Based on the model of Higgins and Goodman, we describe a dynamically generated fuzzy neural network (DGFNN) approach to control, from input–output data, using on-line learning. The DGFNN is complete with the following powerful features drawn or modified from the existing literature: (1) a small FNN is created from scratch—there is no need to specify initial network architecture, initial members...

This paper presents a feedforward control concept for lateral asymmetries in heavyplate hot rolling. A lateral off-center plate position generally entails asymmetric rolling forces, asymmetric mill stretch, and thus a wedge-shaped exit thickness that may cause a cambered plate contour and a rotatory motion of the plate. In this paper, a model of the mill stand and of the plate movement is prese...

The authors discuss the combination of an Artificial Neural Network (ANN) with analytical models to improve the performance of the prediction model of finishing rolling force in hot strip rolling mill process. The suggested model was implemented using Bayesian Evidence based training algorithm. It was found that the Bayesian Evidence based approach provided a superior and smoother fit to the re...

Abstract. The technological process of manufacturing cold-rolled strip with a thickness 0.5-1.5 mm from high-strength steel grades on cold rolling mills can consist 2 or even 3 operating cycles "cold - intermediate annealing". This is due to significant hardening such steels during and, as result, limitations the maximum allowable forces. Each additional cycle annealing" significantly increases...

The objective of this research is to study plant layout of NCRM (Narrow cold rolling mill division) of Bhushan steels Ltd. Mumbai based on the systematic layout planning pattern theory (SLP) for increased productivity. In this case study, amount of equipments and tools in rolling coil production are studied. The detailed study of the plant layout such as operation process chart, flow of materia...

in this study, the effect of cold rolling process on the microstructure and texture evolution in 1wt. % si non-orientedelectrical steel was investigated. for this purpose, all samples were processed through single-stage hot rolling at1100 ° c and two-stage cold rolling (cross rolling and unidirectional rolling) with intermediate annealing at 650 °cfor 35 seconds. finally, all of them were fully...

The quality of steel strip produced in a wide strip rolling mill depends heavily on the careful selection of initial ground work roll profiles for each of the mill stands in the finishing train. In the past, these profiles were determined by human experts, based on their knowledge and experience. In this research, a Self-Organising Migration Algorithm (SOMA), a heuristic optimisation algorithm,...

This work presents improved technology for attaining high-quality rolled metal strip. The new technology is based on an innovative method to model both the static and dynamic characteristics of rolling mill deflection, and it applies equally to both cluster-type and non cluster-type rolling mill configurations. By effectively combining numerical Finite Element Analysis (FEA) with analytical sol...