article · IEEE Access
Controlling a prosthetic leg can be achieved by combining surface electromyography signals, an artificial neural network, and super twisting sliding mode control. Muscle signals are gathered and preprocessed through filtering, rectification, linearisation, and mean average value feature extraction. A feed-forward neural network trained with the Levenberg-Marquardt back-propagation algorithm uses these processed signals alongside target joint data to predict joint angles for level walking, climbing stairs, and descending stairs. A super twisting sliding mode controller then regulates joint movement along these calculated reference trajectories. Simulation tests conducted in MATLAB and Simulink demonstrate that training the network with preprocessed muscle data improves regression performance and reduces trajectory tracking mean squared error compared to conventional sliding mode control. Parameter variation and disturbance analyses show the controller maintains robust performance despite internal parameter alterations and external environmental changes.
Individuals using lower limb prostheses require responsive, natural movement across diverse terrains such as level ground and stairs. By translating muscle electrical signals into accurate joint angles and applying a robust controller, this approach ensures reliable movement that can withstand unexpected environmental disruptions. This helps establish more stable, adaptive, and predictable control systems for assistive mobility devices.
This technology addresses the development of advanced robotic lower limb prostheses for amputees and mobility-impaired individuals. Because the validation was conducted entirely within MATLAB and Simulink simulations, the research is at an early computational stage. Commercial application will require hardware integration, embedded microcontrollers, and physical clinical testing on human users to confirm stability, real-time signal processing, and comfort under everyday operational conditions.
AI-generated from the published abstract. Always read the original work before citing.
This paper presents a method for controlling the prosthetic leg using surface Electromyography (sEMG) signals, Artificial Neural Network (ANN), and Super Twisting Sliding Mode Control (ST-SMC). The triggering signal is extracted from the user’s muscles and intense signal preprocessing that includes filtering, rectification, linearization, and Mean Average Value (MAV) feature extraction. The ANN predicts joint angles for walking, upstairs, and downstairs using the processed sEMG signals of the muscles and measured and filtered target joint angles. The neural network structure is built using Feed-forward Neural Network (FFNN) architecture and Levenberg-Marquardt (LM) back-propagation training algorithm for accuracy, fast convergence, and reliable optimization of nonlinear relationships. The ST-SMC controller regulates the motion of the prosthetic joints according to specified reference trajectories. MATLAB signal analyzers, neural network fitting packages, and Simulink are used to preprocess signals, train the FFNN for dynamic modeling of the system, and design controllers. The proposed ST-SMC is compared with conventional SMC. Simulation results show that training the neural network with processed data increases regression value and decreases trajectory tracking mean squared error (MSE). The controller’s robustness against internal parameter change and external environmental changes is demonstrated through parameter variation and disturbance analysis.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/access.2025.3538689
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
