Learning an inverse thermodynamic model for Pneumatic Artificial Muscles control

G. Wang, R. Chalard, J. Cifuentes, M.T. Pham

Mechatronics Vol. 110, pp. 103359

Summary:

Pneumatic Artificial Muscles (PAMs) are highly nonlinear actuators widely used in robotics, rehabilitation, and other dynamic applications. Their complex behavior poses significant challenges for traditional system identification methods. Although machine learning techniques have shown remarkable success in modeling nonlinear systems, their black-box nature often leads to interpretability issues and susceptibility to overfitting. This study proposes a novel hybrid modeling approach that combines the strengths of analytical models with neural networks to capture the inverse thermodynamic behavior of PAMs. The results demonstrate that the hybrid model outperformed both analytical and purely neural network models. The obtained models were further used for model-based control design and the results show that the application of hybrid model improved the tracking performance.

Spanish layman's summary:

Este estudio propone un modelo híbrido que combina ecuaciones analíticas y redes neuronales para representar el comportamiento inverso de los músculos artificiales neumáticos. Los resultados muestran mayor precisión y mejor desempeño en el control frente a modelos individuales.

English layman's summary:

This study presents a hybrid modeling approach that integrates analytical equations with neural networks to characterize the inverse behavior of pneumatic artificial muscles. The hybrid model outperforms standalone methods and enhances tracking performance in control applications.

Keywords: Neural networks; Hybrid modeling; Pneumatic Artificial Muscles; Model-based control

JCR-JIF Impact Factor and WoS quartile: 3,200 - Q2 (2025)

DOI reference: https://doi.org/10.1016/j.mechatronics.2025.103359

Published on paper: October 2025.

Published on-line: June 2025.

Citation:
G. Wang, R. Chalard, J. Cifuentes, M.T. Pham, "Learning an inverse thermodynamic model for Pneumatic Artificial Muscles control", Mechatronics, Vol. 110, pp. 103359, October 2025. [Online: June 2025] doi: 10.1016/j.mechatronics.2025.103359