51. Seasonal artificial neural network model for water quality prediction via a clustering analysis method in a wastewater treatment plant of China
- Author
-
Min Zhang, Ying Zhao, Junbo Liang, and Liang Guo
- Subjects
Engineering ,business.industry ,media_common.quotation_subject ,Environmental engineering ,Ocean Engineering ,02 engineering and technology ,010501 environmental sciences ,01 natural sciences ,Pollution ,Wastewater ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Water treatment ,Sewage treatment ,Quality (business) ,Water quality ,Raw water ,Cluster analysis ,business ,Effluent ,0105 earth and related environmental sciences ,Water Science and Technology ,media_common - Abstract
For recovering the water quality of a river, it is a key factor to improve purifying capacity of wastewater in wastewater treatment plants (WTPs). The relational model for some key parameters of WTP processes is important for it can reveal the current situation and handling ability of the WTP and offer managers more useful information to design the processes for the optimized operation. The seasonal artificial neural network (ANN) models were designed for improving purifying ability of wastewater in a WTP of Harbin, northeast of China. The ANN models revealed the relationship of raw water quality, energy consumption, and effluent water quality. The effluent water quality could be predicted by the models. The clustering analysis method, an important data mining method, was used to classify the WTP data for building seasonal models. Meanwhile, an annual model was built by the whole data. It indicates that the prediction accuracy of seasonal models is better than the annual model by contrasting the e...
- Published
- 2014
- Full Text
- View/download PDF