Millions of things will soon have digital twins
As a concept, digital twins are not new, and their application can be traced back many decades, at least to the early days of space travel. Nevertheless, digital twins are being billed as one of the most strategic technology trends of the moment, with the potential to massively enhance enterprises’ decision making.
This Economist article delves into the far-reaching possibilities that twinning opens up. It also presents recent examples of companies putting digital twins into use and their rationale for doing so. One case is that of Siemens, with its plant in Amberg, Germany, where pairing a virtual version of the facility with the physical one has made a definite impact on the efficiency of day to day operations.
For more on the topic, read Matti Kemppainen’s recent take on digital twins here: https://industrialinternetnow.com/digital-twins-new-standard-industrial-production/
The new KPIs of efficiency
Companies regularly measure downtime, but what other indices should industrial internet-enabled factories look out for? Dr. Dirk Lange, Technical Director at ARTIS GmbH, talks about the new key performance indicators of manufacturing.
In his opinion, the new KPIs (key performance indicators) of efficiency will include numbers denoting overall equipment effectiveness as well as energy consumption. Lange finds data analysis to be a crucial part in determining these numbers.
“One KPI that I think will continue to be relevant in the future is Overall Equipment Effectiveness, or OEE. This refers to the quality and speed of production. If you have several machines running in a line, performing the same task, the smart factory allows you to compare between their individual performance rates,” says Lange. “Sensors enable the measurement and comparison of productivity between machines, and the resulting data helps to figure out the reason for differences in performance,” he continues.
In addition, the smart factory makes it easier to measure energy consumption and detect opportunities for improvement. According to Lange, energy efficiency is becoming increasingly important to manufacturers. Data from smart machines can help reduce consumption by pointing out which part of the process is eating up energy, for instance.
The right quantity matters as well
In Lange’s view, companies in industries such as steel, pulp and paper, waste-to-energy, ports and shipping, and automotive should focus on measurements that are important to the manufacturing process and that help to detect issues in the quality of work. “Again, the overall equipment effectiveness is very important, but that is only one aspect. Another critical point is that the right quantity is being measured,” Lange says.
“For example, consider the machinery of motor blocks or those in the automotive industry. If you can detect early that something is wrong with the machine—for instance, the surface quality is not like it should be—you can react and stop the machine, which is the easiest solution, or you can adapt the machine to do something else. However, early detection requires having the right sensors measuring the right quantity,” Lange explains.
“Data mining and data analysis will be crucial in the future.”
“It makes no sense to merely integrate sensors in the machine for the sake of doing so. While we have sensors, we must go intelligent and see what kind will really help us. We must use sensors to detect specific conditions such as, for example, damage in spindles and drives, unbalancing, increasing cycle times, decreasing tool life, and worsening quality,” he says.
Measuring predictive maintenance
Lange has been working in his area of expertise for 20 years. According to him, the discussion around the need for predictive maintenance has been going on for about the same time. He shares what has surprised him about the application of measurement to this technique.
“There is not yet a real, reliable solution for predictive maintenance in the machine tools industry,” he reveals. “In high-speed machining, for example, damage is difficult to predict. Because of the high speed of cutting and the variety of tools being used, damage can occur very quickly. But if you look in contrast to aggregates with stable conditions, there are solutions available.”
The role of data analysis tomorrow
Having access to big data also yields new challenges, Lange notes. “To give you an example, in our projects in the automotive industry, process data and condition monitoring data are collected from over a hundred machines. The growing number of sensors results in a vast amount of data, which needs to be stored somewhere. This is a big challenge.”
“Therefore, data mining and data analysis will be crucial in the future. Raw data will have to be collected and compressed into an accessible, intelligible form. To this end, we will have algorithms and strategies which give the user an easy-to-use tool and will, on the other hand, act as the base for a higher grade of automation. This can lead to intelligent factories with increased performance and economy,” Lange concludes.
As Technical Director of ARTIS GmbH, the German tool monitoring company, Dr. Dirk Lange is responsible for product development and application technique.
