Hydrogen meets AI: Digital triplets and the next wave of energy innovation

Get ready to explore the future of energy innovation! In this episode of Energy Transition Talks, CGI experts Diane Gutiw, Lukas Krappmann, and Peter Warren dive into how digital triplets—an evolution of digital twins—are transforming the energy industry. Learn how companies are using AI-powered, interactive models to unlock insights faster, optimize systems, and deliver smarter energy solutions.

From hydrogen electrolyzers in Germany to grid optimization and predictive maintenance, discover how agentic AI and specialized data models are accelerating the shift to a more resilient and sustainable energy landscape. Perfect for tech enthusiasts, energy professionals, and innovation leaders—don’t miss this look into the next wave of digital transformation in energy.

Visit our Energy Transition Talks page

Chapters

• 0:00 Welcome and Introduction to Digital Twins
• 1:22 Understanding Digital Triplets with Diane
• 4:32 Practical Applications in Hydrogen Electrolyzers
• 7:33 Optimizing Energy Systems with AI
• 10:15 Episode Closing and Part Two Preview

Transcript

Peter Warren: 0:00

Hello everyone and welcome back to our ongoing series of conversations about energy transition and how things are changing in industry. We actually just came back from the Hanover Messe, which is the Hanover Fair for manufacturing, and there's a lot of overlap between manufacturing and the energy markets. We're going to touch on that, but the big dive today is talking about a concept called digital twins and digital triplets. So with me I have two great experts, diane and Lukas, and let's start with Diane. Do you want to introduce yourself?

Diane Gutiw: 0:30

Thanks, peter, and thanks for inviting me to the podcast. My name is Diane Gutu. I lead our AI Global Research Center and a lot of our focus has been on digital twins and extending them to digital triplets. So great to be joining the conversation twins and extending them to digital triplets.

Lukas Krappman: 0:48

So great to be joining the conversation, yeah, thanks, thanks, pete. My name is Lukas Kruppmann, from Germany here and I'm responsible for one of the clients active in as well, the manufacturing and energy and utilities industry, and therefore we already worked on a couple of concepts according to digital twins, and also some ideas and triplets. And thanks, pete, happy to also be here today.

Peter Warren: 1:05

That's a great thing. Thanks for joining me. So we're covered from the far coast of Canada over to Germany and middle part of Canada. So thanks very much, diane. Since you're the resident expert in all things digital twins and you've come up with the concept of digital triplets, do you want to give us sort of a baseline conversation on what those are?

Diane Gutiw: 1:22

Sure, absolutely so. The concept of digital triplet is actually quite simple, but it's a fantastic way to extend an existing investment in data and a data ecosystem. So if we look at the different layers, you know you have your physical asset or a group of assets infrastructure that you're monitoring as your physical layer. The digital twin is that digital representation of those things, that person, those people, those pieces of equipment. So when you're looking at a digital twin, it's collecting the data from operational systems, from historic systems, information about each of those assets, as well as anything diagnostic coming from edge computing, iot devices, so that you have a really good holistic view of that ecosystem or that particular item that you want to monitor. Digital twins are not new. They're a great way of looking at operations and interactions between different assets, as well as starting to do with traditional AI, some analysis on different scenarios. So why would digital triplets be important? Well, it's extending that. It's leveraging newer technology, so generative AI, large language models and, in some cases, small language models, which I think we'll go into a bit to be able to explore that digital twin layer and provide an opportunity for an operator to have a conversation using natural language with that data. So the way that the digital triplet works. It's a form of a Gentic AI which, of course we heard in Hanover and other places is a really hot topic which is a group of collaborative agents that are monitoring the layer of data on the digital twin. They're continuously listening and they are able to work autonomously on defined tasks. So, for example, one may be really good at understanding diagnostic information, another one on parsing IoT information and looking for anomalies. You might have one that's able to generate different types of information and then provide it back to the person that's asking the questions.

Diane Gutiw: 3:32

The real value of the digital triplet to me are two things.

Diane Gutiw: 3:36

One is the ability to access information which goes beyond the traditional discrete data coming from operational systems, because we can look at narrative data and images and videos and and have a conversation with that data the same way traditionally we could with discrete data, without having to spend a lot of energy on modeling it. But the most important thing is the accessibility, the fact that you can have a conversation with your data. You can ask what would happen across an energy grid if this part went down or if I need to do some maintenance on a piece of equipment. How then would I readjust both my human resource load as well as the energy load to compensate for anything that needs to change. You can ask information on alerts and you're having that conversation either by text or by phone in natural language. So it's like having your best group of advisors and specialist assistants being able to pull that information for you real time. So a bit of a long-winded explanation, but it's something that's really definitely taking off in the energy space.

