The accuracy of a finite element model for design and analysis of a metal forging operation is limited by the incorporated material model’s ability to predict deformation behavior over a wide range of operating conditions. Current rheological models prove deficient in several respects due to the difficulty in establishing complicated relations between many parameters. More recently, artificial neural networks (ANN) have been suggested as an effective means to overcome these difficulties. In the present work, a previously developed ANN with the ability to determine flow stresses based on strain, strain rate, and temperature is incorporated with finite element code. Utilizing this linked approach, a preliminary model for forging an aluminum wheel is developed. This novel method, along with a conventional approach, is then measured against the forging process as it is currently performed in actual production.

This content is only available via PDF.
You do not currently have access to this content.