Skip to content  

Werken bij de TU/e

PhD Physics-guided neural controllers for high-precision mechatronics

PhD Physics-guided neural controllers for high-precision mechatronics

Aanstellingsfunctie(s)
Promovendus
Faculteit(en)
Faculteit Electrical Engineering
FTE
1,0
Sluitdatum
30/08/2020
Aanvraagnummer
V36.4503

Functieomschrijving

Description of the position

This project focuses on the design of artificial intelligence (AI) based controllers for high-precision linear and rotary motors, utilized in lithography and industrial printing machines. This involves research in design and training of neural networks based on physical insight, neural feedforward control and stability analysis of neural-driven control systems. Validation has to be carried out on an industrial linear motor for the moving stage within a lithography machine. The research is part of the PGN Mechatronics NWO (Dutch Research Council) project and it will be conducted within the Control Systems (CS) group of the Department of Electrical Engineering, TU/e, in cooperation with several high-tech companies (ASML, Océ, Philips, IBS Precision Engineering and Prodrive).

Expanding markets for integrated circuits and 3D printing call for rapid development of more accurate and stable high-precision mechatronics for the semiconductor equipment and printing industries. The main limiting factors for positioning accuracy of high-precision mechatronics are parasitic friction and electromagnetic forces, which are hard to model using first principles. Therefore, data-driven artificial intelligence tools, such as neural networks, have great potential for addressing this challenge due to their universal approximation abilities.

The objective of this PhD research is to design new, physics-guided, neural controllers for data-driven intelligent compensation of parasitic forces that can meet the safety and real-time specifications of high-precision mechatronics.To this end, neural network design and training methods, data-driven control techniques and nonlinear identification methods will be exploited. Experimental validation will be done on an industrial linear motor for the moving stage within a lithography machine with positioning accuracy limited to 100µm by parasitic forces. The aim is to push accuracy closer to 10µm utilizing physics-guided neural controllers. Rotary motors for industrial printers will also be used for validation.

Main research directions

  • Physics-guided neural networks: physical insight will be exploited to dimension, structure and choose basis functions in physics-guided neural networks; specific neural network structures will be exploited to accelerate training algorithms (backpropagation, nonlinear least squares) and to enable separate training of different modules of the network; robustness to noisy data will be investigated.
  • Intelligent feedforward control and commutation: physics-guided neural networks will be used in combination with data-driven control methods to design intelligent feedforward control and commutation algorithms with plug-and-play capabilities.
  • Stability analysis: stability of neural network driven control systems will be investigated.

Control Systems group

The CS group research activities span all facets of systems and control theory, such as linear, nonlinear and hybrid systems theory, model predictive control, distributed control, machine learning for control, modeling and identification, formal methods in control. The CS group has a strong interconnection with industry via national and European funded projects in a variety of application areas like high-precision mechatronics, power electronics, and sustainable energy (mobility, transport, smart grids). CS owns an Autonomous Motion laboratory and hosts several high-tech setups. The PhD student will join the group and interact with the other members of the CS group (around 40 researchers), where he/she will participate in a mix of academic and industrial research activities. Research within the CS Group is characterized by personal supervision. The PhD student will have access to the advanced courses offered by the Dutch Institute for Systems and Control, and will attend the yearly Benelux Meeting on Systems and Control.

Functie-eisen

For the PhD position in this project, a candidate with a MSc degree in Systems and Control, Electrical Engineering, or Mechanical Engineering will be selected and hired as a doctoral student in the Control Systems Group for a 4-year period. The candidate should have the following competences:

  • You are a talented and enthusiastic young researcher.
  • Strong academic background in systems and control.
  • Affinity and/or interest in AI and/or mechatronics; practical experience with electrical motors would be welcome.
  • Good programming skills in Matlab and well-versed in Simulink; experience with DSpace would be welcome.
  • A team-player with excellent communication and cooperation skills in a multi-partner and multi-disciplinary project environment.
  • You are creative and ambitious, hard-working and persistent.
  • Ability to independently organize your work.
  • Good scientific writing skills.
  • Strong command of the English language (knowledge of Dutch is not required).

Arbeidsvoorwaarden

  • Challenging job in a dynamic and ambitious university and a stimulating internationally renowned research environment.
  • Full-time temporary appointment for 4 years.
  • Gross salary between € 2.325,00 and € 2.972,00.
  • An extensive package of fringe benefits (e.g. excellent technical infrastructure, the possibility of child care and excellent sports facilities).

Informatie en sollicitatie

Information

For more information about the project, please contact dr. Mircea Lazar (m.lazar[a]tue.nl):

https://www.tue.nl/en/research/researchers/mircea-lazar/

More information on employment conditions can be found here:

https://www.tue.nl/en/working-at-tue/why-tue/compensation-and-benefits/

Application

If interested, please use the ‘apply now’-button at the top of this page. You should upload the following:

  • a brief cover letter motivating your interest and suitability for the position;
  • a detailed curriculum vitae including research experience and any previous publications;
  • transcripts of academic records indicating courses taken (including grades);
  • half-page summary of your MSc thesis;
  • contact details of two relevant references (email, phone number).

Information

For more information about the project, please contact dr. Mircea Lazar (m.lazar[a]tue.nl):

https://www.tue.nl/en/research/researchers/mircea-lazar/

More information on employment conditions can be found here:

https://www.tue.nl/en/working-at-tue/why-tue/compensation-and-benefits/

Application

If interested, please use the ‘apply now’-button at the top of this page. You should upload the following:

  • a brief cover letter motivating your interest and suitability for the position;
  • a detailed curriculum vitae including research experience and any previous publications;
  • transcripts of academic records indicating courses taken (including grades);
  • half-page summary of your MSc thesis;
  • contact details of two relevant references (email, phone number).

Please note that you can upload 1 document of 10 MB. So if you have more than 1 document you will have to combine them.  Screening of applications will start as soon as applications are received and will continue until the position has been filled.

Applications by e-mail are not accepted!