A multi-resolution physics-informed recurrent neural network: formulation and application to musculoskeletal systems

• Published in: Computational mechanics Vol. 73; no. 5; pp. 1125 - 1145
• Main Authors: Taneja, Karan, He, Xiaolong, He, QiZhi, Chen, Jiun-Shyan
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.05.2024; Springer Nature B.V
• Subjects: Classical and Continuum Physics; Computational Science and Engineering; Elbow (anatomy); Electromyography; Engineering; Joints (anatomy); Kinematics; Mathematical models; Muscles; Muscular function; Neural networks; Original Paper; Parameter identification; Physics; Prediction models; Recurrent neural networks; Theoretical and Applied Mechanics; Wavelet transforms; Musculoskeletal system; Gated recurrent unit; Fast wavelet transform; Multi-resolution recurrent neural network; Physics-informed parameter identification
• ISSN: 0178-7675; 1432-0924
• DOI: 10.1007/s00466-023-02403-x

This work presents a multi-resolution physics-informed recurrent neural network (MR PI-RNN), for simultaneous prediction of musculoskeletal (MSK) motion and parameter identification of the MSK systems. The MSK application was selected as the model problem due to its challenging nature in mapping the high-frequency surface electromyography (sEMG) signals to the low-frequency body joint motion controlled by the MSK and muscle contraction dynamics. The proposed method utilizes the fast wavelet transform to decompose the mixed frequency input sEMG and output joint motion signals into nested multi-resolution signals. The prediction model is subsequently trained on coarser-scale input–output signals using a gated recurrent unit (GRU), and then the trained parameters are transferred to the next level of training with finer-scale signals. These training processes are repeated recursively under a transfer-learning fashion until the full-scale training (i.e., with unfiltered signals) is achieved, while satisfying the underlying dynamic equilibrium. Numerical examples on recorded subject data demonstrate the effectiveness of the proposed framework in generating a physics-informed forward-dynamics surrogate, which yields higher accuracy in motion predictions of elbow flexion–extension of an MSK system compared to the case with single-scale training. The framework is also capable of identifying muscle parameters that are physiologically consistent with the subject’s kinematics data.