Infrastructure asset management provides a framework to handle both short-and long-term planning for the maintenance and rehabilitation of infrastructure. In this study, as major demand forecasting methodologies, artificial neural networks (ANNs) and multiple regression methodologies have been reviewed. For sewer demand forecasting, two forecasting models, artificial neural networks and multiple regression models, were developed and their results were compared. Research findings indicated that the multiple regression model has the ability to explain the relationship between the predictor variables, while the ANN model better represents the non-forecasting allows asset managers to predict the future sewer demand, thus asset managers can identify “critical” sewers (i.e., current hydraulic capacity not meeting the future demand) by comparing the current hydraulic capacity with the future demand. Identifying and rehabilitating “critical” sewers before any major failure occur can prevent health and environmental hazards and lead to cost savings.
Demand forecasting based infrastructure asset management
KSCE J Civ Eng
KSCE Journal of Civil Engineering ; 8 , 2 ; 165-172
01.03.2004
8 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Infrastructure Asset Management
TIBKAT | 1.2014 -
Infrastructure Asset Management Education
Transportation Research Record | 2006
|Asset management of irrigation infrastructure
British Library Online Contents | 1999
|Modern Railway Infrastructure Asset Management
British Library Conference Proceedings | 2005
|Levels of Uncertainty in Infrastructure Asset Management
Transportation Research Record | 2021
|