Noise-suppressing zeroing neural network for online solving time-varying nonlinear optimization problem: a control-based approach

For the lower limb rehabilitation robot, how to better realize intention recognition is the key issue in the practical application. Recognition of the patient’s movement intention is a challenging research work, which needs to be studied from the shallow to the deep. Specifically, it is necessary to ensure that the movement intention of the normal person can be accurately recognized, and then improve the model to realize the recognition of the movement intention of the patients. Therefore, before studying the patient’s movement intention, it is essential to consider the normal person first, which is also for safety considerations. In recent years, a new Hill-based muscle model has been demonstrated to be capable of directly estimating the joint angle intention in an open-loop form. On this basis, by introducing a recurrent neural network (RNN), the whole prediction process can achieve more accuracy in a closed-loop form. However, for the traditional RNN algorithms, the activation function must be convex, which brings some limitations to the solution of practical problems. Especially, when the convergence speed of the traditional RNN model is limited in the practical applications, as the error continues to decrease, the convergence performance of the traditional RNN model will be greatly affected. To this end, a projected recurrent neural network (PRNN) model is proposed, which relaxes the condition of the convex function and can be used in the saturation constraint case. In addition, the corresponding theoretical proof is given, and the PRNN method with saturation constraint has been successfully applied in the experiment of intention recognition of lower limb movement compared with the traditional RNN model.

show abstract

“…Most robot control problems can be converted into the following time-varying nonlinear equations [31][32][33]:…”

Section: Problem Formulationmentioning

confidence: 99%

Lower limb movement intention recognition for rehabilitation robot aided with projected recurrent neural network

Liu

Peng

Shang

2021

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…A nonlinear vector equation called zero-finding problem as described in [23,25,32], the zero-finding problem is considered as an example…”

Section: Zeroing Neural Network Modelmentioning

confidence: 99%

“…The ZNN controller ( 24) can be deemed that provides a control framework for dealing with convergence and robustness issues of the discrete-time model . Moreover, closed-loop model ( 22) can improve the accuracy of motion intentions [23,32]. Then, a comparative experiment of open-loop model and closed-loop model is conducted to verity the effectiveness of the proposed closed-loop model.…”

Section: Discrete-time Closed-loop Estimationmentioning

confidence: 99%

A novel method based on long short term memory network and discrete-time zeroing neural algorithm for upper-limb continuous estimation using sEMG signals

Chai

Liu

et al. 2021

Biomedical Signal Processing and Control

Self Cite

View full text Add to dashboard Cite

“…For the future direction, the raw sEMG signals of anterior deltoid muscle, posterior deltoid muscle triceps muscle, biceps muscle, flexor carpi radialis and extensor carpi radialis will be collected from the spinal cord injury and stroke patients, then, the multiple joint angles of shoulder, elbow and wrist will be estimated by AFNN based on multi-channel sEMG signals. And then, based on the intention recognition of human, the human-robot interaction control algorithms based on neural network [22][23][24] will be designed to control the exoskeleton robot for assisting patients with rehabilitation training [21], so as to achieve the purpose of rehabilitation robot [25][26][27] to help the affected limb to perform rehabilitation training.…”

Section: B Model Comparisonmentioning

confidence: 99%

Intention Recognition of Elbow Joint based on sEMG Using Adaptive Fuzzy Neural Network

Liu

Teng

et al. 2020

2020 5th International Conference on Mechanical, Control and Computer Engineering (ICMCCE)

Self Cite

View full text Add to dashboard Cite

In this paper, the adaptive fuzzy neural network (AFNN) based on the surface electromyography (sEMG) for estimating the elbow joint angle is established and investigated from the perspective of rapidity and accuracy. In addition, back propagation neural network (BPNN) and artificial neural network of radial basis function (RBFNN), as the classical method for data forecasting, have been applied to estimate the elbow joint angle for comparing with AFNN. Ultimately, the experimental simulation and result analysis demonstrate that the rapidity and accuracy of AFNN is superior to BPNN and RBFNN.

show abstract

Noise-suppressing zeroing neural network for online solving time-varying nonlinear optimization problem: a control-based approach

Cited by 49 publications

References 39 publications

Lower limb movement intention recognition for rehabilitation robot aided with projected recurrent neural network

Lower limb movement intention recognition for rehabilitation robot aided with projected recurrent neural network

A novel method based on long short term memory network and discrete-time zeroing neural algorithm for upper-limb continuous estimation using sEMG signals

Intention Recognition of Elbow Joint based on sEMG Using Adaptive Fuzzy Neural Network

Contact Info

Product

Resources

About