Accessibility
Language
AI accelerates development of new materials
The development of new materials poses great challenges for materials science: The methods and experiments are costly and innovative materials are often discovered only by chance. This is set to change through the use of extensive materials databases that can be easily searched using AI.
Search materials databases with AI. (Photo credit: AdobeStock©phonlamaiphoto)
Prof. Dr.-Ing. habil. Marion Merklein, holder of the Chair of Manufacturing Technology at FAU Erlangen-Nuremberg, is working intensively on this topic: "Such material databases have a great benefit and enormous potential to identify previously unrecognized cause-effect relationships between material and product properties in the future." An important part of her work, she says, is therefore to characterize and model materials: "The data obtained are the basis for material databases and thus the starting point for various research projects. These include numerical process analysis and design or scientific work on digital twins of real manufacturing processes from the semi-finished product to the final component and its properties."
Prof. Merklein's research focuses on manufacturing technology, especially forming technology. She researches how to produce functional components and goods from different materials, such as how sheet metal becomes parts for automotive and mechanical engineering. "Material data in the databases are only meaningful if they are recorded together with all the process parameters that acted on the material during production," adds Dr. Nicole de Boer, head of the New Materials Cluster . After all, these framework conditions would contribute to the structure and thus to the actual properties of the component.
KI for superconductors
Possible areas of application for artificial intelligence in the material sciences are many, for example research into superconductors - materials that can conduct electric current without resistance when cooled down. For this, however, the materials usually have to be cooled to extremely low temperatures.
In ceramic materials composed of the chemical elements yttrium, barium, copper, and oxygen (YBCO) and built from a complicated perovskite structure, researchers discovered so-called high-temperature superconductivity, in which the materials need only be cooled to the temperature of liquid nitrogen. However, it is still unknown why superconductivity starts at unexpectedly high temperatures in this YBCO material. Machine learning and AI could help researchers in the future to understand this effect so that they can then conduct targeted research into superconductors that function at room temperature without the need for complex cooling.