This paper details the design and application of a hybrid neural network architecture for the rescheduling problem of batch manufacture. Design issues include the selection of an appropriate neural network paradigm, specification of the network architecture and support for multistep prediction. Application issues include decoupling the network dimension from that of the problem and the definition of suitable rescheduling operators. The ensuing hybrid network is tested against heuristics previously identified as typically representing estimates for best and worst case performance within a cross-section of batch rescheduling problems.
RundhawaS. U.ZengY.Job shop scheduling: An experimental investigation of the performance of alternative scheduling rules. Prod. Planning Control, 1996, 7(1), 47–56.
2.
GenM.ChengR.Genetic Algorithms and Engineering Design, 1996 (John Wiley and Sons, New York).
3.
CheungJ. Y.Scheduling. In Artificial Neural Networks for Intelligent Manufacturing (Ed. DagliC. H.), 1994, Ch. 8, pp. 159–194 (Chapman and Hall, London).
4.
BribroG., et al. Optimisation by mean field annealing. In Advances in Neural Information Systems 1 (Ed. Tour-EtzkyD. S.), 1989, pp. 91–98 (Morgan Kaufmann, San Mateo).
5.
ArizonoI.YamamotoA.OhtaH.Scheduling for minimising total flow time by neural networks. Int. J. Prod. Res., 1992, 30(3), 503–511.
6.
AnsariN.HouE. S. H.YuY.A new method to optimise the Satellite Broadcasting Schedules using the Mean Field Annealing of a Hopfield Neural Network. IEEE Trans. Neural Networks, 1995, 6(2), 470–483.
7.
DagliC. H.SittisathachaiS.Genetic neuro-schedular: A new approach for job shop scheduling. Int. J. Prod. Econ., 1995, 41, 135–145.
JordanM. I.JacobsR. A.Hierarchies of adaptive experts. In Advances in Neural Information Processing Systems 4 (Eds MoodyJ. E.HansonS. J.LippmannR. P.), 1992, pp. 985–992 (Morgan Kaufmann, San Mateo).
