First Contact: Data-driven Friction-Stir Process Control

2025/07/03 by Koch, James, King, Ethan, Choi, WoongJo +4
#FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2507.03177

Abstract

This study validates the use of Neural Lumped Parameter Differential Equations for open-loop setpoint control of the plunge sequence in Friction Stir Processing (FSP). The approach integrates a data-driven framework with classical heat transfer techniques to predict tool temperatures, informing control strategies. By utilizing a trained Neural Lumped Parameter Differential Equation model, we translate theoretical predictions into practical set-point control, facilitating rapid attainment of desired tool temperatures and ensuring consistent thermomechanical states during FSP. This study covers the design, implementation, and experimental validation of our control approach, establishing a foundation for efficient, adaptive FSP operations.

Citations

• Neural Lumped Parameter Differential Equations with Application in Friction-Stir Processing
• Deep Learning Alternative to Explicit Model Predictive Control for Unknown Nonlinear Systems
• Universal Differential Equations for Scientific Machine Learning
• Neural Ordinary Differential Equations

Related

• Neural Lumped Parameter Differential Equations with Application in Friction-Stir Processing
• A Methodology to Determine Tooling Interface Temperature and Traction Conditions from Measured Force and Torque in Materials Processing Simulations Based on Multimesh Error Estimation
• Atomistic Simulation Guided Convolutional Neural Networks for Thermal Modeling of Friction Stir Welding
• Supervised Machine Learning and Physics based Machine Learning approach for prediction of peak temperature distribution in Additive Friction Stir Deposition of Aluminium Alloy
• An Experimental Investigation and Modelling of Friction Stir Processing