PhD position "Development of regularized reconstructions for industrial computed tomography"

(ref. BAP-2023-13)

Laatst aangepast : 16/01/2023

The Manufacturing Processes and Systems (MaPS) group at the Department of Mechanical Engineering of KU Leuven, stands for the study of techniques, methods and devices that are used to manufacture and inspect parts of products and systems based on in-depth knowledge of the material, geometry and derived machine structures. Systematic data monitoring, analysis and management is used in this context, targeting system optimisation. Product specification, modelling, process planning and quality control are integrated aspects of the product-production cycle, for which the sustainability dimension is considered in a life cycle approach. This results in innovative manufacturing processes and systems that are developed in close collaboration with industrial partners. The team of manufacturing metrology research line in the MaPS investigates, develops, optimizes and implements measurement solutions for manufacturing quality control. The group’s expertise covers surface and 3D coordinate metrology using tactile and optical probes as well as X-ray Computed Tomography (XCT).

Project

Dimensional quality control of hidden or hardly accessible features of high added-value products, produced by e.g., additive manufacturing, is becoming feasible using Industrial X-ray Computed Tomography (XCT). However, reducing scanning time by e.g., acquiring corrupted (noisy or incomplete) XCT data while conserving good image reconstruction has remained a challenge up to now. This PhD project focuses on studying, developing and efficiently applying nonlinear regularization techniques on the tomographic reconstruction inverse problem related to XCT with corrupted data. The candidate will make extensive use of continuous optimization techniques and will need to be comfortable with scientific computing implementations. Variational regularization techniques and related algorithms will be studied on a first stage, while deep learning methods will be focused on a posterior stage. Reliability and an optimal computing time are the expected features of the algorithms.  

The PhD outputs (models, algorithms, software) are expected to be applied on academic parts as well as on an industrially relevant case study.

Profile

Successful candidates:

• hold a master’s in applied mathematics or computer science or any other comparable study with a solid mathematical background,
• have a profound knowledge in continuous optimization, signal processing and numerical implementations,
• have a working experience with coding in Python/R/C++.
• like to  work in a multidisciplinary team of international researchers.
• are fluent in English (both spoken and written) or willing to improve their language skills.

Strong plus:

• GPU programming experience (CUDA/OpenCL)
  

• Experience with computed tomography or any other 3D imaging technique.
• Experience in deep neural networks designing and implementation.
  

Offer

KU Leuven is among the top universities in Europe (ranked 48th in general and 45th in engineering according to Times Higher Education world university ranking) and the research performed in the Manufacturing Metrology group is renown in the scientific community (with 3 fellows of CIRP - International Academy for Production Engineering).

We offer:

• a research position in an enticing research environment at the cross-roads of computer science, applied mathematics and mechanical engineering in close contact with key industrial partners,
• an attractive salary package, complemented with multiple benefits (health insurance, access to university infrastructure and sports facilities, etc.),
• a thorough scientific education,
• the opportunity to participate at international conferences,
• to work towards obtaining a PhD degree from a highly-ranked university and become a well-trained, independent researcher.

We encourage everyone to apply for the position.

Interested?

For more information please contact Prof. dr. ir. Wim Dewulf, tel.: +32 16 37 28 81, mail: [email protected] or Dr. Patricio Guerrero, tel.: +32 16 32 24 38, mail: [email protected].

KU Leuven seeks to foster an environment where all talents can flourish, regardless of gender, age, cultural background, nationality or impairments. If you have any questions relating to accessibility or support, please contact us at [email protected].