ADVANCED MATERIALS & PROCESSES | NOVEMBER 2026 10 MACHINE LEARNING | AI AI INSPECTION IMPROVES 3D PRINTING Scientists at the DOE’s Lawrence Livermore National Laboratory (LLNL) developed a camera-based inspection system that can monitor 3D-printed structures layer by layer, using artificial intelligence (AI) and machine learning (ML) to measure tiny variations and potentially identify problems before a part even leaves the printer. The approach could reduce the time and labor required to inspect components produced through direct ink writing, an additive manufacturing (AM) technique. It also presents a way to examine large parts that may be difficult to inspect using conventional x-ray computed tomography, according to the team. The system combines cameras mounted on a 3D printer with ML-based image segmentation and computer vision tools to convert thousands of images captured during printing into detailed measurements and spatial maps of the deposited material. “We now have kind of a brain behind the eyes,” says researcher Brian Weston. “Our system can now see as we’re printing, and we can make data-informed decisions going forward.” The team trained an ML image segmentation model using a cur- ated dataset of nearly 15,000 human-annotated images representing several lattice geometries. A computer vision algorithm then used the model’s results to trace printed strands and measure their dia- meter. In tests involving 55 parts, the automated measurements were typically within a few micrometers of human-derived analysis. Manually measuring a large image could take a person from about 20 minutes to an hour, according to the scientists, while the automated pipeline can perform the analysis in milliseconds. llnl.gov. USING AI FOR FASTER, CHEAPER 3D-PRINTED PARTS Researchers at Washington State University used AI to find a more efficient, less expensive way to 3D- print a high-performance metal alloy, eliminating the need to test more than 100 million options. The findings could one day allow this common aerospace alloy to be printed using widely avail- able commercial equipment, according to the team. The alloy, GRCop-42, com- prises three metals— copper, chromium, and niobium. Developed by NASA, it has high thermal An automated inspection pipeline analyzes images roughly 100,000 times faster than a human can. Courtesy of LLNL. conductivity and remains strong under extreme heat, so it is used in applications such as liquid rocket engine combustion chambers. However, it is expensive and energy-intensive to print, requiring a significant amount of laser power. Researchers have tried unsuccessfully to print the alloy at the lower wattages and laser powers that are used by more common commercial printers, but testing different configurations requires expensive materials, specialized equipment, and significant labor. A single print run can cost hundreds of dollars, while detailed post-print quality analysis can take days. The team used AI-selected process configurations to print GRCop-42 and evaluated the resulting samples. Over three months and within a budget of 40 experiments, the team identified six successful configurations over different laser power levels. The scientists then successfully printed the alloy at 500 watts for the first time, and they believe the same AI-guided framework could be adapted to discover processing conditions for other metal alloys and AM systems. wsu.edu. Researchers used AI to sort through millions of options to identify a more efficient way to print a metal alloy commonly used in the aerospace industry. Courtesy of Alones Creative/iStock.
RkJQdWJsaXNoZXIy MTYyMzk3NQ==