Assisted Research and Optimization of the Proper Neural Network Solving the Inverse Kinematics Problem

Adrian Olaru; Serban Olaru; Dan Paune; Oprean Aurel

doi:10.4028/www.scientific.net/AMR.463-464.827

Paper Titles

TiO₂ Nanowires/Nanobelts Originating from Anodically Grown Nanotube Arrays
p.802

A Theoretical Framework for Healthcare Innovation Management Using Wiki Based Digital Ecosystem
p.811

An Application of Finite Element Modeling to Pneumatic Artificial Muscle from FESTO
p.818

Application of Lignin from Oil Palm Biomass as a Fluid Lost Reducer
p.822

Assisted Research and Optimization of the Proper Neural Network Solving the Inverse Kinematics Problem
p.827

Bioconjugates Containing Ferritin and Metal Nanoparticles
p.833

Effect of HF Concentration on Corrosion Resistance of Biomedical Implants
p.837

Effect of Zr Addition on Mechanical Properties of Ti-Nb-Zr Alloys for Biomedical Applications
p.841

Effects of Different Neutralizing Agents on D-(-)-Lactic Acid Fermentation by Escherichia coli W
p.845

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 463-464Assisted Research and Optimization of the Proper...

Assisted Research and Optimization of the Proper Neural Network Solving the Inverse Kinematics Problem

Abstract:

Finding the better solution of the neural network design to solve the inverse kinematics problem with the minimum of the trajectory errors is very difficult, because there are many variable parameters and many redundant solutions. The presented paper show the assisted research of the influences of some more important parameters to the final end-effector trajectory errors of the proposed neural network model solving the inverse kinematics problem. We were been studied the number of neurons in each layers, the sensitive function for the first and second layer, the magnifier coefficient of the trajectory error, the variable step of the time delay and the position of this block, the different cases of target data and the case when the hidden target data were adjusted. All obtained results were been verified by applying the proper direct kinematics virtual LabVIEW instrumentation. Finally we were obtained one optimal Sigmoid Bipolar Hyperbolic Tangent Neural Network with Time Delay and Recurrent Links (SBHTNN(TDRL)) type, what can be used to solve the inverse kinematics problem with maximum 4% of trajectory errors.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 463-464)

Pages:

827-832

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.463-464.827

Citation:

Cite this paper

Online since:

February 2012

Authors:

Adrian Olaru, Serban Olaru, Dan Paune, Oprean Aurel

Keywords:

Assisted Research, Labview Instrumentation, Neural Network (NN), Neuron

Export:

RIS, BibTeX

Price:

Permissions:

Request Permissions

References

[1] P.J. Alsina, N.S. Gehlot, Direct and inverse kinematics of robot manipulator based on modular neural networks, ICARCV, IEEE, pp.1743-7, 3, (1994).

Google Scholar

[2] R. Manseur, D. Keith, A fast algorithm for reverse kinematics analysis of robot manipulator, International Journal of Robotics Research, 7 (3), 1998, pp.622-648.

Google Scholar

[3] D. Gorinevsky,T. Connoly, Comparations of some neural network and scattered data approximations: The inverse manipulator kinematics example, Neural computation, 3 (6), pp.521-542.

Google Scholar

[4] L. Lee, Training feedforward neural networks: An algorithm givin improved generalization, Neural Networks, 10 (1), pp.61-68, (1997).

DOI: 10.1016/s0893-6080(96)00071-8

Google Scholar

[5] C. Schittenkopf, G. Deco and W. Brauner, Two strategies to avoid overfitting in feedforward networks, Neural Networks, 10 (3), pp.505-516, (1997).

DOI: 10.1016/s0893-6080(96)00086-x

Google Scholar

[6] Olaru, A., Olaru S., Ciupitu, L. Assisted research of the neural network by bach propagation algorithm, OPTIROB 2010 International Conference, Calimanesti, Romania, The RPS Singapore Book, pp.194-200 , (2010).

Google Scholar

[7] Olaru, A., Olaru, S., Paune D., Ghionea A. Assisted research of the neural network, OPTIROB 2010 International Conference, Calimanesti, Romania, The Research Publishing Services Singapore Book, pp.189-194 , (2010).

DOI: 10.4028/www.scientific.net/amr.463-464.1098

Google Scholar

[8] Olaru, A., Olaru, S. Assisted research of the neural network with LabVIEW instrumentation, IEEE ICMENS-2010 Proceedings, Changsha, China, pp.1-8, (2010).

Google Scholar

[9] Olaru, A., Oprean, A., Olaru, S., Paune, D. Optimization of the neural network by using the LabVIEW instrumentation, IEEE ICMERA 2010 Proceedings, ISBN 978-1-4244-8867-4, IEEE catalog number CFP1057L-ART, pp.40-44, (2010).

DOI: 10.4028/www.scientific.net/amr.463-464.1011

Google Scholar

[10] J. J. Hopfield, Neural networks and physical systems with emergent collective computational abilities, Proc. of the National Academy of Sciences, 81, 1984, pp.3088-3092.

Google Scholar

[11] Hajduk, M., Semjon, J., Vagaš, M.: Design of the Welding Fixture for the Robotic Station for Spot Weldind Based on the Modular Concept. In: Acta Mechanica Slovaca No. 3/2009, volume 13, pp.30-35, ISSN 1335-2393.

DOI: 10.2478/v10147-010-0044-y

Google Scholar

[12] Hajduk, M., Sukop, M., Baláž, V., Semjon, J., Vagaš, M.: Improving the performance of manufacturing systems based reconfiguring and computer integration. Košice, (2006).

Google Scholar

[13] Páchniková L., Šalátová, M.: Ciele a efekty pružných výrob. In: Acta Mechanica Slovaca, roč. 12, č. 2-A, 2008, pp.451-454, ISSN 1335-2393.

Google Scholar