Journal cover Journal topic
Mechanical Sciences An open-access journal for theoretical and applied mechanics
Journal topic

Journal metrics

IF value: 1.015
IF1.015
IF 5-year value: 1.403
IF 5-year
1.403
CiteScore value: 1.9
CiteScore
1.9
SNIP value: 0.588
SNIP0.588
IPP value: 0.94
IPP0.94
SJR value: 0.271
SJR0.271
Scimago H <br class='widget-line-break'>index value: 20
Scimago H
index
20
h5-index value: 13
h5-index13
Supported by
Logo Library of Delft University of Technology Logo NWO
Affiliated to
Logo iftomm
Volume 6, issue 1
Mech. Sci., 6, 29–34, 2015
https://doi.org/10.5194/ms-6-29-2015
© Author(s) 2015. This work is distributed under
the Creative Commons Attribution 3.0 License.
Mech. Sci., 6, 29–34, 2015
https://doi.org/10.5194/ms-6-29-2015
© Author(s) 2015. This work is distributed under
the Creative Commons Attribution 3.0 License.

Research article 01 Apr 2015

Research article | 01 Apr 2015

Dimensional synthesis of mechanical linkages using artificial neural networks and Fourier descriptors

N. Khan1, I. Ullah2, and M. Al-Grafi2 N. Khan et al.
  • 1University of Engineering and Technology Peshawar, Pakistan
  • 2College of Engineering, Taibah University, Yanbu, Saudi Arabia

Abstract. Dimensional synthesis of mechanisms to trace given paths is an important problem with no exact solution. In this paper, the problem is divided into representation of curve shape and learning the relation between curve shape and mechanism dimensions. Curve shape is represented by Fourier descriptors of cumulative angular deviation of the curve, which do not depend on the position or scale of the curve. An artificial neural network (ANN) is trained to learn the (unknown) relation between the Fourier descriptors of a planar curve and the dimensions of the mechanism tracing that curve. Presented with any simple, closed, planar curve, the ANN suggests the dimensions of a four-bar whose coupler curve is similar in shape. A local optimization procedure further refines the results. Examples presented indicate the method is successful as long as the curve shape is such that the mechanism is able to trace it.

Publications Copernicus
Download
Short summary
The problem of dimensional synthesis of mechanisms to trace a given closed curve is solved by (a) representation of curve shape using normalized Fourier descriptors and (b) learning the relation between Fourier descriptors and mechanism dimensions by an artificial neural network (ANN). The ANN developed suggests dimensions of a four-bar mechanism with coupler curve of shape similar to the one desired. The dimensions are further refined by optimization.
The problem of dimensional synthesis of mechanisms to trace a given closed curve is solved by...
Citation