Course syllabus - Diagnostics in Energy Systems

Objectives

The course aims to introduce advanced monitoring and diagnostics methods in energy technologies and systems. Participants will gain insight into the use of physics-based and data-driven techniques, focusing on different machine learning techniques, for fault detection, identification, and prognosis. The course also aims to provide an understanding of how these methods support condition-based maintenance and contribute to increased reliability, efficiency, and sustainability in energy production, transportation and consumption.

Learning outcomes

After completing the course, the student should be able to:

1. Describe the fundamental concepts of process monitoring and diagnostics in energy systems.
2. Explain the principles, strengths, and limitations of different data processing and diagnostics methods.
3. Apply data analytics and fault identification methods based on numerical simulations and measurement data.
4. Compare and evaluate different machine learning techniques for diagnostics applications.
5. Analyze real or simulated data to detect faults and predict remaining useful life.
6. Design a basic diagnostic system for condition monitoring in power plants or related facilities.

Course content

The course covers monitoring and diagnostics of important sustainable energy technologies (e.g. batteries, heat pumps) and energy systems (e.g. power system, HVAC system), with a focus on understanding and applying methods for fault detection and condition monitoring. Included topics:

• Data-driven approaches: statistics, machine learning, and deep learning
• Hybrid methods combining physical and data-driven techniques
• Fault detection, identification, and remaining useful life estimation
• Implementation of simple diagnostic systems
• industrial case studies and future technological developments

Specific requirements

120 credits within an engineering program, such as energy engineering, building and construction, environmental engineering or industrial economy program, which include 7.5 credits in mathematics and 7.5 credits in programming or equivalent. In addition, Swedish course 3 or Swedish level 3 and English course 6 or English level 2 are required. For courses given entirely in English exemption is made from the requirement in Swedish course 3 or Swedish level 3.

Examination

PRO1, Project report, 5.5 credits, Learning outcomes: 3-6, grades Fail (U), 3, 4 or 5.

SEM1, Seminar, 2 credits, Learning outcomes: 1-5, grades Pass (G) or Fail (U).

A student who has a certificate from MDU regarding disability study support, can request adaptions for the examination. It is the examiner who takes decisions on any adaptions, based on the certificate and other conditions.

Grade

Grading scale: 5, 4, 3