INTEGRASI ARTIFICIAL INTELLIGENCE DAN DIGITAL TWIN UNTUK PEMELIHARAAN INFRASTRUKTUR DI INDONESIA

Abstract

Infrastructure plays a critical role in the economic and social development of countries, including Indonesia. Traditional, reactive maintenance methods often result in high operational costs, service disruptions, and safety risks. This study investigates the integration of Artificial Intelligence (AI) and Digital Twin (DT) technologies, supported by Structural Health Monitoring (SHM), as a predictive and adaptive approach for infrastructure maintenance. Through a systematic literature review of 15 international and 5 Indonesian studies published in the last decade, the research synthesizes global best practices and examines their relevance to Indonesia’s infrastructure context. Findings indicate that DT enables real-time virtual representation of physical assets, AI enhances predictive accuracy through data-driven analysis, and SHM provides continuous structural condition monitoring. The integration of these technologies creates a synergistic framework that reduces downtime, optimizes operational costs, and extends asset lifespan. Despite promising international applications, Indonesia faces challenges such as limited sensor deployment, low data quality, high investment costs, and adaptation to tropical and disaster-prone conditions. This study highlights the theoretical and practical implications of AI-DT-SHM integration, offering an adaptive maintenance framework that addresses local constraints and bridges the gap between global trends and local implementation