Next Manufacturing Center seminars are open to Center members, as well as other interested members of the CMU community. Next Manufacturing Center Consortium members are able to participate online.

Title: Inference of highly time-resolved melt pool visual characteristics in laser powder bed fusion from acoustic and thermal emission data

Speakers: Burak Kara, professor, mechanical Engineering and Ph.D. candidate Haolin Liu

With a growing demand for high-quality fabrication, the interest in real-time monitoring of laser powder bed fusion (LPBF) processes has increased, leading manufacturers to incorporate a variety of online sensing methods including acoustic sensing, photodiode sensing, and high-speed imaging. However, real-time acquisition of high-resolution melt pool images in particular remain computationally demanding in practice due to the limitation of data caching and transfer. In this work, we present a new acoustic and thermal information-based monitoring approach that can infer critical melt pool morphological features in LPBF and represent them in image forms. We utilize wavelet scalogram matrices of acoustic and photodiode clip data to identify and predict highly time-resolved (within a 1.0 ms window) visual melt pool characteristics via a well-trained data-driven pipeline. With merely the acoustic and photodiode-collected thermal emission data as the input, the proposed pipeline enables data-driven inference and tracking of melt pool visual characteristics with R^2≥0.8. Our work demonstrates the feasibility of using an efficient and cost-effective method to facilitate online visual melt pool characterization, and we believe it can further contribute to the advances in quality control for LPBF.


Burak Kara

Burak Kara headshotL. Burak Kara is a Professor in the Department of Mechanical Engineering at Carnegie Mellon University, with a courtesy appointment in the Robotics Institute. He is the founder of the Visual Design and Engineering Laboratory. His current research interests include computer-aided design and manufacturing, design automation, data-driven design and shape optimization and machine learning, with applications in industrial product design, automotive design, engineering education and bio-medical engineering. He is the recipient of National Science Foundation Career award and American Society of Mechanical Engineers Design Automation Society Young Investigator Award. At CMU, he teaches courses in AI and Machine learning, Engineering Design, Dynamic Systems and Control, and Linear Algebra and Vector Calculus.

Haolin Liu

Haolin Liu headshotHaolin Liu is a Ph.D. candidate in the Department of Mechanical Engineering at CMU. He is currently working with Prof. Levent Burak Kara, Prof. Anthony D. Rollett, and Prof. Jack L. Beuth on acoustic and thermal data-based laser powder bed fusion (LPBF) process monitoring. The general emphasis of his research lies in the broad area of additive manufacturing (AM) and related science, with a specific focus on metallic LPBF. His work in polymer 3D printing and 4D printing has been published in top journals and conferences related to mechanics, design and manufacturing. Beyond research in AM, he is also working on developing a deep-learning and data-driven-based method for statistical and physical inference.

Upcoming Events