Cost Prediction of Tunnel Construction Based on Interpretative Structural Model and Stacked Sparse Autoencoder

Cost management plays a vital role in ensuring the successful execution of different engineering projects, with precise costing serving as the cornerstone of effective cost management strategies. Recently, the machine learning technique offers an accurate and efficient method for forecasting constru...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Engineering letters Jg. 32; H. 10; S. 1966
Hauptverfasser: Zhou, Jing-Qun, Liu, Qi-Ming, Ma, Chang-Xi, Li, Dong
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Hong Kong International Association of Engineers 01.10.2024
Schlagworte:
Construction costs
Construction engineering
Cost analysis
Deep learning
Machine learning
Prediction models
Project management
Structural models
Tunnel construction
ISSN:1816-093X, 1816-0948
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Cost management plays a vital role in ensuring the successful execution of different engineering projects, with precise costing serving as the cornerstone of effective cost management strategies. Recently, the machine learning technique offers an accurate and efficient method for forecasting construction expenses, introducing a novel approach to cost accounting other than conventional calculation techniques. This paper provides an overview of the current research landscape in the realm of cost prediction utilizing machine learning, also addresses some new research focuses and limitations. By utilizing highway tunnel engineering as a case study, this study employs an Interpretative Structural Model (ISM) to analyze the primary factors influencing construction costs. Subsequently, a construction cost prediction model is developed, leveraging a Stacked Sparse Autoencoder (SSAE) network within a deep learning framework. Last, the proposed model is trained using real construction projects as samples. Results show that there are some good prediction outputs with a remarkably low mean absolute percentage error of 0.71%. Thereby, they verified the identifying precision of key influencing factors and the reliability of the cost prediction model.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1816-093X
1816-0948