Title: A hybrid model for isomorphism identification in mechanism design based on intelligent manufacturing

Authors: Liao Ningbo, Yang Ping

Addresses: Laboratory of Advanced Design and Manufacturing, School of Mechanical Engineering, Jiangsu University, Zhenjiang, 212013, PR China. ' Laboratory of Advanced Design and Manufacturing, School of Mechanical Engineering, Jiangsu University, Zhenjiang, 212013, PR China

Abstract: Isomorphism discernment of graphs is an important and complicate problem. The problem is vital for graph theory based kinematic structures enumeration. To solve the problem, a Genetic Algorithm (GA) model and a Hopfield Neural Networks (HNNs) model are developed respectively, and some operators are improved to prevent premature convergence. By a comparative study, the advantages and limitations of the two approaches for graph isomorphism problem are discussed. Based on above, a hybrid Neural-Genetic algorithm is proposed. Numerical experiments demonstrate the performance of the hybrid algorithm is more successful compared with the approach applying GA or HNN simply.

Keywords: hybrid neural-genetic model; GAs; genetic algorithms; HNNs; Hopfield neural networks; graph isomorphism; kinematic structure enumeration; mechanism design; intelligent manufacturing.

DOI: 10.1504/IJMTM.2009.026384

International Journal of Manufacturing Technology and Management, 2009 Vol.18 No.3, pp.282 - 292

Published online: 09 Jun 2009 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article