TY - JOUR
T1 - Ensemble CNN Model for Effective Pipe Burst Detection in Water Distribution Systems
AU - Kim, Sehyeong
AU - Jun, Sanghoon
AU - Jung, Donghwi
N1 - Funding Information:
This work was supported by a National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT) (No. NRF-2021R1A5A1032433).
Publisher Copyright:
© 2022, The Author(s), under exclusive licence to Springer Nature B.V.
PY - 2022/10
Y1 - 2022/10
N2 - Various data-driven anomaly detection methods have been developed for identifying pipe burst events in water distribution systems (WDSs); however, their detection effectiveness varies based on network characteristics (e.g., size and topology) and the magnitude or location of bursts. This study proposes an ensemble convolutional neural network (CNN) model that employs several burst detection tools with different detection mechanisms. The model converts the detection results produced by six different statistical process control (SPC) methods into a single compromise indicator and derives reliable final detection decisions using a CNN. A total of thirty-six binary detection results (i.e., detected or not) for a single event were transformed into a six-by-six grayscale heatmap by considering multiple parameter combinations for each SPC method. Three different heatmap configuration layouts were considered for identifying the best layout that provides higher CNN classification accuracy. The proposed ensemble CNN pipe burst detection approach was applied to a network in Austin, TX and improved the detection probability approximately 2% higher than that of the best SPC method. Results presented in this paper indicate that the proposed ensemble model is more effective than traditional detection tools for WDS burst detection. These results suggest that the ensemble model can be effectively applied to many detection problems with primary binary results in WDSs and pipe burst events.
AB - Various data-driven anomaly detection methods have been developed for identifying pipe burst events in water distribution systems (WDSs); however, their detection effectiveness varies based on network characteristics (e.g., size and topology) and the magnitude or location of bursts. This study proposes an ensemble convolutional neural network (CNN) model that employs several burst detection tools with different detection mechanisms. The model converts the detection results produced by six different statistical process control (SPC) methods into a single compromise indicator and derives reliable final detection decisions using a CNN. A total of thirty-six binary detection results (i.e., detected or not) for a single event were transformed into a six-by-six grayscale heatmap by considering multiple parameter combinations for each SPC method. Three different heatmap configuration layouts were considered for identifying the best layout that provides higher CNN classification accuracy. The proposed ensemble CNN pipe burst detection approach was applied to a network in Austin, TX and improved the detection probability approximately 2% higher than that of the best SPC method. Results presented in this paper indicate that the proposed ensemble model is more effective than traditional detection tools for WDS burst detection. These results suggest that the ensemble model can be effectively applied to many detection problems with primary binary results in WDSs and pipe burst events.
KW - Convolutional neural network
KW - Ensemble
KW - Pipe burst detection
KW - Statistical process control methods
KW - Water distribution system
UR - http://www.scopus.com/inward/record.url?scp=85136597622&partnerID=8YFLogxK
U2 - 10.1007/s11269-022-03291-1
DO - 10.1007/s11269-022-03291-1
M3 - Article
AN - SCOPUS:85136597622
SN - 0920-4741
VL - 36
SP - 5049
EP - 5061
JO - Water Resources Management
JF - Water Resources Management
IS - 13
ER -