Peter Warren: 4:39

I appreciate that definition and I guess it's really a case of these investments in digital models people already have. It's really layering those into a way that's more consumable from a business standpoint, maybe, than from a technical standpoint. Would that be a fair summary?

Diane Gutiw: 4:52

Absolutely, and that's why this is a great place for organizations to start with their AI journey. And accelerating that AI journey is because you are extending your investment in what you already have in place. That may show you opportunities to be able to do more, but by adding a layer of generative AI not just on your documents, the way we're seeing in RAG models, but across your whole data ecosystem you're able to really get very quick insights into information that in the past, were really complex and expensive to be able to do.

Peter Warren: 5:22

Well, that's really interesting and, Lucas, you've got a practical application of this, originally from a manufacturer of energy systems, but do you want to give us a summary of your story there?

Lukas Krappman: 5:32

Yeah, so we basically start with the classic, first, I would say digital representation, for example, of an hydrogen electrolyzer. So most of our clients in Germany are actually building the hydrogen electrolyzers. With regards to the PEM electrolyzers, and what eventually we did is we digitized first the physical model Diane was already referring to and then adding first the telemedicator to it, but also the business processes. So what is, for example, happening before a stack in terms of pressure, temperature, but also current or voltage, and what is happening afterwards, able to looking at that from like a 3d representation and also talking with the data. For example, you're seeing that there's a stack being colored, for example, in red or orange, indicating that something is wrong, and then you can click on it, investigate it and then talk with the data.

Lukas Krappman: 6:23

This is what diane referred to earlier, like in the right hand side, said hey, can you please have a look over the last day, what happens in this particular stack? Do you need to replace it? Was there some I don't know kind of pressure leakage? Was there a spike into voltage? Really, about the digital twins for the hydrogen electrolyzer operations, this is how we started and we're now actually trying to elevate the concept and letting the data which is going in, so telemetry data, speak and connect it to all the historic data.

Peter Warren: 6:54

So this was really came from their desire to digitize and be sort of more modern in their platform, so that they're trying to be more of a data-driven system to bring up a higher level of value. Would that be a good example? They're trying to operate things and optimize their full production. What is the outcome they're looking to get?

Lukas Krappman: 7:13

Yeah, I mean that's the main objective. With the current market and all the new companies putting their products in the market. It's not only about, let's put it, the physical product they're selling, but also about the digital experience. In the past, you were referring to that like about the user experience or how different stakeholders and people can interact with the product. So what we are trying to do, or what we aim to do with the children for the operations, is, as well as provide the internal manufacturers the possibility to improve the product, but also provide, let's say, a digital service to their customers in terms of, okay, accessing the data, integrating it into, for example, other components like the energy grid, but also, for example, the question what should I do really with an electron right? So should I put the remaining energy of the electrons back into it? And these are the questions I can ask the digital twin.

Peter Warren: 8:08

That's really interesting. And, diane, you actually published an article recently hitting on that very same point, which really gets to how do people overcome the barriers and move ahead and looking ahead to this sort of area. But in that article you hit a lot of interesting points about how to optimize not just part of the energy system but the whole energy system.

Diane Gutiw: 8:28

Yeah, I think you know, when you look at how to optimize any system, any infrastructure, including the energy system, focusing on what's the problem you want to solve right, identifying where it is that there is an opportunity to improve and then extending that. A big example that we see would be all of that information that's collected from IoT devices and edge computing. You know, right now we are not really getting the value out of that data because this is information that's collected in a second or a couple of seconds or minutes or a couple of minutes, and there's some fantastic insights, but so much volume of data it's near impossible to be able to pull that. So being able to leverage these newer tools that are able to see patterns without having to spend the time on that level of monitoring really is what's taking it forward.

Diane Gutiw: 9:21

The other thing I think that's shifting is having small language models, which I mentioned in the beginning, which are not using the entire internet. You couldn't ask it how do I make the best apple pie? The way you can with the large language models, but it's absolutely trained on the context of what it needs to do, so it's improving the compute power and the efficiency of the models and it's being able to give much more precise answers to questions on very specific to what the problem is you're trying to solve. For example, you can have a small language model that's fine-tuned and trained specifically on that different types of IoT data to get the real value out of that. So I think, starting with what's a problem where there's an opportunity, and then be able to look at refining each part of that value chain is really critical to getting that return on investment.

Peter Warren: 10:14

Well, that's outstanding. Thank you for that. So we're going to end this first part of a two-part series, so hopefully you guys can catch up with us in the next part, where we're going to talk about more of the innovation that's moving forward here, the impacts of the ongoing geopolitical issues that we are facing right now and really the vision for how things are moving forward. So we'll catch up to you all in part two. Thank you Lucas, Thank you Diane, We'll talk to you again.

Lukas Krappman: 10:37

Thank you, have a nice day, bye-bye. Thanks, peter.