Year: 2024
Type: article
Abstract: In response to issues such as high process load and potential risks of failing to meet discharge standards caused by sudden water pollution incidents in combined industrial and domestic wastewater treatment plants, this study focused on the wastewater treatment plant in an industrial park. The Autoregressive Integrated Moving Average (ARIMA) algorithm was utilized to construct an influent water quality prediction and anomaly warning model. Autocorrelation function (ACF), partial autocorrelation function (PACF), and augmented Dickey-Fuller (ADF) tests are employed to determine the optimal parameters for predicting chemical oxygen demand (COD), ammonia nitrogen (NH3-N), total nitrogen (TN), and total phosphorus (TP), optimizing the water quality prediction models. The impact of different monitoring frequencies and prediction steps on the model's performance were studied. Furthermore, an anomaly warning model for water quality was developed using an autoencoder (AE) and K-nearest neighbors (KNN) algorithm. This work provides a scientific basis for wastewater treatment plants to proactively respond to sudden water pollution events and lays a theoretical foundation for the intelligent transformation of traditional wastewater treatment plants.
Authors: Yaorong Shu, Linghao Chen, Tianming Wu, Mengjie Song, Wen Zhang, Juan Mao
Institution: Huazhong University of Science and Technology
Language: English
Subfield: Waste Management and Disposal
Field: Environmental Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4404123086
