How Digital Twins foster innovation in IoT-enabled environments

Dynamic digital representations, or Digital Twins, are rapidly changing the way industries design, build and operate their products and processes. Gartner predicts, “by 2021, half of large industrial companies will use Digital Twins, resulting in those organizations gaining a 10 percent improvement in effectiveness.”

Powered by the Cloud, IoT, and AI, Digital Twins enrich complex systems like cars, wind turbines and buildings across their entire life cycles. A Digital Twin combines design, production and operational data. It allows assets to be tested before, during and after production, and across a wide range of environments.

IBM Research – Ireland is developing different Digital Twin technologies. These include:

  • A virtual platform for testing of complex IoT systems with live and simulated data.
  • Forming a knowledge graph for IoT that combines reasoning with machine learning to allow the system to autonomously analyze and understand life cycle data.

Utilizing a virtual testing platform for IoT systems

In order to test complex IoT Systems, our researchers are using a virtual platform. This allows designers and developers of transportation services to investigate large-scale connected car services. They achieve this by merging simulations of large-scale automotive IoT deployments with proof-of-concept capabilities provided from real world vehicles. This platform is helping automotive partners design their services at scale while accelerating time to market.

The platform also allows drivers of actual vehicles to experience a large-scale connected scenario first hand. This combination of simulated and real-world data generates valuable insights. These insights are critical to user-centric development, resulting in reliable systems that are ready for the market. By embedding the data from actual vehicles into the digital environment, we can test the effects of assisted and autonomous driving in large-scale traffic simulations, in real time.

For example …

In collaboration with University College Dublin (UCD), we are using our virtual testing platform to evaluate a number of new mobility concepts. For example, we are testing a new car sharing mobility service that dynamically adapts to user preferences. This then allows a group of users to meet based on changeable traffic conditions and their variable pick-up time arrangements.

We are also investigating using IoT services to maximize air quality intake for pedestrians and cyclists by reducing their exposure to pollution. Imagine an electric bike using IoT devices, such as mobile phones and sensors. These IoT devices detect and automatically assist the cyclists when traveling through areas of high pollution. In those areas, the engine of the e-bike would be automatically triggered into operation. When that happens, it reduces the cyclist’s pedaling effort, resulting in a lower breathing rate and lower pollution intake. The virtual testing platform can also be used to connect to the e-bike and monitor how the cyclist would actually react to this new service, investigating the interactions between the cyclist and the bike.

Another service solution we are evaluating would reduce a pedestrian’s exposure to car exhaust pollution. How? The AI controls of a hybrid car to automatically switch between combustion and electric mode when the vehicle is in close proximity to pedestrians and cyclists.

These examples illustrate how a virtual testing platform can help accelerate the development of new services. At the same time, it also helps the transportation industry respond to the ever-increasing demands for environmental accountability.

Automating Insights with a knowledge graph for IoT

At IBM Research – Ireland, we are developing AI technologies to connect and understand IoT data in new ways. We’re combining machine learning with knowledge graph reasoning to enhance data being extracted from an IoT network. And we’re also adding layers of semantic meaning to create new insights within the network. This technology is the Digital Thread at the core of each Digital Twin. It connects information along the lifecycle stages into a knowledge graph. This graph then enables new informed decisions and automation of processes.

By using a knowledge graph, we are able to organize data and its variables being extracted into groups and establish the relationships between the data sets and their variables. The knowledge graph provides a shared vocabulary of information that can be used to create a model of a domain, the types of data within it, their properties and the relationships between the data–and we are using natural language to do all of this.

As a result, our AI solution understands the meaning and the relationships between the different types of data within a network or system. This gives our research teams new ways to derive innovative insights from an IoT system and present them as new knowledge and information to end users.

Self-diagnosing problems

For example, take an IoT temperature sensor in a building. The temperature sensor has data readings, the type of data that it is recording and its location. Our AI system understands general concepts of physics and how temperature is influenced by heating or cooling, such as environmental factors, heat system controls and so on. This allows our system to form a knowledge graph to understand the temperature settings within the building and the multiple factors that impact the temperature within its operating environment. This allows for the self-diagnosis of problems within the system while enabling it to learn and understand this relationship over time. It is also scalable and works across industries such as retail and automotive.

Our virtual testing platform and knowledge graph for IoT demonstrate the value of Digital Twin. We’re enabling industries to create better informed designs, optimize production, and manage efficient operation. The virtual testing platform can simulate these large-scale environments and networks while providing a way to perform controlled user-acceptance tests.

This combination of simulated and real-world data generates valuable insights that are critical to systems development. Our knowledge graph for IoT is a scalable solution that enables IoT to learn system behaviors, to understand management operations and to self­-diagnose problems. And all while making human­-machine interaction more natural and intuitive.

