CONNECT WITH US:
Aug 01, 2020 04:00 JST
Science and Technology of Advanced Materials
Using AI to predict new materials with desired properties
An artificial intelligence approach extracts how an aluminum alloy's contents and manufacturing process are related to specific mechanical properties.
Tsukuba, Japan, Aug 01, 2020 - (ACN Newswire) - Scientists in Japan have developed a machine learning approach that can predict the elements and manufacturing processes needed to obtain an aluminum alloy with specific, desired mechanical properties. The approach, published in the journal Science and Technology of Advanced Materials, could facilitate the discovery of new materials.
Aluminum alloys are lightweight, energy-saving materials which are used for various purposes, from welding materials for buildings to bicycle frames. (Credit: Jozef Polc via123rf)
Aluminum alloys are lightweight, energy-saving materials made predominantly from aluminum, but also contain other elements, such as magnesium, manganese, silicon, zinc and copper. The combination of elements and manufacturing process determines how resilient the alloys are to various stresses. For example, 5000 series aluminum alloys contain magnesium and several other elements and are used as a welding material in buildings, cars, and pressurized vessels. 7000 series aluminum alloys contain zinc, and usually magnesium and copper, and are most commonly used in bicycle frames.
Experimenting with various combinations of elements and manufacturing processes to fabricate aluminum alloys is time-consuming and expensive. To overcome this, Ryo Tamura and colleagues at Japan's National Institute for Materials Science and Toyota Motor Corporation developed a materials informatics technique that feeds known data from aluminum alloy databases into a machine learning model. This trains the model to understand relationships between alloys' mechanical properties and the different elements they are made of, as well as the type of heat treatment applied during manufacturing. Once the model is provided enough data, it can then predict what is required to manufacture a new alloy with specific mechanical properties. All this without the need for input or supervision from a human.
The model found, for example, 5000 series aluminum alloys that are highly resistant to stress and deformation can be made by increasing the manganese and magnesium content and reducing the aluminum content. "This sort of information could be useful for developing new materials, including alloys, that meet the needs of industry," says Tamura.
The model employs a statistical method, called Markov chain Monte Carlo, which uses algorithms to obtain information and then represent the results in graphs that facilitate the visualization of how the different variables relate. The machine learning approach can be made more reliable by inputting a larger dataset during the training process.
National Institute for Materials Science
About Science and Technology of Advanced Materials Journal
Open access journal STAM publishes outstanding research articles across all aspects of materials science, including functional and structural materials, theoretical analyses, and properties of materials.
STAM Publishing Director
Press release distributed by ResearchSEA for Science and Technology of Advanced Materials.
Source: Science and Technology of Advanced Materials
Sectors: Metals/Mining, Nanotechnology, Science & Research, AI
Copyright ©2020 ACN Newswire. All rights reserved. A division of Asia Corporate News Network.
TOYOTA GAZOO Racing Back on Track at SPA
Aug 07, 2020 18:04 JST
Leveraging EV/PHEV as Resources for Virtual Power Plants Commencement of Trial Operation of V2G Business Demonstration Facilities
Aug 07, 2020 09:03 JST
SDK to Record Operating/Non-operating Expenses for Acquisition of Hitachi Chemical's Shares, and Extraordinary Loss
Aug 06, 2020 16:00 JST
Mitsubishi Corporation: Trials of "KnowRoute", AI-Controlled On-Demand Bus Service to Commence in Shiojiri City, Nagano Prefecture
Aug 06, 2020 13:36 JST
Honda's Consolidated Financial Summary for the Fiscal Q1 Ended June 30, 2020 and Forecasts for the FY Ending March 31, 2021
Aug 05, 2020 18:45 JST
DENSO Establishes Pittsburgh Innovation Lab to Accelerate Automated Driving R&D
Aug 05, 2020 16:09 JST
Fujitsu Enhances VPS Series to Drive DX for Production Preparation Tasks
Aug 05, 2020 12:30 JST
Mitsubishi Corporation: R&D on Use of CO2 in Concrete
Aug 05, 2020 11:13 JST
MHPS Receives Contract for AQCS Equipment for a Chemical Plant in Poland
Aug 04, 2020 15:19 JST
MHI Machine Tool Develops "FR Series" of Machines to Manufacture Gears for Robots
Aug 04, 2020 12:10 JST
MHPS to Change Company Name to "Mitsubishi Power"
Jul 31, 2020 16:02 JST
DENSO Announces First Quarter Financial Results
Jul 31, 2020 14:11 JST
BluE Nexus and Toyota to Strengthen Sales Structure of Electrified Systems to Prepare for Accelerated Adoption of Electrified Vehicles
Jul 31, 2020 12:28 JST
Eisai: Application for Additional Indication of Anti Cancer Agent Lenvima for Unresectable Thymic Carcinoma Submitted in Japan
Jul 31, 2020 09:31 JST
Mitsubishi Heavy Industries and Copenhagen Infrastructure Partners Enter into Joint Venture to Develop Offshore Wind in Hokkaido, Japan
Jul 31, 2020 09:06 JST
Mazda Production and Sales Results for June 2020 and for January through June 2020
Jul 30, 2020 16:34 JST
MITSUBISHI MOTORS Announces Production, Sales and Export Figures for June 2020 and First Half of Calendar Year 2020
Jul 30, 2020 15:54 JST
Honda Sets Monthly Records for Automobile Production in China
Jul 30, 2020 15:26 JST
Showa Aluminum Can Has a Ceremony to Celebrate the Completion of the Third Production Base in Vietnam
Jul 30, 2020 15:00 JST
Toyota's Global Sales Recover to 84% of Previous Year's Level in June 2020
Jul 30, 2020 13:38 JST
More Latest Release >>
Let the robot swarms begin!
June 21 2020 18:00 JST
Bringing the green revolution to electronics
February 28 2020 16:00 JST
Gaining more control over fuel cell membranes
February 21 2020 08:00 JST
Using bone's natural electricity to promote regeneration
February 13 2020 01:00 JST
Combined data approach could accelerate development of new materials
February 11 2020 16:00 JST
Measuring the wear and tear of metals
February 06 2020 13:00 JST
Quantum dot imaging advances
April 16 2019 16:00 JST
Electronics at the nanoscale: challenges and opportunities for making metal nanowires
March 26 2019 04:00 JST
The Future of Stretchable Electronics
March 24 2019 16:00 JST
Progress in Self-assembling Nanomaterials
February 07 2019 20:00 JST
More Press release >>