Predictive maintenance: the brainpower behind smart factories
In previous decades, there was no reliable way for factory operators to prevent equipment from breaking down unexpectedly and leaving their operations at a standstill. But with the increasing presence of IIOT sensors that monitor and process data at production plants in real time, this uncertainty is becoming a thing of the past.
Preventive maintenance, and especially edge computing, is transforming manufacturing in today’s smart factories. By enabling the close monitoring of equipment, workers can be alerted well before failures happen. Jason Ng, business development director at Adlink, outlines this and some of the other advantages of edge computing, while pointing out a complex hurdle that manufacturers must first overcome before reaping its full benefits.
Read the article here: http://digitimes.com/supply_chain_window/story.asp?datepublish=2017/08/03&pages=PR&seq=200
Three steps to drive digital innovation
Innovation is key in navigating businesses through digital transformation. Lina Huertas, Head of Technology Strategy for Digital Manufacturing at Manufacturing Technology Centre, talks about the pinch points where companies in traditional industries require support in their digitalization journey.
What are the steps that traditional manufacturing industries should take to foster a culture of innovation and to avoid extinction? In Huertas’ opinion, the steps are the same for any industry. “The first thing is always to be aware and to raise awareness, for example, by visiting events or conferences or by speaking to organizations that can provide more information. If you are not aware of what’s possible, it’s very difficult to get ideas going,” she says.
“Moreover, someone should always be responsible for achieving digitalization. Businesses always have other pressures to deal with, so it’s very important to have someone in charge of the objective,” Huertas continues. “Once you have a view of the landscape and someone has been tasked with the objective, then you need to identify the opportunity, understanding your whole organization. You should recognize your organization’s opportunities for quick wins and for creating the most value,” she explains. “Quick wins create momentum, so you need to understand that the best place to start is where you have the most issues or concerns.”
Start with the problem, not the technology
“Having established what it is that you want to do, you obviously need to build a business case. At the end of the day, however, what is essential is identifying how value will be created. Without awareness, you can’t articulate what the business of a technology solution is going to be,” says Huertas.
She advises companies to start with the problem, not with the technology. “Starting with technology is never a good thing because digital technology is just an enabler. Nobody should try to digitalize for the sake of digitalizing. It’s just a tool kit that will help you achieve your objectives,” she says.
Instead, companies need to define their objectives and the options for creating value. “Once they have these covered, and a strategy laid out, then they can start thinking about how digital technologies can help them achieve the goals,” she explains. “Again, this is where the awareness is important, because unless you understand a little bit about technology, it’s difficult to link it to your own problems.”
Huertas identifies two key areas that are usually taken into consideration afterwards but that should actually be considered from the beginning. “People and process are important in managing change. First, you need change management to make sure the business is managed correctly. It needs to be taken into account from the beginning. Second, people need to be brought on board. They need to understand what the business benefit is going to be and how the change is going to affect their jobs and responsibilities. That way they become part of the process.”
Build a collaboration ecosystem
According to Huertas, collaboration is crucial. “If you collaborate, you can see best practices. You don’t need to possess all the skills, and you can focus on your core competencies instead of trying to learn everything from scratch. Benefits are generated for all the businesses involved. It’s almost as if you are operating as an ecosystem, an environment that is beneficial for everyone,” she continues.
“Nobody should try to digitalize for the sake of digitalizing. It’s just a tool kit that will help you achieve your objectives.”
“It’s really difficult to achieve digitalization on your own. Therefore, you need to understand what it is that you are going to do internally and who you are going to partner with to help you deliver these solutions in the process of transformation. Consequently, it’s important to establish who is playing which role, where the funding is coming from and how time and skills are managed. It’s necessary to form relationships between all the partners, because ultimately you are all going to deliver the solution together,” Huertas says.
