We (Matteo Friedrich and Alexander Reimer) participated in Jugend forscht 2024 (a German youth science competition). For our project, we needed a library capable of simulating, optimizing and visualizing Mechanical Neural Networks (MNNs). Since we couldn't find one, we decided to develop and publish our own: MNN.jl. The source code is available in our GitHub repository.
While this repository is hosted on the profile of Alexander Reimer (alexander.reimer2357@gmail.com), Matteo Friedrich (matteo.r.friedrich@gmail.com) has equally contributed to this project.
Mechanical Neural Networks (MNNs for short) are networks made of mass points connected by springs with variable spring constants. With a large enough network, a MNN can be trained to exhibit almost any behaviour desired by setting the spring constants appropiately. Importantly, they can be trained with multiple behaviours at once to exhibit different reactions depending on the "inputs" (forces acting on them). This makes them potentially useful for airplane wings which adjust theirs shape depending on the force and angle of the wind, body armor absorbing shock, better seat cushions or better wind turbine blades. Besides these examples of shape morphing behaviours, adjusting the resonance curves of MNNs is also possible and opens the door for applications like earthquake safe buildings, better music instruments, objects like walls capable of strengthening or weakening acoustic signals at will.
We based our research and knowledge of MNNs on the 2022 paper "Mechanical neural networks: Architected materials that learn behaviors" by Ryan H. Lee, Erwin A. B. Mulder and Jonathan B. Hopkins. They are, as far as we are aware, the first to describe such Mechanical Neural Networks. Ntwork.
- Simulation of MNNs
- Evaluating the performance of MNNs for shape morphing and resonance behaviour with MSE
- Optimizing the spring constants with Partial Pattern Search or an evolutionary algorithm
For detailed papers (only in German), see the paper branch on GitHub. The most recent one available is from our participation on the national level: paper.pdf
