Development of a neural network model to predict distortion during the metal forming process by line heating

César Pinzón,Carlos Plazaola,Amaly Fong,Ilka Banfield,Adán Vega

doi:10.25043/19098642.77

Abstract

In order to achieve automation of the plate forming process by line heating, it is necessary to know in advance the deformation to be obtained under specific heating conditions. Currently, different methods exist to predict deformation, but these are limited to specific applications and most of them depend on the computational capacity so that only simple structures can be analyzed. In this paper, a neural network model that can accurately predict distortions produced during the plate forming process by line heating, for a wide range of initial conditions including large structures, is presented. Results were compared with data existing in the literature showing excellent performance. Excellent results were obtained for those cases out of the range of the training data.

Highlights

The process of forming three-dimensional surfaces via line heating has been used for several decades in shipbuilding
Network, the prediction of deformation produced during the process of metal forming by line heating is achieved with considerable accuracy, for heat conditions and sizes of plates that have not been possible to achieve with traditional methods of prediction distortions
Many investigation projects have been carried out. They can be divided into three main groups: those seeking to understand the situation [2, 3, and 4], those wishing to develop automatic machines that can bend a plate [5 and 6], and those seeking to understand the relationship between heating conditions and the deformation to be obtained [7 and 8]

Summary

Introduction

The process of forming three-dimensional surfaces via line heating has been used for several decades in shipbuilding. It becomes difficult for shipyards to maintain a sufficient number of technicians, who are able to do this work without many complications [1] This leads us to conclude that it is necessary to automate the system in order to restore the small number of skilled workers. To achieve this goal, many investigation projects have been carried out. Many investigation projects have been carried out They can be divided into three main groups: those seeking to understand the situation [2, 3, and 4], those wishing to develop automatic machines that can bend a plate [5 and 6], and those seeking to understand the relationship between heating conditions and the deformation to be obtained [7 and 8]. The last group being the most difficult task found until now

Methods

Results

Conclusion