Machine Learning Based Monitoring of Contact Tip Wear for Wire Arc Additive Manufacturing
Author(s)
Hussein, Zaky
Advisor(s)
Editor(s)
Collections
Supplementary to:
Permanent Link
Abstract
Wire arc additive manufacturing (WAAM) is a relatively recent field of additive manufacturing that achieves layer by layer deposition of a part geometry with commercially available welders and a motion platform. Due to the complexity of the welding process, process monitoring and control schemes are a focus of the WAAM literature. These studies focus on monitoring to determine, predict, or mitigate defects from the welding process. Despite these efforts, the contact tip and associated wear state is not considered when examining defects. This is likely due to the small size of components produced. Additionally, there is not a standardized method for determining when to replace the contact tip. The contact tip, a consumable component, positions the wire and serves as the electrical contact surface between the wire electrode and the welding power supply. This work seeks to better understand the degradation of the contact tip with respect to WAAM for a 316L wire electrode as well as explore methods of monitoring the contact tip state from process data. This thesis characterized the wear of the contact tip in terms of material loss and material contamination for a set of tips worn to discrete levels as measured by the amount of wire fed or arc time. Optical characterization found a 57% decrease in the area fraction of copper associated colors of the bore surface at 240 meters of wire fed and a 49% increase in the bore exit area at 180 meters of wire fed. Machine learning models were developed to predict the relative bore exit area of the contact tip from arc-based process data and a random forest classifier exhibited favorable performance with a cross-validated f1-score of 0.79. Various regression models were able to predict the relative exit area with an R2 score of 0.62 to 0.69.
Sponsor
Date
2023-11-28
Extent
Resource Type
Text
Resource Subtype
Thesis