Improving neural networks for mechanism kinematic chain isomorphism identification

 

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.

Citation

Please, cite this work as:

[GML07] G. Galan-Marin, E. Merida-Casermeiro, and D. Lopez-Rodriguez. “Improving neural networks for mechanism kinematic chain isomorphism identification”. In: Neural processing letters 26.2 (2007), pp. 133-143.

NoteBibTeX

@article{galan2007improving,
     title={Improving neural networks for mechanism kinematic chain isomorphism identification},
     author={Galan-Marin, Gloria and Merida-Casermeiro, Enrique and Lopez-Rodriguez, Domingo},
     journal={Neural processing letters},
     volume={26},
     number={2},
     pages={133–143},
     year={2007},
     publisher={Springer}
}

Bibliometric data

The following data has been extracted from resources such as OpenAlex, Dimensions, PlumX or Altmetric.

Improving neural networks for mechanism kinematic chain isomorphism identification

Cites

The following graph plots the number of cites received by this work from its publication, on a yearly basis.

Papers citing this work

The following is a non-exhaustive list of papers that cite this work:

1. Luchuan Yu, Shunqing Zhou, Hongbin Wang (2024). Mechanism Isomorphism Identification Based on Decision Tree Algorithm and Hybrid Particle Swarm Optimization Algorithm. Neural Processing Letters DOI
2. Kunal Dewangan, Purushottam Prajapati (2024). Detection of Isomorphism and Inversions of Kinematic Chains Using an Evolutionary Approach. Lecture notes in mechanical engineering DOI
3. Hongbin Wang, An Long, Luchuan Yu, et al. (2023). An efficient approach of graph isomorphism identification using loop theory and hopfield neural networks. Multimedia Tools and Applications DOI
4. Wenjian Yang, Huafeng Ding, Andrés Kecskeméthy (2022). Structural synthesis towards intelligent design of plane mechanisms: Current status and future research trend. Mechanism and Machine Theory DOI
5. Kaijie Dong, Duanling Li, Xianwen Kong (2022). Representation of planar kinematic chains with multiple joints based on a modified graph and isomorphism identification. Mechanism and Machine Theory DOI
6. A. Geigel (2022). Machine learning AI systems and the virtue of inventiveness. AI and Ethics DOI
7. Luchuan Yu, Hongbin Wang, Shunqing Zhou (2022). Graph isomorphism identification based on link-assortment adjacency matrix. Sadhana DOI
8. Huijun Yi, Jianpei Wang, Yongle Hu, et al. (2021). Mechanism isomorphism identification based on artificial fish swarm algorithm. Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science DOI
9. Luchuan Yu, Chenxu Cai, Jianhua Zhang, et al. (2021). A simple and efficient method for isomorphism identification of planar kinematic chains. Soft Computing DOI
10. Luchuan Yu, Chenxu Cai, Jianhua Zhang, et al. (2021). A simple and efficient method for isomorphism identification of planar kinematic chains. DOI
11. Wei Sun, Kong Jianyi, Wang Xing-dong, et al. (2020). Description and Isomorphism Judgment of the Kinematic Chain with Multiple Joints Based on Link-link Adjacency Matrix. Journal of Mechanical Engineering DOI
12. Leiying He, Faxin Liu, Liang Sun, et al. (2019). Isomorphic identification for kinematic chains using variable high-order adjacency link values. Journal of Mechanical Science and Technology DOI
13. Mohammad S. Alam, Mohd Suhaib (2019). A distinct matrix representation of the planar kinematic chains and isomorphism recognition. JOURNAL OF MECHANICAL ENGINEERING AND SCIENCES DOI
14. Vinjamuri Venkata Kamesh, Kuchibhotla Mallikarjuna Rao, Annambhotla Balaji Srinivasa Rao (2017). An Innovative Approach to Detect Isomorphism in Planar and Geared Kinematic Chains Using Graph Theory. Journal of Mechanical Design DOI
15. Hao Liu, Shunyi Shi, Ping Yang, et al. (2017). An Improved Genetic Algorithm Approach on Mechanism Kinematic Structure Enumeration with Intelligent Manufacturing. Journal of Intelligent & Robotic Systems DOI
16. Wei Sun, Jianyi Kong, Liangbo Sun (2017). The improved hamming number method to detect isomorphism for kinematic chain with multiple joints. Journal of Advanced Mechanical Design Systems and Manufacturing DOI
17. Manoj Kumar Lohumi, Aas Mohammad, Irshad Ahmad Khan (2015). A computerized loop based approach for identification of isomorphism and type of mobility in planar kinematic chains. Sadhana DOI
18. Ping Yang, Kehan Zeng, Chunquan Li, et al. (2014). An improved hybrid immune algorithm for mechanism kinematic chain isomorphism identification in intelligent design. Soft Computing DOI
19. Kehan Zeng, Fan Xiao-gui, Mingchui Dong, et al. (2013). A fast algorithm for kinematic chain isomorphism identification based on dividing and matching vertices. Mechanism and Machine Theory DOI
20. Gloria Galán-Marín, Domingo López-Rodríguez, Enrique Mérida-Casermeiro (2010). A New Multivalued Neural Network for Isomorphism Identification of Kinematic Chains. Journal of Computing and Information Science in Engineering DOI
21. Mao Zhong Ge, Jian Yun Xiang, Yong Kang Zhang (2010). Research on Kinematic Chain Isomorphism Identification Method Based on the Standardization Adjacent Matrix. Applied Mechanics and Materials DOI
22. Ping Yang (2010). A review on graph isomorphism identification of mechanism kinematic chain for intelligent and digital manufacturing. International Journal of Materials and Structural Integrity DOI
23. Ping Yang, Kehan Zeng (2009). A high-performance approach on mechanism isomorphism identification based on an adaptive hybrid genetic algorithm for digital intelligent manufacturing. Engineering With Computers DOI
24. Domingo López-Rodríguez, Enrique Mérida-Casermeiro (2009). Shortest Common Superstring Problem with Discrete Neural Networks. Lecture notes in computer science DOI
25. Rafael Marcos Luque‐Baena, Domingo López-Rodríguez, Enrique Mérida-Casermeiro, et al. (2008). Video Object Segmentation with Multivalued Neural Networks. DOI