A team of researchers from the Harvard John A Paulson School of Engineering and Applied Sciences (SEAS) has developed a platform that uses machine learning to programme the transformation of 2D stretchable surfaces into specific 3D shapes.
Advertisement
Flat materials that can morph into 3D shapes have potential applications in areas as diverse as architecture, medicine and robotics; however, currently, programming these shape changes requires complex and time-consuming computations.
The researchers got around this difficulty by first dividing an inflatable membrane into a ten-by-ten grid of square pixels that can either be soft or stiff. They then used what’s known as finite-element simulations to sample this effectively infinite design space and ran the samples through neural networks, which learnt how the location of soft and stiff pixels controlled the deformation of the membrane when it’s pressurised.
Advertisement
‘Once the machine learning model was trained, we came up with an arbitrary 3D shape and passed it to the model,’ said Antonio Elia Forte, a former postdoctoral fellow at SEAS. ‘The neural network then outputs the membrane design and the pressure at which we should inflate the membrane to obtain the desired 3D shape.’
The researchers used the new design method to build and test a device for mechanotherapy that can stimulate tissue around a scar to enhance healing and reduce recovery time. ‘This platform has the potential to quickly and effectively design patient-specific devices for mechanotherapy and beyond,’ said Forte. ‘Before this research, we didn’t know how to use machine learning to unravel nonlinear mappings in inflatable systems, but it turns out that they are very powerful for these purposes.’
The platform can be used to design morphable surfaces at multiple scales for applications from medical devices to architecture.
According to Forte, the work is just the beginning of machine-learning-enabled design of transformable materials. ‘Machine learning could push the boundaries of currently known design strategies and allow us to design and build fully reconfigurable shape-morphing material,’ he said.
The research has been published in Advanced Functional Materials.
