The Role of Digital Twins in Engineering Management: A Review of Predictive Maintenance and System Optimization Strategies

Abstract

Digital twins represent a transformative approach in engineering management, providing virtual replicas of physical systems that allow for real-time monitoring, predictive maintenance, and system optimization. This narrative review explores the role of digital twins in enhancing predictive maintenance and optimizing engineering systems, focusing on how these virtual models contribute to operational efficiency and reliability. The review synthesizes recent literature, highlighting the key benefits and challenges of implementing digital twins across various industries. It discusses the integration of digital twins with IoT, big data analytics, and artificial intelligence, which significantly amplifies their potential. Despite their proven advantages, challenges such as high costs, data quality issues, and system complexity pose barriers to widespread adoption. The review concludes with recommendations for future research aimed at overcoming these challenges, standardizing digital twin applications, and exploring advanced AI-driven optimization techniques. These findings underscore the critical importance of digital twins in the future of engineering management, offering significant implications for enhancing system performance and reliability.