Prediction of temperature and velocity distributions during hot rolling using finite elements and neural network

Abstract

Temperature and velocity distributions during hot strip rolling of a low-alloy steel are determined using a finite element method together with a neural network model. The finite element method is utilized to solve the governing equations of heat conduction and plastic deformation; at the same time a neural network model is employed for assessing flow stress of the metal being deformed. In this way, the effects of temperature, strain, and strain rate on flow stress could be included in the finite element analysis. In order to examine validity of the mathematical model, laboratory hot rolling experiments are carried out where the surface temperature and roll force are recorded. Comparison between the experimental and the predicted results shows a good consistency.

Sales forecasting for thin film transistor liquid crystal display products with data clustering and an evolving neural network model

“…Effective forecasting can help the decision maker in planning the production quantity, cutting down the material costs, and even determine the selling price. It can result in lower inventory levels and achieve the objective of timely product acquisition, according to research carried out in references [1][2][3][4][5]. Barriers to communication of forecasts occurred because managers tended to ignore the application, testing, control key information, and execution of the results of a forecast as described in Johnson and Wichern [6].…”

Reliability Prediction of Near-Isothermal Rolling of TiAl Alloy Based on Five Neural Network Models

“…Hwang, R. used machine learning methods to predict rolling force and temperature in hot rolling [21]. Azadi et al used the finite element method to solve the governing equations of heat conduction and plastic deformation, and used a neural network model to predict the flow stress of the rolling stock [36]. Hosein Alaei et al developed a neural network to predict the thermal expansion of work rolls during rolling, and implemented online monitoring using a validated 3D analytical model to guide and supervise the learning process [37].…”