Temperature field modeling of the plate during hot rolling based on inverse heat conduction problem

Abstract

In the established temperature field model of plate hot rolling process, the heat transfer coefficients of each stage are solved by empirical formula, but due to the complexity of the production environment, temperature field models tend to be less accurate. In order to solve this problem, this paper designs a rolling experiment, collects the actual temperature data, and combines with genetic algorithm, simulated annealing algorithm and particle swarm optimization algorithm to correct the heat transfer coefficients of air-cooling zone, and the three algorithms are compared. Finally, the particle swarm algorithm is selected to establish the temperature field model of the hot rolling process. The average error of the final temperature field model calculation is within 14°C.