Predicting the Construction Quality of Projects by Using Hybrid Soft Computing Techniques

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.