The EluciDATA Lab of Sirris successfully initiates three new thematic ICON projects on AI
With the Flemish Policy Plan on Artificial Intelligence, which started in 2019, Flanders invests 32 million euros annually in Artificial Intelligence (AI). As part of this plan, VLAIO launched a special call for thematic ICON projects on Artificial Intelligence (AI-ICON) with the aim to bridge the gap between research results in the field of artificial intelligence and its applications in Flemish industry.
ICON projects (Interdisciplinary Cooperative Research) allows multidisciplinary research teams of scientists and industry partners to work together to develop innovative solutions that then find their way into the market offerings of the participating partners and beyond. For the special ICON call on AI, the EluciDATA Lab of Sirris, identified 3 topics with a high industrial added value in Flanders, in collaboration with 3 consortia of academic and industrial partners:
- TRACY (Trace Analytics) aims to investigate how to optimally use the log data generated by industrial assets and refine existing AI and machine learning techniques targeted at time series analysis. To this end, TRACY will research how to handle the complexities of log data, e.g., the heterogeneity of the industrial assets, the lack of standardisation amongst log data and the scalable interactive visualisation of the heterogeneous data. The research is validated on complex industrial use cases as optimising the performance of compressors and decreasing the service cost of electrophotographic machines. The consortium consists of Xeikon, CMC, Datylon, I-Care and Yazzoom, and the EluciDATA Lab as a research partner.
- CONSCIOUS (Contextual aNomaly deteCtIon for cOmplex indUstrial aSsets) focusses on context-aware anomaly detection in industrial machines and processes. In these complex environments, anomaly detection remains a big challenge caused by the highly dynamic conditions in which these assets operate. The overall objective is to research effective solutions to achieve a more accurate, robust, timely and interpretable anomaly detection in complex, heterogenous data from industrial assets by accounting for confounding contextual factors. The results will be validated on multiple real-world use cases in different domains. In this project, the EluciDATA Lab will collaborate with Skyline Communications, Duracell Batteries, I-care, Yazzoom, KU Leuven and University of Antwerp.
- ATWI (Hybrid, multi-modal methodology for Automatic Tool Wear Inspection), aims to accurately analyze and predict the tool wear in metal cutting processes. Both direct (vision-based) and non-direct (data-driven) methods will be combined to develop a hybrid approach that defines new methods to extract relevant data for tool wear prediction, identify the correlation between status of the tool-wear and underlying data, and construct an innovative integration of the multimodal information in production strategies. The multidisciplinary Sirris team with experts from the Precision Manufacturing team, the EluciDATA Lab and the Mechatronics team of Sirris will collaborate with Exmore, Goddeeris, Buysse, Melotte, Tisea and KU Leuven.
Despite the highly-competitive call, all three proposals were selected for funding. This will allow the EluciDATA Lab to further support the industry in tackling its real-world challenges related to AI through joint industrial research for innovative solutions.
Authors: EluciDATA LabPermanent URL