ServoLNN: Lagrangian Neural Networks Driven by Servomechanisms
Not on the map. Why?
Abstract (arXiv)
Combining deep learning with classical physics facilitates the efficient creation of accurate dynamical models. In a recent class of neural network, Lagrangian mechanics is hard-coded into the architecture, and training the network learns the given system. However, the current architectures do not facilitate the modelling of dynamical systems that are driven by servomechanisms (e.g. servomotors, stepper motors, current sources, volumetric pumps). This article presents ServoLNN, a new architecture to model dynamical systems that are driven by servomechanisms. ServoLNN is compatible for use in real-time applications, where the driving motion is known only just-in-time. A PyTorch implementation of ServoLNN is provided. The derivations and results reveal the occurrence of a possible family of solutions that the training may converge on. The effect of the family of solutions on the predicted physical quantities is explored, as is the resolution to reduce the family of solutions to a single solution. Resultantly, the architecture can simultaneously accurately find the energies, power, rate of work, mass matrix, generalised accelerations, generalised forces, and the generalised forces that drive the servomechanisms.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 10 of its 23 references that are in the map. First posted on arXiv 27 Feb 2025.
Builds on
10 of 23 references.
References · 10
- 2019Hamiltonian Neural Networkscited by 702
- 2020Lagrangian Neural Networkscited by 388
- 2019Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learningcited by 205
- 2019Symplectic ODE-Net: Learning Hamiltonian Dynamics with Controlcited by 183
- 2020Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraintscited by 102
- 2020Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learningcited by 77
- 2019Deep Lagrangian Networks for end-to-end learning of energy-based control for under-actuated systemscited by 32
- 2021Constructing Neural Network-Based Models for Simulating Dynamical Systemscited by 29
- 2021Combining Physics and Deep Learning to learn Continuous-Time Dynamics Modelscited by 20
- 2022A Review of Machine Learning Methods Applied to Structural Dynamics and Vibroacousticcited by 7
Built on by
Not cited yet.