EUVIMEDEUVIMED entdecken
Crossref

Data-driven differentiable model for dynamic prediction and control in wastewater treatment

Yun-Peng Song, Wen-Zhe Wang, Yu-Qi Wang, Wan-Xin Yin, Jia-Ji Chen, Hao-Ran Xu, Hao-Yi Cheng, Fang Ma, Han-Tao Wang, Ai-Jie Wang, Hong-Cheng Wang

Water Research · 2025-08 · 282 · 123772

DOI: 10.1016/j.watres.2025.123772 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water Research, 2025-08. Verfasst von Yun-Peng Song und 10 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Urban Water Resource and Environment, School of Environment, Harbin Institute of Technology, Harbin 150090, PR China; School …. Hauptthemen laut MEDLINE: Wastewater, Waste Disposal, Fluid, Models, Theoretical, Water Purification. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Science, Technology and Innovation Commission of Shenzhen Municipality.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wastewater treatment plants, while critical for environmental protection, face mounting challenges in operational efficiency and sustainability due to increasing urbanization and stricter environmental standards. In this study, we introduce an innovative continuous-time neural framework based on Neural Ordinary Differential Equations (Neural ODEs) to enhance the modeling of sewage treatment processes. Addressing the dual challenges of operational efficiency and sustainable development in urban wastewater treatment plants (WWTPs), our methodology marks a significant departure from traditional approaches by implementing a continuous-time neural framework that captures the inherent dynamics of wastewater treatment processes while reducing computational demands by 95 % compared to discrete-time models. We analyzed operational data from three full-scale WWTPs over a year, demonstrating that our model not only achieves superior prediction accuracy (R² > 0.95) with various input window sizes but also significantly reduces memory usage-from 111.88-12,484.59 MB to just 17.74-50.92 MB. Notably, our framework exhibits robust performance even with up to 30 % missing data, uncovering new process insights through interpretable feature attribution. Further integration with reinforcement learning has led to a 21.9 % reduction in aeration energy consumption compared to conventional open-loop control strategies while adhering to effluent quality standards. This research establishes a novel paradigm for intelligent wastewater management that optimizes operational efficiency and promotes environmental sustainability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

WastewaterWaste Disposal, FluidModels, TheoreticalWater PurificationNeural Networks, Computer

Stichwörter der Autor:innen

Digital transformationEnergy efficiencyNeural ordinary differential equationsProcess control optimizationReinforcement learning

Substanzen

Wastewater

Autor:innen und Institutionen

  • State Key Laboratory of Urban Water Resource and Environment, School of Environment, Harbin Institute of Technology, Harbin 150090, PR China; School of Eco-Environmental, Harbin Institute of Technology, Shenzhen 518055,…
  • School of Eco-Environmental, Harbin Institute of Technology, Shenzhen 518055, PR China.
  • College of the Environment, Liaoning University, Shenyang 110036, PR China.
  • CAS Key Laboratory of Environmental Biotechnology, Research Center for Eco-Environmental Sciences, Chinese Academy of Sciences, Beijing 100085, PR China.
  • State Key Laboratory of Urban Water Resource and Environment, School of Environment, Harbin Institute of Technology, Harbin 150090, PR China.
  • PowerChina Eco-environmental Group Co., Ltd, Guangdong, Shenzhen 518102, PR China.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Science, Technology and Innovation Commission of Shenzhen Municipality

Zitieren

APA

Song, Y. P., Wang, W. Z., Wang, Y. Q., Yin, W. X., Chen, J. J., Xu, H. R., Cheng, H. Y., Ma, F., Wang, H. T., Wang, A. J., & Wang, H. C. (2025). Data-driven differentiable model for dynamic prediction and control in wastewater treatment. Water Research, 282, 123772. https://doi.org/10.1016/j.watres.2025.123772

Vancouver

Song YP, Wang WZ, Wang YQ, Yin WX, Chen JJ, Xu HR, et al. Data-driven differentiable model for dynamic prediction and control in wastewater treatment. Water Research. 2025;282:123772. doi:10.1016/j.watres.2025.123772

BibTeX
@article{Song2025,
  author = {Song, Yun-Peng and Wang, Wen-Zhe and Wang, Yu-Qi and Yin, Wan-Xin and Chen, Jia-Ji and Xu, Hao-Ran and Cheng, Hao-Yi and Ma, Fang and Wang, Han-Tao and Wang, Ai-Jie and Wang, Hong-Cheng},
  title = {Data-driven differentiable model for dynamic prediction and control in wastewater treatment},
  journal = {Water Research},
  year = {2025},
  volume = {282},
  pages = {123772},
  doi = {10.1016/j.watres.2025.123772}
}
Kostenlos starten →