Researchers are using machine learning to make printing materials that are stronger and tougher, according to a recently published paper. The new materials could have applications that range from industrial to hobbyist 3D printing such as packaging tailored for specific electronics, customized personal protective equipment, or even designer furniture, Keith A. Brown, an engineering professor at Boston University who was among the researchers conducting the study, told Lifewire in an email interview. “Our goal is to learn how to 3D print high-performance mechanical components,” he added. “These can have applications that range from industrial to hobbyist 3D printing such as packaging tailored for specific electronics, customized personal protective equipment, or even designer furniture.”
Print Anything?
In the system that Brown’s team developed, an algorithm performs most of the discovery process to find new printing materials. “Our approach is to combine automated manufacturing and testing with machine learning to rapidly and efficiently identify high-performing components,” Brown said. “In essence, we have an autonomous robot that is studying these mechanical systems under our supervision.” A human selects a few ingredients, inputs details on their chemical compositions into the algorithm, and defines the new material’s mechanical properties. The algorithm then increases or decreases the amounts of those components and checks how each formula affects the material’s properties before arriving at the ideal combination. The researchers used the system to improve a new 3D printing ink that hardens when exposed to ultraviolet light, according to the paper. They identified six chemicals to use in the formulations and set the algorithm’s objective to uncover the best-performing material for toughness, stiffness, and strength. Without AI, optimizing these three properties would be tricky because they can work at cross purposes. For example, the strongest material may not be the stiffest. “Brute force exploration might allow the exploration of 100 or so materials,” Joshua Agar, a professor at Lehigh University who uses machine learning to discover new materials, told Lifewire in an email interview. “AI and automated experiments can enable millions of samples to be searched.” A human chemist typically would try to maximize one property at a time, resulting in many experiments and a lot of waste. But the AI was able to do it far quicker than a human. “Using AI in 3D printing allows [it to perform] hundreds of repetitions with the desired characteristics in the same timeframe of a chemist performing one or two,” Alessio Lorusso, CEO of Roboze, a company that uses AI to develop materials, told Lifewire in an email interview. He was not involved in the MIT research. “This is obviously a remarkable time and cost-cutting technology.”
The Future May Be Printed
The discovery process for printing materials could be made even faster with more automation, Mike Foshey, an MIT professor and co-lead author of the paper, said in a news release. Researchers mixed and tested each sample by hand, but robots could operate the dispensing and mixing systems in future system versions. Eventually, the researchers plan to test the AI process for uses beyond developing new 3D printing inks. “This has broad applications across materials science in general,” Foshey said. “For instance, if you wanted to design new types of batteries that were higher efficiency and lower cost, you could use a system like this to do it. Or, if you wanted to optimize paint for a car that performed well and was environmentally friendly, this system could do that, too.” The possibilities for AI-driven materials are “endless” once the algorithm is developed and the machine has enough data to start applying it accurately, Lorusso said. “We believe that it is useful to find new materials because the performances achieved today by super polymers and composites offer the possibility of producing end-use parts,” he added. “They could replace metals and create a circular economy model, where the raw material continues to regenerate itself through constant recycling.”
