by Thor Olavsrud

Digital twins: 5 success stories

Aug 30, 2022
AnalyticsArtificial IntelligenceDigital Transformation

These five companies are using digital twins to monitor operations, plan predictive maintenance, improve customer service, and optimize their supply chains.

digital twin
Credit: Dell Technologies

Humans have always gathered data to better understand the physical world around us. Today, companies are increasingly seeking to meld the digital world of data with the physical world through digital twins. Digital twins serve as a bridge between the two domains, providing a real-time virtual representation of physical objects and processes.

These virtual clones of physical operations can help organizations simulate scenarios that would be too time-consuming or expensive to test with physical assets. They can help organizations monitor operations, perform predictive maintenance, and provide insight for capital purchase decisions, creating long-range business plans, identifying new inventions, and improving processes.

In a forecast released in June 2022, research firm MarketsandMarkets said the global digital twin market is expected to grow from $6.9 billion in 2022 to $73.5 billion by 2027, a compound annual growth rate (CAGR) of 60.6% over the period.

Here are five examples of how organizations are using digital twins effectively today.

NTT Indycar puts fans behind the wheel

The NTT Indycar Series, comprised of five races including the Indianapolis 500, is using a combination of digital twin, data analytics, and artificial intelligence (AI) capabilities to give fans access to in-depth, real-time insights about races, including head-to-head overtaking, pit predictions, and other elements.

Partner NTT creates a digital twin for every car in the series. Historical data provides a foundation, and each car is equipped with more than 140 sensors that collect millions of points of data during each race to feed the digital twin. The data includes everything from speed to oil pressure to tire wear and G forces. NTT uses AI and predictive analytics on the digital-twin data to deliver fans insights that previously would only have been available to race team engineers, including race strategies and predictions, intercepts and battles for position, pit-stop performance impact, and effects of fuel levels and tire wear.

Indycar delivers the insights to fans via the interactive Indycar app and social media channels. It also supplies insights to NBC’s production team.

“There’s an opportunity for our most avid fans to get closer to a sport they love or a driver or team they love,” says SJ Luedtke, vice president of marketing at Indycar. “That’s where the data and analytics come in. We’re working with the team to take those millions of data points in over the course of a 90-minute race and help fans understand what’s going on.”

Over the past three years, NTT Indycar has doubled engagement and linger time in its app on race weekends, Luedtke says.

Luedtke’s advice: Develop close relationships with your stakeholders. She notes that she and CIO Rebecca Ruselink work hand-in-hand. She says their partnership is strong because IT really tries to understand her team’s pain points and to answer their needs rather than just supplying the solution IT thinks would be best.

“Our teams meet regularly,” Luedtke says. “We have a roadmap of things that we want to accomplish.”

Rolls-Royce improves jet engine efficiency

Multinational aerospace and defense company Rolls-Royce has deployed digital twin technology to monitor the engines it produces. The company can monitor how each engine flies, the conditions in which it’s flying, and how the pilot uses it.

“We’re tailoring our maintenance regimes to make sure that we’re optimizing for the life an engine has, not the life the manual says it should have,” says Stuart Hughes, chief information and digital officer at Rolls-Royce. “It’s truly variable service looking at each engine as an individual engine.”

The company has been offering engine monitoring as a service to its customers for years, but its digital twin capability has enabled Rolls-Royce to tailor the service for specific engines. It has helped the company extend the time between maintenance for some engines by up to 50%, enabling it to dramatically reduce its inventory of parts and spares. The technology has also helped Rolls-Royce improve the efficiency of its engines, saving 22 million tons of carbon to date.

Hughes’ advice: Understand your customer. Knowing how and why to use the power of digital twin is as important as understanding the technology itself. Hughes says the service has been a win because it offers clear benefits to both Rolls-Royce and its customers.

“The benefit to the customer is the customer sees less interruption because the engine is on the plane for longer, so they can use it more. The benefit for us is that we can optimize how we actually do the maintenance,” he says.

Mars optimizes its supply chain with digital twin

Confectionary, pet care, and food company Mars has created a digital twin of its manufacturing supply chain to support its businesses. The company is using Microsoft Azure cloud and AI to process and analyze data generated by production machines in its manufacturing facilities.

“We see digital as a massive business accelerator,” says Sandeep Dadlani, Mars’ chief digital officer. “We’re not doing digital for digital’s sake.”

