Summary
DMaaST aims to enhance the manufacturing ecosystem's resiliency and capability of self-adaptation in response to external events. It is achieved through a Smart Manufacturing Platform comprising 4 layers: The data layer establishes a foundation for mapping manufacturing ecosystem information using ontologies and decentralized knowledge graphs, ensuring a trusted cross-organization real-time data integration. Next, a layer with a two-level cognitive digital twin is created, with the low-level DT modelling two use cases' manufacturing services production line; and the high-level DT modelling the main stages of use-cases’ sectors value chains. The resulting DTs will use human expertise-knowledge, data-driven algorithms and physical modelling to provide a reliable and robust DT of the manufacturing ecosystem. The next layer employs the data and modelling layer's information to present a multi-objective distributed decision support system algorithm combining multi-objective techniques and the latest trends in Federated Deep Learning. This makes DTs actionable models and provides the necessary information to make optimal production decisions. The fourth layer focuses on presenting the information in a user-friendly manner with timely scoreboards. Additionally, a dedicated module will assess the production's circularity and sustainability and considering products traceability through the EU-DPP. Therefore, the sustainability and remanufacturing opportunities of the production process will be improved. The project ensures scalability, providing information for replicating and trying new manufacturing processes thanks to the manufacturing services digital warehouse while assessing risks and opportunities for improvement. DMaaST innovations enable the manufacturing ecosystem to adopt the Manufacturing as a Service concept by smoothly evolving all the technologies from a TRL3 to a consolidated TRL6 in 2 use cases in key sectors, aerospace and electronics.
Unfold all
/
Fold all
More information & hyperlinks
Web resources: | https://cordis.europa.eu/project/id/101138648 |
Start date: | 01-05-2024 |
End date: | 30-04-2028 |
Total budget - Public funding: | 5 862 752,50 Euro - 5 862 752,00 Euro |
Cordis data
Original description
DMaaST aims to enhance the manufacturing ecosystem's resiliency and capability of self-adaptation in response to external events. It is achieved through a Smart Manufacturing Platform comprising 4 layers: The data layer establishes a foundation for mapping manufacturing ecosystem information using ontologies and decentralized knowledge graphs, ensuring a trusted cross-organization real-time data integration. Next, a layer with a two-level cognitive digital twin is created, with the low-level DT modelling two use cases' manufacturing services production line; and the high-level DT modelling the main stages of use-cases’ sectors value chains. The resulting DTs will use human expertise-knowledge, data-driven algorithms and physical modelling to provide a reliable and robust DT of the manufacturing ecosystem. The next layer employs the data and modelling layer's information to present a multi-objective distributed decision support system algorithm combining multi-objective techniques and the latest trends in Federated Deep Learning. This makes DTs actionable models and provides the necessary information to make optimal production decisions. The fourth layer focuses on presenting the information in a user-friendly manner with timely scoreboards. Additionally, a dedicated module will assess the production's circularity and sustainability and considering products traceability through the EU-DPP. Therefore, the sustainability and remanufacturing opportunities of the production process will be improved. The project ensures scalability, providing information for replicating and trying new manufacturing processes thanks to the manufacturing services digital warehouse while assessing risks and opportunities for improvement. DMaaST innovations enable the manufacturing ecosystem to adopt the Manufacturing as a Service concept by smoothly evolving all the technologies from a TRL3 to a consolidated TRL6 in 2 use cases in key sectors, aerospace and electronics.Status
SIGNEDCall topic
HORIZON-CL4-2023-TWIN-TRANSITION-01-07Update Date
22-12-2024
Images
No images available.
Geographical location(s)
Structured mapping
Unfold all
/
Fold all
R&I Objective 1.1: Data ‘highways’ and data spaces in support of smart factories in dynamic value networks
R&I Objective 1.4: Artificial intelligence for productive, excellent, robust and agile manufacturing chains - Predictive manufacturing capabilities & logistics of the future