Please use this identifier to cite or link to this item: http://repositorio.cualtos.udg.mx:8080/jspui/handle/123456789/547
Title: Recurrent neural identification on Xilinx system generator using V7 FPGA for a 2DOF robot manipulator
Other Titles: IEEE World Congrees on Computational Intelligence 2016 (IEEE WCCI 2016)
Authors: Davalos Guzmán, Ulises
Esquivel, Pedro
Jurado Zamarripa, Francisco
Morfín Garduño, Onofre Amador
Castañeda Hernández, Carlos Eduardo
Keywords: Virtex 7 FPGA
extended KF algorithm
two degrees of freedom robot manipulator
Issue Date: 24-Jul-2016
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Citation: Davalos Guzmán, U., Castañeda Hernández, C., Esquivel, P., Jurado Zamarripa, F. and Morfín Garduño, O. (2016). Recurrent neural identification on Xilinx system generator using V7 FPGA for a 2DOF robot manipulator. In: 2016 IEEE World Congress on Computational Intelligence. Vancouver, Canadá: Institute of Electrical and Electronics Engineers (IEEE), pp.2359-2365.
Abstract: This paper describes an identification process for a class of discrete-time nonlinear systems, which includes the Xilinx system generator software and the process is implemented in a Virtex 7 (V7) field programmable gate array (FPGA). This procedure consists of programming a discrete-time nonlinear plant where the dynamics of this plant is reproduced by a discrete-time recurrent high order neural network (RHONN). The neural network is trained on-line with the extended Kalman filter algorithm where the associated state and measurement noises covariance matrices are composed by the coupled variance between the plant states. Additionally, a sliding window-based method for dynamical modeling of nonstationary systems is presented in order to improve the neural identification process. This identification process is implemented on a Virtex 7 (V7) FPGA using Xilinx system generator software where are programed in this FPGA: the discrete-time dynamics of the two degrees of freedom (2DOF) robot manipulator, the RHONN, the extended Kalman filter (EKF) training algorithm and the sliding windowbased method. The obtained results from the FPGA are compared with the results obtained from Matlab/SImulink in order to validate the identification process for the present proposal.
Description: University Center of Los Lagos, University of Guadalajara, Lagos de Moreno, Jalisco México. Technological Institute of la Laguna, Torreón Coahuila, México. Autonomous University of Ciudad Juarez Chihuahua, México.
URI: http://repositorio.cualtos.udg.mx:8080/jspui/handle/123456789/547
ISBN: 978-1-5090-0620-5
Appears in Collections:3304 Capítulo de libro y/o memoria en extenso

Files in This Item:
File Description SizeFormat 
Recurrent neural identification on Xilinx system generator using V7.pdfArtículo1.08 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.