×

Using MLP networks to design a production scheduling system. (English) Zbl 1026.90046

Summary: This paper investigates the application of artificial neural networks to the problem of job shop scheduling with a scope of a deterministic time-varying demand pattern over a fixed planning horizon. The purpose of the research is to design and develop a job shop scheduling system (a scheduling software) that can generate effective job shop schedules using the multi-layered perceptron (MLP) networks. The contributions of this study include designing, developing, and implementing a production activity scheduling system using the MLP networks; developing a method for organizing sample data using a denotation bit to indicate processing sequence and processing time of a job simultaneously; using the back-propagation training process to control local minimal solutions; and developing a heuristics to improve and revise the initial production schedule. The proposed production activity schedule system is tested in a real production environment and illustrated in the paper with a sample case.

MSC:

90B50 Management decision making, including multiple objectives
90B30 Production models
90B35 Deterministic scheduling theory in operations research
92B20 Neural networks for/in biological studies, artificial life and related topics
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Pinedo, M.; Chao, X., Operations scheduling with applications in manufacturing and services (1999), Irwin McGraw-Hill Company, Inc: Irwin McGraw-Hill Company, Inc Boston · Zbl 1094.90561
[2] Silver, E. A.; Pyke, D.; Peterson, R., Inventory management and production planning and scheduling (1998), Wiley: Wiley New York
[3] Yang, S.; Wang, D., A new adaptive neural network and heuristics hybrid approach for job shop scheduling, Computers & Operations Research, 28, 955-971 (2001) · Zbl 0985.90043
[4] Erschler, J.; Roubellat, F.; Vernhes, J. P., Finding some essential characteristics of the feasible solutions for a scheduling problem, Operations Research, 24, 4, 774-783 (1976) · Zbl 0335.90027
[5] Stake, T.; Morikawa, K.; Nakamura, N., Neural network approach for minimizing the makespan of the general job-shop, International Journal of Production Economics, 33, 1, 67-74 (1994)
[6] Feng S, Zheng L. Nonlinear programming neural networks based on economic mechanism: theoretical analysis. Proceedings of International Conference on Large scale systems, Greece, July 15-17, Vol. II, 1998. p. 1066-9.; Feng S, Zheng L. Nonlinear programming neural networks based on economic mechanism: theoretical analysis. Proceedings of International Conference on Large scale systems, Greece, July 15-17, Vol. II, 1998. p. 1066-9.
[7] Jain, S.; Meeran, S., Job-shop scheduling using neural networks, International Journal of Production Research, 36, 5, 1249-1272 (1998) · Zbl 0926.90043
[8] Li, L., Proposing an architectural framework of a hybrid knowledge-based system for production rescheduling, Expert Systems, 16, 4, 282-288 (1999)
[9] Gaafar, L.; Choueiki, M., A neural network model for solving the lot-sizing problem, OMEGA, 28, 175-184 (2000)
[10] Yu, H.; Liang, W., Neural network and genetic algorithm-based hybrid approach to expanded job-shop scheduling, Computers and Industrial Engineering, 39, 337-356 (2001)
[11] Geng, G.; Li, L., Scheduling railway freight cars, Knowledge-Based Systems, 14, 289-297 (2001)
[12] Li, H.; Li, Z.; Li, L.; Hu, B., A production rescheduling expert simulation system, European Journal of Operational Research, 124, 2, 283-293 (2000) · Zbl 1024.90033
[13] Li, H.; Li, L., Integrating systems concepts into manufacturing information systems, Systems Research and Bahavioural Sciences, 17, 135-147 (2000)
[14] Feng, S.; Li, L., An object-oriented intelligent design tool to aid the design of manufacturing systems, Knowledge-Based Systems, 14, 225-232 (2001)
[15] Li, L., An analysis of sources of competitiveness and performance of Chinese manufacturers, International Journal of Operation & Production Management, 20, 299-315 (2000)
[16] Huang, J.; Feng, S.; Zhou, K., Application of production activity scheduling based on neural networks, Journal of Huazhong University of Science and Technology, 8, 11, 27-29 (2000)
[17] Feng, S.; Xu, L., A hybrid knowledge-based system for urban development, Expert Systems With Applications, 10, 1, 157-163 (1996)
[18] Feng, S.; Xu, L., An integrated knowledge-based system for urban planning decision support, Knowledge-Based Systems, 10, 2, 103-109 (1997)
[19] Yang, B.; Li, L.; Xu, J., An early warning system for loan risk assessment using artificial neural networks, Knowledge-Based Systems, 14, 303-306 (2001)
[20] Datta, D.; Tassou, S. A., Artificial neural network based electrical load prediction for food retail stores, Applied Thermal Engineering, 18, 1121-1128 (1998)
[21] Rauch, H., Artificial intelligence in real-time control (1998), Pergamon Press: Pergamon Press Oxford, England · Zbl 0895.68001
[22] Li, H.; Xu, L. D., Feature space theory—a mathematical foundation for data mining, Knowledge-Based Systems, 14, 5-6, 253-257 (2001)
[23] Zhou, S. M.; Xu, L. D., A new type of recurrent fuzzy neural network for modelling dynamic systems, Knowledge-Based Systems, 14, 243-251 (2001)
[24] Zhou, S. M.; Xu, L. D., Dynamic recurrent neural networks for a hybrid intelligent decision support system for the metallurgical industry, Expert Systems, 16, 240-247 (1999)
[25] Feng, S.; Xu, L. D., Decision support for fuzzy comprehensive evaluation of urban development, Fuzzy Sets and Systems, 105, 1, 1-12 (1999)
[26] Feng, S.; Xu, L. D., An intelligent decision support system for fuzzy comprehensive evaluation of urban development, Expert Systems With Applications, 16, 1, 21-32 (1999)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.