The Architecture

The objective of SIROKO is to create and develop a framework that combines harmonized local techniques of adaptive cognitive reasoning with decentralized resources of artificial intelligence and multi-scale modeling for the autonomous operation, support, and decision management at various operational levels of facilities.

Physical level – Factory:

  • data collection from sensors

Data management level:

  • receiving factory data with asynchronous cloud services (Databricks, Data Lake) based on standard protocols (HTTP, MQTT)
  • converting data to a common format based on Object Data Modeling (ODM) library (Mongoose)
  • data pre-processing 🡪 sorted data sets suitable for algorithms
  • storage in MongoDB database

Artificial intelligence level:

  • stored data usage for model training by algorithms
  • software for trained models execution when decision support is requested

Level of process management and decision making:

  • definition of goals and constraints by specialized employees for automatic optimization
The project SIROKO was implemented in the context of the Action RESEARCH – CREATE – INNOVATE and co-financed by the European Union and national resources through the OP. Competitiveness, Entrepreneurship & Innovation (EPANEK).

The project started in June 2021 and is expected to be completed in December 2023.

Scientific co-ordinator is Dr. Dimitrios Tzovaras from CERTH/ITI.