Digital Reflections | Digital Twin Consortium

Strategic Guidance to Reduce the Risk of Digital Twin Adoption

By Ron Zahavi, Executive Director, Digital Twin Consortium, Chief Strategist for IoT Standards, Microsoft Azure IoT

 

 

In my role at Microsoft, I represent the company on several standards organizations and consortia, including the Digital Twin Consortium (DTC). Microsoft was one of the founders of the DTC two years ago with the intent to reduce confusion in the marketplace about the definition of digital twins, to accelerate the market, and address interoperability needs. The resulting ecosystem is capturing best practices, defining case studies, and driving the innovation of digital twin technology.

In December 2020, the Digital Twin Consortium released this definition of a digital twin: “a digital twin is a virtual representation of real-world entities and processes, synchronized at a specified frequency and fidelity. Digital twin systems transform business by accelerating holistic understanding, optimal decision-making, and effective action. Digital twins use real-time and historical data to represent the past and present and simulate predicted futures. Digital twins are motivated by outcomes, tailored to use cases, powered by integration, built on data, guided by domain knowledge, and implemented in IT/OT systems.” The consortium’s definition of digital twin provides a foundation for an emerging marketplace, accelerates digital twin adoption, and encourages collaboration. Most important, our consensus-driven definition unifies an emerging industry and speeds our members' time to market.

Since then, the DTC has launched an open-source initiative with several projects, is capturing the value of digital twins through real case studies as part of its Value Innovation Platform, expanded its reach through regional branches around the world and multiple liaisons, and added new vertical industry working groups. We're also participating in many industry-led digital twin events.

After two years we are seeing rapid adoption of digital twins across many industries, and we have almost 250 companies as members of the DTC. As the market matures, we are seeing a shift from start-ups to larger companies and end users are joining to help capture the requirements for digital twins and address them.

The bottom line is that today, the industry recognizes digital twins as crucial to digital transformation.

I've enjoyed being Secretary of the DTC Steering Committee, and I am honored to have been selected to be the organization’s Executive Director. In this role, I will be working with DTC staff and Steering Committee to identify, define, and drive strategy based on organization and member goals and priorities. We will continue expanding our activities to demonstrate the value of digital twins, to drive standards requirements, and make an impact through innovation and open-source development – to be the authority on digital twins.

Digital Twin Interoperability Framework

Anto Budiardjo, CEO of Padi, and Doug Migliori, Global Field CTO of Cloud Blue, describe the digital twin system interoperability approach taken by the Digital Twin Consortium. The presenters are the Chairs of the DTC Interoperability Tiger Team.

 

 

Machine Learning Unlocks New Real-Time Applications for Digital Twins

By Dr. William Bain, CEO, and founder of ScaleOut Software

 

 

The digital twin concept encompasses use cases for both product lifecycle management (PLM) and for real-time streaming analytics in live systems. The latter is becoming ever more important as our society increasingly relies on a fast-growing population of IoT devices. With billions of smart devices constantly generating data, the task of tracking their telemetry and extracting real-time intelligence has become extremely challenging. Applying the digital twin concept to real-time analytics for IoT promises to address this challenge by revealing real-time insights, enabling immediate responses to emerging issues, and maximizing overall situational awareness.

Consider a software telematics application that tracks a nationwide fleet of trucks to ensure timely deliveries. Dispatchers receive telemetry from IoT-connected trucks every few seconds detailing their location, speed, lateral acceleration, engine parameters, and cargo viability. In a classic needle-and-haystack scenario, dispatchers must continuously sift through telemetry from thousands of trucks to spot issues, such as lost or fatigued drivers, engines requiring maintenance, or unreliable cargo refrigeration. They must also intervene quickly to keep the supply chain running smoothly. Digital twins can implement real-time analytics that helps track these devices and tackle the seemingly impossible task of automatically sifting through telemetry as it arrives, analyzing it for anomalies needing attention, and alerting dispatchers when conditions warrant.

To analyze telemetry streams from IoT devices, such as truck engines or refrigeration units, algorithms for real-time analytics must be able to identify unusual changes that deviate from normal patterns and indicate the need for intervention to avoid expensive, unscheduled downtime. While analytics code can be manually crafted in popular programming languages like Java and C#, creating algorithms that uncover emerging issues hidden within a stream of IoT telemetry can be daunting or, at a minimum, complex to devise. In many cases, the algorithm itself may be unknown because the underlying processes which lead to anomalies and, ultimately, device failures are not well understood. The same challenge applies to telemetry that analyzes human behavior, such as tracking lateral accelerations of a vehicle to detect a fatigued or erratic driver.

