Reduced Order Modeling of a MOOSE-based Advanced Manufacturing Model with Operator Learning

TL;DR

This paper develops a fast, accurate reduced order model for a complex MOOSE-based advanced manufacturing simulation using operator learning, enabling improved process control with deep reinforcement learning.

Contribution

It introduces an operator learning-based ROM using Fourier neural operators for a MOOSE-based manufacturing model, with a benchmark comparison to traditional neural network ROMs.

Findings

OL-based ROM achieves comparable accuracy with faster computation.

Fourier neural operator outperforms conventional deep neural networks in benchmark tests.

The model supports real-time process control in advanced manufacturing.

Abstract

Advanced Manufacturing (AM) has gained significant interest in the nuclear community for its potential application on nuclear materials. One challenge is to obtain desired material properties via controlling the manufacturing process during runtime. Intelligent AM based on deep reinforcement learning (DRL) relies on an automated process-level control mechanism to generate optimal design variables and adaptive system settings for improved end-product properties. A high-fidelity thermo-mechanical model for direct energy deposition has recently been developed within the MOOSE framework at the Idaho National Laboratory (INL). The goal of this work is to develop an accurate and fast-running reduced order model (ROM) for this MOOSE-based AM model that can be used in a DRL-based process control and optimization method. Operator learning (OL)-based methods will be employed due to their capability to learn a family of differential equations, in this work, produced by changing process variables in the Gaussian point heat source for the laser. We will develop OL-based ROM using Fourier neural operator, and perform a benchmark comparison of its performance with a conventional deep neural network-based ROM.