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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Demand forecasting based infrastructure asset management


    Additional title:

    KSCE J Civ Eng


    Contributors:

    Published in:

    Publication date :

    2004-03-01


    Size :

    8 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English





    Infrastructure Asset Management Education

    Smadi, Omar / Akili, Waddah | Transportation Research Record | 2006


    Asset management of irrigation infrastructure

    Moorhouse, I. | British Library Online Contents | 1999


    Modern Railway Infrastructure Asset Management

    Jovanovic, S. | British Library Conference Proceedings | 2005


    Asset management for irrigation and drainage infrastructure

    Malano, H. M. / Chien, N. V. / Turral, H. N. | British Library Online Contents | 1999