Defect Risk Assessment Using a Hybrid Machine Learning Method

Abstract

Defects pose considerable risks to construction projects in terms of both cost and quality, and identifying defects thus is crucial to effective construction quality management. In this study, data for 45 cases were obtained from the Public Construction Management Information System (PCMIS) of Taiwan. A combined machine learning method comprising association rule mining and a Bayesian network was employed to identify the relationships between defects as well as their occurrence probabilities. A total of 33 association rules and 11 high-risk defects were detected. The Swiss cheese model (SCM) was used to formulate four defensive layers and analyze the high-probability, strong-correlation, and multipath characteristics of high-risk defects. Specifically, the defect quality control inspection not implemented had the highest risk values. In the correlation analysis, more high-risk defects meant reduced inspection scores and construction quality; risk values and inspection scores had a strong negative correlation (r=−0.85). This study proposes innovative hybrid machine learning to evaluate the risks of defects, and the SCM was implemented to establish the risk factors and hierarchical relationships of the defects to determine their priority order in management. Future studies should analyze the time series of defects and employ sequential data to forecast their order of occurrence and relationships at different times, thereby increasing the understanding of dynamic construction projects.