Diseño de prototipo de prótesis mioeléctrica con detección de fatiga muscular
Cargando...
Fecha
2025
Autores
Barreto Merlano, Francisco José
Palacio Pedraza, Daniela María
Zárate Rodríguez, Leonel Eduardo
Título de la revista
ISSN de la revista
Título del volumen
Editor
Ediciones Universidad Simón Bolívar
Facultad de Ingenierías
Facultad de Ingenierías
Resumen
Este artículo presenta el diseño y desarrollo de un prototipo de prótesis mioeléctrica de bajo costo con detección de fatiga muscular basada en el análisis de señales electromiográficas (EMG). El sistema integra una estructura mecánica impresa en 3D, un servomotor para la articulación de la mano y un módulo electrónico basado en el microcontrolador ESP32. Para el procesamiento de señales se emplearon registros EMG de la base de datos Ninapro y un sensor MyoWare en fase de validación. Las señales fueron filtradas y segmentadas para la extracción de métricas temporales (RMS, MAV, Varianza y Waveform Length), las cuales alimentaron un clasificador Linear Discriminant Analysis (LDA) encargado de diferenciar entre reposo y contracción. Se simuló la fatiga muscular modificando la amplitud y la frecuencia efectiva de la señal, observando un incremento promedio del 150–300 % en las métricas extraídas y una reducción en la precisión del clasificador (75 % sin fatiga → ≈60 % con fatiga). Los resultados evidencian que la fatiga altera el control mioeléctrico y genera fallos en el movimiento protésico, lo que confirma la necesidad de incorporar sistemas de monitoreo y adaptación en el control de prótesis. El prototipo constituye una base funcional para futuros desarrollos orientados a compensar la fatiga en tiempo real.
his article presents the design and development of a low-cost myoelectric prosthesis prototype with muscle fatigue detection based on the analysis of electromyographic (EMG) signals. The system integrates a 3D-printed mechanical structure, a servo motor for hand articulation, and an electronic module based on the ESP32 microcontroller. For signal processing, EMG recordings from the Ninapro database and a MyoWare sensor (in the validation phase) were used. The signals were filtered and segmented for the extraction of temporal metrics (RMS, MAV, Variance, and Waveform Length), which were then fed into a Linear Discriminant Analysis (LDA) classifier responsible for distinguishing between rest and contraction states. Muscle fatigue was simulated by modifying the signal’s amplitude and effective frequency, resulting in an average increase of 150–300% in the extracted metrics and a decrease in classifier accuracy (75% without fatigue → ≈60% with fatigue). The results show that fatigue alters myoelectric control and causes failures in prosthetic movement, confirming the need to incorporate monitoring and adaptive control systems in prostheses. The prototype provides a functional foundation for future developments aimed at compensating fatigue in real time.
his article presents the design and development of a low-cost myoelectric prosthesis prototype with muscle fatigue detection based on the analysis of electromyographic (EMG) signals. The system integrates a 3D-printed mechanical structure, a servo motor for hand articulation, and an electronic module based on the ESP32 microcontroller. For signal processing, EMG recordings from the Ninapro database and a MyoWare sensor (in the validation phase) were used. The signals were filtered and segmented for the extraction of temporal metrics (RMS, MAV, Variance, and Waveform Length), which were then fed into a Linear Discriminant Analysis (LDA) classifier responsible for distinguishing between rest and contraction states. Muscle fatigue was simulated by modifying the signal’s amplitude and effective frequency, resulting in an average increase of 150–300% in the extracted metrics and a decrease in classifier accuracy (75% without fatigue → ≈60% with fatigue). The results show that fatigue alters myoelectric control and causes failures in prosthetic movement, confirming the need to incorporate monitoring and adaptive control systems in prostheses. The prototype provides a functional foundation for future developments aimed at compensating fatigue in real time.
Descripción
Palabras clave
Prótesis mioeléctrica, Señal EMG, Fatiga muscular, Microcontrolador, Servomotor
