How IBM is using digital twins to optimize AI

Everyone is familiar with IBM’s leadership in IT, AI, and cloud services. It also happens to be one of the leading providers for Enterprise Asset Management software through its Maximo line of software and services. These tools help manage large machines, like factories, powerplants, and heavy equipment.

Now, with the rise of digital twins, IBM is pivoting this business as an onramp to bringing intelligence, agility, and efficiency to a wide range of industries. The company has gone so far as to declare “You cannot have AI without Digital Twin.” The new IBM digital twin exchange promises to create an app store for the digitization of the physical world that brings together enterprises and various services and tools providers.

We caught up with Lisa Seacat DeLuca, distinguished engineer and director of Emerging Solutions at IBM, who leads IBM’s digital twin research. She is also the most prolific woman inventor in company history; she has filed more than 800 patent applications and had over 600 granted.

Her team develops tools that are changing how engineers and technicians do their jobs by combining digital twins, AI, and IoT technologies and allowing organizations to share expertise across common assets.

She has also published two children’s books for geeky kids, “The Internet of Mysterious Things” and “A Robot Story.”

VentureBeat: First off, how would you define digital twins, and why is it essential to think about as a thing as distinct from other tools for organizing data like APIs, data fabrics, data warehouses, and enterprise software tools? 

Lisa Seacat DeLuca: We define digital twins broadly as a digital representation of any physical object. You might picture certain use cases like manufacturing equipment or a generator, but really, anything can be a digital twin if it has a digital counterpart, which opens the door for a number of possibilities of what we can do with them.

Digital twins aren’t meant to replace other tools for organizing data. They’re actually intended to pair with tools like data transfer APIs and data warehouses because they are how you connect the digital to its physical counterpart.

VentureBeat: In what ways has your work on children’s books like “The Internet of Mysterious Things” and “A Robot Story” informed your thinking about digital twins? How would you explain the concept to them? 

DeLuca: As a children’s book author, I’ve realized how even when a concept seems extremely advanced to adults, putting it into terms that are meaningful to kids can still be a helpful way to teach readers of all ages about the world and technology around them. I think that’s especially important with an emerging technology like digital twins that many might not be familiar with yet.

The way I explain digital twins to my kids is an e-book. An e-book is a digital representation of a physical book, which makes it a digital twin. Now, imagine turning the pages in your real book and the e-book changes pages, or even the other way around, changing the page in the e-book changes the physical book page. That two-way relationship between the twin and its physical counterpart represent a mature digital twin and is an example of what’s possible with this technology.

VentureBeat: What is the value of pairing digital twins with AI? How does this work in practice? What’s involved in connecting the dots? 

DeLuca: AI is ultimately the analysis of data and the insights we draw from it. The digital twin provides a more effective way to monitor and share that data, which feeds into AI models. I boldly state that you can’t have AI without digital twins because they can bring users closer to their assets and enable them to draw better, more accurate and more useful insights.

VentureBeat: What kind of tools are your team developing that are changing how engineers and technicians do their jobs by combining digital twins, AI, and IoT technologies and allowing organizations to share expertise across common assets? 

DeLuca: To level the playing field and allow manufacturers, owners, and operators to get started with digital twins, we launched the IBM Digital Twin Exchange last year. The Digital Twin Exchange is a marketplace that connects organizations looking to buy digital twins with members of IBM’s partner ecosystem, who can sell them fault codes, maintenance plans, 3D models, and other data related to physical assets. It’s the first step to playing with digital twins. From there, you can use your AI and IoT solutions to fully capitalize on the value of digital twins. For example, the digital twins can be paired with IBM Maximo enterprise asset management and predict outcomes related to asset performance and maintenance based on the data available.

VentureBeat: What kind of industries do you see getting the most benefit from digital twins today? 

DeLuca: In any industry where optimizing the performance of physical assets is a business imperative, there’s a need to improve and an opportunity for data and digital twins to help. This is especially common in industries such as manufacturing, travel and transportation, and energy and utilities, where downtime or system failure has a direct effect on the bottom line. This need to keep assets operating at peak performance is why we’ve seen Industry 4.0 evolve so much, because technology like AI and open hybrid cloud are helping organizations in these sectors modernize their operations to be more reliable, efficient and profitable.

VentureBeat: What kind of crucial advancement will open digital twin opportunities in other industries? 

DeLuca: Adoption at scale hasn’t happened yet. It is taking some time, but there’s a big opportunity to get companies excited about the value digital twins can bring to their businesses. The way we can do this is implementing more solid and adopted industry standards. Right now, it’s a bit proprietary, and many companies are doing their own thing with digital twins. Digital twins won’t catch on until there’s more of an open model and agreed-upon framework between companies that will allow more innovation to spread quickly around digital twins.

VentureBeat: How do you believe that digital twins are making it easier to collaborate and share information about assets in a way that supports a safer, more technologically advanced future? 

DeLuca: The more information you have about an asset, the more you can do to improve how it’s used and maintained. There are business, sustainability, and safety benefits in predicting failures, proactively doing repairs, and monitoring the general state of assets, but doing so is only possible through near real-time data sharing, which digital twins enable. The benefits of using digital twins to increase users’ understanding of assets include maximizing productivity, extending asset lifespan, limiting consumption, reducing time spent on inspections in dangerous places, and helping prevent hazardous conditions and other emergencies due to system breakdown.