| Description: |
Systems are a collection of collaborating components that provide a service that the individual components cannot provide alone. Systems engineering provides a structured, multidisciplinary approach to managing the entire system lifecycle—from conception and design to operation and retirement. A significant portion of this lifecycle is spent in the operation phase, where maintenance plays an essential role in ensuring reliability, safety, and operational efficiency. Modern maintenance strategies aim to optimize timing and resource use. Just-in-time maintenance, performed shortly before failure, maximizes component lifespan, reduces environmental impact, and maintains product quality. Predictive maintenance leverages technologies such as the Internet of Things (IoT), cloud computing, and artificial intelligence (AI) to estimate component health, enabling proactive and efficient maintenance planning. Digital Twins are digital representations of physical systems. They support real-time monitoring, simulation, and continuous learning, enhancing predictive maintenance capabilities. By integrating Digital Twins with predictive algorithms, robust predictive maintenance systems can be designed. This thesis explores the architectural design of Digital Twin-based predictive maintenance systems, focusing on their features, challenges, and the application of predictive maintenance algorithms across different industrial case studies. |