Online Incremental Dynamic Modeling Using Physics-Informed Long Short-Term Memory Networks for the Pneumatic Artificial Muscle
Shuopeng Wang, Rixin Wang, Junjie Yang, Lina Hao
Abstract
The pneumatic artificial muscle (PAM) is widely applied in various scenarios due to their compliance and high-efficiency characteristics. However, the online modeling method which can accommodate online data remains an unresolved issue when data cannot be obtained off-line. This letter proposes an online incremental modeling method based on the physics-informed LSTM (PI-LSTM) architecture. The modified three-element model is regarded as the physics knowledge, and integrated into the PI-LSTM architecture, enabling the representation of physical constraints through neural networks. Subsequently, the elastic weight consolidation (EWC) method is utilized to combine the online operational data with the offline PI-LSTM model, allowing the model to be updated using the online data. Finally, online dynamic modeling experiments conducted on PAMs under different loads and driving conditions demonstrate the precision of the proposed method. Additionally, the experiments confirm that the proposed method effectively mitigates the catastrophic forgetting problem that can arise from online mini-batch data.
BibTeX
@inproceedings{ral2024_onlineincrementa,
title = {Online Incremental Dynamic Modeling Using Physics-Informed Long Short-Term Memory Networks for the Pneumatic Artificial Muscle},
author = {Shuopeng Wang and Rixin Wang and Junjie Yang and Lina Hao},
booktitle = {RA-L 2024},
year = {2024}
}