We will demonstrate the knowledge graph for IoT at the IEEE flagship IoT conference World Forum IoT, February 5-8th in Singapore.  A prototype of the virtual testing platform will be shown at the ENABLE-S3 consortium General Assembly, Review and Marketplace event. This is scheduled at our Research lab in Dublin on July 4, 2018.

For deeper research on Digital Twins and related topics, see:

Joern Ploennigs, Amadou Ba, Michael Barry, Materializing the Promises of Cognitive IoT: How Cognitive Buildings are Shaping the Way,  IEEE Internet of Things Journal, 2017

Wynita Griggs, Giovanni Russo, Robert Shorten, “Leader and Leaderless Multi-Layer Consensus With State Obfuscation: An Application to Distributed Speed Advisory Systems”,  IEEE Transactions on Intelligent Transportation Systems, 2017

The post How Digital Twins foster innovation in IoT-enabled environments appeared first on Internet of Things blog.

Internet of Things blog

Part 4: Developing IoT-enabled Autos – A Tsunami of Change – Leveraging the IoT

In the first three parts of this series we explained the process transformation that is taking place In IoT-enabled autos. I’ve discussed the emergence of model-based systems engineering (MBSE) and the movement toward the Scaled Agile Framework (SAFe) in modern engineering practices. The final component driving automotive development forward is the promise of cognitive systems and how they help at key junctures in the process.

But we haven’t yet talked about the 700-pound gorilla: The most important part of this journey is the ability to leverage the Internet of Things (IoT). That then lets you directly understand how today’s vehicles operate on the roads.

The IoT is now influencing all aspects of driving.

The IoT means time gaps are narrowing

Traditionally, engineers had to wait months after a vehicle’s release to get a detailed view of how it was performing. After new vehicles are sold, it takes time for consumers to recognize issues and take them back to their dealers. Dealers offload vehicle data and then send periodic information back to OEMs. There could easily be a three- to six-month gap before initial data makes its way back to engineers.

And that’s just the vehicles that were taken back to dealers. What about consumers who allow an issue to linger before doing anything about it? What about data from the other cars that weren’t directly problematic?

There’s also the issue of context. When a problem with a vehicle was observed by its driver, what was the weather like in that moment? Or the road conditions? How was the car being driven when the issue occurred? All of this may be lost through current processes where data is only obtained from the subset of cars that their drivers brought in for service.

We can do much better.

Enabling preventive maintenance

As this transformation unfolds, the sensor systems already in cars will be accessed in real time, through IoT platforms and with vehicle-to-cloud connectivity that enables integration to engineering systems. Engineers should then be able to obtain this data from vehicles as soon as they hit the roads. They can aggregate it, analyze it, and diagnose it before those issues even turn up at a dealership. And with much less time than it would take the same information to traverse through the existing process. This video explains IBM’s vision for how IoT systems will work closely with engineering systems.

The ability of engineers to interact with vehicles directly through over-the-air updates is also a game-changer. It allows engineers to remotely update relevant vehicle software. Vehicle issues that can be fixed through software can be resolved while IoT-enabled autos are parked in their garage overnight. Issues remain for automotive OEMs to work out how these over-the-air updates will affect existing dealer networks in servicing vehicles.

Extending vehicles’ lifespan while improving performance

Over-the-air updates also introduce another new and exciting feature to vehicle owners. Vehicle software will be updated to give owners new capabilities and services throughout the life of the car. We’ve practically taken this for granted on our smartphones, but we still have practically no expectation of attaining new vehicle features remotely in our cars. Tesla, for example, not only deployed its Autopilot as an over-the-air update, but during last summer’s Hurricane Irma in Florida, the company provided an extended battery range capability to nervous customers who were stuck in long traffic jams while evacuating from the affected areas. I would imagine those Tesla owners are highly satisfied.

To find more information about all these innovations, visit IBM’s IoT for Automotive solution for connected vehicles as well as IBM’s Continuous Engineering suite.


The post Part 4: Developing IoT-enabled Autos – A Tsunami of Change – Leveraging the IoT appeared first on Internet of Things blog.

Internet of Things blog

Part 3: Developing IoT-enabled autos – a tsunami of change – the journey to cognitive

We’ve already recognized the emergence of model-based systems engineering (MBSE) and the wisdom of using the Scaled Agile Framework (SAFe) in modern engineering practices. In part three of my series highlighting the ways that automotive product engineering is evolving, we’ll examine the promise of cognitive systems. It’s the final component driving automotive development forward, helping at key junctures in the process.


Cognitive analytics and systems are shaping the future of product development.

Speeding product development with cognitive

To date there are only limited examples, but AI systems will be able to shortcut and further speed vehicle development.

