Part Family Formation Based on Clustering Algorithm and BP Network

Abstract:

To solve the problem of design and manufacturing on the production of many varieties of small batch, the parts grouping method that based on clustering algorithm, clustering validity index and BP neural network method for new parts is proposed. At first, mathematical model of part clustering is built, and parts grouping is based on the similarity of data and cluster centers which is calculated by Euclidean distance, then the effectiveness of parts group is tested by Function Index and optimal number of clusters group can be found. The algorithm is achieved by Matlab clustering toolbox, so the best part family structure is built. Furthermore, the grouped parts are used to train the BP neural network toolbox in Matlab, then simulate new parts on network to find the match group. At last, a case study was also presented to verify the feasibility of this method．

• Periodical: Applied Mechanics and Materials (Volumes 635-637)
• Pages: 1586-1589
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.635-637.1586
• Online since: September 2014
• Authors: Guan Yu Liu*, Shan Li, Yu Long Wang
• Keywords: BP Network, Clustering Algorithm, Coding, Group Technology, Part Family, Validity Index

References

[1] ZHAO Gang, JIANG Pingyu: Computer Integrated Manufacturing Systems, 2006, 12(7): 1007-1009, in Chinese.

[2] XU Xianghui, Cai Jianguo: Group Technology[M]. Beijing: China Machine Press, 2000: 16-19, in Chinese.

[3] SUN Jiegui, LIU Jie, Zhao Lianyu.: Journal of Software. , 2008, 19(1): 48-61, in Chinese.

[4] FAN Jiulun. Studies on new fuzzy clustering algorithms and clustering validity problems [D]. Xi'an : Xidian University, 1998, in Chinese.

[5] MODHA D S, SPANGLER W S: Machine Learning, 2003, 52(3): 217-237.

[6] KWEDLO W: Pattern Recognition Letters, 2011, 32(12): 1613-1621.

[7] YU Jian, CHENG Qiansheng: Chinese Science(E), 2002, 32(2): 274-280, in Chinese.