Video | Business Headlines | Internet | Science | Scientific Ethics | Technology | Search

 

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, July 31, 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.

Paper: https://doi.org/10.1080/14686996.2020.1791676

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.

© Scoop Media

 
 
 
Business Headlines | Sci-Tech Headlines

 

The Narrow Divide: New Poll Shows Tight Political Race For SME Votes

In a major turnaround following nearly a decade of MYOB election polls, Labour is currently the preferred political party of New Zealand’s SMEs, with 38% of SME owners and decision makers intending to vote red in the upcoming General Election, ... More>>

Reserve Bank: Further Easing In Monetary Policy Delivered

Tēnā koutou katoa, welcome all. The Monetary Policy Committee agreed to expand the Large Scale Asset Purchase (LSAP) programme up to $100 billion so as to further lower retail interest rates in order to achieve its remit. The eligible assets remain ... More>>

Retail: Post-Lockdown Retail Card Spending Picks Up

The rise in retail card spending was boosted by sales of furniture, hardware, and appliances, Stats NZ said today. “For a third consecutive month, card spending on the long-lasting goods (durables) remained at higher levels than last year, after ... More>>


Contact: Business Drops, New Generation On Hold

New Zealand’s second-largest energy company Contact Energy (‘Contact’) released its full year financial results for the 12 months to 30 June 2020 (‘FY20’) this morning. More>>

Mining: OceanaGold Announces Receipt Of WKP Mining Permit

MELBOURNE, Australia, Aug. 6, 2020 /CNW/ - OceanaGold Corporation (TSX: OGC) (ASX: OGC) (the 'Company') is pleased to announce it has received the mining permit for Wharekirauponga ('WKP') on the North Island of New Zealand. ... More>>

ALSO:

Economy: COVID-19 Lockdown Has Widespread Effects On Labour Market

In the June 2020 quarter, the seasonally adjusted unemployment rate fell to 4.0 percent, down from 4.2 percent last quarter, while underutilisation rose, Stats NZ said today. More>>

ALSO:

NZ Post: New Research By NZ Post Shows Online Shopping Grew 105% In Alert Level 3

New research by NZ Post into how the COVID-19 response has impacted the way Kiwis shop online, shows online shopping increased 105%* when the country moved into Alert Level 3, and may have changed the way Kiwis shop permanently. Online spend peaked ... More>>

ALSO:

Antarctica NZ: Ice-Olation

Antarctica New Zealand is gearing up for a much reduced season on the ice this year and a very different deployment to normal! Before they head to one of the remotest places on the planet, all personnel flying south with the New Zealand programme will ... More>>

ALSO:

QV Valuations: July House Price Index Illustrates Market Resilience

According to the July 2020 QV House Price Index (HPI) results out today , property values recorded a marginal increase, up 0.2% over the month. This is somewhat of a turnaround from June, after the national index edged 0.2% lower. More>>

ALSO:

Property: Queenstown Rents Experience Biggest Drop In Seven Years

Rental prices in the Queenstown-Lakes district saw the biggest annual percentage drop in seven years after falling 28 per cent on June last year, according to the latest Trade Me Rental Price Index. Trade Me Property spokesperson Aaron Clancy said ... More>>

Seismology: The Quiet Earth

As many daily activities came to a halt during lockdown, the Earth itself became quiet, probably quieter than it has been since humans developed the technology to listen in. Seismologists have analysed datasets from more than 300 international ... More>>

RNZ: James Shaw Says Kiwibank, Not Ministers Should Decide On Investors

Climate Change Minister James Shaw says Kiwibank's decision to stop doing business with companies dealing in fossil fuels is the right one. More>>

ALSO:

FMA: Kiwis Confident Financial Markets Will Recover From COVID-19, Plan To Increase Investments

Despite the majority (60%) of investors experiencing losses as a result of COVID-19, the outlook on investing remains positive, according to a Financial Markets Authority (FMA) survey. Most Kiwis (71%) were optimistic that the pandemic will pass eventually ... More>>

FIRST Union: Warehouse Using Covid For Cover As Extensive Restructure Makes Everyone Worse Off

(FIRST Union comments on The Warehouse consultation and proposed restructure) 'Unfortunately the Warehouse have done the disappointing thing and used Covid-19 to justify a bunch of operational business decisions that will leave hundreds of workers without jobs ... More>>

ALSO: