The elongation of steel-strips in annealing furnace is an important factor that affects the position ofwelding line and safety of air-knife since there is no extra space to install welding line detector in field conditions. Therefore, predicting the elongation of steel-strips in the annealing process is important to fulfill the requirementsof eliminating security risks and improving economic performance. In this paper, we propose a deep architecturescalled I-ELM/MLCSA autoencoders with the concept of stacked generalization philosophy to solve large and complexdata mining problems. The comparison results of the case studies indicate that D-ELMs-AE/MLCSA is apromising prediction algorithm and can be employed for steel-strips elongation predictions with excellent performance.
The elongation of steel-strips in annealing furnace is an important factor that affects the position ofwelding line and safety of air-knife since there is no extra space to install welding line detector in field conditions. Therefore, predicting the elongation of steel-strips in the annealing process is important to fulfill the requirementsof eliminating security risks and improving economic performance. In this paper, we propose a deep architecturescalled I-ELM/MLCSA autoencoders with the concept of stacked generalization philosophy to solve large and complexdata mining problems. The comparison results of the case studies indicate that D-ELMs-AE/MLCSA is apromising prediction algorithm and can be employed for steel-strips elongation predictions with excellent performance.