Course content

This course give an introduction to digitalization technologies applied in industry, from automobile and aviation to maritime operation. We will focus on introducing date driven methods that are used for creating and simplifying models for prediction/classification. Some case studies related to model ship motion will also be presented, so that the students have a complete experience for analysis and modeling of raw data.
Course content:
- Digitalization introduction (State of the art)
- Fundamentals of Digital Twins: Physical Entities, Virtual Models and Services (simulation, verification, monitoring, diagnosis, prognostics, and health management)
- Data analytical overview, including data purification, down sampling and denoising
- Local & global sensitivity analysis approaches, such as Garson, EFAST and Sobol method
- Maritime Case studies

Learning outcome

After passed exam the student should have advanced knowledge within the academic field of digital twin, including entities, models and services.  The student should have knowledge about methods in the field of digital twin from a maritime point of view. Has thorough knowledge of how to find and model the variety of digital twin services. They should be able to apply knowledge and communicate results.     

The student should be able to perform basic digital twin applications, including understanding of physical entities, developing of virtual model and planning of digital services.

The student should be able to communicate extensive independent work and terminology of the academic field of digital twin applied to maritime systems.

Learning methods and activities

The course is given during two weeks, and is organized with lectures on background topics and an introduction to a case study. The case study will then be solved individually or in groups and documented in a project report. The total workload for the course is expected to be 2 weeks including independent research and literature survey supporting the project work.

Specific conditions

Recommended previous knowledge

Basic knowledge of programming, modelling, simulation and data analyses.