Adaptive Control of Meniscus Velocity in Continuous Caster Based on NARX Neural Network Model


Adaptive Control of Meniscus Velocity in Continuous Caster Based on NARX Neural Network Model

Abouelazayem, S.; Glavinic, I.; Wondrak, T.; Hlava, J.

Meniscus velocity in continuous casting process is critical in determining the quality of the steel. Due to the complex nature of the various interacting phenomena in the process, designing model-based controllers can prove to be a challenge. In this paper a NARX neural network model is trained to describe the complex relationship between the applied magnetic field from an Electromagnetic Brake (EMBr) and the meniscus velocity. The data for the model is obtained using a laboratory scale continuous casting plant. The next step was to use Adaptive Model Predictive Control (MPC) to deal with the non-linearity of the model by adapting the prediction model to the different operating conditions. The controller will utilize the EMBr as an actuator to keep the meniscus velocity within the optimum range, and reject disturbances that occur during the casting process such as changing the casting speed.

Keywords: Mining; mineral and metal; Nonlinear system identification; Adaptive control design

Permalink: https://www.hzdr.de/publications/Publ-30476
Publ.-Id: 30476