Cognitive analytics can examine volumes of unstructured information. This includes machine learning, natural language processing and speech/image recognition to find new patterns that mimic human thinking. This can be invaluable wherever AI is applied. Let’s consider a few examples.

AI systems like Watson can be a question-and-answer engine as a single source of knowledge. Engineers in the early stages of development often try to determine new interfaces, materials and capabilities for vehicle software. It’s exceedingly difficult to sort through academic and industry research, consumer studies and global trends to coalesce around the best direction. But learning systems can effectively facilitate that process.

Embracing requirements management

Requirements management is also a great opportunity for cognitive analytics. Quality assessment, resolving duplication and conflicts, as well as finding missing requirement gaps, all can be helped by AI. For example, cognitive systems would be great at classifying and tagging in order to better cross-reference requirements that may have interdependencies.

Using content analytics to limit recalls

And what about recall management? Engineering issues have to be dealt with throughout the vehicle’s life. Automotive recalls have spiked the past few years, leading to some very high-profile, expensive incidents that have harmed certain automakers’ brands and bottom lines. Many of these are software related, and many recalls are identified from consumer complaints and automakers’ submissions to the National Highway Transportation Safety Administration (NHTSA). For faster resolution, these can be analyzed through content analytics to diagnose and mitigate vehicle defects.

But if you’re ready to learn more now, visit IBM’s suite of Continuous Engineering solutions. Or visit us at the upcoming Consumer Electronics Show or the Automotive News World Congress, January 16-17 in Detroit.

Next up: Part 4 – a video overview of autos in an IoT-enabled world.

The post Part 3: Developing IoT-enabled autos – a tsunami of change – the journey to cognitive appeared first on Internet of Things blog.

Internet of Things blog

Part 2: Speeding to SAFe and developing IoT-enabled autos: a tsunami of change

Welcome back! Today is part 2 of my series highlighting the ways that  product engineering for IoT-enabled autos must adapt to new methodologies.

We’ve discussed how model-based systems engineering (MBSE) is transforming product development across the automotive and virtually every industry. Today we’ll look at another big transformation: the overall speed of engineering and subsequent product changes.

SAFe explained

Consumers want their vehicles to fit into their digital lives. That means updates at an Internet pace. That’s why the speed of development matters. Practices can be greatly improved through the Scaled Agile Framework (SAFe).

SAFe relies on three main disciplines:

  • Agile software development that works through collaborative teams.
  • Lean product development that focuses on cost and cycle-time reductions.
  • Systems thinking that considers the functional interrelationship between various sub-systems as part of a larger system.
Retina Display-GettyImages-692580784

Automotive companies are using SAFe to speed development processes.

Collaboration is key

Agile software development relies on collaborative teams being able to move faster. “Standup,” “scrum” and “sprint” meeting formats are the new normal. Developers use these practices to transform their procedures and cut time out of development cycles. It’s all aimed at keeping teams small and highly focused.

Collaboration software, like Team Concert, is the key. It coordinates dispersed teams around near-term achievable goals that drive the process ahead.

Lean development 2.0

Lean product development is not new; it’s an offshoot of lean manufacturing. Popularized by Toyota in the 1980s and 1990s, it focuses extensively on reusable knowledge. When teams drop the “not invented here” syndrome and leverage work that has already been completed, they can more rapidly introduce new product variants. Do lean and agile sound similar? Here’s a good comparison between the two.

Think like a system

Also front and center for automotive developers is the concept of systems thinking. The transportation infrastructure that vehicles must fit into is already complex. It’s becoming even more so as IoT-enabled autos proliferate. They will gather and respond to information from the cloud. Successfully developing autonomous cars adds even more complexity to the equation.

Systems thinking helps explain how multiple systems have co-dependencies and critical connection points. Those are important because they enable the coexistence of many different suppliers across an ecosystem.

Today’s automotive companies have their suppliers regularly integrate new capabilities every six weeks. They can only attain this through a highly structured process. And SAFe allows lean, agile teams to collaborate, align and deliver multi-functional software to complex systems.

IBM fully supports SAFe and enables its deployment through templates in its Collaborative Lifecycle Management solution. We provide extensive support in getting engineering teams started with SAFe.

Next, we’ll talk about the promise of cognitive systems, which is an exciting new frontier for automotive engineering.

In the meantime, to learn more about IBM’s suite of Continuous Engineering solutions, please visit our site. You can also talk to us at CES in Las Vegas or the Automotive News World Congress, January 16-17 in Detroit.

And for an even closer look at the impact Watson IoT is having in the development world, plan on attending Think 2018, March 19-22 in Las Vegas.

The post Part 2: Speeding to SAFe and developing IoT-enabled autos: a tsunami of change appeared first on Internet of Things blog.

