Abstract
Graph theory can be used efficiently for both kinematic and dynamics analysis of mechanical structures. One of the most important and difficult issues in graphs theory-based structures design is graphs isomorphism discernment. The problem is vital for graph theory-based kinematic structures enumeration, which is known to be nondeterministic polynomial-complete problem. To solve the problem, a Hopfield neural networks (HNN) model is presented and some operators are improved to prevent premature convergence. By comparing with genetic algorithm, the computation times of the HNN model shows less affection when the number of nodes were enhanced. It is concluded that the algorithm presented in this paper is efficient for large-scale graphs isomorphism problem.
Similar content being viewed by others
References
Tsai LW (2000) Mechanism design: enumeration of kinematic structures according to function. CRC Press, Boca Raton
Shah YJ, Davida GI, McCarthy MK (1974) Optimum features and graph isomorphism. IEEE Trans Syst Man Cybern 4(3):313–319
Tang C, Liu T (1988) The degree code—a new mechanism identifier. Trends Dev Mechanism Mach Robotics 1:147–151
Yang Z, Zhang M (2002) Judgement of the similarity of the links by link code and similar matrix method. J Beijing Univ Chem Technol 29(2):1–4
Yang P, Liao N, Yang B, Ding J, Yang J (2007) A mixed isomorphism approach for kinematic structure enumeration graphs based on intelligent design and manufacturing. Int J Adv Manuf Technol 31(9–10):841–845
Yang P, Pei Z, Liao N, Yang B (2007) Isomorphism identification for epicyclic gear mechanism based on mapping property and ant algorithm. Eng Comput 23(1):49–54
Kureichik VV, Kureichik VM (2002) Evolution simulation system for graphs isomorphism discernment. In: Proceedings of 2002 IEEE international conference on artificial intelligence systems, Moscow
Chau K (2007) Reliability and performance-based design by artificial neural network. Adv Eng Softw 38(3):145–149
Xie J, Cheng C, Chau K, Pei Y (2006) A hybrid adaptive time-delay neural network model for multi-step-ahead prediction of sunspot activity. Int J Environ Pollut 28(3–4):364–381
Muttil N, Chau KW (2006) Neural network and genetic programming for modelling coastal algal blooms. Int J Environ Pollut 28(3–4):223–238
Acknowledgments
The author would like to acknowledge the support of the National Science Foundation of China, Doctoral Candidate of JiangSu Province (No. CX07B_069z), the Natural Science Foundation of GuangXi province of China, the support program for Young and Middle-aged Disciplinary Leaders in Gangxi Higher Education Institution and Natural Science Foundation for Qualified Personnel of JiangSu University during the course of this work.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhang, M., Liao, N. & Zhou, C. A modified Hopfield neural networks model for graphs-based kinematic structure design. Engineering with Computers 26, 75–80 (2010). https://doi.org/10.1007/s00366-009-0153-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00366-009-0153-2