Semi-Supervised Clustering for Architectural Modularisation

Sofia Feist,Vítor Esteves,Miguel Pires,António Aguiar Costa,Luís Sanhudo

doi:10.3390/buildings12030303

Abstract

Modular construction allows for a faster, safer, better controlled, and more productive construction process, yielding quality results with low risk and controlled costs. However, despite the potential advantages of this methodology, its adoption has remained slow due to the reasonably high degree of standardisation and repetition that projects require, inexorably clashing with the unique building designs created to meet the clients’ needs. The present article proposes performing a modularisation process after the building design is complete, reaping most benefits of modular construction while preserving the unique vision and design of the building. This objective is achieved by implementing a semi-supervised methodology reliant on the clustering of individual rooms and subsequent user validation of the obtained clusters to identify base modules representative of each cluster. The proposed methodology is applied in a case study of an existing apartment complex, in which the modularisation process was previously performed manually—thus serving as a baseline. The acquired results display a 99.6% reduction in the modularisation process’ duration, while maintaining a 96.4% Normalised Mutual Information Score and a 93.3% Adjusted Mutual Information Score, justifying the continuous development and assessment of the methodology in future works.

Highlights

Productivity in the Architecture, Engineering and Construction (AEC) industry has lagged behind other industry sectors for decades [1]
The AEC industry is increasingly shifting from traditional onsite methods towards modular construction, i.e., the process in which building components are prefabricated offsite, in controlled factory conditions, and subsequently transported and assembled onsite [2]
A semi-supervised methodology was developed based on the clustering of room data and subsequent user validation of the obtained clusters, resulting in the identification of a set of modules that can be industrialised for manufacture

Summary

Introduction

Productivity in the Architecture, Engineering and Construction (AEC) industry has lagged behind other industry sectors for decades [1]. To address this issue, the AEC industry is increasingly shifting from traditional onsite methods towards modular construction, i.e., the process in which building components are prefabricated offsite, in controlled factory conditions, and subsequently transported and assembled onsite [2]. The benefits of offsite fabrication have been extensively documented and include faster, safer, and more productive construction processes, as well as higher-quality products with lower risks [3]. Combined with the higher coordination of processes within the construction facility and the optimised logistics of just-in-time delivery, this results in less waste and more sustainable projects [5,6]

Methods

Results

Conclusion