Control of the Coagulation Process in a Paper-mill Wastewater Treatment Process Using a Fuzzy Neural Network

J. Wan, M. Huang, Y. Ma, W. J. Guo, Y. Wang and H. Zhang

Abstract
In this paper, an integrated neural-fuzzy process controller was developed to study the coagulation of wastewater treatment in a paper mill. In order to improve the fuzzy neural network performance, the self-learning ability embedded in the fuzzy neural network model was emphasized for improving the rule extraction performance. It proves the fuzzy neural network more effective in modeling the coagulation performance than artificial neural networks (ANN). For comparing between the fuzzy neural controller and PID controller, a coagulation unit in a paper mill wastewater treatment process (PMWTP) was chosen to support the derivation of a fuzzy control rule base. It is shown that, using the fuzzy neural controller, in terms of cost effectiveness, enables us to save almost 25 % of the operating costs during the time when the controller can be applied.

This work is licensed under a Creative Commons Attribution 4.0 International License

Keywords
Fuzzy neural network, wastewater treatment, predictive control, coagulation process, fuzzy hybrid algorithm