In cases like these, the fast-maturing science of machine learning (ML) can come to the rescue. Instead of trying to devise code that analyzes complex, poorly understood fluctuations in telemetry, application developers can instead train an ML algorithm to recognize abnormal patterns by feeding it thousands of historic telemetry messages that have been classified as normal or abnormal. After training and testing, the ML algorithm can then be put to work monitoring incoming telemetry and alerting personnel when it observes suspected abnormal behavior. No manual analytics coding is required.

The ML algorithm needs to run independently for each data source, examining incoming telemetry within milliseconds after it arrives and then logging events or alerting personnel when required. A new type of digital twin called a “real-time digital twin” provides a powerful new way to accomplish this. Running as a software component within an in-memory computing platform, each real-time digital twin processes telemetry from a unique physical data source, such as a truck within a fleet (or any IoT device). Instead of modeling behavior as a PLM digital twin would, it can host an ML algorithm or other real-time analytics algorithm and can generate alerts when it detects anomalies needing attention.

In this way, digital twins can harness the power of ML to provide predictive analytics that automates the discovery of anomalies that are otherwise difficult for humans to detect. Once an ML algorithm has been trained on historic data, it can be deployed to run independently in each digital twin. Real-time digital twins examine incoming telemetry immediately after it arrives. This technique provides much faster responses than would be possible using offline, big data analytics hosted in a data lake.

Thousands of real-time digital twins run together to track incoming telemetry from their data sources and enable highly granular real-time analysis that assists in timely decision making. The in-memory computing platform routes incoming telemetry to its corresponding real-time digital twin and processes it within a few milliseconds. Each digital twin independently runs its own ML algorithm to spot anomalies from a given data source. By mapping all digital twins to a cluster of physical or virtual servers, the in-memory computing platform can ensure real-time results at scale.

In addition, the platform can continuously aggregate state information from all real-time digital twins and visualize the results to help personnel boost situational awareness. While the digital twins sift through telemetry and generate dynamic information about the state of the data sources, fast in-memory computing creates an aggregate picture that pinpoints strategic issues and trends. For example, the telematics application can quickly spot regions where unusual delays are occurring due to weather conditions or highway blockages, enabling managers to reroute trucks and minimize additional delays.

Even as digital twin technology has exponentially advanced over the last several years, the incorporation of real-time analytics with ML into this technology creates important new opportunities for the digital twin concept. With the explosion in telemetry from billions of IoT devices and other data sources, the need for finding small anomalies that can emerge to impact the operation of live systems has become more difficult than ever. Because digital twins can encapsulate state information about individual data sources and run analytics code in real-time, they are particularly well suited to meeting this challenge. They can unlock new capabilities and enhance situational awareness that enables fast, informed decision-making and better insights than ever before.

 

The Need for a Simple Scalable System Interoperability Mechanism

By Anto Budiardjo - CEO, Padi, Inc. (left) and Doug Migliori - Global Field CTO, CloudBlue (right)

• 
• 

Interoperability is a core concept of computer systems and networks, denoting the ability to discover, connect, and interact with other entities within an application’s broader context. In today’s distributed computing paradigm, efficiently achieving interoperability at all levels of the technology stack is paramount to deriving the most benefit from a system of systems.

For decades, interoperability has focused on making discrete components work in conjunction with one another. The Internet is perhaps the best example of billions of devices interoperating at technical and syntactic levels in a truly distributed fashion. At a smaller scale, the dynamic discoverability and capabilities matching of a simple USB is another example of the value created through a common interoperability mechanism. The ability to instantly use a device connected via USB with our laptops is an impressive feat of technology that we frequently take for granted.

As we discover new applications of digital twin systems for the betterment of business and society, we become increasingly aware of the importance of interoperability. Ensuring that these systems' discrete components and the broader system of systems are interoperable is essential to unlocking their potential with less implementation cost, less risk of failure, and less complexity at scale. In many ways, we strive to create a framework that would enable USB-type compatibility and ease for all systems connected to the Internet and private networks. Developing such a framework is daunting as most systems perform specific tasks and do not inherently interoperate with outside entities. System integrators typically handle such tasks.

The labor-intensive work performed by the $400B+ global system integration industry is often unnecessary. We argue that we may ease this burden by designing systems around a common framework and utilizing common mechanism(s) to interoperate like USB devices. Doing so empowers those working in system integration to maximize their efforts' value, designing applications that perform as intended rather than through point-to-point integrations.

The Digital Twin System Interoperability Framework white paper provides the framework for such activity, delivering on the authors’ aim to characterize the multiple facets of system interoperability. Our descriptions have been distilled into seven key concepts framing the design considerations necessary to make systems interoperate at scale. While the authors may not have contemplated all permutations of system interoperability, evaluating a digital twin perspective within the Digital Twin Consortium has provided the breadth and depth of scope necessary to address this paper’s objectives.

