Numerical Simulation of the Hot Rolling Process of Steel Beams

The complete rolling schedule (25 passes) of steel beams in a mill was simulated to predict the final beam length, geometry of the cross-section, effective stress, effective plastic strain and rolling power for two cases; the first case corresponds to the hot rolling process assuming a constant temperature of 1200 ∘C. The simulation of the second case considered the real beam temperature at each pass to compare the results with in-plant measurements and validate the numerical model. Then, the results of both cases were compared to determine the critical passes of the process with high peaks of required power, coinciding with the reports at the mill. These critical passes share the same conditions, high percentage of reduction in cross-sectional area and low beam temperature. Additionally, a potential reduction of passes in the process was proposed identifying passes with low required power, minimal reduction in area of cross-section and essentially unchanged geometry. Therefore, it is reasonable to state that using the present research methodology, it is possible to have a better control of the process allowing innovation in the production of profiles with more complex geometries and new materials.

Sliding Mode Control with Sliding Perturbation Observer-Based Strategy for Reducing Scratch Formation in Hot Rolling Process

In a hot rolling process, excessive friction between rollers and steel plates may lead to the formation of scratches on the steel plate. To reduce scratch formation in the finishing mill of the hot rolling process, two techniques are proposed in this work: flying touch and velocity synchronization. The proposed flying touch method can reduce the impact of the generated force when the upper roller collides with the steel plate. In addition, the proposed velocity synchronization method can decrease the frictional force resulting from the velocity difference between the rollers and steel plate. The effectiveness of the proposed methods was demonstrated through simulations and experiments using a 1/40 downscaled hot rolling simulator. The simulations and experimental results demonstrate that the proposed methods can reduce the magnitudes of friction and impact forces that lead to scratch formation on the steel plates in the hot rolling process.

Motor Load Balancing with Roll Force Prediction for a Cold-Rolling Setup with Neural Networks

The use of machine learning algorithms to improve productivity and quality and to maximize efficiency in the steel industry has recently become a major trend. In this paper, we propose an algorithm that automates the setup in the cold-rolling process and maximizes productivity by predicting the roll forces and motor loads with multi-layer perceptron networks in addition to balancing the motor loads to increase production speed. The proposed method first constructs multilayer perceptron models with all available information from the components, the hot-rolling process, and the cold-rolling process. Then, the cold-rolling variables related to the normal part set-up are adjusted to balance the motor loads among the rolling stands. To validate the proposed method, we used a data set with 70,533 instances of 128 types of steels with 78 variables, extracted from the actual manufacturing process. The proposed method was found to be superior to the physical prediction model currently used for setups with regard to the prediction accuracy, motor load balancing, and production speed.