Grant: Engage Grants Program
Queen's University
$10,375.00
Forecasting water main breaks in the City of Kingston water distribution network with artificial neural networks
FY 2011-12
Summary
Utilities Kingston (UK) is currently facing heavy costs to repair its aging buried water main assets. An average
of 65 major water main breaks are reported in a typical year in the Kingston water distribution network. These
breaks must be repaired at an average cost of $5,000-$10,000 per break. The high water main failure rate is
putting pressure on the Utility's operating budget and disrupting water services to customers. To address these
issues, UK has identified a need to partner with Dr. Filion at Queen's University to develop water main break
forecasting models to prioritize the replacement and relining of aging water mains in the City of Kingston
water distribution network. This new research partnership will enable UK to reduce water main repair costs and
to improve water quality at the customer's tap.
The project aims to develop water main break forecasting models based on multiple linear regression (MLR)
and artificial neural network (ANN) modelling to simulate water main failure rates in the City of Kingston
water network. The MLR and ANN models will enable UK to prioritize its water main replacement, cement
mortar lining, and cathodic protection programs in the next 5-10 years. The research will yield predictive
correlations between environmental factors (e.g., soil type, leakage) and observed break rates to help UK
develop water main installation and maintenance best practices that will reduce future break rates in the
Kingston network. The forecasting models will guide UK's buried asset management planning strategy and
help it allocate its limited operating budget in a more efficient manner. The forecasting models developed in
this research will be transferable to other municipalities who want to develop water main asset management
plans.
Program
Engage Grants Program
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
419443-2011
Name nom
Filion, Yves
Department département
Civil Engineering
Organization id
29
Institution établissement
Queen's University
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2011
Competition year année de concours
2011
Award amount
10375
Program id
EGP
Program nane en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1553
Committee name en
Ontario Internal Decision Committee
Committee name fr
Comité de décision interne pour l'Ontario
Area of application code
702
Area of application group en
Transportation systems and services
Area of application group fr
Services et systèmes de transport
Area of application en
Water
Area of application fr
Maritime
Research subject code
1000
Research subject group en
Civil engineering
Research subject group fr
Génie civil
Research subject en
Civil engineering
Research subject fr
Génie civil
Partie
1
Nb partie
1
Application title
Forecasting water main breaks in the City of Kingston water distribution network with artificial neural networks
Keyword
NSERC
Application summary
Utilities Kingston (UK) is currently facing heavy costs to repair its aging buried water main assets. An average
of 65 major water main breaks are reported in a typical year in the Kingston water distribution network. These
breaks must be repaired at an average cost of $5,000-$10,000 per break. The high water main failure rate is
putting pressure on the Utility's operating budget and disrupting water services to customers. To address these
issues, UK has identified a need to partner with Dr. Filion at Queen's University to develop water main break
forecasting models to prioritize the replacement and relining of aging water mains in the City of Kingston
water distribution network. This new research partnership will enable UK to reduce water main repair costs and
to improve water quality at the customer's tap.
The project aims to develop water main break forecasting models based on multiple linear regression (MLR)
and artificial neural network (ANN) modelling to simulate water main failure rates in the City of Kingston
water network. The MLR and ANN models will enable UK to prioritize its water main replacement, cement
mortar lining, and cathodic protection programs in the next 5-10 years. The research will yield predictive
correlations between environmental factors (e.g., soil type, leakage) and observed break rates to help UK
develop water main installation and maintenance best practices that will reduce future break rates in the
Kingston network. The forecasting models will guide UK's buried asset management planning strategy and
help it allocate its limited operating budget in a more efficient manner. The forecasting models developed in
this research will be transferable to other municipalities who want to develop water main asset management
plans.