毕业论文

当前位置: 毕业论文 > 外文文献 >

BP神经网络和有限元英文文献和中文翻译

时间:2017-10-10 20:04来源:毕业论文
Using neural network to predict punch radius based on the results of air-bending experiments of sheet metal is a high efficiency work in spite of little error. A three-layer back propagation neural network (BPNN) is developed to best fit t
Using neural network to predict punch radius based on the results of air-bending experiments of sheet metal is a high efficiency work in spite of little error. A three-layer back propagation neural network (BPNN) is developed to best fit this discrete engineering problem involving many parameters of air-bend-ing forming. A genetic algorithm (GA) is used to optimize the weights of neural network for minimizing the error between the predictive punch radius and the experimental one. Then, with the predicted punch radius and other geometrical parameters of a tool, 2D and 3D ABAQUS finite-element models (FEM) are established, respectively. The original forming process of multiple-step incremental air-bending of sheet metal, obtained from geometric planning for semiellipse-shaped workpiece, is simulated using the FEM. This process is further adjusted with simulation-optimization results, because of existing large errors in the workpiece simulated with the original forming process. Finally, a semiellipse-shaped workpiece, with average errors of +0.61/-0.62 mm, is manufactured with the optimized adjustment process. The exper-imental results show that the punch design method is feasible with the prediction model of GA-BPNN,and the means of optimizing process with FEM simulation is effective. It can be taken as a new approach for punch and process design of multiple-step incremental air-bending forming of sheet metal.14132
@2009 Elsevier Ltd. All rights reserved.
1. Introduction
Air-bending (Fig. 1) is performed with a punch and a die with a pair of shoulders. The die gap is set according to the process requirements, and the sheet metal is placed on the shoulders. The punch at the mid-span of the die is given a displacement, and the die is deep enough to avoid the sheet from striking its bottom. This single-step air-bending processing is suitable for workpieces of simple profile. However, parts with complex sur-face can not be bent by the single-step air-bending. To solve this problem, a multiple-step incremental air-bending forming is uti-lized. This forming process is a flexible sheet-metal-forming tech-nology that uses principles of stepped manufacturing. It transforms the complicated geometry information into a series of parameters of single-step, and then the plastic deformation is carried out step by step through the computer numerical con-trolled movements of the punch and sheet feed for getting the de-sired part. Therefore, the process is cost-effective to form large complex parts in small to medium batches such as semiellipse-shaped workpieces which could be used as crane boom, tele-scopic arm of the concrete pump truck, boom of bridge, and petroleum piping.
源自六[维^论'文]网.加7位QQ3249'114 www.lwfree.cn

Air-bending springback is unavoidable in the sheet metal form-ing, and the springback leads to the changes of bending radius,bending arc segment and bending angle. The bending radius of a
sheet metal after unloading is called springback radius; the bend-ing arc segment of a sheet metal after removal from the punch is defined as springback arc segment; the unloaded bend angle is re-ferred as springback angle (Fig. 1). Due to the existence of spring-back, the precision of products and subsequent assembly operations were severely affected. How to effectively control springback angle and springback radius has been the key issue to precision forming and design of air-bending punch. We note that many methods have been proposed to control springback angle. Overbending through a deeper punch stroke is one of the com-monly used methods to control springback angle in air-bending. However, overbending has a minor influence to springback radius. Therefore, in order to accurately control springback radius, a non-linear prediction model of punch radius, taking springback radius as the model input, is established in this paper.
As punch radius, as the output of the non-linear model, is too difficult to be calculated exactly by table checking and experi-ence, artificial neural network happens to map the non-linear relationship [1]. It provides a new way to solve the complex, non-linear, polytropic, discrete engineering problem involving in many parameters of air-bending forming. In recent years, much BP神经网络和有限元英文文献和中文翻译:http://www.lwfree.cn/fanyi/20171010/14578.html
------分隔线----------------------------
推荐内容