Optimization of Cooling Spray Water in Cold Strip Mill.pdf

6th World Congresses of Structural and Multidisciplinary Optimization Rio de Janeiro, 30 May - 03 June 2005, Brazil Optimization of Cooling Spray Water in Cold Strip Mill H.T. Zhu1, A.K. Tieu1, C. Lu1, Z.Y. Jiang1 and Giovanni D′Alessio2 1School of Mechanical, Materials and Mechatronics Engineering, University of Wollongong, Wollongong, Australia hongtao@uow.edu.au 2 Packaging Products, BlueScope Steel, Port Kembla, Australia Abstract The aim of this paper is to optimize the amount of cooling spray water that can contribute to the shape performance of the final strip products. First, a detailed cross-sectional shape in cold strip mill was calculated from the neural network with many input variables. To overcome the correlation effects among the process variables and the problem of dimensionality, principal component analysis was introduced to the shape prediction model. The model predicts the dynamic shape of the strip across the width and length compared very well with the measured data of a cold rolling mill. Next, another strip shape prediction model was developed to analyze the relationship between the strip shape quality, rolling parameters and amounts of cooling spray water on the strip and on the work rolls. From this model, a table of optimized settings of water pressure was recommended for the cold rolling process. Keywords: cooling spray water, neural network, strip shape 1. Introduction With the increasing demand for improving the control quality and product accuracy in the steel industry, the shape control has become an important issue in cold strip mill. In cold rolling, the strip shape is measured by a change of elongation across the strip width and is dependent on the effective roll gap opening between two work rolls. The roll gap and relevant strip shape is mainly governed by the coupled effects of the following factors, such as the rolling force and tension, deformation of the work rolls and backup rolls, wor