Simulation of Control of a Scara Robot Actuated by Pneumatic Artificial Muscles Using RNAPM

This paper describes the simulation of movement control of a one-degree-of-freedom articulated robot arm SCARAactuated by a pair of McKibben pneumatic artificial muscles. The pneumatic artificial muscle is the actuator andemulates the behavior of biological muscles; due to its nonlinear behavior, th...

Descripción completa

Detalles Bibliográficos
Autores: Escobar, F., Díaz, S., Gutiérrez, C., Ledeneva, Y., Hernández, C., Rodríguez, D., Lemus, R.
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2014
País:México
Institución:UNIVERSIDAD NACIONAL AUTÓNOMA DE MÉXICO
Repositorio:Journal of Applied Research and Technology
Idioma:inglés
OAI Identifier:oai:ojs2.localhost:article/173
Acceso en línea:https://jart.icat.unam.mx/index.php/jart/article/view/173
Access Level:acceso abierto
Palabra clave:Control Systems
Artificial Neural Networks
Multilayer Perceptron
Pneumatic Artificial Muscle
Descripción
Sumario:This paper describes the simulation of movement control of a one-degree-of-freedom articulated robot arm SCARAactuated by a pair of McKibben pneumatic artificial muscles. The pneumatic artificial muscle is the actuator andemulates the behavior of biological muscles; due to its nonlinear behavior, there is also a need to develop controlsystems for robot arms using this type of actuator. Research begins with the transfer function that represents, inmathematical language, the movement of the robot arm’s joints; this allows using a PID controller on the transferfunction and generating data to train the Multilayer Perceptron Artificial Neural Network (RNAPM). So far, the PIDcontrol system has been able to control the movement of robot arms but, based on experimental tests, the RNAPMhas proved to outperform the PID control’s response time by up to 2.95 seconds, minimizing the angular error by 1.3°and avoiding the oscillation problem due to its continuous, constant behavior.