Course content

The course will introduce students with the principles of predictive maintenance facilitated by digital twins. Central to the concept of digital twins is the optimization of physical sensor usage on real assets. The fundamental idea involves constructing a simulation model, utilizing analytical, finite element, or big data models, to replicate the behavior of the physical asset. This digital twin is then equipped with virtual sensors that furnish supplementary information crucial for predictive maintenance and decision support. Implementation of the digital twin can take the form of a swift local edge, a gradual IoT cloud solution, or a combination of both for optimal flexibility. This approach not only minimizes reliance on physical sensors but also enhances adaptability in deploying digital twins tailored to specific operational needs. The course contains a selection of the following topics:

• Modelling and simulation
• State and parameter estimations/filters
• Actuator and sensor systems
• Condition monitoring and predictive maintenance
• Inverse methods
• Edge and cloud solutions

More details about the curriculum will provided during the start of semester.

Learning outcome

Knowledge

Students will gain a comprehensive understanding of the fundamental principles underlying digital twin modeling and simulation for predictive maintenance. This encompasses acquiring knowledge about sensors, data filtering techniques, inverse methods for load identification, and data processing strategies crucial for decision support. Additionally, students will receive foundational knowledge concerning edge and IoT solutions, as well as familiarity with digital modeling and simulation tools. In particular, upon completion of the course:

• The student knows the basic principal of digital twins and predictive maintenance
• The student knows modeling methods for digital twins
• The student knows various method for filtering
• The student knows about edge and IoT solutions
• The student understands the limits of digital twins
• The student understands how simple and complex systems may be modelled, simulated and visualized

Skills

Upon completion of the course:

• The student can model and simulate a physical system
• The student is able to develop a digital twin of a simple system
• The student is able to implement various data filtering methods
• The student is able to implement digital twins for predictive maintenance
• The student can analyze the system in the time-domain
• The student can visualize simulations of the system

General competence

Upon completion of the course:

• The student is able to use digital tools for simulation of physical systems
• The student can reflect on the usefulness of simulations for solving real world problems
• The student can formulate scientific problems, propose solutions, and present results both orally and in writing to a technical audience
• The student can make evaluations about societal and ethical aspects of technological developments

Learning methods and activities

Learning activities generally include a mix of lectures, tutorials and practical lab/project work. A constructivist approach for learning is endorsed, with focus on problem solving and practical application of theory.

Compulsory assignments

• Compulsory learning activities

Specific conditions

Required previous knowledge

The course has no prerequisites. It is a requirement that students are enrolled in the study programme to which the course belongs.

Course materials

An updated course overview, including curriculum is presented at the start of the semester.

Credit reductions