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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.