PhD Student in Deep Learning for Railway Catenary-Pantograph Monitoring

The Chair of Intelligent Maintenance Systems focuses on developing intelligent algorithms to improve performance, reliability and availability of complex industrial assets and making the maintenance more cost efficient. Our research focuses on deep learning, domain adaptation, hybrid approaches (combing physical performance models and deep learning algorithms), and deep reinforcement learning.

The Chair of Structural Mechanics & Monitoring focuses on development of algorithmic frameworks for structural health monitoring & system identification, nonlinear dynamics & vibration mitigation, data-driven & hybrid methods for condition assessment, and monitoring-driven decision support structures for predictive maintenance and life-cycle assessment.

Continual use and exposure to rough environments weaken critical components of railway assets exposing them to possible failures. This can adversely impact vehicle components, for instance in case of faults on the interacting catenary/pantograph system. One of the difficulties lies in understanding the dynamics of the highly interactive vehicle/catenary system. To timely detect damage, predict deterioration and assure safety, current railway vehicles are subjected to regular checks, which imply significant downtime, decrease in availability and an increase in operational costs.

The project will be embedded In-SErvice diagnostics of the cateNary/panTograph and wheelset axle systems through INtELligent algorithms. SENTINEL aims at developing diagnostic techniques to be applied in operation, for assessing the state of the pantograph/catenary system (and the wheelset axle -> which is considered in another PhD project). The strategy deploys heterogeneous sensing relying on coupling of vibration and optical sensing schemes.

You will drive the research in the field of deep learning applied to condition monitoring data from catenary-pantograph monitoring, in particular with the focus on the following tasks:

• Develop methodology for multi-modal learning
• Develop domain generalization algorithms that are robust to different operating conditions
• Develop a methodology for monitoring the system health and prediction of its evolution in time based on automatic processing of high frequency data
• Develop a methodology for pattern discovery and matching for temporal and spatial interrelationship

The position involves a close collaboration with involved industrial project partners (including Siemens and SBB) from different departments. It is further foreseen to collaborate with other railway operators who are collecting similar types of data on catenary-patrograph monitoring. The collaboration will be focused on for data collection, data pre-processing, development of the solutions and their knowledge transfer to the application field.

Moreover, the position involves:

• Supervision of Msc students
• Limited teaching responsibilities
• Involvement in academic activities (e.g., conference, seminar organisation,…)

We are looking for a PhD student with a strong analytical background and an outstanding Msc degree in Engineering, Computer Science, Physics, Applied Mathematics, or a related field. You should have a proven experience in deep learning and in the application of deep learning to solve a real-world problem. The candidate should have good programming skills in Python, in particular Tensorflow or Pytorch and have knowledge in signal processing (Wavelet/spectral analysis, time series processing). Professional command of English (both written and spoken) is mandatory. German is an advantage. We expect the candidate to be self-driven with strong problem solving abilities and out-of-the-box thinking. The duration of the PhD position is foreseen for three years.

We look forward to receiving your online application until December 15, 2021 including:

• Letter of motivation
• CV
• Brief research statement (one page) describing your project idea relevant to the job description, making connection to your experience in this area and the related work from the literature
• One publication (e.g. Msc thesis or preferably a conference or journal publication)
• Transcripts of all obtained degrees (in English)
• Contact details of at least two referees

Only complete applications containing all the required documents will be considered. Please note that we exclusively accept applications submitted through our online application portal. Applications via email or postal services will not be considered. The review of applications will continue until the position is filled, with the position to start as soon as possible.

For more information about the chair please visit: Intelligent Maintenance Systems and Structural Mechanics and Monitoring. Questions regarding the position should be directed to Prof. Dr. Olga Fink or Prof. Eleni Chatzi by email ofink@ethz.ch or chatzi@ibk.baug.ethz.ch (no applications).

In line with our values, ETH Zurich encourages an inclusive culture. We promote equality of opportunity, value diversity and nurture a working and learning environment in which the rights and dignity of all our staff and students are respected. Visit ourEqual Opportunities and Diversity websiteto find out how we ensure a fair and open environment that allows everyone to grow and flourish.