Real-time distortion prediction in metallic additive manufacturing via a physics-informed neural operator approach

TL;DR

This paper introduces a physics-informed neural operator model for real-time prediction of distortion in metal additive manufacturing, combining physical laws with deep learning for accurate, efficient, and physically consistent long-term predictions.

Contribution

It develops a novel PINO-based approach that decouples thermo-mechanical fields and incorporates physical constraints, enabling real-time, long-horizon distortion prediction in additive manufacturing.

Findings

Achieves low maximum errors of 0.9733 mm in z-direction and 0.2049 mm in y-direction.

Ensures physical consistency by embedding heat conduction equations as soft constraints.

Demonstrates high accuracy, low error accumulation, and computational efficiency for real-time applications.

Abstract

With the development of digital twins and smart manufacturing systems, there is an urgent need for real-time distortion field prediction to control defects in metal Additive Manufacturing (AM). However, numerical simulation methods suffer from high computational cost, long run-times that prevent real-time use, while conventional Machine learning (ML) models struggle to extract spatiotemporal features for long-horizon prediction and fail to decouple thermo-mechanical fields. This paper proposes a Physics-informed Neural Operator (PINO) to predict z and y-direction distortion for the future 15 s. Our method, Physics-informed Deep Operator Network-Recurrent Neural Network (PIDeepONet-RNN) employs trunk and branch network to process temperature history and encode distortion fields, respectively, enabling decoupling of thermo-mechanical responses. By incorporating the heat conduction equation as a soft constraint, the model ensures physical consistency and suppresses unphysical artifacts, thereby establishing a more physically consistent mapping between the thermal history and distortion. This is important because such a basis function, grounded in physical laws, provides a robust and interpretable foundation for predictions. The proposed models are trained and tested using datasets generated from experimentally validated Finite Element Method (FEM). Evaluation shows that the model achieves high accuracy, low error accumulation, time efficiency. The max absolute errors in the z and y-directions are as low as 0.9733 mm and 0.2049 mm, respectively. The error distribution shows high errors in the molten pool but low gradient norms in the deposited and key areas. The performance of PINO surrogate model highlights its potential for real-time long-horizon physics field prediction in controlling defects.