Physics-guided denoiser network for enhanced additive manufacturing data quality

TL;DR

This paper introduces a physics-informed neural network-based denoising method that improves the quality of sensor data in additive manufacturing by reducing noise and ensuring physical consistency, enabling better real-time monitoring and control.

Contribution

The work presents a novel physics-guided denoising framework combining energy-based models and Fisher score regularization, validated on benchmark problems and applied to real LPBF data.

Findings

Outperforms baseline neural denoisers in noise reduction.

Effectively denoises thermal emission data from LPBF processes.

Enables real-time, robust interpretation of sensor data for additive manufacturing.

Abstract

Modern engineering systems are increasingly equipped with sensors for real-time monitoring and decision-making. However, the data collected by these sensors is often noisy and difficult to interpret, limiting its utility for control and diagnostics. In this work, we propose a physics-informed denoising framework that integrates energy-based model and Fisher score regularization to jointly reduce data noise and enforce physical consistency with a physics-based model. The approach is first validated on benchmark problems, including the simple harmonic oscillator, Burgers' equation, and Laplace's equation, across varying noise levels. We then apply the denoising framework to real thermal emission data from laser powder bed fusion (LPBF) additive manufacturing experiments, using a trained Physics-Informed Neural Network (PINN) surrogate model of the LPBF process to guide denoising. Results show that the proposed method outperforms baseline neural network denoisers, effectively reducing noise under a range of LPBF processing conditions. This physics-guided denoising strategy enables robust, real-time interpretation of low-cost sensor data, facilitating predictive control and improved defect mitigation in additive manufacturing.