4 ECTS credits
110 h study time

Offer 1 with catalog number 4018889FNR for all students in the 2nd semester at a (F) Master - specialised level.

Semester
2nd semester
Enrollment based on exam contract
Impossible
Grading method
Grading (scale from 0 to 20)
Can retake in second session
Yes
Taught in
English
Partnership Agreement
Under interuniversity agreement for degree program
Faculty
Faculteit Ingenieurswetenschappen
Department
Electricity
External partners
Université libre de Bruxelles
Educational team
Michel Kinnaert (course titular)
Activities and contact hours
24 contact hours Lecture
24 contact hours Seminar, Exercises or Practicals
Course Content

The valid fiche can be found at the following link : MATH-H503. Change the language to English in the dropdown menu on top of the page.

Residual generation by the parity space approach and by observer based methods; statistical change detection algorithms; change detection based on parameters estimation.

Teaching methods : the lectures alternate with exercises based on computer simulations.

Teaching material : copies of slides

Additional info

This course is an extended version of a 3 credit course.

The additional one credit is placed at the beginning of the course and aims at providing some prerequisite materials, namely:

- a refresher on stochastic processes and response of LTI systems to stochastic signals

- a review of Luenberger observer and Kalman filtering

The content of the 3 credit course is separated in two parts: design of fault indicators, also called residuals, and design of decision systems by adequate statistical processing of the residuals.

The first part includes residual generation by the parity space approach, by observer based methods and by parameters estimation based methods.

The second part addresses off-line and on-line statistical change detection/isolation algorithms

Lectures and lab sessions using MATLAB/SIMULINK alternate so that the students gain hand on experience on each algorithm and learn how to exploit the theoretical results to thoroughly validate their software codes.

Information can be found at the following link : MATH-H503. Change the language to English in the dropdown menu on top of the page.

Learning Outcomes

Algemene competenties

- ability to design a model based condition monitoring system

- understanding of the performance trade-offs in fault detection and isolation systems

- ability to validate in a systematic way software codes involving random signals

Information can be found in the course sheet at the following link : MATH-H503. Change the language to English in the dropdown menu on top of the page.

Grading

The final grade is composed based on the following categories:
Other Exam determines 100% of the final mark.

Within the Other Exam category, the following assignments need to be completed:

  • exam with a relative weight of 1 which comprises 100% of the final mark.

Additional info regarding evaluation

The oral evaluation consists of a question and answer session based on an individual report on the labs.  The focus is on checking the understanding of the main concepts, the hypotheses associated to each method and the way to combine the different tools to build a complete fault detection and isolation system.

Information can be found at the following link : MATH-H503. Change the language to English in the dropdown menu on top of the page.

Allowed unsatisfactory mark
The supplementary Teaching and Examination Regulations of your faculty stipulate whether an allowed unsatisfactory mark for this programme unit is permitted.

Academic context

This offer is part of the following study plans:
Master of Electromechanical Engineering: Aeronautics and Aerospace (only offered in Dutch)
Master of Electromechanical Engineering: Energy (only offered in Dutch)
Master of Electromechanical Engineering: Aeronautics
Master of Electromechanical Engineering: Energy