Adaptive data-derived anomaly detection in the activated sludge process of a large-scale wastewater treatment plant

Research output: Contribution to journalArticleScientificpeer-review

Standard

Adaptive data-derived anomaly detection in the activated sludge process of a large-scale wastewater treatment plant. / Haimi, Henri; Mulas, Michela; Corona, Francesco; Marsili-Libelli, Stefano; Lindell, Paula; Heinonen, Mari; Vahala, Riku.

In: ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, Vol. 52, 01.06.2016, p. 65-80.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

APA

Vancouver

Author

Bibtex - Download

@article{1b5b069df73c454ab9712cc501fa690d,
title = "Adaptive data-derived anomaly detection in the activated sludge process of a large-scale wastewater treatment plant",
abstract = "This work examines real-time anomaly detection and isolation in a full-scale wastewater treatment application. The Viikinm{\"a}ki plant is the largest municipal wastewater treatment facility in Finland. It is monitored with ample instrumentation, though their potential is not yet fully exploited. One reason that prevents the use of the instrumentation in plant control is the occasional insufficient measurement performance. Therefore, we investigate an intelligent anomaly detection system for the activated sludge process in order to motivate a more efficient use of sensors in the process operation. The anomaly detection methodology is based on principal component analysis. Because the state of the process fluctuates, moving-window extensions are used to adapt the analysis to the time-varying conditions. The results show that both instrument and process anomalies were successfully detected using the proposed algorithm and the variables responsible for the anomalies correctly isolated. We also demonstrate that the proposed algorithm represents a convenient improvement for supporting the efficient operation of wastewater treatment plants.",
keywords = "Adaptive process monitoring, Anomaly detection, Principal component analysis, Wastewater treatment",
author = "Henri Haimi and Michela Mulas and Francesco Corona and Stefano Marsili-Libelli and Paula Lindell and Mari Heinonen and Riku Vahala",
year = "2016",
month = "6",
day = "1",
doi = "10.1016/j.engappai.2016.02.003",
language = "English",
volume = "52",
pages = "65--80",
journal = "ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE",
issn = "0952-1976",
publisher = "Elsevier Limited",

}

RIS - Download

TY - JOUR

T1 - Adaptive data-derived anomaly detection in the activated sludge process of a large-scale wastewater treatment plant

AU - Haimi, Henri

AU - Mulas, Michela

AU - Corona, Francesco

AU - Marsili-Libelli, Stefano

AU - Lindell, Paula

AU - Heinonen, Mari

AU - Vahala, Riku

PY - 2016/6/1

Y1 - 2016/6/1

N2 - This work examines real-time anomaly detection and isolation in a full-scale wastewater treatment application. The Viikinmäki plant is the largest municipal wastewater treatment facility in Finland. It is monitored with ample instrumentation, though their potential is not yet fully exploited. One reason that prevents the use of the instrumentation in plant control is the occasional insufficient measurement performance. Therefore, we investigate an intelligent anomaly detection system for the activated sludge process in order to motivate a more efficient use of sensors in the process operation. The anomaly detection methodology is based on principal component analysis. Because the state of the process fluctuates, moving-window extensions are used to adapt the analysis to the time-varying conditions. The results show that both instrument and process anomalies were successfully detected using the proposed algorithm and the variables responsible for the anomalies correctly isolated. We also demonstrate that the proposed algorithm represents a convenient improvement for supporting the efficient operation of wastewater treatment plants.

AB - This work examines real-time anomaly detection and isolation in a full-scale wastewater treatment application. The Viikinmäki plant is the largest municipal wastewater treatment facility in Finland. It is monitored with ample instrumentation, though their potential is not yet fully exploited. One reason that prevents the use of the instrumentation in plant control is the occasional insufficient measurement performance. Therefore, we investigate an intelligent anomaly detection system for the activated sludge process in order to motivate a more efficient use of sensors in the process operation. The anomaly detection methodology is based on principal component analysis. Because the state of the process fluctuates, moving-window extensions are used to adapt the analysis to the time-varying conditions. The results show that both instrument and process anomalies were successfully detected using the proposed algorithm and the variables responsible for the anomalies correctly isolated. We also demonstrate that the proposed algorithm represents a convenient improvement for supporting the efficient operation of wastewater treatment plants.

KW - Adaptive process monitoring

KW - Anomaly detection

KW - Principal component analysis

KW - Wastewater treatment

UR - http://www.scopus.com/inward/record.url?scp=84978477009&partnerID=8YFLogxK

U2 - 10.1016/j.engappai.2016.02.003

DO - 10.1016/j.engappai.2016.02.003

M3 - Article

AN - SCOPUS:84978477009

VL - 52

SP - 65

EP - 80

JO - ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE

JF - ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE

SN - 0952-1976

ER -

ID: 6666834