Innovate through strategic partnerships
Huertas identifies the areas where businesses require most support in their digital transformation. These include strategy, collaboration, business change and innovation. “Many organizations are very structured, and having gone through similar transformation processes earlier, they know that having a strategy is important in the long run. However, I think strategy is sometimes overlooked by organizations. A company may be tempted to just start straight away with technology, diving into the deep end, so to say. But there is a danger of starting in the wrong place or creating solutions that will cause fragmentation,” she warns. “Strategy is something a company can get external support for, but there also needs to be someone who understands strategy internally.”
Another area with potential barriers is identifying key partners that can meet the organization’s requirements. “Choosing between one candidate or the other without being a technology specialist is extremely difficult, so support in that area is important. Moreover, external consultancy in terms of business change might be required if the organization doesn’t have a lot of experience in undergoing similar processes,” says Huertas.
When it comes to innovation, she feels it is important to point out that in Europe, there are many research organizations that are partly funded by government. “They have the infrastructure that enables them to take the risk of innovation. Collaborating with those organizations – and basically using their infrastructure – allows companies to better manage risks because not all organizations can afford to test the solutions on their own.”
Huertas concludes with a piece of advice: “In driving digital transformation, the focus should be on understanding the business opportunity and optimizing the process. In a way, technology should come last because there are people dedicated to thinking about technology. Focus on your core competencies and play with your strengths. Once you have the right process, then you can digitalize.”
Lina Huertas is Head of Technology Strategy for Digital Manufacturing at Manufacturing Technology Centre, an independent research and technology organization with the objective of bridging the gap between academia and industry.
— IndIntNow (@IndIntNow) September 30, 2017
Digital twins, event-thinking and continuous adaptive security are among Gartner’s Top Ten Technology Trends for 2018
Gartner recently released its latest list of the strategic technology trends it predicts will have the greatest potential for impact on enterprises over the next five years. The IT research firm also introduces a concept that ties the ten technologies on this latest list together. This is the “intelligent digital mesh” or the intertwining of people, devices, content and services, which according to David Cearley, Vice President and Gartner Fellow, will be the foundation for future digital business and ecosystems.
The first three strategic trends on Gartner’s list relate to the pervasive spread of AI into virtually every technology, and its potential to enable more dynamic and flexible autonomous systems. The next four concern the merging of the digital and physical worlds to form an immersive, digitally enhanced environment. The final three trends revolve around the increasing interconnections between people, businesses, devices, content and services to deliver digital outcomes.
Explore Gartner’s Top 10 Strategic Technology Trends for 2018 here: http://www.gartner.com/smarterwithgartner/gartner-top-10-strategic-technology-trends-for-2018/
When investing in AI, start where you see potential profit
Traditional industries such as steel manufacturing are not immune to the transformation emerging technologies is bringing about in the world as we know it. Jane Zavalishina, an Artificial Intelligence expert and the CEO of Yandex Data Factory, shares her thoughts on why steel companies should invest in AI solutions. She also outlines the steps industry players can take to make these efforts prosper.
“I believe that smart technology solutions will bring the most economic benefits to any industrial manufacturing company in the next three to five years,” asserts Zavalishina, when discussing the impetus for industrial companies to fully embrace digitalization. “The capabilities are there, the data is there, and the motivation is there. So, I think it’s a no-brainer that you need to use it.”
She points to a critical question executives and decision makers should be asking themselves before adopting AI technologies. “How much value can it bring to your particular business?” she says, continuing, “You ought to start where you can quickly see a return on your investment.”
Zavalishina argues that with technologies changing so rapidly and so profoundly, the best place to begin is where potential for easy profit can be found: “The technologies are universal. Strategically, they can function in a rather disruptive manner, but they can also work just for activation purposes –instead of changing current processes, they can simply improve them, thus making businesses more profitable.”
Focus on revenue, experiment, and get everyone on board
Zavalishina re-emphasizes the importance of focusing on revenue, saying that this is the first step to making a successful investment in AI. She also warns decision makers against the danger of getting overwhelmed by the seeming limitlessness of the opportunities that rapidly developing technologies offer.
“If the innovation you are trying isn’t paying for itself, then focus on something else.”
