Created by mechanical engineers at the University of California - Los Angeles (UCLA), the material is composed of a structural system made of ‘tuneable beams’ that can alter its shape and behaviours in response to dynamic conditions.
The materials could have applications in construction, aerospace and imaging technologies, amongst others.
“This research introduces and demonstrates an artificial intelligent material that can learn to exhibit the desired behaviours and properties upon increased exposure to ambient conditions,” said mechanical and aerospace engineer Professor Jonathan Hopkins, who led the research. “The same foundational principles that are used in machine learning are used to give this material its smart and adaptive properties.”
Used in aircraft wings, for example, the material “could learn to morph the shape of the wings based on the wind patterns during a flight to achieve greater efficiency and manoeuvrability of the plane,” the researchers claimed.
Building structures ‘infused’ with the material could self-adjust their rigidity in certain areas to improve overall stability during an earthquake or other disasters, they added.
The team developed the mechanical equivalent of artificial neural networks (ANNs), the algorithms that drive machine learning, to create the material.
The mechanical neural network (MNN), as they call it, consists of individually tuneable beams arranged in a triangular lattice pattern. Each beam features a voice coil, strain gauges and flexures that enable the beam to change its length, adapt to its changing environment in real time, and interact with other beams in the system.
The voice coil, which gets its name from its original use in speakers, initiates the fine-tuned compression or expansion in response to new forces placed on the beam. The strain gauge is responsible for collecting data from the beam’s motion, which is used in the algorithm to control the learning behaviour. The flexures essentially act as flexible joints amongst the moveable beams that connect the system.
An optimisation algorithm then regulates the entire system, taking the data from each of the strain gauges and determining a combination of rigidity values to control how the network should adapt to applied forces.
The researchers also used cameras trained on the ‘output nodes’ of the system to check the validity of the strain gauge-monitored system.
The system is currently about the size of a microwave oven, but the researchers plan to simplify the MNN design so that thousands of the networks can be manufactured on the micro-scale, within 3D lattices for practical material applications.
Apart from using the material in vehicles and construction, the researchers also suggested MNNs could be incorporated into armour to deflect shockwaves, or in acoustic imaging technologies to harness sound waves.
The work was published in Science Robotics.
Navigate a turbulent future by attending Aerospace & Defence (28 November – 2 December). Register for FREE today.
Content published by Professional Engineering does not necessarily represent the views of the Institution of Mechanical Engineers.