Varying Parameters of the Object Model on Fuzzy Neural Network Controller for Activated Sludge Method of the Sewage Treatment System


Article Preview

In this paper, we take characteristics of wastewater treatment and process technology, drawing on the effectiveness of thetraditional PID control and on the basis of its lack, with the key steps in the sewage treatment process - Aeration control of part of the process parameters, Fuzzy neural network control of dissolved oxygen concentration (DO) to achieve negative feedback control loop,design a model-based closed-loop cascade control system. Fuzzy systems, membership function, the structure of the network topology and algorithms are based on the actual issues identified in the fuzzy variables. Aiming at the four parts of the fuzzy control, adopting four fuzzy neural network based on the standard model - the input layer, Fuzzy layer,Inference layer,Clear layer are corresponding with it. Standing on two points: the dissolved oxygen concentration control and the rate of change from the error ,then design the Fuzzy neural network controller. Then the fuzzy neural network control technology could be used in wastewater treatment on the specific application of process control.



Advanced Materials Research (Volumes 230-232)

Edited by:

Ran Chen and Wenli Yao




Z. H. Shi and C. Z. Wang, "Varying Parameters of the Object Model on Fuzzy Neural Network Controller for Activated Sludge Method of the Sewage Treatment System", Advanced Materials Research, Vols. 230-232, pp. 339-345, 2011

Online since:

May 2011




[1] Liu CS. Automation is the development direction of China's water[J], Water & Wastewater Engineering, 1998(12)24: 1-1.

[2] Water and Wastewater Treatment (The Swedish Experience), Ministry of Foreign Affairs & Swedish Environmental protection Agency(1999).

[3] Ohto T. Control, computers and communications: Fusion in instrumentation, control and automation of water and wastewater system in Japan. Water Science and Technology.Vol. 37, no. 6, pp.15-19(1998).


[4] Du SX. Modeling of Biological Wastewater Treatment Process and Control[J]. Control Theory & Applications, 2002, 19(5): 660-666.

[5] Kabouis JC, Georgakos AP, Camara A. Optimal control of the activated sludge process: Effect of sludge storage. Water Research, 1992, 26(4): 507-517.


[6] Capodaglio Andrea G. Sludge bulking analysis and forecasting application of system identification and artificial neural computing technologies, Wat. Res, 1991, 25(10): 1217-1224.


[7] Belanche L. Prediction of the bulking phenomenon in wastewater treatment plants. Artificial Intelligence in Engineering. 2000, 14: 307-317.


[8] Cui YW, Wang SY, Yu DS. The feasibility study of computer control parameters on DO as the treatment of saline wastewater SBR[J]. Water & Wastewater Engineering, 2009, 29(6): 54-57.