“Think of a particular business case, about specific products and customers, and then decide where to start,” she advises.
According to Zavalishina, the second step in successful investing is experimentation. “It’s highly beneficial to actually try out new technologies because they are just changing so fast. You can’t build a five-year plan, as no one can forecast what the reality will be in five or ten years’ time,” she argues.
That’s why she recommends trying as many new things as possible, but at the same time, maintaining the costs on a moderate level. “If the innovation you are trying isn’t paying for itself, then focus on something else. There’s no need to spend vast amounts of money on every experiment. Instead, be precise and honest in measuring the results against the costs. If it seems wiser to move on to the next thing, then do so,” she underlines. “But you need to be sure you have understood what these technologies mean for your specific business – and that’s something you only learn from practice.”
She then describes the third step as being closely linked to the second one: “To succeed in all this, you of course need to have your people on board. And that requires a bigger, more comprehensive change of your entire organizational culture. In order to really embrace change, you must accept continuous experimentation as an inseparable part of your business,” Zavalishina sums up.
Taking the industry to the next level
So, what makes advanced technologies such a driving force, especially for the steel business? Zavalishina says that there are a few prerequisites that enable new smart technologies to be applied efficiently, and that many steel makers already happen to have working in their favor.
One is historical data. In general, steel manufacturers operate the same equipment for decades, which one could say is an un-innovative approach, and might therefore be assumed to be a disadvantage. But on the flip side, this also means that those companies might have accumulated up to ten years of data from their equipment and production processes.
“This is where utilizing AI can really be fruitful, because by analyzing this historical data, AI can learn from it in order to make highly precise operational decisions ,” says Zavalishina.
Another factor is an attitude of experimentation. Here the asset is not the equipment, but the people. “When dealing with the steel industry, you inevitably deal with data-driven individuals coming from engineering backgrounds. Testing and measuring usually comes naturally to them, and they understand the importance of comparing different methods. It’s much harder to convince a banker, for example, about the benefits of spending time experimenting, even if it’s a necessary part of the process.”
Finally, Zavalishina points out the advantage of the industry’s long history: “The industry’s processes are pretty stable, and there haven’t really been any fundamental changes to them in the past decades. You can almost say that the industry has explored practically all the ways to optimize their processes with the current tools – and that motivates them to employ new technologies like AI to achieve the next level.”
When resources are limited
What about the companies with limited financial resources? How can smaller players navigate the world of AI and succeed against the competition?
“Well, if you are a giant, industry-leading player, you actually have less choice. You simply must invest in R&D and try as many things as possible because it’s the only way to maintain your top position,” says Zavalishina. “On the other hand, as a smaller company, you don’t want to stay in the background forever either. In this case, a step-by-step approach is the smartest route.”
To conclude, Zavalishina returns to her advice on the importance of profit. “Don’t invest much. Make sure that every step you take helps your business generate returns. Give a specific experiment three to six months, and if it doesn’t deliver any measurable value in that time, then move on to the next thing.”
“And yes, some of your experiments will fail. That’s what innovation is about, and that’s just fine. But if you stick to this paradigm where you keep going, then you’re very likely to succeed at some point. You might spend 50,000 dollars and lose all of it. Then again, you could spend another 50,000 and win half a million,” she ventures.
Jane Zavalishina is the CEO of Yandex Data Factory, an industrial AI company belonging to Yandex, one of Europe’s largest internet companies. She was recently named in Silicon Republic’s Top 40 Women in Tech as an Inspiring Leader.
— IndIntNow (@IndIntNow) June 15, 2017
Connecting the Connected Mine
Mining companies today are looking for ways to benefit from greater data access, real-time analytics, autonomous systems and services such as remote monitoring. In order to do that, they are going to need a network infrastructure that will tie all of those technologies and capabilities together.
The challenges are unique: mining operations can span hundreds of miles above and below ground, and are usually set in far-off areas with minimal or no communications infrastructure. Douglas Bellin and Paul McRoberts propose in their article in Engineering and Mining Journal that “[t]he first step for mining companies is to converge their information technology (IT) and operations technology (OT) systems into a single, unified network infrastructure. This eliminates silos of information and, as result, enables seamless information sharing across an entire mining operation.”
