Blind/Semi-blind Source Separation in complex rotating/reciprocating machinery

For the Department of Mechanical Engineering, Production Engineering, Machine Design and Automation (PMA) Section we are looking for an (Electro-mechanical) engineer with strong background and interest in signal processing, blind source separation, measurements and vibroacoustic condition monitoring of complex rotating/reciprocating machinery.

The proposed research track runs at the KU Leuven Noise and Vibration Research Group which currently counts 74 researchers and is part of the Mechanical Engineering Department, a vibrant environment of close to 250 researchers (www.mech.kuleuven.be). Doctoral training is provided in the framework of the Leuven Arenberg Doctoral School (https://set.kuleuven.be/phd).
The Noise and Vibration Research Group has a longstanding history and internationally highly recognized expertise in the fields of numerical modeling, engineering dynamics, automotive engineering, vibro-acoustic analysis, identification and robust optimal control of (non-)linear systems, active control, numerical modeling and lightweight structure design and analysis. The Noise and Vibration research group is also recognized for its yearly Acoustics (ISAAC) and Modal Analysis (ISMA) courses and for organizing the biennial ISMA Noise and Vibration Engineering Conference (www.isma-isaac.be). Furthermore, the group is Partner of the Strategic Research Centre Flanders Make and coordinates the Flanders Make Department of Mechatronics and Design Methods.
The research group's international research flavour is illustrated amongst others by the large portfolio of research projects (http://www.mech.kuleuven.be/en/pma/research/mod/projects) which includes regional, national and international funded activities through which the group cooperates with leading mechatronic and machine & vehicle-building companies in Flanders and throughout Europe.
http://www.mech.kuleuven.be/en/pma/research/mod/
Project
The vibroacoustic signature of a machine contains pivotal information about the state of the machine and its components. The sensors are placed as close as possible to the components of interest; however this is not always feasible due to restrictions such as the manufacturer’s warranty policy and inaccessibility. As a result an important difficulty in diagnosis of faults in components of rotating machinery is that the vibration signals (recorded by a transducer at a given point such as the location of a defective bearing) are always a mixture of ambient noise and vibrations produced by different nearby parts. This problem is encountered especially in complex systems where numerous components are tightly packed together, e.g. in engines and rotorcrafts. In order to solve this problem, the procedure of Blind Source Separation (BSS) has been proposed. BSS methods consist in recovering, from a finite set of observations recorded by sensors, the contributions of different physical sources independently from the propagation medium and without any a priori knowledge on the sources. BSS has been widely used in several areas of applications including: wireless and communication systems, radar and sonar systems, biomedical applications, speech and audio processing. However, although in these fields BSS has reached a level of maturity, when it comes to deal with vibration signals; it faces a number of difficulties.
The PhD research will focus on the development and application of methodologies in order to address the Blind Source Separation problem in the context of rotating machinery. The first objective will be the extension of the framework of Blind Source Separation in order to cover mechanical applications working under non-stable (fluctuating), variable or non-stationary operating conditions. The second objective will be the development of semi-blinded or guided separation techniques which will be based on some level of informedness. Both objectives focus to the health monitoring of complex rotating/reciprocating machinery. The performance and the effectiveness of the techniques will be evaluated, demonstrated and validated through numerical simulation, experimental studies and well established signal databases.

Profile
We are looking for a highly motivated, enthusiastic, communicative and eager to learn researcher with a Master of Science in Engineering (preferably in Mechanical or Electrical Engineering). The candidate should have a strong background and interest in signal processing, blind source separation, measurements and vibroacoustic condition monitoring of complex rotating/reciprocating machinery.
The candidate is expected to:
• Have a very good knowledge of English (spoken and written)
• Be team player
• Be able to work independently, accurately and methodically
• Have the willing to present research findings at national and international conferences
• Have the willing to publish research findings in international journals

Offer
Full-time employment in an international context
Starting a PhD track on this topic is required.
Start date: as soon as possible

Interested?
For more information please contact Prof. Dr. Ir. Konstantinos Gryllias, tel.: +32 16 32 30 00, mail: konstantinos.gryllias@kuleuven.be
You can apply for this job no later than October 11, 2015 via the online application tool (Bij publicatie komt hier automatisch de link naar de online sollicitatiepagina.)
KU Leuven carries out an equal opportunity and diversity policy.

  
 
 
 

follow us

PHM Society on Facebook Follow PHM Society on Twitter PHM Society on LinkedIn PHM Society RSS News Feed