Nonlinear model predictive control of functional electrical stimulation

Kirsch, Nicholas; Alibeji, Naji; Sharma, Nitin

doi:10.1016/j.conengprac.2016.03.005

Cited by 79 publications

(43 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The H model based on the neural network is a ''black box'' model suitable for complex and time-varying nonlinear systems [18]- [20]. The model combines the advantages of the Hammerstein and neural networks and embodies the characteristics of static nonlinearity and dynamic linearity of the system.…”

Section: B Discussion and Analysis Of The H Modelmentioning

confidence: 99%

See 1 more Smart Citation

Estimating the Ankle Angle Induced by FES via the Neural Network-Based Hammerstein Model

et al. 2019

View full text Add to dashboard Cite

Functional electrical stimulation (FES) has been widely used in limb rehabilitation. The first step for the precision rehabilition is to clarify the variation of limb angle induced by FES. In this study, an electric stimulator and an inertial sensor are used to build a human body experimental platform. Motion characteristics of ankle angle induced by electrical stimulation pulse variation are obtained through experiment. The obtained ankle angle characteristics are used to train a neural network-based Hammerstein (H) model and the model parameters are identified by the genetic algorithm, which can effectively predict the ankle angle change induced by electrical stimulation. The structural parameters of the H model are adjusted according to the normalized root mean square error value (NRMSE) of the training data. The 10-fold cross-validation is used to verify the feasibility and effectiveness of the model. Experimental results show that the neural network-based H model can effectively predict the output change of the ankle angle induced by the electrical stimulation pulse, and its root mean square error (RMSE) and NRMSE are 2.78 ± 0.33 • and 23.70 ± 1.77%, respectively. Therefore, the proposed model can provide a theoretical basis for predicting ankle angle change in an electrical stimulation closed-loop control system.INDEX TERMS Functional electrical stimulation, ankle angle, Hammerstein model, neural network, genetic algorithm.

show abstract

Section: B Discussion and Analysis Of The H Modelmentioning

confidence: 99%

“…The ankle angle model induced by the FES is a complex system with many unknown variables, and its nonlinearity and time-variability complicate its quantification in the model [18]- [20]. In this study, the relationship between electrical stimulation parameters and ankle angle is established by using the ''black box'' nonlinear model [21].…”

Section: Introductionmentioning

confidence: 99%

Estimating the Ankle Angle Induced by FES via the Neural Network-Based Hammerstein Model

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Where f is Hyperbolic tangent function, x is input of the controller, and the ℎ and k are the bias weighting values of the output layer and hidden layer respectively [13]. In addition, the x as the controller input is as follows:…”

Section: -1-2 Adaptive Pid Controllermentioning

confidence: 99%

“…Some of the reported works are focused on rehabilitation of the lower limbs [4][5][6][7][8][9]. Different categories of the adaptive and nonadaptive control strategies have been utilized for position control or torque control in the exoskeletons [4]- [10][11][12][13][14][15]. The servo-motors are usually are uses as the main actuators of such robots [16]- [17].…”

Section: Introductionmentioning

confidence: 99%

A Hybrid-FES Based Control System for Knee Joint Movement Control

Rastegar

Kobravi

2021

BCN

View full text Add to dashboard Cite

In this paper, a new control algorithm has been proposed which was designed based on a combination of functional electrical stimulation (FES) and an active mechanical actuator to control the knee joint movement. An adaptive controller and a PD controller have adjusted the motor torque and stimulation intensity, respectively. The FES controller was activated whenever a disturbance observer detected the presence of the external disturbance. In this manner, the occurrence of the muscle fatigue arises from the FES can be postponed. The simulation studies were carried out on a model of muscle-joint system along with a model of a servo-motor. The achieved results prove the ability of the proposed control strategy to not only reject the external disturbance but also compensate the muscle fatigue. In this research, the trajectories envisioned as the knee joint reference trajectory were designed using the recorded human data.

show abstract

“…Therefore, to limit the control performance, the unknown system parameter needs to be estimated and the estimated parameter needs to be considered in the control algorithms. One way to handle such problems is to develop an adaptive MPC which can achieve the specified control objectives by compensating the modeling error due to parametric uncertainties 12‐14 . Nowadays, many research works have been focused on this concern 13,15,16 .…”

Section: Introductionmentioning

confidence: 99%

Adaptive model predictive control design using multiple model second level adaptation for parameter estimation of two‐degree freedom of helicopter model

Dutta

Das

2021

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

This paper proposed an adaptive nonlinear model predictive control approach for a 2‐DoF helicopter model with both parametric uncertainties and input–output constraints. In the proposed control technique, the nonlinear helicopter model is linearized along the prediction horizon using a state and parameter‐dependent state‐space model. Furthermore, a linear quadratic objective function with constraints is carried out using the developed linearized model. Here, the multiple estimation model and the concept of second‐level adaptation are used to handle the parametric uncertainty of the nonlinear system. To ensure the boundedness of the estimated parameter within a predefined compact region, a projection based adaptive law is used. The adaptive tuning laws for the unknown parameters are derived by Lyapunov stability analysis. An ensemble Kalman filter has been used to observe the unavailable states of the 2‐DoF helicopter model. The effectiveness of the proposed control algorithm has been verified successfully in simulation as well as real‐time experimental setup of 2‐DoF of helicopter model and results are documented in tabular form to show superiority with an existing approach.

show abstract

Nonlinear model predictive control of functional electrical stimulation

Cited by 79 publications

References 45 publications

Estimating the Ankle Angle Induced by FES via the Neural Network-Based Hammerstein Model

Estimating the Ankle Angle Induced by FES via the Neural Network-Based Hammerstein Model

A Hybrid-FES Based Control System for Knee Joint Movement Control

Adaptive model predictive control design using multiple model second level adaptation for parameter estimation of two‐degree freedom of helicopter model

Contact Info

Product

Resources

About