Advanced Hybrid Fuzzy-Neural Controller for Industrial Wastewater Treatment
Publication: Journal of Environmental Engineering
Volume 127, Issue 11
Abstract
Many uncertain factors affect the operation of wastewater treatment plants. These include the physical and chemical properties of wastewater streams as well as the degradation mechanisms exhibited by biological processes. Because of the rising concerns about environmental and economic impacts, improved process control algorithms, using artificial intelligence technologies, have received wide attention. Recent advances in control engineering suggest that hybrid control strategies, integrating some ideas and paradigms existing in different soft computing techniques, such as fuzzy logic, genetic algorithms, and neural networks, may provide improved control of effluent quality. The methodology proposed in this study employs a three-stage analysis that integrates three soft computing approaches for generating a representative state function, searching a set of multiobjective control strategies, and autotuning the fuzzy control rule base used for controlling a treatment plant. The case study, using an industrial wastewater treatment plant in Taiwan as an example, demonstrates the applicability of the approach. The findings from this research suggest that a genetic-algorithm–based hybrid fuzzy-neural controller can produce better plant performance than does a simple fuzzy logic controller, in terms of both environmental and economic objectives. This methodology can be extended to control many other types of wastewater treatment processes, as well, by making only minor modifications.
Get full access to this article
View all available purchase options and get full access to this article.
References
1.
Boscolo, A., Mangiavacchi, C., Drius, F., Rongione, F., Pavan, F., and Cecchi, F. ( 1993). “Fuzzy control of an anaerobic digester for the treatment of the organic fraction of the MSW.” Water Sci. and Technol., 27(2), 57–68.
2.
Busby, J. B., and Andrews, J. F. ( 1975). “Dynamic modeling and control strategies for the activated sludge process.” J. Water Pollution Control Fedn., 47(5), 1055–1065.
3.
Cashion, B. S., Keinath, T. M., and Schuk, W. W. ( 1975). “Control strategies for the activated sludge process.” J. Water Pollution Control Fedn., 51(4), 815–823.
4.
Chang, N. B., and Chen, W. C. ( 1999). “Fuzzy controller design for municipal incinerators with the aid of genetic algorithms and genetic programming techniques.” Waste Mgmt. and Res., London, 18(5), 429–443.
5.
Chang, N. B., Chen, W. C., and Shieh, W. K. ( 2000). “Optimal control of wastewater treatment plants via integrated neural network and genetic algorithms.” Civ. Engrg. and Envir. Sys., 18, 1–17, 2001.
6.
Culevski, N. ( 1996). “Artificial neural networks and genetic algorithms: Computational models.” PhD thesis, California State University, Long Beach, Calif.
7.
Czogala, E., and Rawilk, T. ( 1989). “Modeling of a fuzzy controller with application to the control of biological process.” Fuzzy Sets Sys., 31, 13–22.
8.
Enbutsu, I., Baba, K., Hara, N., Waseda, K., and Nogita, S. ( 993). “Integration of multi AI paradigms for intelligent operation support systems–fuzzy rule extraction from a neural network.” Water Sci. and Technol., 28(11/12), 333–340.
9.
Fu, C. S., and Poch, M. ( 1995). “Fuzzy modeling pattern recognition for dynamic process and its application for an activated sludge process.” Chemical Engrg. Sci., 50(23), 3715–3725.
10.
Fu, C. S., and Poch, M. ( 1998). “Fuzzy model and decision of COD control for an activated sludge process.” Fuzzy Sets Sys., 41, 281– 292.
11.
Hiraoka, M., and Tsumura, K. ( 1989a). “An approach to the control of the activated sludge system by use of a succession model.” Water Sci. and Technol., 13, 327–332.
12.
Hiraoka, M., and Tsumura, K. ( 1989b). “System identification and control of the activated sludge process by use of a statistical model.” Water Sci. and Technol., 21, 1161–1172.
13.
Holland, J. H. ( 1975). Adaptation in natural and artificial systems, University of Michigan Press, Ann Arbor, Mich.
14.
Hughey, P. W., Meredith, D. D., and Middleton, A. C. (1982). “Algorithm for optimal activated sludge operation.”J. Envir. Engrg. Div., ASCE, 108(2), 349–366.
