Symbolic image of the use of artificial intelligence in corrosion research. Compiled from Adobe Stock images. - © MPIE

Artificial intelligence designs advanced materials

Merging texts and numbers

“Every alloy has unique properties concerning its corrosion resistance. These properties do not only depend on the alloy composition itself, but also on the alloy’s manufacturing process. Current machine learning models are only able to benefit from numerical data. However, processing methodologies and experimental testing protocols, which are mostly documented by textual descriptors, are crucial to explain corrosion”, explains Dr. Kasturi Narasimha Sasidhar, lead author of the publication and former postdoctoral researcher at the Max-Planck-Institut für Eisenforschung.

The researcher team used language processing methods, akin to ChatGPT, in combination with machine learning (ML) techniques for numerical data and developed a fully automated natural language processing framework. Moreover, involving textual data into the ML framework allows to identify enhanced alloy compositions resistant to pitting corrosion. “We trained the deep-learning model with intrinsic data that contain information about corrosion properties and composition. Now the model is capable of identifying alloy compositions that are critical for corrosion-resistance even if the individual elements were not fed initially into the model”, says Dr. Michael Rohwerder, co-author of the publication and head of the group Corrosion at the Max-Planck-Institut für Eisenforschung.

Pushing boundaries: automated data mining and image processing

In the recently devised framework, Sasidhar and his team harnessed manually gathered data as textual descriptors. Presently, their objective lies in automating the process of data mining and seamlessly integrating it into the existing framework. The incorporation of microscopy images marks another milestone, envisioning the next generation of AI frameworks that converge textual, numerical, and image-based data.

Original publication:

K.N. Sasidhar, N.H. Siboni, J.R. Mianroodi, M. Rohwerder, J. Neugebauer, D. Raabe: Enhancing corrosion resistant alloy design through natural language processing and deep learning. In: Science Advances 9 (2023) eadg7992. DOI: 10.1126/sciadv.adg7992

(Source: Press Release of Max-Planck-Institut für Eisenforschung GmbH, Author: Yasmin Ahmed Salem)


AICorrosionDeep LearningMachine Learning

Verwandte Artikel


TRUMPF and Join Forces for AI-Lasers

The two companies are developing AI chips and software to improve welding, cutting and marking processes.

AI Computer-Chips E-Mobility Laser Technology Machine Tools Software Welding
Read more

Production Solutions in the Agricultural Industry

At the end of June, a symposium on "Innovative solutions in the agricultural industry" was held at the CLOOS headquarters in Haiger.

AI Automation Cobot Welding
Read more

Kunststoffe im Automobilbau: Auf dem Weg zur Kreislaufwirtschaft

Kunststoffe bleiben im Automobilbau unverzichtbar. Doch wie kann die Nutzung in Zukunft nachhaltiger werden, bis hin zu einer funktionierenden Kreislaufwirtschaft? Das di...

AI Automobilbau KI Kunststoffe Leichtbau Nachhaltigkeit
Mehr erfahren
AdobeStock_659051383.jpg AdobeStock_659051383.jpg Smart Electronic Factory e.V. und ai-omatic solutions treiben KI in Fabriken voran.

Smart Electronic Factory e.V. und ai-omatic solutions treiben KI in Fabriken voran

Der KI-basierte Wartungsassistent von ai-omatic solutions erkennt in Echtzeit den Zustand von Maschinen und Abweichungen vom Normalzustand.

AI Assistenzsysteme Fertigung Industrie 4.0 Instandhaltung KI Mittelstand Produktion Smarte Produktion Wartung
Mehr erfahren

5 CIO-Tipps für eine KI-Roadmap

Die unternehmensweite Einführung von KI funktioniert nur mit engagierten IT-Teams. Doch es knirscht es in deutschen IT-Abteilungen. Laut einer Ivanti-Studie befürchten 4...

Mehr erfahren