Peng Cheng, Wu Zeming, Zhang Shudi, Lin Boran, Nie Lei, Tian Weilu, Zang Hengchang
NMPA Key Laboratory for Technology Research and Evaluation of Drug Products, School of Pharmaceutical Sciences, Cheeloo College of Medicine, Shandong University, Shandong, Jinan 250012, China.
Beijing Fresenius Kabi Pharmaceutical Co.,Ltd, Beijing 102600, China.
Water Res. 2025 May 1;275:123165. doi: 10.1016/j.watres.2025.123165. Epub 2025 Jan 18.
Water quality monitoring is one of the critical aspects of industrial wastewater treatment, which is important for checking the treatment effect, optimizing the treatment technology and ensuring that the water quality meets the standard. Chemical oxygen demand (COD) is a key indicator for monitoring water quality, which reflects the degree of organic matter pollution in water bodies. However, the current methods for determining COD values have drawbacks such as slow speed and complicated operation, which hardly meet the demand of online monitoring. This article firstly proposed a novel quantitative analysis method based on NIR spectroscopy and multi-preprocessing stacking, successfully enabling real-time online monitoring of COD values during industrial wastewater treatment. First, the existing swarm intelligence algorithm was enhanced to optimize the hyperparameters of various base models. Next, multiple spectral preprocessing techniques were innovatively combined with a stacking strategy to construct multi-preprocessing stacking models, enabling comprehensive extraction of effective spectral information. Finally, various combinations of base models were evaluated, leading to the selection of the multi-preprocessing stacking model with optimal performance. The results indicate that the model achieves excellent predictive performance and strong generalization ability. For equalization tank samples, the R and RMSE values were 0.8640 and 326.6845 mg/L, respectively. For secondary settling tank samples, the R and RMSE values were 0.8798 and 15.1917 mg/L, respectively. Compared to traditional single and stacking models, the RMSE was reduced by at least 12.75 % and 5.11 %, respectively. In addition, the method has a relatively low modeling cost and offers interpretability. This study presents an efficient and straightforward solution for the online monitoring of COD values in industrial wastewater treatment, laying a solid technical foundation for the efficient management of industrial wastewater and the protection of water resources and the ecological environment.
