Recognition of Lubrication Defects in Cold Forging Process with a Neural Network
Bernard F. Rolfe (Deakin University, Australia), Yakov Frayman (Deakin University, Australia), Georgina L. Kelly (Deakin University, Australia) and Saeid Nahavandi (Deakin University, Australia)
Copyright: © 2006
This chapter describes the application of neural networks to recognition of lubrication defects typical to industrial cold forging process. The accurate recognition of lubrication errors is very important to the quality of the final product in fastener manufacture. Lubrication errors lead to increased forging loads and premature tool failure. Lubrication coating provides a barrier between the work material and the die during the drawing operation. Several types of lubrication errors, typical to production of fasteners, were introduced to sample rods, which were subsequently drawn under both laboratory and normal production conditions. The drawing force was measured, from which a limited set of statistical features was extracted. The neural-network-based model learned from these features is able to recognize all types of lubrication errors to a high accuracy. The overall accuracy of the neural-network model is around 95% with almost uniform distribution of errors between all lubrication errors and the normal condition.