MODELLING OF AIR BENDING USING NEURAL NETWORKS

• Type: Article in International Conference Proceedings Book
• Date: 2014

Authors

M. Romano Barbosa (Author) FEUP; J. Bessa Pacheco (Author) FEUP; Abel D. Santos (Author) FEUP

Conference proceedings International

Title: 11th World Congress on Computational Mechanics, WCCM 2014, 5th European Conference on Computational Mechanics, ECCM 2014 and 6th European Conference on Computational Fluid Dynamics, ECFD 2014

Pages: 4239-4250

Joint 11th World Congress on Computational Mechanics, WCCM 2014, the 5th European Conference on Computational Mechanics, ECCM 2014 and the 6th European Conference on Computational Fluid Dynamics, ECFD 2014

20 July 2014 through 25 July 2014

Indexing

ISI Web of Knowledge - 1 Citation

Scopus - 0 Citations

Scientific classification

FOS: Engineering and technology > Mechanical engineering

CORDIS: Technological sciences > Engineering > Mechanical engineering

Other information

Authenticus ID: P-00G-1JF

Abstract (EN): The main problem considered in this work is the development of a method capable of establishing the required punch displacement to obtain a given forming angle, in Press Brake bending. Current solutions can be based on analytical methods derived from geometrical formulations and additional correction factors [1-3]. These methods provide a quick solution but its applicability can be limited, especially if localized deformation is to be considered. Numerical simulation is increasingly been used and provides accurate results, accordingly to the models used [2]. However the time frame for a solution to be obtained can be a limiting factor. An alternative heuristic method, based on the use of artificial neural networks (NN), is presented in this work. The main justification for this approach lies on the inherent capability of NN to map nonlinear functions [4, 5] and generalization. The experiments were based on data obtained from numerical simulation of the forming process using different sheet metal thicknesses and tool geometries. The results obtained show that NN can provide a better approximation of the function relating the forming angle with the punch displacement.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 12