Intelligent Monitoring of Engineering Systems

 

Key Info

Basic Information

Degree:
Master
Semesters:
Summersemester
Lecturer:
Univ.-Prof. Dr.-Ing. Bernd Markert
Language:
English

Further Information

Contact

Name

Bernd Markert

Institutsleiter, Rektoratsbeauftragter für Alumni

Phone

work
+49 241 80 94600

Email

E-Mail
 

Content

The elective course „Intelligent Monitoring of Engineering Systems“ links artificial intelligence / machine learning with the field of sensor-driven monitoring of engineering systems. The focus of the course is on practical group work, so the participants will apply the basics learned during the first half of the semester to solve a project task during the second one.

Topics

  • Introduction: monitoring of engineering systems
  • hands on: MATLAB
    • scalars & vectors
    • scripts
    • plotting
    • data import and export (*.csv, *.xls, *.ods, *.txt)
  • sensing and data acquisition
    • measurement chain
    • sensors
    • data acquisition & conversion processes
  • signal processing
    • continuous- & discrete-time signals
    • (Fast) Fourier Analysis & Transform (FFT)
    • window functions
    • spectral leakage
    • digital filters
  • Machine Learning (ML)
    • data preprocessing
    • applications
  • Non-destructive Testing (NDT)
    • wave propagation
    • Acoustic Emission (AE) analysis
    • Tomography
    • Thermography
  • Structural Health Monitoring (SHM)
    • elastic guided waves for damage detection
    • condition monitoring of a CNC milling machine

 

Further information

Course Requirements

Programming skills in

  • MATLAB
  • (alt.: Python)

are helpful.
A MATLAB-hands-on is offered.

 

Course Objectives

The participants acquire basic knowledge in:

  • Sensing
  • Signal processing
  • Machine learning
  • Non-Destructive Testing (NDT)
  • Structural Health Monitoring (SHM)
  • Data pre- and postprocessing using MATLAB

 

Teaching and Learning Methods

The course curriculum consists of seminar lectures followed by a semester project. During the seminar lectures, the students will receive the necessary theoretical background to independently plan and execute the project in small groups. Consultation hours are offered to discuss challenges and problems arising during the course of the project. Finally, each group presents their achievements and results live and in form of a written report.

Accompanying literature

Nazarchuk, Z., Skalskyi, V., Serhiyenko, O., Acoustic Emission – Methodology and Application. Springer. 2017.

Farrar, C. R., Worden, K., Structural Health Monitoring: A Machine Learning Perspective. Wiley & Sons. 2013.

Goodfellow, I., Bengio, Y., Courville, A., Deep Learning. MIT Press. 2016.