How AI can help find new metals to make better gadgets

Artificial intelligence (AI) could be essential to finding new materials used to build long-lasting, lightweight personal gadgets.

In a recent study, researchers used AI to find properties and experiment to identify new alloys. Without AI, sifting through the vast number of possible element combinations is a difficult task.

“As manufacturing technology advances, the alloy composition and processing space expands,” said S. Mohadesh Taheri-Mousavi, professor of materials science and engineering at Carnegie Mellon University, who was not involved in the study. said in an email interview with Lifewire. “For example, alloys containing more than ten alloying elements are currently found in airframes such as aircraft. Beyond the brain.—Dimensional space.”

Better gadgets with AI

AI is already being used to discover new materials. In an e-mail interview with Lifewire, technical consultant and IEEE member Yale Fox explained that scientists can use AI to make ion selection cheaper, more effective, and for many applications such as wastewater treatment and biomedical devices. The researchers also discovered several new solid-state materials that conduct lithium. This can be used to improve the latest battery technology.

“The hottest area right now is batteries: how to charge them faster, keep them charged longer, make them lighter, make them more environmentally friendly,” Fox added. “This will have a positive impact on electric vehicles such as cars and planes.”

New AI-created semiconductors could enable faster computing speeds or more powerful artificial intelligence algorithms, Adnan Masood, chief AI architect at UST, said in an email. . By better understanding how different materials behave under different conditions, scientists can develop more effective treatments for diseases such as cancer or create safer nuclear reactors. You can

Artificial intelligence has also helped build new alloys, semiconductors, ceramics, and other types of materials by enabling scientists to process large amounts of data quickly and efficiently.

“Benefits of the new materials include improved performance, lighter weight and increased strength,” added Masood. “AI can help us discover lighter, stronger materials by analyzing data from experiments and simulations and optimizing material compositions through trial-and-error simulations. There is no possibility that it will take.”

Miguel Modestino, a professor in the Department of Chemical and Biomolecular Engineering at New York University, says AI can take experimental results and guide researchers on where and how to find the most likely conditions leading to new materials and better processes. Accelerate discovery by guiding. Lifewire via email. “This has the potential to significantly reduce the time it takes to make new discoveries, as well as reduce energy use and material waste,” he added.

Discovery of new environmentally friendly materials

Modestino’s lab combines AI and autonomous research tools to run hundreds to thousands of experiments a day, reducing the time from idea to discovery by more than 100x. Researchers are seeking to discover new chemical reactions that can produce existing materials in new, more efficient ways that reduce the negative environmental impact of current approaches to manufacturing chemicals.

According to Modestino, most of our everyday items are made from materials produced in the chemical industry. His group has focused on manufacturing nylon 66. More than 5 million tonnes of nylon are produced annually, of which his 2 million tonnes is nylon 66, which is used to make textile fibers used in winter jackets and plastics that make automobiles lighter and lighter. Includes auto parts. fuel efficiency. Modestino said the chemicals used to make nylon and most chemicals are produced by burning fossil fuels, resulting in 10% of global energy consumption and 20% of carbon emissions from industry. said it does.

“Using AI, we have discovered a new, more energy-efficient way to manufacture nylon 66 precursors based on electricity instead of fossil fuel combustion,” he added. “We were able to do this by training a machine learning model on information from a limited number of experiments to accelerate the discovery of optimal conditions for this process.”