Abstract
The future of manufacturing is envisioned to be fulfilled in a cross-border and digitized environment that will engage a large population of manufacturer enterprises collaborating on a shared understanding of the tasks for delivering Manufacturing as a Service (MaaS). Instead of owning excess production capacities to hedge against demand fluctuation, companies will adopt an open business model by implementing manufacturing capabilities as a scalable and changeable production network to achieve quick response and adjust capacities through an agile enterprise structure within an augmented and complementary manufacturing resource pool. Therefore, a stronger push for MaaS is to be expected. In this context, DIGItal Twins for CIRCuLar Economy (DIGIT4CIRCLE) revolves around the application of the Digital Twin (DT) paradigm to production processes in the Circular Economy (CE), in an effort of obtaining more sustainable supply chains based on recycling and reusing products. It argues that the biggest challenge in establishing digital representations of production processes does not concern the characterization of the individual stages, but rather is connected to the information flow that must be harmonized and spread to convey a meaningful representation. Indeed, applying DT to individual instances of production processes to obtain a MaaS is a relatively established practice, but closing the loop to obtain a CE clashes with the problems of characterizing the myriads of events occurring during the lifecycle of a product that ultimately determined its termination. To this end, the project successfully designed and validated a comprehensive framework combining both methodological advancements and technological implementations for DT–enabled CE scenarios. Various iterations and verticalizations of the framework were also explored and assessed to ensure adaptability across different use cases. The resulting architecture integrates multiple layers of information technologies and is supported by well-defined methodologies for modelling, data acquisition, analysis, and secure data exchange.
Results achieved
The following results were achieved: R1. a virtualized platform was designed and implemented for the representation and federation of distributed processes/resources. This includes approaches for modelling heterogeneous resources and enabling the convergence of domain-specific digital representations. The platform enables on-demand federation of distributed resources (e.g., production units) and demonstrates dynamic adaptation capabilities through localized intelligent feedback mechanisms, validating both the architectural design and the underlying mechanisms; R2. comprehensive data acquisition and management procedures were defined and implemented, covering the collection, integration, and processing of heterogeneous data across the resource lifecycle. Integrated data pipelines, aligned with MLOps practices, were developed to ensure continuous data flow, traceability, and reproducibility. Building on these procedures, machine learning techniques were applied for the classification of functional behaviours, anomaly detection, and lifecycle analysis, enabling both predictive and prescriptive insights and supporting runtime adaptation of processes; R3. a secure dataspace solution was designed and implemented, supported by methodological guidelines for trusted data sharing across heterogeneous stakeholders and domains. The approach incorporates privacy-preserving mechanisms and secure data exchange protocols, enabling controlled and reliable interactions among actors with different roles and ownerships. This component ensures seamless interoperability while addressing data sovereignty, security, and trust requirements, thereby enhancing the adoption potential of the overall framework. The project achieved its core objectives by delivering an integrated set of methodologies and technological solutions for DT-based modelling, data-driven decision-making, and secure information exchange. The proposed framework was validated as a scalable and transferable approach for supporting circular economy scenarios and advancing sustainable, data-driven industrial processes. For more information, please refer to the project website at in [1]. [1] PRIN PNRR Digit4Circle, "PRIN PNRR 2022 — Digit4Circle: Digital Twins for Circular Economy," Digit4Circle Project Website, 2026. [Online]. Available: https://digit4circle.github.io/prinpnrr2022/. [Accessed: Jul. 6, 2026].Project details
Unibo Team Leader: Armir Bujari
Unibo involved Department/s:
Dipartimento di Informatica - Scienza e Ingegneria
Coordinator:
ALMA MATER STUDIORUM - Università di Bologna(Italy)
Total Eu Contribution: Euro (EUR) 263.683,00
Total Unibo Contribution: Euro (EUR) 140.000,00
Project Duration in months: 27
Start Date:
30/11/2023
End Date:
28/02/2026