We have created a framework capable of unlocking significant value in complex distributed computing systems such as digital twins. As we invite you to review, challenge, refine, and adopt this framework, we hope it proves helpful in designing computing systems that improve our lives.

For more information about the framework, download it here or watch the webinar on-demand: How System Interoperability Empowers Digital Twins.

An Introduction to the Next Generation of Digital Twins

By Maximilian Mayr, Lead Web Developer, Tributech Solutions GmbH

A holistic view of products, processes, or even the whole value chain to enable closed-loop engineering, cross-company digital services, and more is a crucial success factor for any data-driven organization. The next generation of digital twin technologies will play a key role in standardizing and automating business processes across current boundaries of systems and companies. This blog post introduces the general concept behind digital twins and the latest standards in this area.

A digital twin is usually a digital representation or abstraction of a real-world entity like a machine or device. They are already a part of the daily business in many industries and applications. However, most of today's digital twin solutions are siloed applications with a minimal scope regarding the life cycle or value chain. We are just beginning a robust growing technology ecosystem that will transform businesses worldwide by rapidly increasing their process efficiency and automation. A recent market analysis from grand view research predicts an annual growth rate of 42.7% from 2021 to 2028, expanding the market size from $7.14 billion to $86.09 billion.

The next generation of digital twin technologies and standards will enable applications with a holistic view along the value chain and life cycle. These technologies will also simplify development and business operations across boundaries of a system or company by standardizing access, configuration, and representation of physical assets, processes, and more. As a member of the Digital Twin Consortium, Tributech is working at the forefront of a rapidly growing ecosystem around new digital twin technologies.

In this blog post, we are going to look at the general concept of digital twins. In a nutshell:

• Digital twins are a digital clone/representation of an entity, asset, process, or more.
• Organizations can use them to standardize operations by introducing a common and business-specific vocabulary.
• Organizations can use them to run simulations without affecting the actual devices.
• Organizations should reflect changes to an actual device in the digital twin and vice versa.

For example, an organization can model an (IoT) thermometer as a digital twin by describing its properties, interactions, and data. In technical terms, a digital twin should be the Single Source of Truth (SSOT) of a physical asset. The twin offers the possibility to communicate between the digital and the physical world. Due to that, organizations should apply any property change n the twin on the actual device. Additionally, real-time data of the device should also be accessible on-demand via its digital twin.

Going back to our thermometer example, instead of looking at the device from a high-level perspective, it is also possible to represent the thermometer as a combination of different components like sensors, processors, and antennas. If each of these components again has its capabilities and data output defined using a digital twin, new possibilities would arise. By basing all device interactions on these digital twins, we can, for example, take one of the components of the actual device and replace it with its digital twin. In this way, we simulate how a device will react to different states and inputs of a replaced component.  Modeling a complete production line on digital twins, an organization can see the production increases or decreases based on various parameters.

Available Digital Twin Standards

We define digital twin vocabulary based on ontology, which allows the description of categories, properties, and relationships between concepts, data, and entities. Ontologies are expressed in a machine-readable format like RDF, Turtle, JSON-LD, and others. The most commonly known ontology is the schema.org ontology created by Google, Microsoft, Yahoo, and Yandex that is used throughout the world wide web to add metadata to websites that can get picked up by crawlers. Google, for instance, uses this information to populate its knowledge graph. You can use the graph to display an infobox in your search, where the essential information is immediately displayed. Furthermore, it is used to improve the overall results by understanding how entities are connected.

The goal is to have entities that can describe themselves using a so-called self-description. This self-description, shortly called SD, should tell you everything you need to know about the digital twin.

There are different standards to describe digital twins, for example, the Asset Administration Shell (AAS), the Web of Things (WoT) standard, and the Digital Twins Definition Language (DTDL).

 

© https://xkcd.com/

Each of those standards has some heavy players behind them. We at Tributes evaluated all of the standards and decided to use the DTDL standard initiated by Microsoft. The main reason for choosing DTDL is that it allows us and our customers to easily describe their use-case as a custom vocabulary based on linked data. Combined with the limited set of building blocks (Interface, Telemetry, Property, Command, Component, and Relationship), organizations can use DTDL to describe physical or digital things, processes, products, or entities that offer enough flexibility keeping the complexity as low as possible. Additionally, the representation of a DTDL instance is always the same, eliminating the need for complex parsing logic on the edge side.

We learned that we could use digital twins to handle assets, entities, or processes standardized, but why stop there? Why shouldn't we take a step further and introduce the benefits like time and money savings to other areas?

One example we use internally is configuration twins for IoT devices and microservices. Instead of adapting service configurations, we only modify the corresponding twin manually, and the service automatically adjusts itself.

I hope this article provided some new insight into the next generation of digital twins and their possibilities.