A Machine Learning Approach to Generate Residual Stress Distributions using Sparse Characterization Data in Friction-Stir Processed Parts

TL;DR

This paper introduces a machine learning model that accurately predicts full-field residual stress distributions in friction-stir processed parts from limited measurement data, reducing the need for extensive experiments.

Contribution

It presents a novel ML-based Residual Stress Generator trained on simulated data to infer stress distributions from sparse measurements, validated on real experimental data.

Findings

High predictive accuracy on simulated stresses

Effective generalization to experimental data

Reduces experimental effort in residual stress characterization

Abstract

Residual stresses, which remain within a component after processing, can deteriorate performance. Accurately determining their full-field distributions is essential for optimizing the structural integrity and longevity. However, the experimental effort required for full-field characterization is impractical. Given these challenges, this work proposes a machine learning (ML) based Residual Stress Generator (RSG) to infer full-field stresses from limited measurements. An extensive dataset was initially constructed by performing numerous process simulations with a diverse parameter set. A ML model based on U-Net architecture was then trained to learn the underlying structure through systematic hyperparameter tuning. Then, the model's ability to generate simulated stresses was evaluated, and it was ultimately tested on actual characterization data to validate its effectiveness. The model's prediction of simulated stresses shows that it achieved excellent predictive accuracy and exhibited a significant degree of generalization, indicating that it successfully learnt the latent structure of residual stress distribution. The RSG's performance in predicting experimentally characterized data highlights the feasibility of the proposed approach in providing a comprehensive understanding of residual stress distributions from limited measurements, thereby significantly reducing experimental efforts.