What is a digital twin?

An explanation of the concept, benefits and risks of creating 'digital twins' to assets.

Online versions of infrastructure
Online versions of infrastructure
At a recent ICE AI workshop we explored the question “What would be the benefits of a digital twin of the built environment and what are the steps we need to take to get there?” The following explores some of the aspects of that discussion.

The ‘digital twin’ of a physical asset helps us to understand how assets operate in a wider system and how they interact with other assets. A digital twin is a ‘bridge’ between the physical and digital world. They can be predictive and adapt physical systems to reflect changes in the environment or operations. The benefits include harmonisation of operations to deliver optimal user outcomes, clash identification and automated remediation, and ultimately cost/risk reductions.

Singapore has undertaken a mapping process which might be considered to be a ‘digital twin’. However, this is a small area to map in depth, and the decision to undertake this was made from the ‘top down’. The cost and scale of creating large-scale digital twins elsewhere might be considered prohibitive, but small-scale, in-depth models offer considerable benefits for infrastructure owners and operators.

However, managing and analysing the volume of data required presents a significant challenge. Most industries analyse very little of the data they already gather. This is often characterised as ‘the bucket’ – a lot gets put in, but very little comes out. By making use of good quality data we have access to more information, which can ultimately inform better decisions. For example, Google realised savings of 40% on its own data centres using Deep Mind analysis on data from its own assets.

Effective use of data and digital twins means industry needs to fully integrate data expertise into its teams, as well as working more closely with tech sector – going beyond traditional alliancing models. Additionally, clients need to start seeing digital integration as standard, not just ‘nice to have’. But there is also a need to draw on other sectors, like social sciences, to avoid simply replicating existing design biases from physical environment into digital environment.

In the policy and planning environment Government and local authorities need to identify and address clashes which prevent the realisation of ‘digital twins’. For example, 5G building penetration may be inhibited by regulations around the use of certain types of window.

Security is now at the forefront of any digital discussion, and is a major consideration as ‘digital twins’ become more common. However, we have to acknowledge data security will never be 100%, so a risk management rather than risk prevention mind-set is required to ensure innovation and development is not inhibited. And as we know, much of that risk prevention is going to be down to ensuring that people are, as a whole, more security minded.

Further links
Read about Lord Adonis and the National Infrastructure Commission's drive to create the UK's first digital twin

Read more about digital twins and artificial intelligence.

Book for ICE's Shaping a Digital World to conference to explore these advances and more in person.
Top