Mars is using Microsoft’s Azure Digital Twins IoT service to augment operations across its 160 manufacturing facilities, with help from Accenture’s digital manufacturing and operations consultants. The company is creating software simulations to improve capacity and process controls, including boosting the uptime of machines via predictive maintenance and reducing waste associated with machines packaging inconsistent product quantities. Using the digital twin construct, Mars can also generate a virtual “app store of use cases” that can be reused across its business lines.

Looking ahead, the company plans to use digital twin data to account for climate and other situational considerations that affect its products, establishing greater visibility into its supply chain from product origination to the consumer.

Dadlani’s advice: Experiment and embrace failure. Mars encourages its employees to consider solving problems using AI and other emerging technologies where it makes sense. It’s all part of a massive effort to change the company’s culture to one that embraces experiments and expects staff to learn from failure so it can be applied to future successes. Last December, the company convened a virtual AI Festival to celebrate 200 AI use cases deployed across various business lines.

“If you can define a problem very well, you should feel empowered to solve it using AI,” Dadlani says.

TIAA reduces client service complexity

The Teachers Insurance and Annuity Association of America-College Retirement Equities Fund (TIAA) helps teachers manage their retirement funds. To reduce the complexity of onboarding new institutional clients, the not-for-profit financial service provider is using a digital twin powered by a graph database.

“At TIAA, we have a very complicated retirement product offering, based on all the regulations the IRS has,” says Alex Pecoraro, managing director and head of retirement services technology at TIAA. “In order to do the setup, it requires quite a bit of business knowledge, and we have whole teams organized around doing that.”

TIAA’s Outsourced Services consist of more than 600 features, which can yield more than one trillion possible client configurations. Prior to deploying digital twin technology, specialized TIAA teams manually created and tested the technical configurations against a client’s desired operating model. As a result, TIAA’s associates were highly “functionalized” according to their expertise, meaning associates could handle only certain types of offers. This also made scaling operations difficult.

To tackle the issue, Pecoraro’s team created a digital twin consisting of a graph database that represents the 600-plus features, with control nodes used to represent the complex grouping logic. Data nodes represent the data fields required for implementing a feature, and relationship links denote dependencies, validations, and exclusions.

The database has reduced the amount of time and expertise required for client onboarding.

Pecoraro’s advice: Change your perspective. Pecoraro says the key to the project was taking a product adoption approach rather than viewing it as a technical configuration problem.

“There was one fellow on the team who came up with this idea of shifting our attention from configuration to what the client is doing and what offer they’re purchasing,” Pecoraro says. “That perspective shift was the linchpin. It might seem obvious in retrospect, but when you’re immersed in all the details, you can get lost in the forest for the trees.”

Bayer Crop Science reshapes strategy with virtual factories

Bayer Crop Science has leveraged digital twins to create “virtual factories” for each of its nine corn seed manufacturing sites in North America. Seeds are harvested from Bayer’s fields, go through the nine sites for processing and bagging, and are then distributed to the farmer.

“Now we can reimagine our business processes. We can reimagine our decisions through the application of these machine learning algorithms or simulations,” says Naveen Singla, the Data Science Center of Excellence (COE) lead at Bayer Crop Science.

Bayer has created a dynamic digital representation of the equipment, process and product flow characteristics, bill of materials, and operating rules for each of the nine sites, enabling the company to perform “what-if” analyses for each one.

As the commercial team introduces new seed treatment offerings or new pricing strategies, the business can use the virtual factories to assess the site’s readiness to adapt its operations to deliver those new strategies. The virtual factories can also be leveraged for making capital purchase decisions, creating long-range business plans, identifying new inventions, and improving processes. Bayer can now compress 10 months of operations across nine manufacturing sites into two minutes, enabling it to answer complex questions regarding the SKU mix, equipment capability, process order design, and network optimization.

Singla’s advice: Know the business domain. Singla says a big key to Bayer’s success was that the decision science team tasked with building the digital twins, lead by Shrikant Jarugumilli, head of decision science – connected virtual systems, spent a lot of time at the manufacturing sites to understand their operations and win the support of stakeholders.

“Having our data scientists understand the domain of the business has been so critical, and that’s where Shrikant comes in,” Singla says. “He and his team spent numerous weeks at these seed manufacturing sites trying to understand the operations, understand the nuances so that the message as they are talking to leadership is in the language of leadership itself versus the parlance of machine learning.”