Priore, Paolo; de la Fuente, David; Puente, Javier; Gómez, Alberto Dynamic scheduling of flexible manufacturing systems through machine learning: An analysis of the main scheduling systems. (Spanish. English summary) Zbl 1069.90531 Qüestiió (2) 25, No. 3, 523-549 (2001). Summary: A common way of dynamically scheduling jobs in a flexible manufacturing system is by means of dispatching rules. The drawback of this method is that the performance of the manufacturing system depends on the state the manufacturing system is in at each moment, and no one rule exists that overrules the rest in all the possible states that the manufacturing system may be in. It would therefore be interesting to use the most appropriate dispatching rule at each moment. To achieve this goal, a scheduling system which uses machine learning can be used. By means of this technique, and by analysing the previous performance of the manufacturing system (training examples), knowledge is generated that can be used to decide which is the most appropriate dispatching rule at each moment in time. This paper provides a review of the main scheduling systems that use machine learning to vary the dispatching rule dynamically that have been described in the literature. MSC: 90B35 Deterministic scheduling theory in operations research 90B30 Production models 68T20 Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) 68M20 Performance evaluation, queueing, and scheduling in the context of computer systems Keywords:Dynamic Scheduling; Machine Learning; Flexible Manufacturing Systems; Dispatching Rules; Simulation PDFBibTeX XMLCite \textit{P. Priore} et al., Qüestiió (2) 25, No. 3, 523--549 (2001; Zbl 1069.90531) Full Text: EuDML