Machine Learning and Condition Monitoring


Content, progress and pedagogy of the module

Learning objectives


  • Have fundamental knowledge on data driven machine learning methods and models
  • Have fundamental knowledge of the use of databases and common data formats to manage, store and process data
  • Have comprehension of the benefits of preventive and predictive maintenance and condition monitoring in the industrial sector
  • Have comprehension on the machine learning models and methods used in condition monitoring


  • Be able to analyse data for vibrational machinery condition monitoring and the fundamental effects of vibration Measuring equipment includes sensors, signal conditioners, and video cameras
  • Be able to analyse typical case studies, and identifications of malfunction
  • Be able to implement data driven modelling and machine learning based systems for condition monitoring and anomaly detection
  • Be able to assess the performance of data driven models for condition monitoring


  • Be able to monitor the condition and develop measurable preventive maintenance for given service industry problems
  • Be able to monitor machinery condition with vibration effects and computer vision using various electronic equipment and video cameras
  • Be able to evaluate and compare modern data driven models and algorithms for condition monitoring
  • Be able to apply a data driven approach to analyse, and implement condition monitoring methods
  • Be able to use frameworks to develop machine learning based condition monitoring systems

Type of instruction

The course module will be targeted with a mixture of lectures, self-preparatory presentation by students, and discussion on various real time case studies supplemented with e-learning activities.

Extent and expected workload

Since it is a 5 ECTS course module, the work load is expected to be 150 hours for the student.



Name of examMachine Learning and Condition Monitoring
Type of exam
Written or oral exam
Permitted aids
With certain aids:
For more information about permitted aids, please visit the course description in Moodle.
Assessment7-point grading scale
Type of gradingInternal examination
Criteria of assessmentThe criteria of assessment are stated in the Examination Policies and Procedures

Facts about the module

Danish titleMaskinlæring og tilstandsovervågning
Module codeE-APEL-K1-3C
Module typeCourse
Duration1 semester
Language of instructionEnglish
Empty-place SchemeYes
Location of the lectureCampus Esbjerg
Responsible for the module


Education ownerMaster of Science (MSc) in Engineering (Advanced Power Electronics)
Study BoardStudy Board of Build, Energy, Electronics and Mechanics in Esbjerg
DepartmentDepartment of Energy
FacultyThe Faculty of Engineering and Science