Physics-informed data-driven machine health monitoring for two-photon lithography

2025-10-16

AI Summary

Current two-photon lithography (TPL) systems rely on experience-based maintenance, leading to unplanned downtime or excessive maintenance and severely compromising manufacturing quality and efficiency. To address this, we propose a physics-informed, data-driven health monitoring method. Specifically, we develop a degradation modeling framework based on Physics-Informed Neural Networks (PINNs), jointly trained on experimental data comprising six process parameter combinations and six structural feature dimensions. The framework integrates regression-based prediction with statistical analysis to enable quantitative, multi-scenario health state assessment. Our approach significantly improves accuracy and robustness in health state identification, reliably distinguishing distinct degradation levels. Extensive validation across diverse operational conditions confirms its generalizability and practical applicability. This work establishes an interpretable, deployable paradigm for condition-based intelligent maintenance of TPL systems.

Technology Category

• Machine Learning: Hardware-aware ML
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Two-photon lithography (TPL) is a sophisticated additive manufacturing technology for creating three-dimensional (3D) micro- and nano-structures. Maintaining the health of TPL systems is critical for ensuring consistent fabrication quality. Current maintenance practices often rely on experience rather than informed monitoring of machine health, resulting in either untimely maintenance that causes machine downtime and poor-quality fabrication, or unnecessary maintenance that leads to inefficiencies and avoidable downtime. To address this gap, this paper presents three methods for accurate and timely monitoring of TPL machine health. Through integrating physics-informed data-driven predictive models for structure dimensions with statistical approaches, the proposed methods are able to handle increasingly complex scenarios featuring different levels of generalizability. A comprehensive experimental dataset that encompasses six process parameter combinations and six structure dimensions under two machine health conditions was collected to evaluate the effectiveness of the proposed approaches. Across all test scenarios, the approaches are shown to achieve high accuracies, demonstrating excellent effectiveness, robustness, and generalizability. These results represent a significant step toward condition-based maintenance for TPL systems.

Problem

• Monitoring machine health in two-photon lithography systems
• Addressing untimely or unnecessary maintenance through predictive models
• Integrating physics-informed data-driven approaches for fabrication quality

Innovation

• Integrating physics-informed data-driven predictive models
• Combining statistical approaches for complex scenarios
• Achieving high accuracy in machine health monitoring