May 08, 2023
The transition towards a Circular Economy is estimated to represent a $4.5 trillion global growth opportunity by 2030. Digital Twins availability is largely recognized as an accelerator and an enabler of Circular Economy in business and in production, but significant challenges are still standing in relation to its development within the present technological framework, the needed skill sets, and the implementation costs.
AUTO-TWIN addresses the technological shortcoming and economic liability of the current system engineering model by:
1) introducing a breakthrough method for automated process-aware discovery towards autonomous Digital
Twins generation, to support trustworthy business processes in circular economies;
2) adopting an (International Data Space) IDSbased common data space, to promote and facilitate the secure and seamless exchange of manufacturing/product/business data within value-networks in a circular-economy ecosystem;
3) integrating novel hardware technologies into the digital thread, to create smart Green Gateways, empowering companies to perform data and digital twin enabled green decisions, and to unleash their full potential for actual zero-waste Circular Economy and reduced dependency from raw materials.
Politecnico di Milano
The AUTO-TWIN Consortium is composed by 13 partners and associated entities across 7 countries.
Politecnico di Milano is the most important technical university in Italy and one of best in Europe according to recent rankings. Since 1836, Politecnico di Milano has been active in several scientific and technical fields and will join through the Department of Mechanical Engineering. The Department of Mechanical Engineering is ranked 1st in Italy, 5th in Europe and 17th worldwide (Engineering – Mechanical, Aeronautical & Manufacturing – QS 2018) and it is among the 180 “Excellent Departments” selected in 2018 by the Italian Ministry of Education, University and Research. It has 128 full-time faculty members, 68 research fellows, 194 Ph.D. candidates and 52 technical and administrative staff. The mission of the Department of Mechanical Engineering is to promote and develop culture, research and innovation in its sectors of reference, but also in new fields doomed to become more and more important in society and in our present background. For example, it specifically deals with transports and sustainable mobility, power technologies, biomechanics and service robotics, bio materials, smart materials and hybrid materials, manufacturing and production systems, space and security.
The Auto-Twin project
AUTO-TWIN vision is addressing four specific objectives, each one solving a well-defined research challenge,
resulting in measurable exploitable results, used as clear and realistic indicators for the achievement of the project goals. These objectives, and their underlying research questions defined in section Methodology, will guide all the activities of the work plan of this Research and Innovation action. AUTO-TWIN concept is agnostic and domain independent.
OBJECTIVE 1 – Automated digital twin generation, operations, and maintenance in circular value chains.
AUTO-TWIN will develop a novel data-driven method based on a process mining approach for generation and adaptation of multi-fidelity resolution digital twins from data acquired, at multiple levels, along the value chain. Full automation, trustworthiness, and “skill-free” play are key-selling points of the project approach, based on sparse traces of manufactured objects flowing in the value chain. The project will rely on multiple automated actors to discover the flows in the value chain and to automatically generate and update digital twins of complex business processes, starting from the specific manufacturing processes till the whole supply chain.
OBJECTIVE 2 – Trustworthy high resolution track & trace of products and processes among different actors in circular value chains
The consistency of data and information sharing among stakeholders across the value network are fundamental for the validity of digital twins. AUTO-TWIN aims to: i) enable high resolution track&tracing through precise and detailed data and information about products and processes; ii) manage data and access rights in a seamless, secure, powerful and flexible way; iii) manage data sharing and sovereignty within circular data spaces. AUTO-TWIN will define, implement and test its systems and solutions in real business environments in very different sectors to define business guidelines and best practices and share them with the community.
OBJECTIVE 3 – Reduce skills and knowledge gaps for all involved actors through augmented intelligence.
In order to perform significant progress in the state-of-art, the design of a new approach for assessing skills and mapping production processes is a mandatory requirement. It should be reliable, complete and built on standardized frameworks. The AUTO-TWIN project answers to this requirement developing: (i) Explainability for Artificial Intelligence (XAI) techniques able to decrease the required skills; (ii) tools to assess the current skills of the single worker in a specific production context and (iii) to identify (through a data-driven approach) the most efficient upskilling paths for operators as well as their related production processes.
OBJECTIVE 4 – Augmented intelligence algorithms for decision making at Green Gateways.
AUTO-TWIN will define new methods and algorithms to extend knowledge and support actors in decision-making at Green Gateways. Artificial Intelligence techniques and process mining algorithms will be developed to extract significant correlations, then transformed into explainable knowledge, underlying the product data along their life cycles and their manufacturing and logistic processes as well as the dependency of the demand on pricing and product characteristics. This knowledge, together with digital twin predictions on relevant multidimensional indicators (i.e., circularity indices, productivity indices, supply chain indices) will be used with augmented knowledge and real time production data for optimal coordination of the value chain under stochastic behavior
The role of Politecnico di Milano in the Auto-Twin project
Coordinator, Research & Development
Politecnico di Milano (PMI) will coordinate the project’s efforts and ensure the timely and cost-effective project execution. PMI will also be heavily involved in exploiting its experience in process mining research applied to manufacturing systems for developing algorithms for learning, adapting, and tuning the component models of a digital twin. Also, PMI will support the development of functional modules for automatically converting graph models into discrete event simulation models, as well as executing them and validating the results online. Similarly, PMI will develop process mining techniques, that exploit conformance checking results to enhance a knowledge graph model, and multicriteria optimization methods.
ACKNOWLEDGMENTS
This project has received funding from the Horizon Europe programme under the Grant Agreement No. 101092021
This article has been extracted and freely adapted from the Auto-Twin official website and Proposal.