The content on this page was translated automatically.
AI supports analysis of metallic materials
The inner structure of crystalline individual regions, so-called "grains", is decisive for the properties of metallic materials. Their arrangement has a decisive influence on the strength and deformation behavior of the metals. So-called shape memory alloys, for example, change their shape due to temperature-induced changes in the internal crystal structure. "Creating a suitable microstructure in these special materials is a major technical challenge. Checking this in detail with the help of X-ray analyses is particularly complex," explains Prof. Dr.-Ing. Thomas Niendorf, head of the Metallic Materials department.
For this purpose, researchers often use the methods of X-ray diffraction. In this process, they direct a focused X-ray beam onto the material samples. The beam is deflected at its crystal lattice - in physical terms, diffracted. A detector receives the diffracted X-rays and software displays their intensity in a so-called pole figure. They rotate and tilt the material sample until a pole figure is created from the measurement data. These series of measurements often last for several days. Using the pole figures, the researchers can computationally determine the arrangement and orientation of the crystals in the metal.
"With our specially developed algorithm, we are three times faster," reports David Meier, an information scientist from Helmholtz-Zentrum Berlin and the Department of Intelligent Embedded Systems at the University of Kassel (headed by Prof. Bernhard Sick). "With machine learning, it is trained to create a complete reconstruction of the pole figure from only a small section of real measurement data of a few hours. It differs only minimally from the original." To do this, Meier worked with the materials engineers to create pole figures of random arrangements of grains in the metal using a simulation. Using these simulated images, a customized deep-learning architecture learns to generate the complete pole figure from a section. This "reconstruction network" can reconstruct the remaining areas for a small section of a real measured pole figure. The subsequent comparison of reconstruction and real, complete measurement results of the sample shows: The reconstruction network can analyze the sample with sufficient accuracy for the applied example. But: in order to statistically prove that the developed method works in other real-life scenarios, it needs to be evaluated in follow-up studies with further samples from different materials, says David Meier.
The researchers in the Department of Metallic Materials are enthusiastic about the collaboration with computer science: "We now only need a few hours to analyze the micro-crystal structure and can even reliably reconstruct areas that we would not have been able to reach at all technically with our experimental setup," says Dr.-Ing. Alexander Liehr, head of the X-ray fine structure analysis group. In the future, too, the combination of modern measurement technology and artificial intelligence could support the research and development of high-performance and durable materials.
Meier, D., Ragunathan, R., Degener, S., Liehr, A., Vollmer, M., Niendorf, T., Sick, B.: Reconstruction of incomplete X-ray diffraction pole figures of oligocrystalline materials using deep learning Scientific Reports. 13, 5410 (2023). https://doi.org/10.1038/s41598-023-31580-1
Department of Intelligent Embedded Systems
Phone: +49 561 804-6048
University of Kassel
Communications, Press and Public Relations
Phone: 0561 804-1961