EUVIMEDEUVIMED entdecken
Crossref

Prediction model of dissolved oxygen mixture in wastewater treatment based on dual attention mechanism

Leilei Liu, Fei Zheng, Zhe Jia

Journal of Environmental Management · 2026

DOI: 10.1016/j.jenvman.2026.129808 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Environmental Management, 2026. Verfasst von Leilei Liu und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical Engineering, Ningxia University, Yinchuan, 750000, China. Hauptthemen laut MEDLINE: Oxygen, Wastewater, Waste Disposal, Fluid. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: Ningxia Hui Autonomous Region Natural Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dissolved oxygen (DO) is core to wastewater treatment, and its accurate prediction is critical for aeration optimization and energy conservation. To address the limitations of existing models in capturing the temporal dynamics and multivariate couplings of DO time series, this study proposes a hybrid DA-BiLSTM-RBF model integrating parallel dual-stage attention, bidirectional long short-term memory (BiLSTM) and radial basis function (RBF) network, with hyperparameters optimized via Bayesian optimization. The temporal attention identifies critical time steps, while the feature attention quantifies contributions of key process parameters; the RBF network outperforms traditional fully connected layers in nonlinear dynamic modeling, especially for DO in abrupt change regions. Validated on real operational data from wastewater treatment plants (WWTPs), the model achieves high accuracy with a coefficient of determination (R2) of 0.980. Ablation studies confirm that removing feature attention reduces R2 to 0.893, while removing the complete dual attention mechanism plummets R2 to 0.056; the RBF network cuts the MAE of DO prediction in abrupt change regions by 63.39% relative to fully connected layers. This work provides an effective approach for precise DO control and energy-efficient aeration operation in WWTPs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

OxygenWastewaterWaste Disposal, FluidModels, TheoreticalBayes TheoremRadial Basis Function NetworksLong Short Term Memory

Stichwörter der Autor:innen

Data-driven modelingDissolved oxygen predictionDual attention mechanismWastewater treatment optimization

Substanzen

OxygenWastewater

Autor:innen und Institutionen

  • School of Mechanical Engineering, Ningxia University, Yinchuan, 750000, China.
  • Basic Experimental Teaching and Engineering Training Center, North Minzu University, Yinchuan, 750000, China.
  • School of Mechanical Engineering, Ningxia University, Yinchuan, 750000, China. Electronic address: jiazhe125@nxu.edu.cn.

Förderung

  • Ningxia Hui Autonomous Region Natural Science Foundation

Zitieren

APA

Liu, L., Zheng, F., & Jia, Z. (2026). Prediction model of dissolved oxygen mixture in wastewater treatment based on dual attention mechanism. Journal of Environmental Management. https://doi.org/10.1016/j.jenvman.2026.129808

Vancouver

Liu L, Zheng F, Jia Z. Prediction model of dissolved oxygen mixture in wastewater treatment based on dual attention mechanism. Journal of Environmental Management. 2026. doi:10.1016/j.jenvman.2026.129808

BibTeX
@article{Liu2026,
  author = {Liu, Leilei and Zheng, Fei and Jia, Zhe},
  title = {Prediction model of dissolved oxygen mixture in wastewater treatment based on dual attention mechanism},
  journal = {Journal of Environmental Management},
  year = {2026},
  doi = {10.1016/j.jenvman.2026.129808}
}
Kostenlos starten →