Early cost estimating of road tunnel construction using neural networks

K. Petroutsatou, E. Georgopoulos, S. Lambropoulos, J. P. Pantouvakis

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

Road tunnel construction is subject to underground uncertainties and risks, and as such it is difficult to predict the final construction cost, especially at the conception phase where issues are evaluated and important design decisions are made. A system assisting in the early cost estimation of road tunnels would therefore be of great value as it would allow the quick costing of alternative and more economical solutions. The development of such an early cost estimation system is discussed in this paper. First, the basic parameters (geological, geometrical, and work quantities-related) affecting temporary and permanent support and final construction cost are determined. After that, appropriate real-world data derived from the analysis of 33 twin tunnels of 46km total length constructed for the Egnatia Motorway in northern Greece from 1998 to 2004 and related to work quantities is collected and normalized. Appropriate price lists are then applied to calculate the costs; subsequently, cost-estimating models are developed using two types of neural networks: (1)the multilayer feed-forward network; and (2)the general regression neural network. Finally, these models are compared against real quantities and costs for accuracy and robustness. The main conclusion is that the models developed are fit for their purpose and may lead to fairly accurate work quantities and cost estimates of road tunnels.

Original languageEnglish
Pages (from-to)679-687
Number of pages9
JournalJournal of Construction Engineering and Management - ASCE
Volume138
Issue number6
DOIs
Publication statusPublished - Jun 2012
Externally publishedYes

Fingerprint

Cost estimating
Tunnels
Neural networks
Costs
Road construction
Multilayers
Roads
Cost estimation
Construction costs

Keywords

  • Construction costs
  • Estimation
  • Neural networks
  • Tunnel construction

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Strategy and Management
  • Industrial relations
  • Building and Construction

Cite this

Early cost estimating of road tunnel construction using neural networks. / Petroutsatou, K.; Georgopoulos, E.; Lambropoulos, S.; Pantouvakis, J. P.

In: Journal of Construction Engineering and Management - ASCE, Vol. 138, No. 6, 06.2012, p. 679-687.

Research output: Contribution to journalArticle

Petroutsatou, K. ; Georgopoulos, E. ; Lambropoulos, S. ; Pantouvakis, J. P. / Early cost estimating of road tunnel construction using neural networks. In: Journal of Construction Engineering and Management - ASCE. 2012 ; Vol. 138, No. 6. pp. 679-687.
@article{00d32d28cba047f6bff5b02cf1b1a43b,
title = "Early cost estimating of road tunnel construction using neural networks",
abstract = "Road tunnel construction is subject to underground uncertainties and risks, and as such it is difficult to predict the final construction cost, especially at the conception phase where issues are evaluated and important design decisions are made. A system assisting in the early cost estimation of road tunnels would therefore be of great value as it would allow the quick costing of alternative and more economical solutions. The development of such an early cost estimation system is discussed in this paper. First, the basic parameters (geological, geometrical, and work quantities-related) affecting temporary and permanent support and final construction cost are determined. After that, appropriate real-world data derived from the analysis of 33 twin tunnels of 46km total length constructed for the Egnatia Motorway in northern Greece from 1998 to 2004 and related to work quantities is collected and normalized. Appropriate price lists are then applied to calculate the costs; subsequently, cost-estimating models are developed using two types of neural networks: (1)the multilayer feed-forward network; and (2)the general regression neural network. Finally, these models are compared against real quantities and costs for accuracy and robustness. The main conclusion is that the models developed are fit for their purpose and may lead to fairly accurate work quantities and cost estimates of road tunnels.",
keywords = "Construction costs, Estimation, Neural networks, Tunnel construction",
author = "K. Petroutsatou and E. Georgopoulos and S. Lambropoulos and Pantouvakis, {J. P.}",
year = "2012",
month = "6",
doi = "10.1061/(ASCE)CO.1943-7862.0000479",
language = "English",
volume = "138",
pages = "679--687",
journal = "Journal of Construction Engineering and Management - ASCE",
issn = "0733-9364",
publisher = "American Society of Civil Engineers (ASCE)",
number = "6",

}

TY - JOUR

T1 - Early cost estimating of road tunnel construction using neural networks

AU - Petroutsatou, K.

AU - Georgopoulos, E.

AU - Lambropoulos, S.

AU - Pantouvakis, J. P.

PY - 2012/6

Y1 - 2012/6

N2 - Road tunnel construction is subject to underground uncertainties and risks, and as such it is difficult to predict the final construction cost, especially at the conception phase where issues are evaluated and important design decisions are made. A system assisting in the early cost estimation of road tunnels would therefore be of great value as it would allow the quick costing of alternative and more economical solutions. The development of such an early cost estimation system is discussed in this paper. First, the basic parameters (geological, geometrical, and work quantities-related) affecting temporary and permanent support and final construction cost are determined. After that, appropriate real-world data derived from the analysis of 33 twin tunnels of 46km total length constructed for the Egnatia Motorway in northern Greece from 1998 to 2004 and related to work quantities is collected and normalized. Appropriate price lists are then applied to calculate the costs; subsequently, cost-estimating models are developed using two types of neural networks: (1)the multilayer feed-forward network; and (2)the general regression neural network. Finally, these models are compared against real quantities and costs for accuracy and robustness. The main conclusion is that the models developed are fit for their purpose and may lead to fairly accurate work quantities and cost estimates of road tunnels.

AB - Road tunnel construction is subject to underground uncertainties and risks, and as such it is difficult to predict the final construction cost, especially at the conception phase where issues are evaluated and important design decisions are made. A system assisting in the early cost estimation of road tunnels would therefore be of great value as it would allow the quick costing of alternative and more economical solutions. The development of such an early cost estimation system is discussed in this paper. First, the basic parameters (geological, geometrical, and work quantities-related) affecting temporary and permanent support and final construction cost are determined. After that, appropriate real-world data derived from the analysis of 33 twin tunnels of 46km total length constructed for the Egnatia Motorway in northern Greece from 1998 to 2004 and related to work quantities is collected and normalized. Appropriate price lists are then applied to calculate the costs; subsequently, cost-estimating models are developed using two types of neural networks: (1)the multilayer feed-forward network; and (2)the general regression neural network. Finally, these models are compared against real quantities and costs for accuracy and robustness. The main conclusion is that the models developed are fit for their purpose and may lead to fairly accurate work quantities and cost estimates of road tunnels.

KW - Construction costs

KW - Estimation

KW - Neural networks

KW - Tunnel construction

UR - http://www.scopus.com/inward/record.url?scp=84862152230&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862152230&partnerID=8YFLogxK

U2 - 10.1061/(ASCE)CO.1943-7862.0000479

DO - 10.1061/(ASCE)CO.1943-7862.0000479

M3 - Article

VL - 138

SP - 679

EP - 687

JO - Journal of Construction Engineering and Management - ASCE

JF - Journal of Construction Engineering and Management - ASCE

SN - 0733-9364

IS - 6

ER -