AIDEAS will develop AI technologies for supporting the entire lifecycle (design, manufacturing, use, and repair/reuse/recycle) of industrial equipment as a strategic instrument to improve sustainability, agility and resilience of the European machinery manufacturing companies. AIDEAS will deploy 4 integrated Suites:

1) Design: AI technologies, integrated with CAD/CAM/CAE systems, for optimising the design of industrial equipment structural components, mechanisms and control components;

2) Manufacturing: AI technologies for industrial equipment purchased components selection and procurement, manufactured parts processes optimisation, operations sequencing, quality control and customisation;

3) Use: AI technologies with added value for the industrial equipment user, providing enhanced support for installation and initial calibration, production, quality assurance and predictive maintenance for working on optimal conditions;

4) Repair-Reuse-Recycle: AI technologies for extending the useful life of machines through prescriptive maintenance (repair), facilitating a second life for machines through a smart retrofitting (reuse) and identification of the most sustainable end-of-life (recycle). The AIDEAS Solutions will be demonstrated in 4 Pilots of machinery manufacturers that provide industrial equipment to different industrial sectors: metal, stone, plastic and food.

MKLab, the participating team from CERTH, is the coordinator of the AIDEAS project and is leading the development of the machine passport and will support the development of data communication protocols, standards, and interfaces for smart trustful data storing, sharing and exchange between different AIDEAS Suites. MKLab is responsible for providing real-time large-scale knowledge management algorithms that exploit robust and explainable AI techniques to provide the rationale for any derived decision making process, to apply early analysis on manufacturing data aiming to discover critical latent insights about the entire machine life cycle, and to reveal causal relationships among data variables.