Effluent quality prediction of wastewater treatment plant based on fuzzy-rough sets and artificial neural networks

Authors:
Fei Luo;Ren-hui Yu;Yu-ge Xu;Yan Li
Affiliations:
South China University of Technology, College of Automation Science and Engineering, Guangzhou, China;South China University of Technology, College of Automation Science and Engineering, Guangzhou, China;South China University of Technology, College of Automation Science and Engineering, Guangzhou, China;South China University of Technology, College of Automation Science and Engineering, Guangzhou, China
Venue:
FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 5
Year:
2009

Citing 4
Cited 0

Rough Sets: Theoretical Aspects of Reasoning about Data

Rough Sets: Theoretical Aspects of Reasoning about Data
Semantics-Preserving Dimensionality Reduction: Rough and Fuzzy-Rough-Based Approaches

IEEE Transactions on Knowledge and Data Engineering
Prediction of chaotic time series based on the recurrent predictor neural network

IEEE Transactions on Signal Processing
Hybrid intelligent systems for time series prediction using neural networks, fuzzy logic, and fractal theory

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Effluent ammonia-nitrogen (NH3), chemical oxygen demand (COD) and total nitrogen (TN) removals are the most common environmental and process performance indicator for all types of wastewater treatment plants (WWTPs). In this paper, a soft computing approach based on the back propagation (BP) neural networks and fuzzy-rough sets (FRBP) has been applied for forecasting effluent NH3-N, COD and TN concentration of a real WWTP, in which the fuzzy-rough sets theory is employed to perform input selection of neural network which can reduce the influence due to the drawbacks of BP such as low training speed and easily affected by noise and weak interdependency data. The model performance is evaluated with statistical parameters and the simulation results indicates that the FR-BP modeling approach achieves much more accurate predictions as compared with the other traditional modeling approaches.