Digital Twin and AI in Construction

Abstract

Digital Twin technology is projected to reduce the industry’s costs by as much as $1.2 trillion per year as project design and operational efficiencies are improved. Data integration, unrealistic upfront costs and lack of skilled mankind is a hindrance in the universal adoption of these technologies. The aim of this study is to study the combined effect of AI and Digital Twin technologies on construction industry. This paper explores how the combination of these technologies solves problems to this problem in construction management and makes project results, including lower cost, more efficient time frame, and better decision making better. The approach for research is to be a quantitative methods using the structured surveys. It has sample of 40-60 professionals who have hands-on experience in combining Digital Twin and AI in the construction projects. Partial Least Squares Structural Equation Modeling (PLS-SEM) by means of Smart PLS software is used as a tool to analyze complex relations between key variables. The preliminary results show that Digital Twin and AI integration helps improve construction management in terms of efficiency of the project, reduction of errors, as well as optimizing resource allocation. But the current adoption is impeded by data interoperability issues, high setup costs, and the need for training of a specialist. On the basis of this study, a practical framework is provided which can help understand the drivers and the barriers to the adoption of the Digital Twin and AI Technologies in construction for a better understanding on the dual aspects from the perspective of the Technology Acceptance Model. The results helps policymakers, technology developers, and construction firms overcome implementation hindrances and gain the big benefit of these technologies.