MATERIALS
The Convergence of Artificial Intelligence and Machine Learning in Advanced Laser Processing
- 1 Ship propulsion plants Department of the Faculty of Engineering Nikola Vaptsarov Naval Academy
Abstract
The application of laser technology across manufacturing, from automotive to aerospace, has been a key driver of modern industrial efficiency. However, traditional laser processes often rely on static parameters and manual oversight, which can lead to inconsistencies and defects. The recent integration of artificial intelligence (AI) and machine learning (ML) is fundamentally transforming this landscape, moving laser processing from a static, pre-programmed task to a dynamic, self-optimizing system.
References
- Precitec GmbH & Co. KG. (2024). Laser Welding Monitor with AI-Powered Defect Prediction: Product Specification and Case Study. Online.
- Choi, J., et al. (2024). Real-time Defect Detection in Automotive Laser Welding Using AI-driven Multisensor Data Fusion. In Journal of Manufacturing Science and Engineering, 146(3), 031005.
- The Manufacturing Institute. (2025). Industry Report: The Impact of AI on Maintenance and Operational Efficiency in High- Volume Production. Washington, D.C.: The Manufacturing Institute Press.
- Sutton, R. S., & Barto, A. G. (2018). Reinforcement Learning: An Introduction. Cambridge, MA: The MIT Press.
- Chen, L., et al. (2024). Autonomous Optimization of Laser Welding Parameters Using Deep Reinforcement Learning. In Applied Physics Reviews, 11(2), 021401.