Model-free adaptive iterative learning control of melt pool width in wire arc additive manufacturing

Authors

Chunyang Xia, University of WollongongFollow
Zengxi Stephen Pan, University of WollongongFollow
Shiyu Zhang, University of WollongongFollow
Hui Jun Li, University of WollongongFollow
Yanling Xu
Shanben Chen

RIS ID

145451

Publication Details

Xia, C., Pan, Z., Zhang, S., Li, H., Xu, Y. & Chen, S. (2020). Model-free adaptive iterative learning control of melt pool width in wire arc additive manufacturing. International Journal of Advanced Manufacturing Technology, 110 (7-8), 2131-2142.

Abstract

© 2020, Springer-Verlag London Ltd., part of Springer Nature. Wire arc additive manufacturing (WAAM) is a Direct Energy Deposition (DED) technology, which utilize electrical arc as heat source to deposit metal material bead by bead to make up the final component. However, issues like the lack of assurance in accuracy, repeatability and stability hinder the further application in industry. Therefore, a Model Free Adaptive Iterative Learning Control (MFAILC) algorithm was developed to be applied in WAAM process in this study. The dynamic process of WAAM is modelled by adaptive neuro fuzzy inference system (ANFIS). Based on this ANFIS model, simulations are performed to demonstrate the effectiveness of MFAILC algorithm. Furthermore, experiments are conducted to investigate the tracking performance and robustness of the MFAILC controller. This work will help to improve the forming accuracy and automatic level of WAAM.