ORIGINAL ARTICLE A novel approach for the prediction of bend allowance in air bending and comparison with other methods Hasan Kurtaran Received: 6 September 2006 / Accepted: 19 February 2007 / Published online: 17 March 2007 # Springer-Verlag London Limited 2007 Abstract Air-bending is a major sheet-metal forming operation, where precise prediction of the developed shape is a key factor for the accuracy assessment of the final shape for the part after bending. To predict the blank shape, accurate estimation of the bend-allowance (BA) is neces- sary, which can be defined as the length of the un-stretched fiber at the bent state of shape. There are several different approaches to find the BA values depending on either experience-based or knowledge-based techniques. In this paper, a brief summary is provided for different approaches to find the BA values by comparing their advantages as well as, their drawbacks. They are evaluated in terms of accuracy, efficiency and ease of implementation for integrated CAD/CAM environment. Then, a novel ap- proach; by using higher order response surface (RS) fitting for the prediction of BA during air-bending is demonstrat- ed. This technique is in general found very promising as an integrated tool for both CAD interfaces, as well as CNC machine tools. The RS predictions, which are generated from over 1,000 bending experiments using combinations of bending radius, bending angle and material thickness, are built for different orders and are compared to Artificial Neural Network (ANN) models that are also trained by using the same experimental data. Keywords Air-bending . Artificial neural network . Response surface model 1 Introduction Bending can be defined as “the plastic deformation of a sheet-metal along a straight line” [1]. The most common bending operation is air-bending, which is basically a free bending process that usually can be conducted by using a press-brake as shown in Fig. 1. Even though, air-bending is one of the most inaccurate methods of all, this process is widely used among other sheet-metal forming methods. The reasons are obvious: – The tooling is simple and can be used for more than one flange and for more than one part even with a different thickness. – There is no need to change the dies and the tooling to obtain different bending angles. – Relatively smaller forces are needed. However, consistent and repeatable air-bending process- es comprise some critical details; such as the necessity of accurate and adaptive control of the punch stroke, which is the factor determining the bending angle and eventually the amount of spring-back. Developing machine tool technol- ogies overcome this problem with the help of new generation controllers equipped with advanced algorithms [2–4]. CNC press-brakes are preferred for this kind of operations, where narrow bands of tolerances can be achieved for the bending angles and flange lengths. Air-bending process causes dramatic changes in the initial blank size and the shape depending on the material thickness, bending angle, bending radius, properties of the material and the tooling. Effects of tooling geometry, bending angle, bending radius and material properties on the air-bending process have been investigated extensively [5–15]. Several numerical, experimental and analytical approaches have been proposed for this purpose. A very big portion of these research concentrate on springback predictions in air-bending operations. Compared to the Int J Adv Manuf Technol (2008) 37:486–495 DOI 10.1007/s00170-007-0987-y H. Kurtaran (*) Department of Design and Manufacturing Engineering, Gebze Institute of Technology, PK. 141, Gebze-Kocaeli, Turkey e-mail: hasan@gyte.edu.tr