Detection of water quality failure events at treatment works using a hybrid two-stage method with CUSUM and random forest algorithms

Near-real-time event detection is crucial for water utilities to be able to detect failure events in their water treatment works (WTW) quickly and efficiently. This paper presents a new method for an automated, near-real-time recognition of failure events at WTWs by the application of combined stati...

Description complète

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gerald Riss, Michele Romano, Fayyaz Ali Memon, Zoran Kapelan
Format:	article
Langue:	EN
Publié:	IWA Publishing 2021
Sujets:	cusum event recognition online monitoring random forest water treatment works Water supply for domestic and industrial purposes TD201-500 River, lake, and water-supply engineering (General) TC401-506
Accès en ligne:	https://doaj.org/article/8880079e0fa541f9aede728543352a17
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

id	oai:doaj.org-article:8880079e0fa541f9aede728543352a17
record_format	dspace
spelling	oai:doaj.org-article:8880079e0fa541f9aede728543352a172021-11-06T10:08:33ZDetection of water quality failure events at treatment works using a hybrid two-stage method with CUSUM and random forest algorithms1606-97491607-079810.2166/ws.2021.062https://doaj.org/article/8880079e0fa541f9aede728543352a172021-09-01T00:00:00Zhttp://ws.iwaponline.com/content/21/6/3011https://doaj.org/toc/1606-9749https://doaj.org/toc/1607-0798Near-real-time event detection is crucial for water utilities to be able to detect failure events in their water treatment works (WTW) quickly and efficiently. This paper presents a new method for an automated, near-real-time recognition of failure events at WTWs by the application of combined statistical process control and machine-learning techniques. The resulting novel hybrid CUSUM event recognition system (HC-ERS) uses two distinct detection methodologies: one for fault detection at the level of individual water quality signals and the second for the recognition of faulty processes at the WTW level. HC-ERS was tested and validated on historical failure events at a real-life UK WTW. The new methodology proved to be effective in the detection of failure events, achieving a high true-detection rate of 82% combined with a low false-alarm rate (average 0.3 false alarms per week), reaching a peak F1 score of 84% as a measure of accuracy. The new method also demonstrated higher accuracy compared with the CANARY detection methodology. When applied to real-world data, the HC-ERS method showed the capability to detect faulty processes at WTW automatically and reliably, and hence potential for practical application in the water industry. HIGHLIGHTS The novel HC-ERS combines the conventional SPC-type method with RF advanced machine-learning technique to ultimately detect WTW-level failure events.; When applied on unseen data HC-ERS proved to be capable of detecting failure events in WTW processes in near-real-time.; HC-ERS outperformed threshold-based and CANARY event detection methods.; HC-ERS showed potential for practical application in the water industry.;Gerald RissMichele RomanoFayyaz Ali MemonZoran KapelanIWA Publishingarticlecusumevent recognitiononline monitoringrandom forestwater treatment worksWater supply for domestic and industrial purposesTD201-500River, lake, and water-supply engineering (General)TC401-506ENWater Supply, Vol 21, Iss 6, Pp 3011-3026 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	cusum event recognition online monitoring random forest water treatment works Water supply for domestic and industrial purposes TD201-500 River, lake, and water-supply engineering (General) TC401-506
spellingShingle	cusum event recognition online monitoring random forest water treatment works Water supply for domestic and industrial purposes TD201-500 River, lake, and water-supply engineering (General) TC401-506 Gerald Riss Michele Romano Fayyaz Ali Memon Zoran Kapelan Detection of water quality failure events at treatment works using a hybrid two-stage method with CUSUM and random forest algorithms
description	Near-real-time event detection is crucial for water utilities to be able to detect failure events in their water treatment works (WTW) quickly and efficiently. This paper presents a new method for an automated, near-real-time recognition of failure events at WTWs by the application of combined statistical process control and machine-learning techniques. The resulting novel hybrid CUSUM event recognition system (HC-ERS) uses two distinct detection methodologies: one for fault detection at the level of individual water quality signals and the second for the recognition of faulty processes at the WTW level. HC-ERS was tested and validated on historical failure events at a real-life UK WTW. The new methodology proved to be effective in the detection of failure events, achieving a high true-detection rate of 82% combined with a low false-alarm rate (average 0.3 false alarms per week), reaching a peak F1 score of 84% as a measure of accuracy. The new method also demonstrated higher accuracy compared with the CANARY detection methodology. When applied to real-world data, the HC-ERS method showed the capability to detect faulty processes at WTW automatically and reliably, and hence potential for practical application in the water industry. HIGHLIGHTS The novel HC-ERS combines the conventional SPC-type method with RF advanced machine-learning technique to ultimately detect WTW-level failure events.; When applied on unseen data HC-ERS proved to be capable of detecting failure events in WTW processes in near-real-time.; HC-ERS outperformed threshold-based and CANARY event detection methods.; HC-ERS showed potential for practical application in the water industry.;
format	article
author	Gerald Riss Michele Romano Fayyaz Ali Memon Zoran Kapelan
author_facet	Gerald Riss Michele Romano Fayyaz Ali Memon Zoran Kapelan
author_sort	Gerald Riss
title	Detection of water quality failure events at treatment works using a hybrid two-stage method with CUSUM and random forest algorithms
title_short	Detection of water quality failure events at treatment works using a hybrid two-stage method with CUSUM and random forest algorithms
title_full	Detection of water quality failure events at treatment works using a hybrid two-stage method with CUSUM and random forest algorithms
title_fullStr	Detection of water quality failure events at treatment works using a hybrid two-stage method with CUSUM and random forest algorithms
title_full_unstemmed	Detection of water quality failure events at treatment works using a hybrid two-stage method with CUSUM and random forest algorithms
title_sort	detection of water quality failure events at treatment works using a hybrid two-stage method with cusum and random forest algorithms
publisher	IWA Publishing
publishDate	2021
url	https://doaj.org/article/8880079e0fa541f9aede728543352a17
work_keys_str_mv	AT geraldriss detectionofwaterqualityfailureeventsattreatmentworksusingahybridtwostagemethodwithcusumandrandomforestalgorithms AT micheleromano detectionofwaterqualityfailureeventsattreatmentworksusingahybridtwostagemethodwithcusumandrandomforestalgorithms AT fayyazalimemon detectionofwaterqualityfailureeventsattreatmentworksusingahybridtwostagemethodwithcusumandrandomforestalgorithms AT zorankapelan detectionofwaterqualityfailureeventsattreatmentworksusingahybridtwostagemethodwithcusumandrandomforestalgorithms
_version_	1718443808379633664

Detection of water quality failure events at treatment works using a hybrid two-stage method with CUSUM and random forest algorithms

Documents similaires