A FeatureEncoded PhysicsInformed Parameter Identification Neural Network for Musculoskeletal Systems

Abstract

Identification of muscletendon force generation properties and muscle activities from physiological measurements, e.g., motion data and raw surface electromyography (sEMG), offers opportunities to construct a subjectspecific musculoskeletal (MSK) digital twin system for health condition assessment and motion prediction. While machine learning approaches with capabilities in extracting complex features and patterns from a large amount of data have been applied to motion prediction given sEMG signals, the learned datadriven mapping is blackbox and may not satisfy the underlying physics and has reduced generality. In this work, we propose a featureencoded physicsinformed parameter identification neural network (FEPIPINN) for simultaneous prediction of motion and parameter identification of human MSK systems. In this approach, features of highdimensional noisy sEMG signals are projected onto a lowdimensional noisefiltered embedding space for the enhancement of forwarding dynamics prediction. This FEPIPINN model can be trained to relate sEMG signals to joint motion and simultaneously identify key MSK parameters. The numerical examples demonstrate that the proposed framework can effectively identify subjectspecific muscle parameters and the trained physicsinformed forwarddynamics surrogate yields accurate motion predictions of elbow flexionextension motion that are in good agreement with the measured joint motion data.