Evolving a Hybrid Model of a Fed-batch Fermentation Process

Created by W.Langdon from gp-bibliography.bib Revision:1.4216

  author =       "B. McKay and C. Sanderson and M. J. Willis and 
                 J. Barford and G. Barton",
  title =        "Evolving a Hybrid Model of a Fed-batch Fermentation
  institution =  "Chemical Engineering, Newcastle University",
  year =         "1996",
  address =      "UK",
  keywords =     "genetic algorithms, genetic programming",
  URL =          "http://lorien.ncl.ac.uk/sorg/paper6.ps broken",
  abstract =     "This paper presents a novel method for the system
                 identification of the fed-batch fermentation process
                 defined in the problem statement of the
                 Biotechnological Control Forum Modelling and Control
                 Competition. The identification methodology involves a
                 hybrid of mechanistic modelling and Genetic Programming
                 techniques. It provides an accurate model of the system
                 which should be extremely useful in both the
                 optimisation and control of this process. The
                 performance of the model as a 25 time unit ahead
                 predictor of product concentration (on unseen
                 verification data) is such that the root mean square
                 error between the actual and predicted output is less
                 than 5% over the range of interest.",
  notes =        "MSword postscript not camptible with unix",
  size =         "12 pages",

Genetic Programming entries for Ben McKay C Sanderson Mark J Willis J Barford Geoffrey W Barton