Researchers from Delft University of Technology in the Netherlands have developed a new artificial intelligence (AI) tool known as “Deep-DRAM” to discover and fabricate novel metamaterials with unparalleled ease and accessibility.
The groundbreaking method promises to revolutionize metamaterial development by streamlining the discovery and creation of durable, custom-designed materials with “unprecedented functionalities” and “unusual properties.”
“Traditionally, designers use the materials available to them to design a new device or a machine. The problem with that is that the range of available material properties is limited. Some properties that we would like to have just don’t exist in nature,” study co-author and professor of biomechanical engineering, Dr. Amir Zadpoor, explained in a press release by Delft University.
“Our approach is: tell us what you want to have as properties and we engineer an appropriate material with those properties. What you will then get is not really a material but something in-between a structure and a material, a metamaterial.”
Metamaterials are materials engineered to have properties not found in naturally occurring substances. These engineered composites can defy conventional material properties by deriving their unique characteristics from a structure’s geometry rather than molecular composition.
Metamaterials are currently employed in various industries, serving practical purposes such as improving antenna performance in telecommunications and controlling sound waves for noise reduction or focusing in acoustic engineering. Recent advancements include creating the world’s first genuine “one-way glass,” showcasing metamaterials, versatility, and potential for innovative applications.
In 2006, two research papers published in Science demonstrated that metamaterials could be used to manipulate the propagation and transmission of specified light frequencies and electromagnetic radiation to render an object invisible.
Recent publications from Sandia National Laboratories, the U.S. Naval Institute, and Northrop Grumman have discussed the military potential of metamaterials, suggesting the possibility of creating real-life versions of the fictional “Klingon Cloaking Device” or “Harry Potter Invisibility Cloak.” However, despite ongoing research efforts, practical metamaterial cloaking technology has yet to be publicly demonstrated thus far.
This most significant challenge in developing novel metamaterials stems from solving the so-called “inverse problem” or calculating the specific geometry needed to produce desired properties.
“Even when inverse problems were solved in the past, they have been limited by the simplifying assumption that small-scale geometry can be made from an infinite number of building blocks,” lead author Dr. Helda Pahlavani explained. “The problem with that assumption is that metamaterials are usually made by 3D printing and real 3D printers have a limited resolution, which limits the number of building blocks that fit within a given device.”
Enter Deep-DRAM: an AI-driven modular framework combining deep learning models, generative models, and finite element simulations to address these challenges head-on.
Researchers say Deep-DRAM stands out by tackling the inverse design problem from a new angle, enabling the creation of materials with tailored properties such as double auxeticity (materials that expand in two directions when stretched) and high stiffness.
Dr. Pahlavani underscored the importance of Deep-DRAM being able to overcome previous constraints, stating, “We can now simply ask: how many building blocks does your manufacturing technique allow you to accommodate in your device? The model then finds the geometry that gives you your desired properties for the number of building blocks that you can actually manufacture.”
In a paper published in the journal Advanced Materials, researchers detailed how the application of Deep-DRAM extends beyond theoretical advancements, showcasing real-world implications through extensive simulations and 3D-printed specimens.
Researchers note that the framework’s ability to generate microarchitectures resistant to fatigue and fracture highlights Deep-DRAM’s potential to produce metamaterials that are not only innovative but also durable and reliable for practical applications.
This focus on durability differs from most existing metamaterial designs, which often fail after repeated use.
“So far, it has been only about what properties can be achieved,” Dr. Zadpoor described the current processes for developing metamaterials. “Our study considers durability and selects the most durable designs from a large pool of design candidates. This makes our designs really practical and not just theoretical adventures.”
Researchers say that one of the remarkable aspects of Deep-DRAM is its modular design, allowing for the integration of various computational models to solve complex design problems efficiently. This modular approach accelerates the design process and minimizes computational costs, making it an attractive option for a wide range of applications.
The implications of the innovative Deep-DRAM framework extend far beyond the laboratory, offering tangible solutions to real-world challenges. With the ability to tailor durable metamaterials to specific needs, industries ranging from healthcare to aerospace could benefit immensely from this recent marriage of Artificial intelligence and material science.
Assistant Professor Dr. Mohammad J. Mirzaali, who also served as a corresponding author of the study, says the potential of metamaterials is limitless. However, because their optimal design has historically relied on intuition and trial and error, the metamaterials’ full potential has never been truly realized.
Yet, researchers believe the AI-driven inverse design process of Deep-DRAM could revolutionize the development of metamaterials, opening avenues for applications such as orthopedic implants, surgical instruments, soft robots, adaptive mirrors, and exosuits.
“We think the step we have taken is revolutionary in the field of metamaterials,” said Dr. Mirzaali. “It could lead to all kinds of new applications.”
Tim McMillan is a retired law enforcement executive, investigative reporter and co-founder of The Debrief. His writing typically focuses on defense, national security, the Intelligence Community and topics related to psychology. You can follow Tim on Twitter: @LtTimMcMillan. Tim can be reached by email: tim@thedebrief.org or through encrypted email: LtTimMcMillan@protonmail.com