BIG DATA PLATFORM FOR OPTIMIZED AND REPLICABLE INDUSTRIAL AND FACILITY MANAGEMENT MODELS

20
M€ total value
16
M€ EU Funding
23
Partners
1
Platform
12
Testbeds
3
Application areas
Objectives
  1. Provide a full-fledged platform enabling easy access to heterogeneous HPC-based cloud resources for advanced big-data services

  2. Design big data services for storage, management, fusion, and analysis by exploiting interoperability standards and by ensuring security and privacy

  3. Develop intelligent services for distributed digital twins covering advanced Machine Learning algorithms, physical simulation, on-line and off-line optimization

  4. Deliver distributed digital twins in the field of manufacturing for production optimization and predictive maintenance

  5. Delivering distributed twins in the field of facility management and processes optimization

  6. Promote innovative business models for digital twins adoption in SMEs

 
01

Manufacturing testbeds

4 industrial pilots providing predictive maintenance services that exploit sensors data to forecast the time to failure and produce maintenance plans that optimize maintenance costs;

 
02

Facility Management Testbeds

3 testbeds for identification of criticalities,  optimization techniques to provide efficient facility management plans, operation optimal schedules, and renovation/maintenance plans

 
03

Replicability Testbeds

5 tesbeds to demonstrate the replicability and the scalability of the IoTwins platform and of the former manufacturing and facility management testbeds

01 / 03

BENEFITS FOR COMPANIES

As concrete outcomes, the IoTwins project will deliver:

  1. a world-class architecture (and its reference implementation) for the coordination and interworking of distributed cloud-, edge-, and IoT-hosted twins, specifically tailored to SME-oriented test-beds for industrial production processes and facility management operations;

  2. a PaaS layer simplifying access and integration of cloud resources (also hosted on HPC-specific resources when needed) for industrial IoT, heterogeneous big data sources, and remote edge components, capable of providing application developers with composability and integration facilities for distributed digital twin functions;

  3. an edge computing framework (compliant with emerging standard specifications in the field, such as ETSI MEC) enabling dynamic deployment of edge twins, dynamic migration of pre-elaborated control models to them, and open orchestration of their control/reconfiguration actions with the cloud-hosted counterparts when needed. The framework will consider operating under industrial latency/reliability constraints, which will affect also the above decisions on dynamic deployment, model migration, and orchestration of production quality management actions;

  4. vertical, industrial, and distributed digital twins for online quality management of production processes and optimization of facility management operations, which are central to the interest and core business of the consortium partners;

  5. a well-assessed methodology for replicability towards companies even for different application sectors, for scalability, and for business models definition covering new forms of platform servitization, on premise deployment, and performance standardization/homogenization.

Governance

FRANCESCO MILLO Bonfiglioli Riduttori Project Coordinator
PAOLO BELLAVISTA Alma Mater Studiorum Bologna Project Scientific Coordinator
ISELLA VICINI Be WARRANT Project Manager
ALEJANDRO SIMON DE DIOS Wavestone Exploitation Manager
PAOLO COMINETTI Bonfiglioli Riduttori Risk Manager
DEBORA FACCHINI ART-ER Dissemination & Communication Manager

Coordinator & Partners