Read more about how wireless communications can help improve efficiencies, enhance safety and reduce costs: http://www.e-mj.com/features/6923-connecting-the-connected-mine.html
Automation of Blast Furnaces at Tata Steel with NetBeans
JAXenter reports that the Automation Division of Tata Steel Ltd has developed a Level2 system Blast Furnace and implemented a H–Blast Furnace at Tata Steel Jamshedpur.
Blast Furnace Level2 system is a collection of mathematical & mass-energy balance models which, based on first principles, mathematical equations and numerical methods, simulate the blast furnace process in segments on real time basis. The models extract plant data like flow, temperature, pressure, distance, velocity etc from the field devices and convert them into trends using fundamental principles of physical laws. The Level2 system helps operators to visualize the process of the blast furnace and in turn assists them in operation with better control facilities.
Read more about Blast Furnace Level2 system at: https://jaxenter.com/netbeans/automation-blast-furnaces-tata-steel-netbeans
Digital twins – a new standard in industrial production
The digital twin is a burning topic within manufacturing industries. While it is often included in lists of today’s most strategic technologies, it has yet to be widely adopted in practice. Matti Kemppainen, Director of Research and Innovation at Konecranes, discusses the implications for manufacturers of the rolling out of digital twins. According to Kemppainen, digital twins are set to be a new standard for industry.
A digital twin refers to a virtual representation or model of a physical entity or system, or even an entire factory. The real world and the digital world are brought together via sensors attached to the physical asset, generating real-time data, which is analyzed in the cloud and presented to users in a way that helps them to better understand it and to make decisions based on data.
The uses of a digital twin include analysis, simulation and control of real-world conditions as well as potential changes and improvements in the manufacturing process. Matti Kemppainen, Director of Research and Innovation at Konecranes, recognizes a strong hype around digital twins. According to him, however, there are not yet many functioning examples of them.
Kemppainen’s unit is working towards discovering the best way to create a digital twin of a new product. “The creation of a digital twin ought to start from the very beginning of the chain, and therefore it should cover the design phase of the new product. The digital twin’s heart starts to beat when the completed product is equipped with sensors and connected to the digital world. Traditionally, the design or model of a product is ‘dead’ in the sense that after the product is built and completed, the model remains as it is. In contrast, the digital twin ‘lives’ with the product throughout the product’s lifespan,” Kemppainen explains.
Multiple benefits for businesses
The business benefits of digital twins are clear: The digital twin grants control over the whole production chain, which increases productivity. Maintenance and interruptions can be predicted more accurately, and it is possible to experiment with simulation. “Simulation allows for planning improvements in the process, such as the replacement of components, without interrupting manufacturing, and enables the preparing of alternative plans in case of malfunctions or disturbances,” says Kemppainen. Moreover, safety is improved when processes are simulated continuously. “The device and the products are under continuous control, and there should be no more surprises,” he says.
Operator training is one use case of the digital twin. Kemppainen gives an example: “A crane operator can wear augment reality (AR) glasses and operate a digital version of the crane that behaves exactly like the real crane. Moreover, with AR glasses, machinery can be virtually disassembled into its components in front of the trainee’s eyes. It then becomes easier for a learner to understand how it functions than by looking at the real unit, the insides of which are normally covered by a hood when the machine is up and running.”
“A digital representation of a physical asset is particularly useful in conditions where they are difficult to reach, for instance in wind parks or in ships sailing in the middle of the sea.”
The combination of a digital twin and augmented reality has another advantage. “A digital representation of a physical asset is particularly useful in conditions where they are difficult to reach, for instance in wind parks or in ships sailing in the middle of the sea. It may not be efficient to have an expert technician onboard all the time. With a digital twin and AR glasses, technicians can solve occurring problems remotely,” Kemppainen explains. “In such environments, well-executed digital twins help to predict maintenance, and building them is worth the cost,” Kemppainen states.
Making the most out of a digital twin
In terms of individual products, data gathered throughout the lifespan of a product is useful, but in Kemppainen’s view, comparable data is what creates the most value. According to Kemppainen, the most benefit can be gained when there are digital twins of an entire series of products. “Data from multiple sets of twins can be compared to one another to find out whether a problem occurs frequently in products that are used in similar conditions. Hundreds, even thousands of variables can be compared to find clusters of products that are used similarly and that are in different stages of their lifespan,” he says.
“Devices connected to AI can order maintenance independently, based on observations of the device’s performance. However, sometimes comparison against data on other devices’ performance reveals that there is in fact no need to do anything, because the performance observed is normal under prevailing conditions. When there is a reference list comprising a million devices and all their parameters, it is possible to find a parallel that helps to predict use or assess condition,” says Kemppainen. He illustrates: “For instance, if there is a reference list of hundreds of thousands of cranes at hand containing all data on each individual crane throughout its lifespan, it is possible to match and compare the performance of a group or batch of cranes and find a pattern in how the environment and surrounding conditions impact performance. Consequently, an individual crane’s maintenance and use can be predicted more realistically. Without real use data, all we have are estimates.”
The challenge of getting started
From Kemppainen’s perspective, the reality is that there is still plenty of work to do in order to keep a set of digital twins in good condition throughout the product’s lifespan. Obviously, setting up a digital twin requires a heavy IT system. As the lifespan of industrial products can range from 30 to 40 years, the price tag of a digital twin may turn out to be sizeable. Products and components are repaired and replaced, IT systems are updated, and converting data to new formats is not without cost. Human interference also causes trouble: “Mechanical devices such as hoists cannot be covered entirely with sensors, so if a digital twin of a hoist is in use, the system is going to require manual updates whenever maintenance or other changes take place. Humans are not as accurate as computers, and therefore manual updating always entails a risk of error,” notes Kemppainen.
Accordingly, many companies speculate whether they will need all the sensors that a digital twin would require. “Investing in a digital twin may feel pointless if other components in the system are incompatible. It is easy to end up in a chicken-or-egg situation, where it is difficult to decide when to kick off the digitalization of processes,” Kemppainen says. Therefore, he would rather emphasize the gains of digital twins in new products, systems and facilities. “In an old factory, it is not too realistic to expect everything to be digitalized, especially if there are components of different ages included. But in the future, when a new factory is built, basically all of it will be represented digitally. This can constitute a technological leap that makes the difference and really sets the factory in the position to beat the older competitors.”
The biggest advantages from digital twins are currently seen in critical processes and in very limited contexts, such as aircraft turbines. Kemppainen, however, maintains that manufacturers in all industries should keep a close eye on new developments and get ready to make the leap into the digital world at the right moment. “We should bear in mind that even smaller scale digitalization benefits companies. It’s a matter of getting started and moving forward area by area. Soon it will be standard procedure that a digital twin is included in all new acquisitions, as manuals currently are.”
Matti Kemppainen works as Director of Research and Innovation at Konecranes.
Machine Learning Will Help Us Fix What’s Broken Before It Breaks
Digital twins, exact virtual replicas physical devices, are computer models operating identically to the physical versions, able to detect problems before they have the chance to happen in the real world. Combined with predictive machine learning, the digital twins are hoped to reduce downtime resolving problems before they even occur.
However, as Big Think reminds us on their article on machine learning, there are still devices in service predating the notion of digital twins, especially in industrial settings. Luckily there are several companies developing bridge technologies that would bring the benefits of digital twins to devices without one. They are harnessing machine learning for analyzing data to pick up subtle variations from normal operation that may predict imminent malfunctions. Their approaches vary from analyzing sounds machines make to detecting changes in machine-produced vibrations.
Read more about how machine learning and AI can keep machines and industrial plants operating at: http://bigthink.com/robby-berman/machine-learning-will-help-us-fix-whats-broken-before-it-breaks