A Self-Learning Algorithm Based on Support Vector Machine for Scheduling a Job-Shop-Like Knowledgeable Manufacturing Cell

Abstract:

The job-shop-like knowledgeable manufacturing cell scheduling is a NP-complete problem and there has not been a completely valid algorithm for it until now. An algorithm with self -learning ability is proposed through the addition of precedence constraint of operations on the basis of directed graph. A method based on support vector machine is constructed to choose accurately interchangeable operations by small samples earning to obtain the better scheduling. The classification accuracy can be improved by the continuous addition of new instances to the sample library. The results of simulation show that the algorithm performs well for the job-shop-like knowledgeable manufacturing cell.

• Periodical: Applied Mechanics and Materials (Volumes 148-149)
• Pages: 369-373
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.148-149.369
• Online since: December 2011
• Authors: Wen Chao Li, Hong Sen Yan
• Keywords: Constraint Guided, Job-Shop, Knowledgeable Manufacturing Cell, Self-Learning

References

[1] Yan Hongsen, Liu Fei. Knowledgeable manufacturing system—a new kind of advanced manufacturing system[J]. Computer Integrated Manufacturing Systems, 2001, 7(8): 7-11(in Chinese).

[2] Yan Hongsen. A new complicated knowledge representation approach based on knowledge meshes[J]. IEEE Transactions on Knowledge and Data Engineering, 2006, 18(1): 47-62.

DOI: 10.1109/tkde.2006.2

[3] Yang Renzi, Yan Hongsen. Measure method and its application of knowledge representation based on knowledge mesh[J]. System Engineering—Theory & Practice, 2010, 30(6): 1067-1076(in Chinese).

[4] Yang Hong-bing, Yan Hong-sen. Adaptive strategy of dynamic scheduling in knowledgeable manufacturing system[J]. Control and Decision, 2007, 22(12): 1335-1340(in Chinese).

[5] Meng Xiangang, Yan Hongsen. Purchase forecasting in knowledgeable manufacturing systems based on self-learning fuzzy Petri-nets[J]. Control and Decision, 2009, 24(3): 371-376 (in Chinese).

[6] Garey M. R., Johnson D S, and SETHI R. The complexity of flow-shop and job-shop scheduling[J]. Mathematics of Operations Research, 1976, 1(2): 117-129.

[7] Ashour S., Hiremath S. R. A branch-and-bound approach to the job-shop scheduling problem[J]. Internal Journal of Production Research, 1973, 11: 47-58.

DOI: 10.1080/00207547308929945

[8] Brucker P., Jurisch B. A new lower bound for the job-shop scheduling problem[J]. European Journal of Operation Research, 1993, 64, 156-167.

DOI: 10.1016/0377-2217(93)90174-l

[9] Luh P. B., Zhao xing, Wang Yajun, etc. Lagrangian relaxation neural networks for Job shop scheduling[J]. IEEE TRANSACTIONS on Robotics and Automation, 2000, 16(1): 78-88.

DOI: 10.1109/70.833193

[10] Zhang C. Y, P. Li, Y. Rao, etc. A very fast TS/SA algorithm for the job-shop scheduling problem[J]. Computers and Operations Research, 2008, 25(1): 282-294.

DOI: 10.1016/j.cor.2006.02.024

[11] Pinedo M. Scheduling: Theory, algorithm, and system[M]. Beijing: China Machine Press, (2005).

[12] Haykin S. Neural networks: a comprehensive foundation [M]. 2nd. Beijing: China Machine Press, (2004).