Summary: Published at the Second International Conference on ``Intelligent Systems Engineering'', Hamburg, Sept. 1994.
APPLICATION OF FUZZY LOGIC AND NEURAL NETWORK TO THE CONTROL OF A FLAME
PROCESS
Wenjing Tao and Hans Burkhardt
Technische Informatik I, Technische Universit¨at Hamburg­Harburge, 21071 Hamburg, Germany
1 INTRODUCTION
For optimal control of a combustion process, which is
normally highly nonlinear and ill­defined, it is nec­
essary to deal with a large amount of information
derived from sensors. In general one kind of sen­
sor (physical, electrochemical, optical, etc.) alone is
not sufficient to cover the overall characteristics for
analysis and ultimately for the control of the pro­
cess. Multi­sensor systems are therefore necessary
in practical applications. To explore the possibili­
ties of application of a sort of optical sensors, namely
CCD­arrays, to the control of a flame process, we de­
veloped a prototype for controlling a Bunsen burner
flame in our laboratory (Fig. 1). The control vari­
ables gas and oxygen can be adjusted by stepping

Source: Albert-Ludwigs-Universität Freiburg, Institut für Informatik,, Lehrstuhls für Mustererkennung und Bildverarbeitung

Collections: Computer Technologies and Information Sciences