Affiliation:
1. Department of Precision Engineering, Korea Advanced Institute of Science and Technology, Taejon, Korea
Abstract
In a hydroforming process, forming pressure versus punch stroke is critical to product quality, and thus the operating pressure curve is strictly controlled according to a preplanned control method. The conventional method of determining such a curve is trial and error, which demands tremendous effort and high cost. In this paper, a neural network approach is proposed to replace the conventional method. It automatically generates the appropriate operating curve whenever any changes in part material properties and forming geometries occur. The network maps non-linear relationships between part geometric variables and forming pressure throughout the punch stroke. The performance of the trained network was tested for various drawing ratios and punch shapes which had not been used for training. The results show that the proposed neural network approach yields products of uniform thickness, thus exhibiting the ability to design an operating pressure curve necessary for guaranteeing good product quality.
Subject
Mechanical Engineering,Control and Systems Engineering
Cited by
7 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献