Learning and Adaptation in Wire Arc Additive Manufacturing Bead Geometry Control

2026-05-27

AI Summary

This study addresses the challenge of weld bead geometric inconsistency in robotic wire arc additive manufacturing (WAAM), which arises from the nonlinear thermo-geometric coupling dynamics during deposition. To overcome this, the authors propose a recurrent neural network–based control framework integrated with an online adaptive mechanism. The approach constructs a data-driven input/output model that combines one-step-ahead predictive control with line-scan feedback, and continuously updates the model using prediction errors from the preceding layer to adapt to evolving thermal field conditions in real time. Experimental validation on a robotic WAAM platform demonstrates that the proposed method significantly enhances the consistency of both bead height and width, achieving superior geometric accuracy and robustness compared to baseline strategies employing fixed parameters or static models.

Abstract

Robotics Wire Arc Additive Manufacturing (WAAM) is governed by complex and nonlinear process dynamics coupling thermal field to the build geometry. The process may be regarded as a multi-input/multi-output dynamical system with welding torch speed and wire feed rate as inputs and weld bead deposition height and width as outputs. In this paper, we use the input/output data to learn a data-driven model and use it for weld planning and control. We show that a simple recurrent neural network architecture and one-step-ahead predictive control can improve the process performance in terms of height and width consistency. To account for the changing thermal conditions during the printing process, we update the learning model using prediction error from the previous layer. This adaptation step further improves the prediction accuracy and controller performance. Experiments on a robotic WAAM testbed with integrated line-scanner feedback significant improvements in height and width consistency compared to constant input and static model baselines. The proposed learning and adaptation framework provides a practical pathway toward robust, data-driven regulation of additive manufacturing processes.

Problem

• Wire Arc Additive Manufacturing
• bead geometry control
• process dynamics
• thermal conditions
• height and width consistency

Innovation

• recurrent neural network
• predictive control
• online adaptation
• wire arc additive manufacturing
• data-driven modeling