Artificial intelligence designs advanced materials

Scientists of the Max-Planck-Institut für Eisenforschung have pioneered a new machine learning model for corrosion-resistant alloy design.

By Yasmin Ahmed Salem for Max Planck Institute

In a world where annual economic losses from corrosion surpass USD 2.5 trillion, the quest for corrosion-resistant alloys and protective coatings is continuous. Artificial intelligence (AI) is playing an increasingly pivotal role in designing new alloys. Yet, the predictive power of AI models in foreseeing corrosion behaviour and suggesting optimal alloy formulas has remained elusive. Scientists of the Max-Planck-Institut für Eisenforschung (MPIE) have developed a machine learning model that enhances the predictive accuracy by up to 15% compared to existing frameworks. This model uncovers new, but realistic corrosion-resistant alloy compositions. Its distinct power arises from fusing both numerical and textual data. Initially developed for the critical realm of resisting pitting corrosion in high-strength alloys, this model’s versatility can be extended to all alloy properties. The researchers have published their results in the journal Science Advances.

Merging texts and numbers

“Every alloy has unique properties concerning its corrosion resistance. These properties depend not only 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 MPIE.
The research team used language processing methods akin to ChatGPT, in combination with machine learning (ML) techniques for numerical data, to develop a fully automated natural language processing framework. Moreover, involving textual data in the ML framework allows the identification of 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 MPIE.

Figure 1. (A) Schemiatc representation of the entire process-aware deep neural network model. (B) Schematic illustration of the data processing workflow carried out within the natural language processing (NLP) module. LSTM: long short-term memory. Figure 1. (A) Schemiatc representation of the entire process-aware deep neural network model. (B) Schematic illustration of the data processing workflow carried out within the natural language processing (NLP) module. LSTM: long short-term memory. Image taken from Science Advances, DOI: 1126/sciadv.adg7992
Figure 1. (A) Schemiatc representation of the entire process-aware deep neural network model. (B) Schematic illustration of the data processing workflow carried out within the natural language processing (NLP) module. LSTM: long short-term memory. Image taken from Science Advances, DOI: 1126/sciadv.adg7992

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.

About MPIE

The team of the Max-Planck-Institut für Eisenforschung conducts advanced basic materials research for the fields of mobility, energy, infrastructure, medicine and digitalisation. The focus lies on nanostructured metallic materials as well as semiconductors.

About this Tech Article

This tech article appeared in Stainless Steel World, January/February 2024 magazine. To read many more articles like these on an (almost) monthly basis, subscribe to our magazine (available in print and digital format) – SUBSCRIPTIONS TO OUR DIGITAL VERSION ARE NOW FREE.

Every week we share a new Featured Story with our Stainless Steel community. Join us and let’s share your Featured Story on Stainless Steel World online and in print.

Previous articleNickel Industries support environmental sustainability
Next articleDynamic duplex materials: strong and sustainable
Stainless Steel World is part of The KCI Media Group, a group of companies focused on building and sustaining global communities in the flow control industries. We publish news on a daily basis and connect business-to-business professionals through our online communities, publications, conferences and exhibitions.