Internet of Things blog

Part 1 Developing IoT-enabled autos: a tsunami of change

Welcome to 2018! This year will see a continuation of the far-reaching transition that’s underway in the world of complex product engineering. To get you up to “speed” on IoT-enabled autos, I’ve written a four-part series. I’ll highlight the ways that automotive product engineering must adapt to new methodologies if they want to stay competitive and improve the customer experience.

And it’s just in time for the Consumer Electronics Show (CES), Automotive News World Congress and the North American International Auto Show (NAIAS). All promise exciting car technology to start off the year.

2018 continues a far-reaching transition that’s underway in the world of complex product engineering. To get you up to “speed” on IoT-enabled autos, I’ve written a four-part series. I’ll highlight the ways that automotive product engineering must adapt to new methodologies if they want to stay competitive and improve the customer experience.

Cars in transition

Entirely new development systems, agile methods and the introduction of cognitive, AI-driven analytics have dramatically improved how IoT-enabled vehicles are brought to market. These changes also impact how cars are updated throughout their lifecycle.

Many of these changes have been driven by consumer demand. Drivers want their connected vehicles to not only work flawlessly, but to be updated with new capabilities for as long as the they are in use.

Automakers and their partners are using IoT to improve performance, safety and development processes. Automotive companies in particular are striving for leadership in several interdependent areas. In these areas, requirements are evolving rapidly even as capabilities are still growing. They include:

  •    Development of new cloud-based information services.
  •    Cybersecurity in connected and autonomous vehicles.
  •    Alternative propulsion systems.
  •    Improved active-safety.
  •    The race toward autonomous driving.
  •    Differentiating the in-vehicle experience

So, is that enough on their plates? Only a fraction of this was in play a decade ago. And it requires dramatic changes in how cars are being developed.

Welcome to a complex world of code

In the premium segment, vehicles have 10s of millions of lines of code. And it must all be verified, tested and maintained to produce the most exciting products on the planet.

The days where your 10-year-old vehicle is frozen in time (before smartphones) will soon be behind us. And just like your other smart devices, cars will be updated with new capabilities through software delivered via the cloud.

Transitioning to Model-based Systems Engineering

The overall approach to the discipline of engineering is experiencing a long transition to model-based systems. These require deployment of new software and processes, particularly in systems engineering. Though engineers have used CAD models for many years to document designs, even the most sophisticated auto manufacturers largely rely on text- and document-based systems when developing functional systems and product architectures.

Goodbye, Microsoft Office

Text-based systems are exactly what you’re probably envisioning. They include information input in text by engineers during development. Engineers have long utilized many of the same basic tools that are a staple throughout the corporate world. MS Office, Visio, Wikis and other text-based documentation systems are used to build incredibly complex products.

Process diagrams may be drawn with flow figures, lines and arrows that remain static until manually re-drawn. Other schematics, photos and development collateral may be available as well. Even companies that have done a good job with repositories and tagging still have issues with the efficiency of product development.

That may work for simple products. However, cars and planes have lifecycles that are decades long. As engineering teams work on the various systems described above, how will they make sure that functional interdependencies aren’t affected by changes in one sub-system that may touch others?

Hello, model-based systems engineering

This is where model-based systems engineering (MBSE) comes in. MBSE was originally developed by the International Council of System Engineering (INCOSE), which provides a nice primer on why it makes sense.

Not too long ago, we hosted the third IBM Watson IoT Continuous Engineering Summit. We brought together engineers from several industries, including automotive. There, they shared how their approach to innovation in product development and lifecycle management is changing. At the event, Johan Gunnarsson from Combitech AB/Saab suggested that the change to MBSE will be so dramatic that automobiles are fast becoming as complex as fighter jets.

I agree with him. That’s why I appreciate MBSE-focused engineering software, like IBM’s Rhapsody. It provides the basis for developing domain models that become common communication tools among engineers. Rhapsody also allows the entire system to be simulated to understand interdependencies between sub-systems and components. This is particularly helpful when developing complex products like vehicles, which are built by OEMs through a multi-tiered network of suppliers.

The transformation in systems engineering addresses the need to efficiently deal with product variants. That’s valuable because consumers want vehicles that can be personalized both physically and digitally. MBSE also helps address change management to both vehicle hardware and software throughout its long life.

Tomorrow, I’ll discuss product development within a scaled agile framework. In the meantime, if you’d like more information about these trends and IBM’s suite of Continuous Engineering solutions, visit our landing page.

And if you’re at CES, please stop by the Las Vegas Convention Center, say hello and see how #AccessibleOlli is changing transportation.

The post Part 1 Developing IoT-enabled autos: a tsunami of change appeared first on Internet of Things blog.

Internet of Things blog