Selected expert groups from the data innovation alliance will present themselves at this half-day event. Current projects, trends and potential collaborations will be presented, discussed and worked on in interactive sessions.
|Expert Group Break-out (1)
|Expert Group Break-out (2)
Kai Hencken is Corporate Research Fellow for “Physical and Statistical Modeling” at the ABB Corporate Research Center, Baden-Dättwil, Switzerland. He holds a Ph.D. and a habilitation in theoretical physics from the university of Basel, where he is currently a lecturer. He joined the ABB Corporate Research Center in Baden-Dättwil in 2005 as a member of the theoretical physics group. His research interests are the combination of physical modeling, data analytics, and statistical methods to solve problems related to industrial devices. He works predominantly on developing diagnostics and prognostics approaches for different products, covering the range from sensors and signal processing to mathematical methods in prognostics.
Predictive Maintenance is one of the main application areas of the Industrial Internet of Things. The wide deployment of sensors and their connectivity allows to collect big amounts of data from devices in the field. The exponential increase of computing power and the recent developments in data analytics and machine learning makes the application of advanced algorithms possible. We are also facing changes in the way maintenance work is done and how its importance is seen.
ABB is a technology company providing devices and solutions in the area of electrification and automation. Many of their offerings in the area of digitalization and specifically predictive maintenance are geared towards their own products. This leads to topics that are specific for these cases in addition to the common ones.
In my talk I will discuss some of these issues and how they can be addressed: The domain knowledge and the simulation capabilities within the company are one of the big assets of any manufacturer. Reusing this for predictive maintenance solutions is an important aspect. For highly reliable products failure data will remain scarce even for a large installed base. This is a major bottleneck for any data-driven approach and needs to be overcome. The focus of many solutions developed is to provide monitoring and diagnostics capabilities. The prognostics aspect and the proposal of actions to be taken to remedy potential problems are often more important for the final customer. Examples are taken predominantly from electrification and motion devices.
- 14:45 – 14:55 – Intro and introductions
- 14:55 – 15:30 – Presentation: Nicole Königstein, Chief Data Scientist, Head of AI & Quant Research, Wyden Capital AG: “Financial Times Series Prediction in the Age of Transformers”+ Open discussion and Q&A
- 15:30 – 16:00 – Break
- 16:00 – 16:30 – Presentation: Guillaume Raille, Engagement Director & Data Scientist at Unit8 SA: “From Contract to Insights: Unveiling the challenges of an advanced LLM application for computable insurance contracts”+ Open discussion and Q&A
- 16:30 – 17:00 – Discussion on topics that might be relevant for the DIA in the future and how to organize