A PARTICLE SWAM OPTIMISATION WITH STACKED NEURAL NETWORK APPROACH FOR BATCH PROCESSES MANUFACTURING
Keywords:
Batch processes, Neural networks, Particle swam optimisation, ReliabilityAbstract
An optimal control strategy for batch processes manufacturing using particle swam optimisation (PSO) and stacked neural networks is presented in this paper. Stacked neural networks are used to improve model generalisation capability, as well as provide model prediction confidence bounds. In order to improve the reliability of the calculated optimal control policy for batch processes manufacturing, an additional term is introduced in the optimisation objective function to penalise wide model prediction confidence bounds. PSO can cope with multiple local minima and could generally find the global minimum. Application to a simulated fed-batch process demonstrates that the proposed technique is very effective.
Downloads
References
Bonvin D (1998) , J. Process Control,Vol. 8, 355-368.
Zhang J (2005) , “Transactions Instrumental Measurement Control”,Vol. 27, 391-410.
Zhao S J Zhang J Xu Y M (2006) “Industrial Engineering Chemistry Research”,Vol. 45, 3843-3852.
TianY Zhang J Morris A J (2001), “Industrial Engineering Chemistry Research”, Vol. 40, 4525-4535.
Sridhar D V Seagrave R C Bartlett E B (1996), “American Institute of Chemical Engineers Journal” (AIChE J)., Vol.42, 2529-2539.
Zhang J Martin E B Morris A J Kiparissides C (1997) “Computer Chemical Engineering”,Vol. 21, s1025-s1030.
Zhang J (1999), Neurocomputing, Vol.25, 93-113.
Zhang J (2004), Ind. Eng. Chem. Res., Vol.43, 1030-1038.
Kennedy J Eberhart R (1995), “Particle Swarm Optimization”, In Proceedings of the 1995 IEEE international conference on neural networks, Perth, Australia. Vol VI, 1942 – 1948.
Kennedy J Mendes R (2006), “IEEE Transacations System Man Cybernetics. Part C-Appl. Rev., Vol.36, 515-519.
Terwiesch P Ravemark D Schenker B Rippin D W T (1998), Computer Chemical Engineering,Vol. 22, 201-213.
