# [Off-Topic Tuesday] Digital Twins all around us!

Many of you may already be familiar with the concept of Digital Twin, especially in the manufacturing space. For those who are not, at it’s simplest definition, digital twins are virtual replicas of physical entities, and we can create these twins by integrating data from sensors, cameras, and other sources that monitor the physical entity. Then, you can run simulations and experiments in the digital twin before ever touching the real world, saving time and money!

Neat right? But maybe sounds a little unrealistic or something of the far away future sometimes? Think again!

I recently read this article Swimming in Data | The Mathematical Intelligencer which discusses the role of digital twins in competitive swimming. It was fascinating to me (especially with my Biomedical Engineering background) because the human body is the greatest, most complex machine, right? Surely we can’t replicate it digitally in an accurate manner? But we can

It’s worth the read (especially if you are coming down from the high of watching the Olympic swimming the past couple of weeks ) but to provide a super high level summary, this article covers how we are now able to enhance swimming performance by applying advanced mathematical and physical modeling to simulate and optimize a swimmer’s technique and performance.

What I found really cool, is that these digital twins are used to apply personalized coaching to each swimmer (focussed on minimize weaknesses & inefficiences and enhancing natural strengths and talent). See a snippet of the article below that I won’t bother summarizing because they do it so well!

In Figure 9, we compare the digital twins of two elite breaststrokers executing the first phase of a “pullout,” which fans cannot see, since it takes place underwater. The pullout phase consists of a powerful push off the wall followed by a streamline glide, and it ends with a single dolphin kick. The graph in the figure overlays the acceleration in the direction of the swim measured in g ’s, gravitational acceleration. One can see that the orange swimmer has an extraordinary streamline, since her graph sits slightly below 0g , reflecting almost no deceleration. On the other hand, the blue swimmer decelerates significantly in glide. The orange breaststroker also has a weaker dolphin kick, which she executes almost one second earlier. In terms of strategy, the orange swimmer might consider delaying the execution of the dolphin kick due to her superior streamline and weak kick, while the other breaststroker might want to execute her more powerful kick earlier to mitigate the inferiority of her glide. By running different simulations, we are able confirm these speculations, offer optimal timing of execution with confidence, and also provide the expected time savings to boot. Why guess?

So cool!

Would love to hear other’s thoughts on the concept of digital twin as well:

• Where else have you seen successful applications of digital twin?
• Have you attempted a digital twin of your shop floor? If so, how is it going?
• What concerns do you have about using a digital twin to replicate the physical world?

(Tagging you @mellerbeck because we briefly chatted about Digital Twin not so long ago! and of course tagging @giladl since he is our resident Digital Twin guru at Tulip)

3 Likes

The concept of digital twins is fascinating particularly wit Tulip because it adds an interesting layer to this technology. Tulip emphasizes the practical, on-the-ground applications of digital twins, focusing on real-time visibility and agility in manufacturing processes. Their approach to digital twins isn’t just about creating a virtual model but enabling frontline workers to interact with and optimize processes in real-time.

What I find most interesting, especially in the context of Tulip’s platform, is how digital twins can democratize data access and empower operators with actionable insights right at the point of production. This shift from a top-down data flow to a more integrated, worker-centric model could significantly enhance efficiency and responsiveness on the shop floor.

I’ve seen successful applications of digital twins in various forms such as for optimizing production lines or monitoring the health and performance of equipment. Tulip’s approach, however, is to uniquely focus on making these capabilities accessible to operators and engineers directly, which is a step forward in closing the loop between data and action.

As for attempting a digital twin of a shop floor in Tulip can be challenging yet rewarding. We use a The integration of various data sources and ensuring real-time accuracy is a common hurdle, but Tulip’s platform reportedly simplifies this process by offering tools that are intuitive and adaptable to specific operational needs. We also have a unique set of best practices on how to implement a digital twin. Its a topic that I also write about in my blog.

One concern I have about using digital twins, particularly in the way Tulip defines and uses them, is ensuring that the digital model remains an accurate and useful reflection of the physical world. In dynamic environments, where conditions can change rapidly, keeping the digital twin updated and relevant might require continuous monitoring and adjustments.

Would love to hear more about others’ experiences and thoughts on this!