Functional Electrical Stimulation System for Drop Foot Correction Using a Dynamic NARX Neural Network

Simão Carvalho,Cristina P Santos,Ana Correia,Joana Figueiredo,Jorge M Martins

doi:10.3390/machines9110253

Abstract

Neurological diseases may reduce Tibialis Anterior (TA) muscle recruitment capacity causing gait disorders, such as drop foot (DF). The majority of DF patients still retain excitable nerves and muscles which makes Functional Electrical Stimulation (FES) an adequate technique to restore lost mobility. Recent studies suggest the need for developing personalized and assist-as-needed control strategies for wearable FES in order to promote natural and functional movements while reducing the early onset of fatigue. This study contributes to a real-time implementation of a trajectory tracking FES control strategy for personalized DF correction. This strategy combines a feedforward Non-Linear Autoregressive Neural Network with Exogenous inputs (NARXNN) with a feedback PD controller. This control strategy advances with a user-specific TA muscle model achieved by the NARXNN’s ability to model dynamic systems relying on the foot angle and angular velocity as inputs. A closed-loop, fully wearable stimulation system was achieved using an ISTim stimulator and wearable inertial sensor for electrical stimulation and user’s kinematic gait sensing, respectively. Results showed that the NARXNN architecture with 2 hidden layers and 10 neurons provided the highest performance for modelling the kinematic behaviour of the TA muscle. The proposed trajectory tracking control revealed a low discrepancy between real and reference foot trajectories (goodness of fit = 77.87%) and time-effectiveness for correctly stimulating the TA muscle towards a natural gait and DF correction.

Highlights

Stroke is the leading cause of death and disability globally, often resulting in paralysis for stroke survivors
We presented an initial design of feedback and feedforward control strategy by combining a PD and a NARX neural network-integrated in an Functional Electrical Stimulation (FES) wearable system, for real-time Drop Foot (DF) correction during gait
This paper proposes a real-time trajectory tracking control strategy, based on a Neural Network with Exogenous inputs (NARXNN) combined with a PD, to control the foot angle trajectory using a newly designed wearable FES system for assist-as-needed DF correction

Summary

Introduction

Stroke is the leading cause of death and disability globally, often resulting in paralysis for stroke survivors. The pulse parameter modelling is relevant when considering different muscle types, and their non-linear and time-variant dynamics behaviour [2]. FES-based DF correction systems currently available in the market fail to take into consideration the time-variant dynamics of the electrically stimulated muscles [2], the onset of muscular fatigue, and any external disturbances [3]. This deprives the user of an assisted-as-needed experience, promoting the early onset of fatigue and failing to deliver optimal excitation patterns for the muscle’s nervous tissue, generating coarse movements [4]. FES rehabilitation treatment should be tailored using a personalized muscle model in order to capture the user-specific dynamics of the electrically stimulated muscle

Methods

Results

Conclusion