NARX-NN MODEL OF 2-DOF ROBOT ARM DYNAMICS DRIVEN BY FLUIDIC MUSCLES

Abstract

The article contains the results of identification of manipulator arm dynamics that is driven by pneumatic artificial muscles (specifically, fluidic muscles). The NARX architecture model - a multilayer perceptron network (MLP model) was selected for identification. Simulations were realized using MATLAB, especially with use the System Identification Toolbox. The simulation results were tracked at 3 different delays for the upper and lower axis of the manipulator separately. The NRMSE criterion (Normal Root Mean Square Error) serves to compare simulation results by comparing output of simulations and measured output data.

Recommended articles

ANALYSIS OF BAR FEEDING INTO THE DRAWING TOOL

Jan Rihacek, Kamil Podany, David Kabilka, Libor Mrna
Keywords: CK67 steel | buckling stability | bar drawing | numerical simulation | ANSYS

PREDICTING THE BEHAVIOR OF THE VEHICLE IN A FRONTAL COLLISION INTO RIGID BARRIER BY USING A SYSTEM IDENTIFICATION TOOLBOX

Jozef Kmec, Jozef Pavelka, Jaroslav Soltes
Keywords: Transfer function model. | Polynomial model | Process model with transfer function | state-space model | System Identification Toolbox | Matlab

METHODOLOGY FOR RISK ASSESSMENT OF NOISE EFFECTS AT WORKPLACE

Michaela Balazikova, Miriam Andrejiova, Barbora Wysoczanska
Keywords: workplace safety | non-auditory noise effects | risk | noise

PROGRAM FOR CALCULATION OF WORM GEARING SYSTEM

Slavko Pavlenko, Luba Bicejova
Keywords: worm gear | worm | program