Machine Learning Modeling for Real-Time Melt Pool Monitoring in Laser Powder Bed Fusion Additive Manufacturing: A Hybrid Approach
arXiv:2606.23851v1 Announce Type: new Abstract: This work investigates the implementation of artificial intelligence and machine learning (AI/ML) for real-time monitoring in laser powder bed fusion (LPBF) additive manufacturing. We developed a binary image classification framework for distinguishing normal and abnormal melt pool images using a balanced dataset of 1,200 images collected from Nickel superalloy 625 on the NIST AMMT platform. The study evaluates accuracy and inference time based on control requirements and hardware limitations of open-architecture LPBF machines. We benchmark three
The proliferation of AI/ML techniques and the increasing demand for quality control and efficiency in advanced manufacturing processes like additive manufacturing are driving this development.
This development allows for real-time monitoring and quality control in additive manufacturing, which is critical for scaling production of high-performance components and reducing defects.
The ability to integrate AI-driven real-time quality assurance into manufacturing processes significantly improves reliability and speed compared to traditional post-production inspection methods.
- · Additive manufacturing companies
- · Materials science
- · AI/ML providers
- · Aerospace and defence
- · Traditional inspection services
- · Manufacturers with high defect rates
Increased adoption of in-situ monitoring in advanced manufacturing, particularly for critical components.
Acceleration of research and development in AI-driven material science and process optimization.
Potential for fully autonomous manufacturing facilities with self-correcting production lines.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG