All posts by Eurotech

Digital Twins for industrial automation

Digital Twin and Its Future in Industrial Automation

Industrial automation is undergoing a digital revolution as ‘Industry 4.0’ and Digital Twin technologies introduce new and innovative ways to execute manufacturing processes.

With IoT, artificial intelligence (AI), machine learning, and deep learning at the forefront, manufacturers will have spent close to $70 billion on these new technologies by 2020 to meet new demands.

Investments in new IoT and AI technologies for digital twins

Among these technologies, Digital Twin is changing how industrial manufacturers approach product design, operations, and post-sale services.

“Digital Twin solutions open new opportunities for industrial firms to speed up their Big Data- and AI-driven innovation transformation efforts,” Forrester reports.

A combination of vendor marketing and education—along with real-world benefits realized in Digital Twin use cases—are driving Digital Twin adoption among industrial manufacturers as they become an integral part of companies’ IoT and digital strategy investments.

What is a ‘Digital Twin’?

“Digital twins — digital representations of people, processes and things — will become more connected, providing a rich and real-time view of company processes and assets. Enterprise architecture and technology innovation leaders must plan for a diverse environment with integration challenges.”

Gartner, Top 10 Strategic Technology Trends for 2019: Digital Twins, 2019

A ‘Digital Twin’ is a digital model of a real-life object, most often a physical machine. Gartner defines a digital twin as “a software design pattern that represents a physical object with the objective of understanding the asset’s state, responding to changes, improving business operations and adding value.”

For industrial manufacturers, a digital twin allows them to create digital models of real machines, then combine both digital and physical data to deliver a better understanding of the performance and potential value of those physical machines.

This applies to all aspects of the machine’s functionality—production, maintenance, user experience, and more.

Each Digital Twin is used as a proxy for a real machine, allowing manufacturers to test concepts and hypotheses before applying them to physical machines themselves.

This digital technique—called ‘encapsulation’—allows manufacturers to adapt the digital ‘machine’ before applying changes to real hardware, which is costly and may impact other connected systems.

Digital Twins therefore have a wide variety of benefits and applications. Manufacturers can simulate plans, processes, and systems with zero risk, helping them visualize any variety of new strategies—and their results—before investing real resources in their development.

Conceptually, Digital Twins are simple. There is one Digital Twin ‘per thing,’ and that Digital Twin is updated alongside the ‘thing.’

This allows for the best possible results during experimentation. But despite its simplicity, Digital Twins have a wide range of applications, and are suitable for just about any machine model.

How to use Digital Twin for industrial automation?

Digital Twins have proven especially useful when integrated with IoT systems in industrial manufacturing.

“We see digital twin adoption in all kinds of organizations,” says Benoit Lheureux, research vice president at Gartner. “However, manufacturers of IoT-connected products are the most progressive, as the opportunity to differentiate their product and establish new service and revenue streams is a clear business driver.”

This is especially critical as IoT becomes more commonplace in industrial manufacturing environments. IoT sensors are already collecting data on real-world machines for analysis in cloud environments—building a congruous Digital Twin with each machine is a cost-effective addition to this already connected model, and can only help manufacturers improve machines and processes in the supply chain.

“The Digital Twin is not a new idea: Designers and makers of machines have long recognized the value of being able to simulate those machines on a computer screen. But growing enthusiasm for connecting machines to the Internet of Things (IoT), and for delivering services instead of only selling products, means that the Digital Twin is becoming relevant to a broader audience.”

Forrester, “Digital Twins Combine Enterprise Data And IoT To Drive New Business Value,” 2019

In this way, Digital Twins significantly reduce the cost and work required to maintain and enhance physical things.

AI, machine learning, and deep learning allow for increased automation in these processes as well. Manufacturers can introduce new concepts in digital environments, then count on digital tools to both optimize them and execute them among their physical counterparts.

Digital Twin and industrial automation use cases

Industrial automation streamlines processes in multiple manufacturing environments and use cases, and its integration with Digital Twins is no exception. Humans can manipulate digital environments, suggest or make changes, and introduce additional resources to optimize Digital Twin (and subsequently machine) performance.

Industrial automation allows for these processes to unfold automatically in digital environments before applying new revelations to physical ones. This relieves humans of these responsibilities but safeguarding equipment until automated solutions are confirmed in digital environments.

As Gartner describes, “When combining the twin data with business rules, optimization algorithms or other prescriptive analytics technologies, digital twins can support human decisions or even automate decision making.”

This is especially useful in IoT environments, where data from machines can be fed directly into integrated Digital Twin and business intelligence (BI) solutions. IoT sensors allow BI solutions to pinpoint problem areas and opportunities to optimize, before developing a comprehensive solution on which manufacturers can act.

In one scenario, a Digital Twin for industrial robots was implemented. The Digital Twin allowed manufacturers to program the robots offline for multiple scenarios, where virtual commissioning of the system could be tested.

This dramatically speeds up testing processes and minimizes downtime for the physical machines themselves, “resulting in a higher availability as well as a higher reliability with less failure risk.” The introduction of automation into this scenario rapidly speeds up the virtual commissioning process, delivering results faster and with greater efficacy.

As machines provide real-time feedback via IoT into a Digital Twin, manufacturers can use the Digital Twin to automated predictive aspects of machine performance and maintenance.

In another scenario, the Digital Twin of a locomotive can analyze real-time and historical data and provide recommendations about on-board system status for predictive maintenance and remote monitoring, with minimal human oversight.

The shared evolution of industrial automation, IoT and Digital Twin technologies

“The rise of Digital Twins coincides with the rise of the IoT. When buying machines and other assets, support for Digital Twins and continuous development of twin capabilities should be a selection factor.”

W. Roy Schulte, Distinguished Vice President Analyst, Gartner

IoT empowers industrial manufacturers to learn more about their equipment and better understand processes in real time. However, IoT adds a new layer of complexity to manufacturing environments, where the optimal application and investment strategy for IoT sensors isn’t always clear upfront.

Industrial BI leaders can use Digital Twins to optimize IoT applications and get the most out of their data. Unlike incongruous systems, Digital Twins help manufacturers improve their IoT strategy, clarifying what are the highest-impact IoT applications to render desirable results in Digital Twin environments that reflect their physical counterparts.

Digital Twins streamline the delivery of real-world IoT data as well, where Digital Twin systems are designed to be congruous with those of physical machines. This is a desirable alternative to discerning IoT data in other analytical environments, where the data must be processed to suit the system.

Manufacturers and other companies are realizing the value of marrying IoT and Digital Twin technologies. Already, 13% of organizations implementing IoT projects use at least one Digital Twin; 62% are either establishing or plan to establish a Digital Twin alongside IoT processes, Gartner reports.

Optimizing Digital Twin with manufacturing intelligence

“Rapidly expanding Internet of Things and analytics programs powered by machine learning and artificial intelligence — as well as improving models and simulations — mean that Digital Twins are coming to fill a number of roles. And they’re going to make life better.”

Forbes, How Orlando’s Work with Digital Twins May Change How We Engineer Everything,” 2019

Industrial manufacturers have already identified dozens of successful use cases for automated and BI tools like machine learning, AI, and deep learning systems.

Digital Twins lend themselves to these environments as they connect seamlessly in existing machine applications. They simply serve as an alternative to physical machines in the application of these technologies to optimize results.

Scholars define this application as an ‘Intelligent Digital Twin’. It “consists of all the characteristics of a Digital Twin as well as artificial intelligence to realize an autonomous system”:

The Intelligent Digital Twin can therefore implement machine learning algorithms on available models and data of the Digital Twin to optimize operation as well as continuously test what-if-scenarios, paving the way for predictive maintenance and an overall more flexible and efficient production through plug and produce scenarios.

Automation Technology, “An architecture of an Intelligent Digital Twin in a Cyber-Physical Production System,” 2019

The introduction of automation allows manufacturers to increasingly remove human beings from processes where they are no longer required, instead applying human resources only to mission critical areas in much larger processes.

In this way, Digital Twins can realize their true potential—simulating vast industrial environments with intense precision, and without increasing workloads for human workers.

Conclusion: Digital Twins and our automated industrial future

Gartner predicts that by 2022, over two-thirds of companies who have already implemented IoT will have deployed at least one Digital Twin.

Today, Digital Twin solutions are most often delivered in coordination or even by the manufacturers of physical equipment in which companies invest. But while this model makes sense today, companies will increasingly look to integrate Digital Twins with one another to accommodate each ‘thing’ in increasingly integrated manufacturing environments.

It’s through edge analytics solutions—specifically, IoT-edge computing frameworks—that industrial manufacturers will realize their ideal Digital Twin integrations.

IoT Edge Framework architecture
The adoption of IoT Edge Frameworks – like Eurotech Everyware Software Framework – simplifies the abstraction of Digital Twins of real assets

Eurotech provides a user-friendly and simplified application development environment. It enables asset digitalization to manage their Digital Twins for advanced analytics and data management. Contact us today to learn more about how Digital Twins and industrial automation can transform manufacturing for your company.

Level 5 Autonomous Driving Challenges

The challenges of Level 5 Autonomous Driving

Autonomous Driving is classified according to the amount of human driver intervention. It ranges from Level 0 (no automation) up to Level 5 (full automation).

Enabling Level 5 Autonomous Driving in Automotive, Defense and other Industries requires collecting, storing and processing data at an unprecedented degree. This has been until now unattainable by Embedded Devices and Edge Computers.

Companies in the Automotive industry are spending billions of dollars in investments for developing Level 5 Autonomous Driving technologies. All these players are encountering a number of new challenges that span across many disciplines and technologies.

Embedded systems installed into vehicles must face six main challenges to enable Level Five Autonomous Driving:

  • Performance
  • Storage capacity
  • Ruggedness
  • Certifications
  • Compactness
  • Cooling

Performance

Sensors, LIDARS and other technologies supporting autonomous driving generate unprecedented amounts of data. They require ultra-high computational performance that goes beyond the traditional embedded computer capabilities.

Some sophisticated sensors require a bandwidth of 40Gb/s to transfer data, not only in peak conditions, but for continuous operations. Moreover, Level 5 Autonomous Driving applications require constant, reliable and real-time operations while keeping latency as low as possible.

Storage capacity

Level 5 Autonomous Driving applications largely exceed the storage capacity of typical embedded computing devices. Thinking about the 40Gb/s bandwidth mentioned above, it translates to almost 20TB in only an hour of operations.

Ruggedness

High Performance Embedded Computing (HPEC) systems and data loggers installed on vehicles must provide reliable, continuous operations for long period of time. They must operate in very harsh environments: withstanding shocks, vibrations, dust and wide temperature ranges.

DynaCOR 40-34 High Performance Embedded Computing system for Level 5 Autonomous Driving

Certifications

Embedded and electronic systems and Edge Computers installed into vehicles must comply with industry standards.

Automotive certifications, such as E-Mark and IEC 60068-2-6 / 60068-2-27 for shock and vibration are objective ways for characterizing the behavior of the system under stress in actual operating conditions.

Compactness

Space is more than often at a premium in embedded applications. Systems designed to fit into embedded environments must come with compact size, to be easily installed into vehicles.

However, HPEC systems provide tremendous amount of computational power and they easily heat up. Dissipating such an intense heat would require a proper and powerful cooling system that can be easily installed in the vehicle.

Cooling

High Performance Computing systems are typically bulkier than embedded systems due to heat dissipation issues: they are usually equipped with big fans that cannot be used in embedded applications where performance is sacrificed to adapt to space constraints.

However, High Performance Embedded Computing systems for Autonomous Driving must provide HPC performances into a vehicle.

Eurotech has a lot of expertise in designing liquid-cooled HPC (High Performance Computing) and HPEC systems. Liquid cooling is an ideal solution for HPEC systems in Autonomous Driving, as most of the cars are already equipped with liquid cooling systems.

Compared to air cooling, liquid cooling allows more computational density and a better energy efficiency: even though Eurotech’s HPEC systems can use up to 500W, the coolant would maintain a temperature of around 41-43°C.

The DynaCOR 40-34 and the DynaCOR 50-35 are unique examples of High Performance Embedded Computing systems that comply with all these requirements, winning the challenges of Level 5 Autonomous Driving: they provide flexible and configurable platforms that allow the creation of in-vehicle Data Centers to bring Artificial Intelligence to the Edge (Edge AI).

3 key railway standards with which every on-board embedded and IoT system should comply

Railway companies looking for new on-board electronic equipment or intelligent transportation systems should consider products that follow specific requirements in terms of operating temperature, shock and vibration resistance, EMC, and so on, in order to guarantee consistent and reliable performance in harsh and contaminated environments such as trains.

That is why on-board electronic devices like IoT gateways, edge computers and intelligent transportation systems should comply with the parameters defined by specific railway certifications. We will discuss three key standard requirements to meet the needs of today’s on-board railway and rolling stock applications..

Continue reading 3 key railway standards with which every on-board embedded and IoT system should comply

Does your enterprise depend on the Mobile Edge? Considerations for mobile computing at the edge of fleet enterprises

In the United States alone there are over 26 million commercial vehicles on the roadways and in operations1, ranging across the spectrum of logistics and heavy moving equipment to agriculture equipment and waste management vehicles.  In today’s connected enterprises, these commercial fleets are managed through tightly integrated operational systems that perform a multitude of services, including fleet management (automatic vehicle location, asset tracking, route optimization), monitoring of vehicle health and diagnostics, vehicle operator console operations, electronic data recording, and video capture.  These systems improve operational efficiencies, reduce costs, and enable delivery of enhanced services.

Enabling technology for all of these applications is the “Mobile Edge”, the ability to extend an enterprise’s operational systems to mobile computing platforms on deployed fleet vehicles.  A variety of options present themselves to both operators deploying these systems and technology companies offering communications solutions to those operators.  In choosing the right solution for the Mobile Edge, the operator or integrator must consider both hardware and software aspects of their system requirements.

Continue reading Does your enterprise depend on the Mobile Edge? Considerations for mobile computing at the edge of fleet enterprises

IT-Centric IoT Device Management

The edge of the IoT is where solutions connect, communicate and interact using sensors, actuators, gateways, agents and controllers. As technology advances vendors are touting “advanced management capabilities” for these devices at the edge. These capabilities vary, ranging from the simple ability to turn a device on and off to more complex actions such as updating software, managing Wifi connections, configuring security policies or changing data parameters.esf_framework

Continue reading IT-Centric IoT Device Management

The Benefits of a Java-Based Application Framework for IoT Projects

IoT projects present many challenges, even when the hardware is designed exactly to customer specifications. Building on proven architecture and software building blocks that would require many years to develop, the use of a Java-based IoT application framework will result in shorter, more deterministic device software development. Using an IT-centric approach to implement the device logic in smart edge devices improves both device management and embedded application management. Once this standard software platform is in place, connecting and getting business relevant data to the cloud is simpler than it ever has been before.

An advanced software framework that leverages OSGi and Java both isolates the developer from the complexity of the hardware and communications infrastructure and also complements the Multi-Service Gateway hardware for an integrated hardware and software solution.

MSGateway_Gate_Text

The benefits of IT-centric application development to implement business logic in smart edge devices/service gateways are:

Continue reading The Benefits of a Java-Based Application Framework for IoT Projects

agriculture wine plants

The Internet of Things: how IoT helps producing high quality wine

It’s easy to slip into the habit of thinking of the Internet of Things as a highly technical, industrial tool at home in factories, or fleets of high powered vehicles, but who’d have thought it can also help plants grow?

It can be near impossible to predict what any one growing season will bring. So much is at the mercy of the weather, availability or certification of crop protection products and numerous other factors which have to be given a ‘best guess’ in order to plan for them. The best way to predict the most likely outcome in any season is, of course, experience.

Continue reading The Internet of Things: how IoT helps producing high quality wine

How Important is it to Protect Athletes from Concussion and Injury?

Football Player

Sports are fun. Fun to play, fun to watch, and I hear they can even be fun to coach. When I was kid running cross-country, the biggest challenge was getting up the killer hill on the Montpelier, VT high school course. My kids played different sports growing up, where they were getting into tight quarters, battling for a puck or ball with one or more players at a time. Their challenges in the midst of a competition required serious pads and gear to protect their growing bodies. I know from experience as a parent how important it is to protect all athletes from concussion and injury, from the youngest lacrosse player to the professional football player.

Continue reading How Important is it to Protect Athletes from Concussion and Injury?

Think about IoT Security Holistically

As new technology evolves, it is not uncommon for both vendors and customers to jump on the bandwagon before thinking about the overarching issues, such as security.  The Internet of Things presents a whole new set of security concerns – from the device side to the cloud and everywhere in between.  Security is all too often an afterthought in IoT deployments.

Eurotech has been considering IoT security from the start and we believe in thinking about IoT security holistically.  Our priority is to maintain customer trust and confidence by ensuring the integrity, availability and confidentiality of customer data.  There is no singular IoT security solution, however creating a secure system is a step by step process to ensure total data integrity.

Continue reading Think about IoT Security Holistically

Going from Maker to Developer

Open source hardware can be a great starting point for skunkworks projects and weekend hobbyists, and may even make sense for developers trying out their earliest concepts. Students, hackers, and experimenters find the cheap, open source hardware to be readily available and all that they need for their side projects.

For engineers and developers in the corporate world, responsible for creating dependable and specialized products, there comes a time when a project is ready to move from a resource-constrained ideation phase to full on product development. Rugged, small form factor, highly integrated embedded computer boards like Eurotech’s CPU-351-13 are what product development teams rely on to evolve quickly and successfully from early concepts to saleable products that are backed by a strong business case.

Continue reading Going from Maker to Developer