Abstract
Fluidized bed incinerators can burn waste in a short time by stirring waste and fluidized sands. However, recently refuse shows various temperament and high calorie output. Changes in quality and quantity of waste cause fluctuations in combustion, and burning in fluidized bed incinerators is sometimes incomplete when much waste is supplied at one time. Furthermore, since these combustion systems are nonlinear and multi-variable, it is difficult to form mathematical models and to control them through an ordinary control algorithm. Therefore we adopted a neural network controller which can express characters as nonlinear and multi-variable. The proposed neural network controller learns so as to reduce disturbances, such as changes of waste type, adaptively in a stability area, together with controlling by an ordinary controller. We call this neural network control system RANC (robust adaptive neurocontroller). The method was applied to a real plant. The manipulated variable is amount of secondary air to the freeboard and the controlled variable is the concentration of O2. O2 is used as an index of stable combustion. The usefulness was verified since this method was able to reduce the fluctuation of O2 concentration and CO concentration.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: TRANSACTIONS OF THE JAPAN SOCIETY OF MECHANICAL ENGINEERS Series C
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
