Abstract
A common way of dynamically scheduling jobs in a manufacturing system is by means of dispatching rules. The problem of this method is that the performance of these rules depends on the state the system is in at each moment, and no rule exists that overrules the rest in all the possible states that the system may be in. The system’s state is defined by a set of control attributes. It would therefore be interesting to use the most appropriate dispatching rule at each moment. To achieve this goal, a scheduling approach which uses machine learning is presented in this paper. By means of this technique, by analysing the previous performance of the system (training examples), a set of heuristic rules are generated that can be used to decide which is the most appropriate dispatching rule at each moment in time. This approach is applied to a job shop configuration. The results demonstrate that this approach produces an improvement in the performance of the system when compared to the traditional method of using dispatching rules.
Zusammenfassung
Die übliche Vorgangsweise bei der dynamischen Arbeitsplatzplanung in einem Herstellungssystem erfolgt mittels Verteilungsregeln. Das Problem dabei ist, dass deren Funktionseigenschaften jederzeit systemabhängig sind, und dass es keine Regel gibt, die alle anderen möglichen Systemzustände ausschaltet. Der Systemzustand wird durch eine Reihe von Regelmerkmalen ausgezeichnet. Daher wäre es interessant, jederzeit die geeignetste Regel zu verwenden. Der vorliegende Beitrag stellt eine Planungsannäherung mittels maschinellen Lernens vor. Durch diese Technik wird über die Analyse der vorhergehenden Systemleistung (Übungsbeispiele) ein Satz heuristischer Regeln hervorgebracht, der zur Bestimmung der jeweils geeignetsten Regel verwendet werden kann. Diese Annäherung kommt in einem Job Shop-Zusammenhang zur Anwendung. Die Ergebnisse zeigen auf, dass sie eine Verbesserung der Systemleistung im Vergleich zur traditionellen Verwendungsmethode von Verteilungsregeln herstellt.
Similar content being viewed by others
References
Aytug, H., Bhattacharyya, S., Koehler, G. J., Snowdon, J. L.: A review of machine learning in scheduling. IEEE Transactions on Engineering Management 41 (1994), No. 2, pp. 165–171.
Baker, K. R.: Sequencing rules and due-date assignments in a job shop. Management Science 30 (1984), No. 9, pp. 1093–1104.
Chiu, C., Yih, Y.: A learning-based methodology for dynamic scheduling in distributed manufacturing systems. International Journal of Production Research 33 (1995), No. 11, pp. 3217–3232.
Fox, M. S., Smith, S. F., ISIS: A knowledge-based system for factory scheduling. Expert Systems 1 (1984), No. 1, pp. 25–49.
Ishii, N., Talavage, J.: A transient-based real-time scheduling algorithm in FMS. International Journal of Production Research 29 (1991), No. 12, pp. 2501–2520.
Kusiak, A., Chen, M.: Expert systems for planning and scheduling manufacturing systems. European Journal of Operational Research 34 (1988), No. 2, pp. 113–130.
Lee, C.-Y., Piramuthu, S., Tsai, Y.-K.: Job shop scheduling with a genetic algorithm and machine learning. International Journal of Production Research 35 (1997), No. 4, pp. 1171–1191.
Michalski, R. S.: A theory and methodology of inductive learning. In: Michalski, R., Carbonell, J., Mitchell, T. (eds.): Machine learning, Palo Alto. CA: Tioga. 1983.
Nakasuka, S., Yoshida T.: Dynamic scheduling system utilizing machine learning as a knowledge acquisition tool. International Journal of Production Research 30 (1990), No. 2, pp. 411–431.
Piramuthu, S., Raman, N., Shaw, M. J. Learning-based scheduling in a flexible manufacturing flow line. IEEE Transactions on Engineering Management 41 (1994), No. 2, pp. 172–182.
Quinlan, J. R.: C4.5: Programs for Machine Learning. San Mateo: Morgan Kaufmann Publishers. 1993.
Shaw, M. J., Park, S., Raman, N.: Intelligent scheduling with machine learning capabilities: The induction of scheduling knowledge. IIE Transactions 24 (1992), No. 2, pp. 156–168.
Shaw, M. J., Whinston, A.: An artificial intelligence approach to scheduling in flexible manufacturing systems. IIE Transactions 21 (1989), No. 2, pp. 170–183.
Stecke, K. E., Solberg, J. J.: Loading and control policies for a flexible manufacturing system. International Journal of Production Research 19 (1981), No. 5, pp. 481–490.
Wu, S. D., Wysk, R. A.: An application of discreteevent simulation to on-line control and scheduling in flexible manufacturing. International Journal of Production Research 27 (1989), No. 9, pp. 1603–1623
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Priore, P., de la Fuente, D. Learning-based scheduling in a job shop. Elektrotech. Inftech. 116, 370–375 (1999). https://doi.org/10.1007/BF03159198
Issue Date:
DOI: https://doi.org/10.1007/BF03159198