PhD in Deep Learning for Acoustic Diagnostics and Prognostics of Complex Systems 100 %

School: School of Engineering
Starting date: 1.9.2024

Your role

In collaboration with the Aerospace Structures & Materials (ASM) Department at the Delft University of Technology (TU Delft) and the company Hitachi Energy, we are now looking for an outstanding Ph.D. student.

The focus of the Ph.D. will be on physics-informed deep learning algorithms for acoustic diagnostics and prognostics of complex systems. This includes exploring how novel neural network algorithms can exploit physics and engineering knowledge of the system together with available acoustic data to improve acoustic diagnostics and prognostics.

• You will develop innovative approaches using state of the art statistical, machine learning and deep learning methods algorithms for detection, diagnostics and prognostics of incipient failures in industrial assets.
• You will combine engineering knowledge with data-science techniques (physics-informed machine learning).
• You will closely collaborate with our industry partners in order to implement your algorithms in the operational environment.
• The focus of your work will be on algorithm research and development, with relatively little data management/engineering.
• You will have the opportunity to co-supervise student research projects.
• You will be supported by experienced colleagues from the team in order to further develop your technical and scientific skills.
• Your daily work will typically allow for a high level of flexibility and freedom. 

The Ph.D. project will be part of a research project funded for max. 4 years. As part of our team, you will enjoy an exciting and rewarding international working environment, combining close industrial collaboration with multidisciplinary innovative research. The compensation will be according to the guidelines of the Swiss National Science Foundation (www.snf.ch).
 
The supervision of this Ph.D. project will be carried out by Dr. Manuel Arias Chao at the ZHAW and the Air Transport & Operations (ATO) group at TU Delft. The promotor of the PhD is Prof. Dr. Dimitrios Zarouchas from the Aerospace Structures & Materials Department at TU Delft. Upon successful completion of the PhD program, the doctoral degree will be awarded by the Delft University of Technology.

Your profile

• You have a master degree in engineering, physics, computer science, statistics, applied mathematics or a related discipline.
• You have programming experience in Python. Experience with TensorFlow and PyTorch is an advantage.
• You have experience with applying data analytical and machine learning methods.
• Experience with deep leaning algorithms is advantageous.
• You have high oral and written communication skills in English.
• You are curious to learn and develop new methods and algorithms and apply them in real industrial systems.
• You are motivated to develop your personal research skills, coached by experienced researchers. 

We encourage applications from proactive and self-motivated candidates with analytical thinking and strong problem-solving passion and abilities, good communication skills and original thinking.

This is what we stand for

Zurich University of Applied Sciences ZHAW is one of Switzerland's largest multidisciplinary universities of applied sciences, with over 14'000 students and 3'400 faculty and staff.

ZHAW is committed to gender-mixed and diverse teams in order to promote equality, diversity and innovation.

As one of the leading Engineering Faculties in Switzerland, the ZHAW School of Engineering emphasises topics which will be relevant in the future. Our 14 institutes and centres guarantee superior-quality education, research and development with an emphasis on the areas of energy, mobility, information and health.

The Institute of Data Analysis and Process Design (IDP) is a center of competence for the development and application of quantitative methods in the areas of data analysis and operations research. The Smart Maintenance Team of the IDP develops innovative solutions for intelligent condition monitoring, fault detection, diagnostics and prognostics of technical equipment.

Contact