Fuzzy controller design for municipal incinerators with the aid of genetic algorithms and genetic programming techniques

Mass bum waterwall incinerator has been the most widely used technology for processing the municipal solid waste (MSW) streams in many metropolitan regions since 1970. Not only the heterogeneity of physical composition and chemical property of the MSW but also the complexity of combustion mechanism would significantly influence the performance of waste incineration. As a result, a successful operation requires an advanced combustion control system for handling many uncertain factors. Conventional automatic combustion control (ACC) technology was found to be insufficient to handle such a highly nonlinear system. The successful applications of those intelligent combustion control (ICC) technologies, such as fuzzy control technology, for reducing the operational risk have received wide attention in recent years. This paper illustrates the principles, algorithms, and application potentials of the genetic fuzzy controller that is particularly designed for improving the traditional fuzzy control logic with the aid of genetic algorithms/genetic programming techniques. Practical implementation of this methodology was assessed by a simulation analysis based on three representative types of mass bum waterwall incinerators in Taiwan. It indicates that the quality of combustion control in those three municipal incinerators can be possibly enhanced via the use of genetic fuzzy control logic. The application of such a hybrid fuzzy control technology can be easily extended to many other types of industrial incinerators, such as modular, rotary kiln, and fluidized bed incinerators, by a slightly different approach.

[1]  A. Kandel,et al.  Application of fuzzy reasoning to the control of an activated sludge plant , 1990 .

[2]  Sangbong Park,et al.  A neuro-genetic controller for nonminimum phase systems , 1995, IEEE Trans. Neural Networks.

[3]  H. Ono,et al.  Combustion control of refuse incineration plant by fuzzy logic , 1989 .

[4]  Chin-Teng Lin,et al.  Neural-Network-Based Fuzzy Logic Control and Decision System , 1991, IEEE Trans. Computers.

[5]  Kumpati S. Narendra,et al.  Identification and control , 1998 .

[6]  ANDREAS BASTIAN,et al.  Selection of input variables for model identification of static nonlinear systems , 1996, J. Intell. Robotic Syst..

[7]  Wei-Ling Chiang,et al.  Construction of an on-line fuzzy controller for the dynamic activated sludge process , 1994 .

[8]  Mark J. Willis,et al.  Using a tree structured genetic algorithm to perform symbolic regression , 1995 .

[9]  Luis J. de Miguel,et al.  Fuzzy Identification of Systems and Its Applications to Fault Diagnosis Systems , 1997 .

[10]  M. Sugeno,et al.  ErratumFuzzy modelling and control of multilayer incinerator , 1988 .

[11]  Hitoshi Iba,et al.  System identification approach to genetic programming , 1994, Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE World Congress on Computational Intelligence.

[12]  Kazuyuki Suzuki,et al.  Stable Combustion in Sludge Melting Furnace by Fuzzy Logic Control , 1993 .

[13]  Farrokh Janabi-Sharifi,et al.  Collision: Modeling, simulation and identification of robotic manipulators interacting with environments , 1995, J. Intell. Robotic Syst..

[14]  Derek A. Linkens,et al.  Fuzzy-neural control: principles, algorithms and applications , 1995 .

[15]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.