Skip to Main content Skip to Navigation
Conference papers

Neural Network Modeling of a Flexible Manipulator Robot

Abstract : This paper presents an artificial neural networks application for a flexible process modeling. A flexible planar single-link manipulator robot is considered. The dynamic behavior of this process is described using Lagrange equations and finite elements method. The artificial neural networks are all variations on the parallel distributed processing (PDP) idea. The architecture of each network is based on very similar building blocks which perform the processing. Therefore, two feed-forward and recurrent neural networks are developed and trained using back-propagation algorithm to identify the dynamics of the flexible process. Simulation results of the system responses are given and discussed in terms of level of error reduction. Finally, a conclusion encloses the paper.
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.inria.fr/hal-01551709
Contributor : Hal Ifip <>
Submitted on : Friday, June 30, 2017 - 2:43:04 PM
Last modification on : Saturday, July 1, 2017 - 1:06:46 AM
Long-term archiving on: : Monday, January 22, 2018 - 8:19:46 PM

File

978-3-642-33260-9_34_Chapter.p...
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Rahma Boucetta, Mohamed Abdelkrim. Neural Network Modeling of a Flexible Manipulator Robot. 11th International Conference on Computer Information Systems and Industrial Management (CISIM), Sep 2012, Venice, Italy. pp.395-404, ⟨10.1007/978-3-642-33260-9_34⟩. ⟨hal-01551709⟩

Share

Metrics

Record views

96

Files downloads

203