Frank Muecklich from Saarland University. Photo: Maximilian Schlosser.
Frank Muecklich from Saarland University. Photo: Maximilian Schlosser.

Using machine learning techniques, computer scientists and materials scientists at Saarland University in Saarbrücken, Germany, have developed a method for classifying steel that is much more accurate and objective than conventional quality control procedures. They report their results in a paper in Scientific Reports.

When scientists from two different disciplines collaborate on a research project, they first need to learn to speak the same language. “It took a fair amount of time before the computer scientists had understood why the internal structures of a material and their representation in image form play such an important role for materials scientists,” says Dominik Britz, a PhD student in the Department of Functional Materials at Saarland University.

These internal structures are important because they are closely related to the mechanical properties exhibited by the material. “As modern steels are being supplied in ever greater varieties and because they exhibit increasingly complex internal structures, error tolerances are becoming ever tighter,” says Britz. “This poses a huge challenge for the engineers who develop new steels and who need to meet stringent quality requirements.”

For Seyed Majid Azimi at the Max Planck Institute for Informatics, his first job was to explain to Britz how the machine learning ('deep learning') methods that he employs are able to produce significantly more accurate results than image analyses conducted manually by expert materials scientists. To achieve such results, Azimi feeds his high-performance computer with image data that has previously been 'hand-classified' by experts. This data is used to train the computer models, which are subsequently tested by comparing them against additional sets of human-classified image data. But how can the computer generate such strikingly good results without having any real 'knowledge' of the materials involved?

In this particular study, which focused on classifying steel microstructures, the answer lies in understanding the steel production process. “Manufacturing special steels is an extremely complex process that depends on many individual factors including the chemical composition of the material, the rolling process used and the types of heat treatment that the material is subjected to. Every stage of the production process influences the internal structure of the steel,” explains Britz.

Materials scientists refer to this internal structure as the material's 'microstructure'. This microstructure is composed of 'grains', each of which is a tiny crystallite with a particular crystal structure and spatial orientation. In fact, the grains differ not only in terms of their orientation, but also in terms of their individual shapes and their spatial connectivity, resulting in microstructures of high geometrical complexity. “These extremely complex structures can be made visible during the material development and the quality control stages by taking microscopic images. Specially prepared samples are evaluated using optical and electron microscopy,” says Britz.

Classifying a material involves comparing these microscope images with reference images that exhibit a typical geometrical microstructure. Over time, experienced engineers in company quality assurance departments develop a discerning eye for determining which particular steel microstructure they are dealing with.

“But even these practised experts will sometimes make an incorrect call, as the differences between the images are sometimes barely discernible with the naked eye,” says Frank Muecklich, director of the Steinbeis Materials Engineering Center Saarland (MECS), who supervised the study. “Although humans are pretty good at distinguishing small relative differences, we are not very good at recognizing absolute geometric standards.”

The materials scientists were interested in finding an objective procedure that was far less prone to error and that could be applied irrespective of the user's level of expertise. “Machine learning methods allow computers to recognize complex patterns very rapidly and to assign the geometry of the microstructures in microscope images. They can learn the features of previously classified microstructures and compare these with recognized patterns,” explains Muecklich.

Using this approach, the research team at Saarland University was able to determine the microstructures of low-carbon steel at a level of accuracy that was not previously possible. “When using our system for microstructural classification, we achieved a level of accuracy of around 93%. With conventional methods, only about 50% of the material samples are correctly classified,” says Muecklich.

“We see this as just the beginning of a close cooperative partnership with Saarbrücken's highly respected computer science research teams. The new deep learning methods will not only help us assess the quality of steel more objectively and more accurately, we also anticipate that our results will be transferable to many other production processes and materials,” he adds.

This story is adapted from material from Saarland University, with editorial changes made by Materials Today. The views expressed in this article do not necessarily represent those of Elsevier. Link to original source.

Frank Muecklich from Saarland University. Photo: Maximilian Schlosser.