Open Access
ARTICLE
Predicting the Construction Quality of Projects by Using Hybrid Soft Computing Techniques
Department of Civil Engineering, Republic of China Military Academy, Kaohsiung, 830, Taiwan
* Corresponding Author: Ching-Lung Fan. Email:
(This article belongs to the Special Issue: Soft Computing Applications of Civil Engineering including AI-based Optimization and Prediction)
Computer Modeling in Engineering & Sciences 2025, 142(2), 1995-2017. https://doi.org/10.32604/cmes.2025.059414
Received 07 October 2024; Accepted 23 December 2024; Issue published 27 January 2025
Abstract
The construction phase of a project is a critical factor that significantly impacts its overall success. The construction environment is characterized by uncertainty and dynamism, involving nonlinear relationships among various factors that affect construction quality. This study utilized 987 construction inspection records from 1993 to 2022, obtained from the Taiwanese Public Construction Management Information System (PCMIS), to determine the relationships between construction factors and quality. First, fuzzy logic was applied to calculate the weights of 499 defects, and 25 critical construction factors were selected based on these weight values. Next, a deep neural network was used to identify the relationship between the critical construction factors (input variables) and construction quality (output variable). Finally, the prediction model’s performance was evaluated to confirm the impact of these critical construction factors on project outcomes. This study employed an innovative hybrid soft computing technique, combining fuzzy logic and an artificial neural network, to effectively predict the relationship between critical construction factors and construction quality, achieving a model accuracy of 96.08%. Project managers can utilize the findings of this study to enhance project management practices and establish effective construction management strategies, thereby improving project construction quality.Keywords
Cite This Article

This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.