Abstract
Chapters 5 and 6 illustrate that the BOXES methodology works very well in prolonging the duration of motion of a freely hinged pole that is attached to a constantly moving cart driven by a theoretically instantly reversible motor. The algorithm reads the state variables and issues one of two possible control signals connected to the motor control system thus enforcing right/left motion. There are many other dynamic systems that are controlled in a bang-bang fashion and consequently, candidates for the BOXES methodology. This chapter describes three case studies focusing on applications in which the BOXES system learns to switch a process variable on or off based on a signature table that is populated by appropriate learning laws. The applications described in this chapter are a fedbatch bioreactor, a trash to steam plant, and a system that learns to reverse a tractor trailer.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Quiennec I, Dahhou B & Sevely Y. (1991) Theoretical and Experimental Results in Optimisation of Fedbatch Fermentation Processes. J. Systems Engineering, 1(1): 31–40.
Constantinides A, Spencer JP. & Gaden EL. (1970) Optimization of Batch Fermentation Processes. II. Optimum Temperature Profiles for Batch Penicillin Fermentations. Biotechnol Bioeng. 12: 1081–1098.
Calam CT. & Russell DW. (1973) Microbial Aspects of Fermentation Process Development. J. Appl. Chem. Biotechnol. 23: 225–237.
Williams D, Yousefpour P & Wellington MH. (1986) On-line Adaptive Control of a Fedbatch Fermentation of Saccharomyces Cerevisiae. J. Biotechnol & Bioengineering. XXVII:631–645.
Rosenbrock, HH., (1960) An Automatic Method for Finding the Greatest or Least Value of a Function. Compu J. 3 (3): 175–184.
Ghose TK, Tyagi RD (1979).Rapid Ethanol Fermentation of Cellulose Hydrolsate. Product and Substrate Inhibition and Optimization of Fermentor Design. Biotechnol Bioeng. 21:1401–1420.
Russell DW (1991) Further Studies in AI Augmented Process Control. Annual Review in Automatic Programming.Vol: 16(1): 75–79.
Nguyen, DH and Widrow, B (1990) Neural Networks for Self-learning Control Systems. IEEE Control Systems Magazine. April: 19–23
Woodcock N et al. (1991) Fuzzy BOXES as an Alternative of Neural Networks for Difficult Control Problems. Applications of Artificial Intelligence in Engineering VI. Rzevski and Adey RA (eds) CML. 903–919.
Wieland AP (1991) Evolving Neural Network Controllers for Unstable Systems. Proc. IJCNN-91 Seattle International Joint Conference on Neural Networks. Vol II: 667–673.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag London
About this chapter
Cite this chapter
Russell, D.W. (2012). Other On/Off Control Case Studies. In: The BOXES Methodology. Springer, London. https://doi.org/10.1007/978-1-84996-528-6_9
Download citation
DOI: https://doi.org/10.1007/978-1-84996-528-6_9
Published:
Publisher Name: Springer, London
Print ISBN: 978-1-84996-527-9
Online ISBN: 978-1-84996-528-6
eBook Packages: EngineeringEngineering (R0)