Examination arrangement

Course content

The course is divided into the following 4 modules  

1. Preventive Maintenance

• Terminology related to predictive maintenance
• Innovation processes within predictive maintenance
• Establish goals and strategies for predictive maintenance
• Management of predictive maintenance  

2. Inspection and condition monitoring

• Prerequisites for inspection and condition monitoring
• Organization of inspection and condition monitoring
• Selected methods for inspection and condition monitoring
• Methodology for collecting condition data
• Methodology for analysis and washing of condition data  

3. Diagnosis and prognosis using condition data

• Maticematical models
• Machine learning
• Visualization of diagnosis and prognosis  

4. Maintenance decisions

• Use of diagnosis and prognosis derived from condition data, in maintenance decisions

Learning outcome

After completing the course, the candidate should have the following basic knowledge of, skills in and general competence, related to predictive maintenance.

The candidate has knowledge of: Collection of condition data on technical installations. Diagnosis of condition of technical installations Use of condition data in assessment of residual life Maintenance decisions based on knowledge of condition and remaining life How predictive maintenance can contribute to better resource utilization and optimal operational security. How knowledge of condition and remaining life can be used in the development of optimal maintenance Opportunities in using digital condition data in maintenance analyzes and decisions.

Skills: The candidate can: Participate in professional discussions about the use of predictive maintenance Choose favorable method for diagnosing the condition of technical installations Choose a methodology for collecting and assessing condition data Use tools for assessing degradation and residual life of electrical and mechanical equipment Visualize their assessments of degradation and longevity Use information about degradation and residual life in maintenance decisions Communicate consequences associated with using predictive maintenance.

General competence: The candidate has the following competence: Practical understanding and insight into how predictive maintenance affects: - reliability and longevity - health, environment and economy Practical understanding of and insight into the use of tools and methods used in predictive maintenance. Ability to formulate and discuss technical solutions in predictive maintenance with skilled workers and leading personnel on a professional basis. Be critical and reflective of predictive maintenance. Demonstrate an understanding of consequences with a focus on lifelong thinking. The candidates are familiar with key innovation processes within predictive maintenance The candidates are familiar with the implementation of digital tools in predictive maintenance.

Learning methods and activities

In addition to teaching in the physical space, all lectures to be streamed. Recorded lectures to be placed on blackboard

• Interactive lectures 
• Guest lecturers from the industry (internet based)
• Use of videos
• Digital exercises in blackboard
• Supervised excercises
• Laboratory excercise 
• Project work / problem based learning in groups

Mandatory work requirements:

Quizzes in the Black Board: 75% of the quizzes are required to be approved.

At least 12 blogs must be submitted in Blackboard and be approved to gain access to the exsam.

Compulsory assignments

• Quizz in BlackBoard
• Blogg in BlackBoard

Further on evaluation

Mandatory work from previous semester can be accepted by the Department by re-take of an examination if there have not been any significant changes later.

Allowed exam aids: Tekniske tabeller, Cappelen.

Re-sit examination in August. If there is a re-sit examination, the examination form may be changed from written to oral. 

Continuation and voluntary repetition / improvement can be carried out for some sub-evaluations without having to reassess both sub-evaluations in a topic. There is an opportunity to complain about partial assessments in this topic before all sub-evaluations have been completed.

Specific conditions

Recommended previous knowledge

Basic knowledge of programming, python or the like.

MAST2006 or the like.

Course materials

Will be announced at the start of the course.