Japan’s Showa Denko establishes neural network models to envisage mechanical properties of aluminium alloys accurately

The pioneer in Japan’s chemical industry, Showa Denko K.K. has established neural network models to envisage mechanical properties of 2000-series aluminium alloys from their design conditions with high accuracy in collaboration with the National Institute for Material Science (NIMS) and the University of Tokyo (UTokyo).

The developed models can accelerate the process to explore optimal compositions and heat-treatment conditions for aluminium alloys that can maintain strength at high temperatures and shorten development time for aluminium alloys to about half to one-third of that with conventional development method, which used to be not an easy task in the past.

The metal aluminium has several applications because it is lighter than iron and easy to work with. However, it is usually used as an aluminium alloy containing copper, magnesium and other additive elements because pure aluminium has low strength. The development of aluminium alloys that can maintain sufficient strength for a particular use at high temperatures is desired because conventional aluminium alloys lose strength when their temperature rises to 100 degrees Celsius or higher. However, the mechanical properties of aluminium alloys depend on many process factors, including many kinds of additive elements and heat-treatment conditions. Developing high-performance aluminium alloys usually takes time because designing aluminium alloys requires developers' knowledge-rich experience and repetition of analysis and evaluation.

Intending to resolve these issues, SDK has been taking part in a project under Council for Science, Technology and Innovation (CSTI), Cross-ministerial Strategic Innovation Promotion Program (SIP), "Materials Integration" for Revolutionary Design System of Structural Materials. In this Development, SDK, NIMS, and UTokyo have collaboratively developed a computer system using neural networks, an artificial intelligence (AI) algorithm, to accelerate the development of materials and explore globally for aluminium-alloy designing conditions that realize optimal mechanical properties.

In this development, the focus was on 2000-series aluminium alloys, utilized design data of 410 records of aluminium alloys listed in public databases, including the Japan Aluminum Association, and developed neural network models that accurately predict the strength of aluminium alloys at various temperatures ranging from room temperature to high temperature. In addition, it was optimized the architecture and parameters of the neural network with Bayesian inference by applying the replica-exchange Monte Carlo Method. As a result, it became possible to evaluate aluminium alloy strength and its prediction uncertainty. Moreover, this neural network model can estimate the strengths of aluminium alloys under 10,000 different conditions within 2 seconds. Thus it became possible to evaluate aluminium alloys with various design factors comprehensively in a short time.

Furthermore, SDK successfully developed "an inverse design tool," which suggests a set of aluminium-alloy design conditions that maximize the probability of satisfying the desired strength at arbitrary temperature. Thus it enables to design of high-strength aluminium alloys at high temperatures above 200 degrees Celsius.

In its long-term vision for Newly Integrated Company, the Showa Denko Group has announced: “We will continue committing itself to make the most of artificial intelligence and computational science, which is the core of its fundamental research activities. We will accelerate our material development programs by applying the results of this Development to our activities to develop various new materials, and provide our customers with solutions for their problems, thereby contributing to the prosperity of society.