EUROPEAN RESEARCH COMMUNITY
MASTA is involved in multiple European innovations programs to bring our customers products backed up by state-of-the-art concepts and technologies.
Capability- and Capacity- based Supplier and Customer Matching
CaCaMat facilitates matching of Fabrication-as a-Service providers in the metal industry with their customers requiring custom-made parts. Matching will make sure that the potential supplier has both the technological capability and capacity to deliver in minimal time. To this goal CaCaMat develops a semantic model describing the fabrication operations, capabilities of the machines and scheduling operations as well as three applications – intuitive creator of custom bent elements; suppliers side application for exposing the capabilities of the machine park, validating the design, and scheduling the production; and intermediary application matching suppliers with the customer. All the applications integrate with and communicate via the Market4.0 platform.
Execution Tracking and Capacity Sharing
ExtraCash develop a solution supporting lot-size-one manufacturers in getting near real time insights into their production schedule and helping them to expose the order status, production capacity and machines capabilities to their existing and future customers. The solution is cloud-based with web-app deeply embedded in the EFPF framework and offered via the EFPF marketplace.
Advance Predictive Maintenance
The APEMAN project develops a distributed edge-cloud Digital Twin model applicable to predictive maintenance of machines on the shopfloor. An edge device – Integrated Sensing and Analysis Box (ISAB) is able to collect and analyse data using deep neural network models in order to monitor the machines and predict their failures. The ISABs deployed in a single installation analyse the data locally in real time and transfer it to the cloud to retrain and adapt the Digital Twin models according to the incoming data and events annotated by the operators. The system is based on the Apache tool chain of the MIDIH architecture and uses both levels of data processing – the Data-in-Motion is responsible for real-time analysis of incoming data directly on the edge devices, whereas the Data-at-Rest layer is used to validate and retrain the real-time models.