Engineers are always looking for materials with very specific properties for their projects. Unfortunately, there are far too many options for researchers to just guess and check until they find what they’re looking for. Even if they were to simulate materials instead of testing them in the laboratory, it would take far too long to find a suitable material.
Fortunately, researchers have used artificial intelligence to develop algorithms that find the right material for each project. In a recent article, a team of researchers from Carnegie Mellon University and the University of Calgary improved one of these algorithms so that researchers can find materials with the properties they want quickly and accurately.
“Since the material space is so large, it is very difficult to characterize the material properties experimentally and mathematically,” said Amir Barati Farimani, assistant professor of mechanical engineering at the CMU. “So we create algorithms or models that can be used to quickly predict the material properties.”
To use artificial intelligence or AI, researchers first need to train the algorithm using known data. Then the algorithm learns to extrapolate new ideas from this information. Barati Farimani and his team trained the algorithm with data on the chemical composition of materials. In particular, they contained information about the role that electrons play in determining material properties. According to Barati Farimani, these chemical data created a new material descriptor for the algorithm.
Because this algorithm can predict the properties of a wide variety of materials, it has many uses. For example, the algorithm could find a material with thermal properties that is suitable for solar panels. In addition, materials used to manufacture medicines and batteries could be identified. To use this algorithm, a researcher can simply let the pre-built deep learning models find the property they are looking at.
The way these algorithms are improved is by becoming faster and more accurate. If the algorithm is not accurate enough, the results are useless. If the algorithm is too slow, researchers will never have access to the results. Currently, the team has found that their algorithm is better than other leading algorithms.
“You can use this algorithm, train a deep learning model, and predict it in a split second,” said Barati Farimani. “The point is to prove that different types of materials can be predicted with great accuracy – then any industry can use them.”
Your article was published in Physical verification materials. CMU postdoctoral fellow Mohammadreza Karamad, Ph.D. Student Rishikesh Magar and researcher Yuting Shi were also listed as co-authors. Other authors are Samira Siahrostami and Ian D. Gates from the University of Calgary.
The algorithm predicts the composition of new materials
More information:
Mohammadreza Karamad et al. Convolution network of the orbital graph to predict material properties, Physical verification materials (2020). DOI: 10.1103 / PhysRevMaterials.4.093801
Provided by Carnegie Mellon University Mechanical Engineering
Quote: To order! AI finds the correct material (2020, October 16), accessed on October 16, 2020 from https://phys.org/news/2020-10-ai-material.html
This document is subject to copyright. Except for fair trade for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.
These were the details of the news Order it! AI finds the right material for this day. We hope that we have succeeded by giving you the full details and information. To follow all our news, you can subscribe to the alerts system or to one of our different systems to provide you with all that is new.
It is also worth noting that the original news has been published and is available at de24.news and the editorial team at AlKhaleej Today has confirmed it and it has been modified, and it may have been completely transferred or quoted from it and you can read and follow this news from its main source.
