Issue |
E3S Web of Conf.
Volume 393, 2023
2023 5th International Conference on Environmental Prevention and Pollution Control Technologies (EPPCT 2023)
|
|
---|---|---|
Article Number | 02014 | |
Number of page(s) | 5 | |
Section | Ecological Protection and Sustainable Development Research | |
DOI | https://doi.org/10.1051/e3sconf/202339302014 | |
Published online | 02 June 2023 |
Research on water quality prediction based on PE-CNN-GRU hybrid model
1 College of Logistics Engineering, Shanghai Maritime University, Shanghai 201306, China
2 Shanghai Urban Construction Design & Research Institute (Group) Co., Ltd., Shanghai
* Corresponding author’s e-mail address: 1397731887@qq.com
Sewage treatment is a complex and nonlinear process. In this paper, a prediction method based on convolutional neural network (CNN) and gated recurrent unit (GRU) hybrid neural network is proposed for the prediction of dissolved oxygen concentration in sewage treatment. Firstly, akima 's method is used to complete the filling preprocessing of missing data, and then the integrated empirical mode decomposition (EEMD) algorithm is used to denoise the key factors of water quality data. Pearson correlation analysis is used to select better water quality parameters as the input of the model. Then, CNN is used to convolve the data sequence to extract the feature components of sewage data. Then, the CNN-GRU hybrid network is used to extract the feature components for sequence prediction, and then the predicted output value is obtained. The mean absolute error (MAE), root mean square error (RMSE) and mean square error (MSE) were used as evaluation criteria to analyze the prediction results of the model. By comparing with RNN model, LSTM model, GRU model and CNN-LSTM model, the results show that the PCA-EEMD-CNN-GRU (PE-CNN-GRU) hybrid model proposed in this paper has significantly improved the prediction accuracy of dissolved oxygen concentration.
© The Authors, published by EDP Sciences, 2023
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.