Home / Blog / DT evolution in Manufacturing – V

DT evolution in Manufacturing – V

A digital twin can become a product in itself that a company may create and sell to a customer. It will be up to the customer to instantiate the Digital Twin to serve in the intended environment. In this picture the idea of a digital twin acquired by a third party that can be used in the manufacturing process. Rather than buying a robot a company will be able to buy a digital twin of a robot with the capability of instantiating it to match existing robots in a specific environment to take care of specific tasks. Image credit: Siemens

If we stretch this idea of a Digital Twin as a “product” able to deliver value to the customer we can foresee an evolution (at stage 5 and beyond) where some companies will be in the business of creating and selling Digital Twins. This will operate as software applications running on a platform, like a smartphone, an industrial platform like Mindsphere, a Government public platform and coming soon (end of this decade) a communication platform like 6G.

What would be the difference between a software package we are used today and that kind of Digital Twin? Well the Digital Twin (to be faithful to its name) is a software package that mimics an entity. So you might have, as an example, a company that offers a Digital Twin to mimic a person. You and me will buy that Digital Twin (may be running it on our smartphone), and will instantiate it to mimic our person, for the traits we are interested in. As an example after buying this “person’s digital twin” from a company I will instantiate it by opening my EHR to it, providing access to my wearable to get the stream of physiological data that these harvest, connect it to my doctor and provide its identity in my EHR so that in case of need the emergency room of any hospital can get in touch with it to share data.

In the manufacturing area we could buy a Digital Twin (a model of a manufacturing process, of a generic robot in an assembly line, of a warehouse …) and instantiate it to the factory environment. The Digital Twin “model” will be expanded/refined to match the current physical entities and will acquire the “thread”, historical record of those entity. Furthermore it will be connected to the physical entities to shadow them. From that moment on it becomes an instance of the digital twin acquired and the real digital twin of the associated entities.

This mechanism is based on the idea that we can create a generic Digital Twin with an embedded model and a set of features along with a tool (it can be part of a platform) that can support the client/user in the instantiation of the Digital Twin by adding specific knowledge.

The idea of a Digital Twin embedding knowledge (that is more than the concept of a static modelling that is part of the Digital Twin Digital Model) derives from the work done by IBM to create a digital twin mirroring the newer models of robots used in manufacturing. These newer models have a greater level of autonomy and can work, taking autonomous decisions and sharing them with the environment (like other robots in the assembly line and in the supply/delivery chain). This autonomy requires a knowledge of the context and of the goals (plus a framework of do’s and don’ts). In 2018 IBM came up with the concept of Cognitive Digital Twins to match the evolution of robots in manufacturing and this le to an extension of the concept of Digital Twin.

The ongoing shift in automation on the shop floor involving smarter and smarter robots is also known as Robotic Process Automation, RPA. The Cognitive Digital Twins -CDT- are an integral part of this transformation. 

Notice that knowledge is both embedded in a CDT and shared across several CDT creating a knowledge infrastructure that is both characterising the knowledge space of operation of CDTs and of DTs. In other words the knowledge space of a CDT becomes the operation environment for all digital twins operating in that environment.

About Roberto Saracco

Roberto Saracco fell in love with technology and its implications long time ago. His background is in math and computer science. Until April 2017 he led the EIT Digital Italian Node and then was head of the Industrial Doctoral School of EIT Digital up to September 2018. Previously, up to December 2011 he was the Director of the Telecom Italia Future Centre in Venice, looking at the interplay of technology evolution, economics and society. At the turn of the century he led a World Bank-Infodev project to stimulate entrepreneurship in Latin America. He is a senior member of IEEE where he leads the New Initiative Committee and co-chairs the Digital Reality Initiative. He is a member of the IEEE in 2050 Ad Hoc Committee. He teaches a Master course on Technology Forecasting and Market impact at the University of Trento. He has published over 100 papers in journals and magazines and 14 books.