Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2016 Aug 8:6:31303.
doi: 10.1038/srep31303.

Prediction of Filamentous Sludge Bulking using a State-based Gaussian Processes Regression Model

Yiqi Liu  1   2 , Jianhua Guo  2 , Qilin Wang  2 , Daoping Huang  1
Affiliations

Prediction of Filamentous Sludge Bulking using a State-based Gaussian Processes Regression Model

Yiqi Liu et al. Sci Rep. .

Abstract

Activated sludge process has been widely adopted to remove pollutants in wastewater treatment plants (WWTPs). However, stable operation of activated sludge process is often compromised by the occurrence of filamentous bulking. The aim of this study is to build a proper model for timely diagnosis and prediction of filamentous sludge bulking in an activated sludge process. This study developed a state-based Gaussian Process Regression (GPR) model to monitor the filamentous sludge bulking related parameter, sludge volume index (SVI), in such a way that the evolution of SVI can be predicted over multi-step ahead. This methodology was validated with SVI data collected from one full-scale WWTP. Online diagnosis and prediction of filamentous bulking sludge with real-time SVI prediction was tested through a simulation study. The results showed that the proposed methodology was capable of predicting future SVIs with good accuracy, thus providing sufficient time for predicting and controlling filamentous sludge bulking.

PubMed Disclaimer

Figures

Figure 1
Figure 1. The schematic of construction of prediction model and fault prognosis (SVI: sludge volume index; OS GPR: One-step Gaussian Processes Regression; MS GPR: Multi-step Gaussian Processes Regression; y: SVI; y−: SVI − 2σ; y+: SVI + 2σ).
Figure 2
Figure 2. Schematic diagram of a full-scale oxidation ditch process.
Figure 3
Figure 3. Comparisons of Gaussian processes for micro sludge bulking diagnosis with different covariance functions (covSE: Squared-Exp kernel; covNN: Neural Network kernel; covMatérniso: Matérniso kernel; covAdd: Addictive kernel) and other models (RBF: Radical Basis Function; DeepNN: Deep Neural Network; PLS: Partial Squares Least; More details about the Kernel can see Supplementary Information).
Figure 4
Figure 4. Comparisons of prognosis with different multi-steps ahead prediction models for serious sludge bulking diagnosis.
Figure 5
Figure 5. Fault alarms and model uncertainty analysis.
See this image and copyright information in PMC

References

    1. Guo J. et al. Control filamentous bulking caused by chlorine-resistant Type 021N bacteria through adding a biocide CTAB. Water research 46, 6531–6542 (2012). - PubMed
    1. Olsson G. ICA and me – A subjective review. Water Research 46, 1585–1624 (2012). - PubMed
    1. Martins A. M. P., Pagilla K., Heijnen J. J. & van Loosdrecht M. C. M. Filamentous bulking sludge—a critical review. Water Research 38, 793–817 (2004). - PubMed
    1. Dürrenmatt D. J. & Gujer W. Data-driven modeling approaches to support wastewater treatment plant operation. Environmental Modelling & Software 30, 47–56 (2012).
    1. Mogens H., Willi G., Takashi M. & Mark V. L. Activated sludge models ASM1, ASM2, ASM2d and ASM3. (IWA publishing, 2000).

Publication types

LinkOut - more resources