October AMP_Digital

A D V A N C E D M A T E R I A L S & P R O C E S S E S | O C T O B E R 2 0 1 8 1 1 materials. The system can find imper- fections in the metal that were previ- ously undetectable. FHI designed a new scenario that can artificially create data relating to the real world. The researchers were able to use this to generate about 80,000 images of the various kinds of defects and displacements to produce an effective AI model to identify differ- ent crystal structures in practical situ- ations. This data has been released to the public so people can learn their own algorithms. “In theory, all metallic materi- als have perfect symmetry, and all the items are in the correct place, but in practice because of various reasons such as cheap manufacturing there are defects,” explains Ph.D. candidate Devinder Kumar. “All these current methods fail when they try to match actual ideal structures, and most of them fail when there is even a one per- cent defect. We have made an AI-based algorithm that can classify these kinds of symmetries even up to 40 percent defect.” www. uwaterloo.ca. nickel-base superalloy. The team was able to show not only which grain boundaries are stronger but also the specific properties that improve their performance. This finding could ulti- mately allow engineers to build stron- ger metals by designing them with those characteristics. tamu.edu . STUDYING CRACK PROPAGATION WITH 3D IMAGING A Texas A&M University research team has taken the first 3D image of a microscopic crack propagating through a metal damaged by hydrogen. Previ- ously, the only way to analyze this kind of metal failure was to look at the sep- arated pieces of a completely fractured component, and add some educated guesses to the failure analysis. The new research shows what is happening at the crack tip as a part begins to fracture. The team identified 10 microscopic structures that make metals stron- ger and less susceptible to hydrogen embrittlement. Scientists have studied this process for over 150 years, but it remains difficult to predict because the mechanisms behind it are not yet com- pletely understood. Researchers employed two dif- ferent synchrotron tools—high-energy diffraction microscopy and x-ray ab- sorption tomography—to analyze the microscopic structure of a crack in a Advanced imaging provides clues to predicting fracture in metals. Courtesy of Texas A&M.