The optimal process control requires a reliable measurement of the stirring intensity, for which the induced ladle wall vibrations have proved to be a potential indicator. An experimental cold water ladle with two eccentric nozzles and eight mono-axial accelerometers was thus investigated to measure the vibrations. The effect of the sensors’ positions with respect to the gas plugs on the vibration intensity was analyzed, and experimental data on several points of the ladle were collected for future numerical simulations. It is shown that the vibration root-mean-square values depend not only on process parameters, such as gas flow rate, water, and oil heights, but also on the radial and axial positions of the sensors. The vibration intensity is clearly higher, close to the gas plumes, than in the opposite side. If one of the nozzles is clogged, the vibration intensity close to the clogged nozzle drops drastically (−36 to −59%), while the vibrations close to the normal operating nozzle are hardly affected. Based on these results, guidelines are provided for an optimized vibration-based stirring.