Carnegie Mellon develops deep-learning alternative to in-situ PBF-LB monitoring
May 7, 2024
Researchers from Carnegie Mellon University’s College of Engineering, Pittsburgh, Pennsylvania, USA, have developed a deep-learning approach that offers a novel way to capture and characterise melt pools in Laser Beam Powder Bed Fusion (PBF-LB) Additive Manufacturing using airborne or thermal emissions. The method, recently detailed in the Journal of Additive Manufacturing, reportedly enables manufacturers to acquire essential melt pool geometries and predict transient melt pool variabilities almost instantaneously.
Many things can go wrong when additively manufacturing metal and without in-situ process monitoring, defects can only be detected and characterised after a product is built. Most commonly, manufacturers will use a high-speed camera to keep an eye on the melt pool geometry and its variation during a short period of the PBF-LB Additive manufacturing process. This requires an expensive piece of equipment, extensive memory storage (i.e. saving 20,000-30,000 high-resolution photos each second) and laborious human efforts to collect and categorise the data. These eventually elevate the cost of online visual tracking and process analysis.
“By leveraging the underlying physics of multi-modal process signals and the advantages of data-driven artificial intelligence, our pipeline enables engineers to reconstruct critical melt pool characteristics using very affordable and accessible sensors such as microphones or photodiodes,” said Haolin Liu, PhD candidate in Mechanical Engineering.
One benefit of this new approach is its potential ability to identify spatially dependent lack-of-fusion (LOF) defects in PBF-LB. As one of the most typical process anomalies, LOF occurs when there is insufficient melt pool overlap as the laser works its way across the powder layer. The resultant unmelted powder leaves the part with huge unfused gaps and residual pores that could severely undermine the durability and other mechanical properties of the final product. Therefore, capturing these local flaws as well as melt pool variations in real-time is critical to manufacturing consistently durable products.
The team conducted a series of PBF-LB experiments to explore various printing parameters of the titanium alloy Ti-6Al-4V (Ti-64). Airborne acoustic, thermal, and high-speed imaging data was collected and synchronised for each corresponding process condition from a pre-designed, as-built structure to successfully reconstruct accurate melt pool geometries. The team even tracked the melt pool oscillational behaviours over a period as short as only a few milliseconds. The approach is said to have also exhibited promising capabilities to effectively detect local LOF defects between two adjacent laser scanlines.
“This method is allowing melt pool monitoring using low-cost sensors that can be installed in any laser powder bed AM machine. The generation of artificial videos of high-speed melt pools from acoustic and photodiode sensor data is unique to the AM community,” said Jack Beuth, Mechanical Engineering Professor and co-director of Carnegie Mellon’s NextManufacturing Center.
Moreover, the team’s research is also said to have resulted in a crucial step toward better understanding the physical correlation between multi-modal in-situ process signals.
“The intercorrelations between these signals have not yet been fully explored in the scientific community,” Liu shared. “Though our research was focused on a deep learning, data-driven pipeline, we revealed that certain rudimental connections exist between acoustic signatures, thermal emissions, and melt pool morphologies, the physics and dynamics of which require further scientific exploration and experimental investigation.”
“Although many experts have been aware of the interplay between acoustic emissions, thermal emissions, and the resulting melt pool dynamics in laser printing, the precise relationships are still largely unknown,” stated Levent Burak Kara, Mechanical Engineering Professor. “In this work, we established and demonstrated a data-driven predictive model that relates these three phenomena in a quite accurate and physically meaningful way.”
According to Anthony Rollert, materials science and engineering professor and co-director of the NextManufacturing Center, acoustic behaviours entail essential physical interactions between laser and materials.
“To our surprise, it reveals more than we had expected and it turns out to be very useful for informing process-related quantities that could potentially impact manufacturing quality.”
Liu added, “We hope to better understand acoustic the pool variability, keyhole oscillation, and other spatially dependent process features.”
Moving forward, the team plans to explore more real-time monitoring applications driven by acoustic and thermal emission data for materials other than Ti-64 and across different platforms and Additive Manufacturing processes.
“With a deeper interpretation of potentials of acoustic and thermal emission, we hope to better understand their relationships to melt pool variability, keyhole oscillation, and other spatially dependent process features,” said Liu. “One day, we may build advanced surrogate models and fully functional digital twins for other process characterisation equipment like synchrotron x-ray machines and the entire AM process too!”
The full paper – ‘Inference of highly time-resolved melt pool visual characteristics and spatially-dependent lack-of-fusion defects in laser powder bed fusion using acoustic and thermal emission data’ – is available here.
Download Metal AM magazine
