BAIYu-xin,TIANLi,WANGQing-jiao,et al.Early Warning and Risk Control for Total Nitrogen Exceeding Discharge Standard in Wastewater Treatment Plants Based on Machine Learning[J].China Water & Wastewater,2025,41(19):109-115.
Early Warning and Risk Control for Total Nitrogen Exceeding Discharge Standard in Wastewater Treatment Plants Based on Machine Learning
China Water & Wastewater[ISSN:1000-4062/CN:12-1073/TU]
volume:
第41卷
Number:
第19期
Page:
109-115
Column:
Date of publication:
2025-10-01
- Keywords:
- wastewater treatment plant; grey correlation analysis; machine learning; critical value exceeding the discharge standard; prediction of effluent total nitrogen
- Abstract:
- Total nitrogen (TN) is a critical parameter for assessing river water quality. Regulating the TN in the effluent from wastewater treatment plants is of significant importance for effective river water quality management. This study collected a dataset comprising 5 108 instances of online monitoring operational data from a wastewater treatment plant in Shenzhen, and selected seven indicators with a correlation degree equal or greater than 0.5 using grey correlation analysis, to accurately predict the TN in the effluent of a wastewater treatment plant. Subsequently, three machine learning models—specifically, the support vector machine (SVM), XGBoost, and LightGBM—were employed to predict the TN in the effluent. Among these models, LightGBM demonstrated the best goodness of fit and achieved the highest prediction accuracy. Finally, key indicator warning values affecting the TN exceeding the discharge standard were identified through the analysis of production data. These included an influent C/N ratio equal or lesser than 6, dissolved oxygen equal or lesser than 1.6 mg/L or DO greater 2.2 mg/L, and mixed liquor suspended solids (MLSS) equal or lesser than 4 500 mg/L. The effluent TN was effectively controlledand maintained within the limit specified in the discharge standard by integrating these parameters with the prediction model.
Last Update:
2025-10-01