Accounts of using the Tustin-Net architecture on a rotary inverted pendulum
This work addresses system identification for control systems, but it is incremental as it adapts an existing architecture to a specific domain.
The authors tackled the problem of system identification for a rotary inverted pendulum using the Tustin-Net architecture, finding that with standard training, it underperformed compared to first-principles models, but a transfer learning strategy enabled competitive accuracy without extensive setup knowledge.
In this report we investigate the use of the Tustin neural network architecture (Tustin-Net) for the identification of a physical rotary inverse pendulum. This physics-based architecture is of particular interest as it builds on the known relationship between velocities and positions. We here aim at discussing the advantages, limitations and performance of Tustin-Nets compared to first-principles grey-box models on a real physical apparatus, showing how, with a standard training procedure, the former can hardly achieve the same accuracy as the latter. To address this limitation, we present a training strategy based on transfer learning that yields Tustin-Nets that are competitive with the first-principles model, without requiring extensive knowledge of the setup as the latter.