top of page

Development of Component Health Indicators from Fingerprint Cycles of industrial Assets




Job description

The capability of robustly modeling the degradation of components in complex machinery is critical to data-driven prognostics and health management (PHM) systems in manufacturing. It allows to:
• optimize the cost and resource efficiency of maintenance operations,
• prevent unplanned machine downtime and secondary damages due to critical failures.

Industrialized predictive maintenance solutions are yet scarce among most real-world manufacturing use cases: A large amount of data is required to robustly model degradation considering the high level of process variance most machines are subject to and the cost of acquiring enough run-to-failure data is prohibitively high in most use cases. By acquiring diagnostics data from a “fingerprint” reference cycle, which is engineered to exhibit information regarding the state of key components of the system, most of the process variance can be removed from the equation. Thus, machine learning solutions in “small data” scenarios become possible.
A solution based on the intrinsic sensors of a machine is under successful development with one of our industry partners and has been demonstrated by multiple machine tool manufacturers. We aim to reduce the development effort for similar solutions and to make the solution more accessible to machinery with a low level of digitization. For this purpose, we plan to demonstrate its feasibility solely relying on the data acquired via a retrofit vibration sensor.

remote or Alpnach, Switzerland

Study Project, Master Thesis, Bachelor Thesis

May 1, 2023

To apply send us an e-mail to:


Your task will be to design a data preprocessing, training, and evaluation pipeline to produce machine learning models capable of outputting reliable health indicator for multiple components of the system. Your aim will be to demonstrate this procedure within the presented use case using real-world data from a machine tool manufacturer.

Essential requirements

• good communication skills and a willingness to closely collaborate with our team,
• an understanding of machine and deep learning, particularly applied to time-series data,
• proficiency in Python and a common ML/DL framework (Pytorch, Tensorflow),
• a basic understanding of version control (Git) and databases (SQL),
• a desire to produce results with a lasting impact.

(plus not must)

What we offer you

Our CTO, a skilled practitioner in the industrialization of deep learning solutions, will be your direct supervisor. We hope to grant you a great learning experience as a machine learning engineer with an interesting real-world use case at your fingertips.

If you believe our expectations to match, contact us. We will be happy to hear from you!

All qualified applicants will receive consideration for employment without regard to color, religion, sex, sexual orientation, gender identity, national origin or disability.
EU Citizenship is required for most positions.

bottom of page