Progress management of prefabricated construction projects based on combination of machine learning and multi-objective optimization

Zhao Zeng and Ying Gao

International Journal of Low-Carbon Technologies, 2025, vol. 20, 881-892

Abstract: The high speed of implementation of prefabricated constructions has caused them to become one of the most popular and widely used construction elements today. Prefabricated construction projects are sensitive to uncertainties that may cause delays in project progress due to the need for high coordination and interdependence between installation activities. Hence, it is essential to monitor the progress of the installation to avoid actual project delays. Separating the prefabricated module from the environment, recognizing its type and also identifying its installation mode are three essential prerequisites for managing the progress of construction projects based on prefabricated modules. Considering the variety of separation of prefabricated modules from the environment, and the difficulty of identifying its type as well as identifying the installation mode of each module, a new method with three basic steps was used in this study. These three actions consist of the following: (1) use of NSGA-II to frame segmentation and determine regions of interest; (2) module type identification using Convolutional Neural Network (CNN) and Cuckoo Search Optimization (CSO) in conjunction; (3) a combination of CNN and CSO used to evaluate the installation quality in each category of modules. The case study's findings demonstrated that, in both the prefabricated module type identification and progress analysis stages, the suggested approach outperformed alternative models in terms of accuracy, precision, recall, and F-Measure indices. The suggested model's superiority over the compared models is further supported by the receiver operating characteristic analysis.

Keywords: progress management; prefabricated construction; multi-objective optimization; NSGA-II; convolutional neural network; cuckoo search optimization (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1093/ijlct/ctae207 (application/pdf)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:oup:ijlctc:v:20:y:2025:i::p:881-892.

Access Statistics for this article

International Journal of Low-Carbon Technologies is currently edited by Saffa B. Riffat

More articles in International Journal of Low-Carbon Technologies from Oxford University Press
Bibliographic data for series maintained by Oxford University Press ().