AI, knowledge transfer, Flemish industry, Adoption of AI
The AI Impulse program is an initiative of the Flemish government to support innovative academic research and industrial technology transfer initiatives in Flanders around AI.
It focuses on four main research challenges in the field of AI:
- data science for supporting complex decision making;
- delivering artificial intelligence to the edge;
- interactions between independently programmed AI systems;
- communicating and collaborating seamlessly with humans.
The EluciDATA Lab is mainly participating in this program by contributing to challenge 1 and 4 and coordinating proof-of-concepts (PoCs) around:
Prognostics and health monitoring for ageing wind turbines (in the framework of challenge 1):
The objective of this use case is to study how data-driven and knowledge-based models can reinforce one another by combining them in a hybrid methodology to perform more accurate prognostics and management of ageing industrial machinery. This includes research towards improved techniques for:
- Diagnostics, for characterizing the health state of the machine, in function of its degradation;
- Prognostics, for monitoring the evolution of the health state & the degradation process, towards remaining useful life prediction;
- Decision support, for providing stakeholder-centric insights w.r.t. aspects in a machine’s health state that influence its remaining lifetime.
Smart environments supporting humans in their tasks (in the framework of challenge 4):
The aim of this proof-of-concept is to demonstrate how advanced AI technologies can contribute to the realisation of smart environments relevant to the Flemish industry, supporting its users in performing their tasks in the most possibly correct, efficient and safe way.
As a technological contribution towards the realisation of this proof-of-concept, the EluciDATA Lab focuses on the realisation of a technology demonstrator for recognising user activities and activities of daily living, deriving the daily routines of the monitored users and flagging deviations from these routines.
Start date: 01/07/2019
End date: 31/12/2020
More information on the program:
This research received funding from the Flemish Governement under the Onderzoeksprogramma Artificiële Intelligentie (AI) Vlaanderen" program.