1. Prediction of influent wastewater quality based on wavelet transform and residual LSTM.
- Author
-
Zhang, Wen, Zhao, Jiangpeng, Quan, Pei, Wang, Jiawei, Meng, Xiaoyu, and Li, Qun
- Subjects
WAVELET transforms ,SEWAGE ,SEWAGE disposal plants ,CHEMICAL reduction - Abstract
Accurate prediction on influent wastewater quality is of great importance to energy saving and chemical dosage reduction of wastewater treatment plants (WWTPs). However, the existing methods ignore the data noise caused by water sensors working in harsh conditions and the intrinsic variable dynamics inherent in the time series of wastewater quality. To tackle this problem, we propose a novel approach called wt-ResLSTM (w avelet t ransform and Res idual L ong S hort- T erm M emory) to predict the influent wastewater quality. Specifically, we adopt wavelet transform and semi-soft thresholding to remove the noise from influent wastewater quality data adaptively. Then, we use autoencoder to learn the latent representation of the recent fluctuation of wastewater quality to capture its transient uncertainty. Further, the residual LSTM is adopted to learn both the long-term and short-term sequential dependencies of influent wastewater quality from the historical wastewater quality and the latent representation of its recent fluctuation. Experiments on the dataset from a large-scale urban WWTP in Beijing demonstrate that the proposed wt-ResLSTM approach outperforms state-of-the-art techniques in predicting influent wastewater quality in terms of level accuracy and directional accuracy. • This paper proposes a novel approach called wt-ResLSTM for the prediction on influent wastewater quality. • The wt-ResLSTM approach considers both noise removal and transient uncertainty in recent fluctuations of wastewater quality. • The wt-ResLSTM approach can be used to accomplish precise control of WWTPs for energy saving and chemical dosage reduction. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF