Abstract
Detection of isomorphism among kinematic chains is essential in mechanical design, but difficult and computationally expensive. It has been shown that both traditional methods and previously presented neural networks still have a lot to be desired in aspects such as simplifying procedure of identification and adapting automatic computation. Therefore, a new algorithm based on a competitive Hopfield network is developed for automatic computation in the kinematic chain isomorphism problem. The neural approach provides directly interpretable solutions and does not demand tuning of parameters. We have tested the algorithm by solving problems reported in the recent mechanical literature. Simulation results show the effectiveness of the network that rapidly identifies isomorphic kinematic chains.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Tischler CR, Samuel AE and Hunt KH (1995). Kinematic chains for robot hands-I, orderly number-synthesis. Mechan Mach Theory 30: 1193–1215
Rao AC and Varada Raju D (1991). Application of the Hamming number technique to detect isomorphism among kinematic chains and inversions. Mechan Mach Theory 26: 55–75
Cubillo JP and Wan J (2005). Comments on mechanism kinematic chain isomorphism identification using adjacent matrices. Mechan Mach Theory 40: 131–139
Mruthyunjaya TS and Balasubramanian HR (1987). In quest of a reliable and efficient computational test for detection of isomorphism in kinematic chains. Mechan Mach Theory 22: 131–139
Hwang WM and Hwang YW (1992). Computer-aided structural synthesis of planar kinematic chains with simple joints. Mechan Mach Theory 27: 189–199
Chang Z, Zhang C, Yang Y and Wang Y (2002). A new method to mechanism kinematic chain isomorphism identification.. Mechan Mach Theory 37: 411–417
He PR, Zhang WJ and Li Q (2005). Some further development on the eigensystem approach for graph isomorphism detection. J Franklin Inst – Eng Appl Math 342: 657–673
Kong FG, Li Q and Zhang WJ (1999). An artificial neural network approach to mechanism kinematic chain isomorphism identification. Mechan Mach Theory 34: 271–283
Zhang WJ (2002). Letter to the editor. Mechan Mach Theory 37: 639–640
Wilson GV and Pawley D (1988). On the stability of the TSP algorithm of Hopfield and Tank. Biol Cybern 58: 63–70
Peng M, Gupta NK and Armitage AF (1996). An investigation into the improvement of local minima of the Hopfield network. Neural Networks 9: 1241–1253
Galán-Marín G, Mérida-Casermeiro E and Muñoz-Pérez J (2003). Modelling competitive Hopfield networks for the maximum clique problem. Comput Oper Res 30: 603–624
Galán-Marín G and Muñoz-Pérez J (2001). Design and analysis of maximum Hopfield networks. IEEE Trans Neural Networks 12: 329–339
Mérida-Casermeiro E, Galán-Marín G and Muñoz-Pérez J (2001). An efficient multivalued Hopfield network for the traveling salesman problem. Neural Process Letters 14: 203–216
Takefuji Y and Lee KC (1991). An artificial hysteresis binary neuron: a model suppressing the oscillatory behaviors of neural dynamics. Biol Cybern 64: 353–356
Wang JH and Tang Z (2004). An improved optimal competitive Hopfield network for bipartite subgraph problems. Neurocomputing 61: 413–419
Wang JH, Tang Z and Cao OP (2004). Stochastic competitive Hopfield network and its application to maximum clique problem. IEICE Trans Fundam Elect Commun Comput Sci E87A: 2790–2798
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Galan-Marin, G., Merida-Casermeiro, E. & Lopez-Rodriguez, D. Improving Neural Networks for Mechanism Kinematic Chain Isomorphism Identification. Neural Process Lett 26, 133–143 (2007). https://doi.org/10.1007/s11063-007-9047-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-007-9047-8