15.
Kabouris, J. C., Georgakakos, A. P., and Camara, A. ( 1990). “Optimal control of the activated sludge process: Effect of sludge storage.” Water Res., 26(4), 507–517.
16.
Lech, R. F., Grady, C. P., Lim, H. C., and Koppel, L. B. ( 1978). “Automatic control of the activated sludge process: Efficiency of control strategies.” Water Res., 12, 91–110.
17.
Lee, D. S., and Park, J. M. ( 1999). “Neural network modeling for on-line estimation of nutrient dynamics in a sequentially-operated batch reactor.” J. Biotechnology, 75, 229–239.
18.
Lin, C. T., and Lee, C. S. G. ( 1991). “Neural network–based fuzzy logic control and decision system.” IEEE Trans. on Computers, 40(12), 1320–1336.
19.
Maclennan, G. A. ( 1994). “The application of genetic algorithms to neural networks.” MS thesis, Dalhousie University, Halifax, N.S., Canada.
20.
Naci, H., Michael, O., and Stenstrom, K. (1994). “KBES for process control of nitrification in activated sludge process.”J. Envir. Engrg., ASCE, 120(1), 87–107.
21.
Narendra, K. S., and Parthasarathy, K. ( 1990). “Identification and control of dynamical systems using neural networks.” IEEE Trans. on Neural Networks, 1, 4–27.
22.
Novotny, V. ( 1992). “Real time control of wastewater treatment plant operations.” Water Sci. and Technol., 125(4), 89–101.
23.
Ossenbruggen, P. J., Constantine, K., Collin, M. R., and Bishop, P. L. ( 1987). “Toward optimum control of the activated sludge process with reliability analysis.” Civ. Engrg. Sys., 4, 27–44.
24.
Sandhu, S. S. ( 1995). “Training of feedforward neural networks with quardratic random optimization and genetic algorithms.” MS thesis, University of Nevada, Reno, Nev.
25.
Spall, J. C., and Cristion, J. A. ( 1997). “A neural network controller for systems with unmodeled dynamics with applications to wastewater treatment.” IEEE Trans. on Sys., Man and Cybernetics—Part B: Cybernetics, 27(3), 369–375.
26.
Stenstrom, M. K., and Andrews, J. F. (1979). “Real-time control of activated sludge process.”J. Envir. Engrg. Div., ASCE, 105(2), 245– 260.
27.
Sugeno, M., and Kang, G. T. ( 1986). “Fuzzy modelling and control of multilayer incinerator.” Fuzzy Sets and Sys., 18, 329–346.
28.
Takagi, T., and Sugeno, M. ( 1985). “Fuzzy identification of systems and its applications to modeling and control.” IEEE Trans. on Sys., Man, and Cybernetics, 15(1), 116–132.
29.
Tong, R. M., Beck, M. B., and Latten, A. ( 1980). “Fuzzy control of the activated sludge wastewater treatment process.” Automatica, 16, 659–701.
30.
Tsai, Y. P., Ouyang, C. F., Chiang, W. L., and Wu, M. Y. ( 1994). “Construction of an on-line fuzzy controller for the dynamic activated sludge process.” Water Res., 28(4), 913–921.
31.
Tsai, Y. P., Ouyang, C. F., Wu, M. Y., and Chiang, W. L. ( 1996). “Effluent suspended solid control of activated sludge process by fuzzy control approach.” Water Envir. Res., 68(6), 1045–1053.
32.
Watanabe, S., et al. ( 1993). “Intelligent operation support system for activated sludge process.” Water Sci. and Technol. 128(11), 325–332.
33.
Williams, V. ( 1996). “Evolutionary neural networks: Models and applications.” PhD thesis, Aston University, U.K.
34.
Yi, C., Cao, Z., and Kandel, A. ( 1990). “Application of fuzzy reasoning to the control of an activated sludge plant.” Fuzzy Sets and Sys., 38, 1–14.
Information & Authors
Information
Published In
Journal of Environmental Engineering
Volume 127 • Issue 11 • November 2001
Pages: 1048 - 1059
History
Received: Aug 18, 2000
Published online: Nov 1, 2001
Published in print: Nov 2001
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.