From Reactive to Predictive Maintenance – An IoT-enabled Manufacturing Leap
Predictive maintenance is taking the place of calendar-based and reactive maintenance practices. More than a quarter of manufacturers are now tracking product performance through predictive maintenance applications, and the global spend on IoT solutions is expected to increase from $29 billion in 2015 to $70 billion in 2020, Data Scientist and Statistical Modeller Ravishankar Kandallu writes in his blog post for Industrial Internet Consortium.
IoT enables companies to solve problems before customers realize they exist, resulting in reduced downtime and maintenance costs, hence better customer experience. Kandallu reminds us that “[w]ith the IoT emerging as a strong transformational force, it is very quickly becoming indispensable for manufacturing companies to choose the right predictive maintenance model for plant equipment maintenance and customer experience enhancement purposes.”
Read more about how to take your predictive maintenance efforts to new level: http://blog.iiconsortium.org/2017/07/from-reactive-to-predictive-maintenance-an-iot-enabled-manufacturing-leap.html
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.
The Internet of Smart Things – humanizing the IOT
David Grebow, CEO of KnowledgeStar and former co-director of the IBM Institute for Advanced Learning, believes that the Internet of Smart Things (IosT) is the most significant opportunity that has come out of the IoT world, especially for manpower-intensive heavy industries. He spoke with Industrial Internet Now about IosT’s potential to humanize the IoT and realize companies’ returns.
What is the Internet of Smart Things and how does it differ from IoT in its implications on work as we know it?
The IoT was originally designed as an interconnected system of computing devices that could transfer data over a network. The original focus was to enable machine-to-machine transfer and display of data. The primary output was the data that informed a few people about how the interconnected devices were functioning. The emphasis was on managing that data, driving new business value from the investment of the infrastructure supporting the IoT, and finding more effective and efficient ways of doing business made possible by the IoT. It was not focused on how people could more safely and effectively use the machines, since there was no human-to-machine interface.
The Internet of Smart Things™ (IosT) incorporates that human-to-machine interface and uses the interconnected computing devices to alert and inform people about what they need to know and do to safely and effectively do their jobs. Imagine if the equipment you use in the workplace could show you what you need to know about how they operate, tell you how to use them correctly and efficiently in your native language, help you be safer working with or around them, offer you details to complete and submit regulatory forms and checklists. What if they could also show you how to fix them if they are broken, provide you with the schematics and diagrams you need, help you contact a mentor or emergency assistance, and more?
“Imagine if the equipment you use in the workplace could show you what you need to know about how they operate, tell you how to use them correctly and efficiently in your native language. What if they could also show you how to fix them if they are broken, provide you with the schematics and diagrams you need, help you contact a mentor or emergency assistance, and more?”
What if all this information was delivered automatically whenever you were within a short distance of the machine? Imagine if it was instantly and securely viewable from any nearby internet-connected device. Think of the enormous impact that could have: increasing safety, eliminating errors, boosting employee productivity, proving timely compliance, among others. It could dramatically reduce injuries and associated worker’s compensation and insurance costs – all of which would have an immediate and positive effect on the bottom line.
We’ve all heard and read about how the Internet of Things in the home will transform the ways in which we live. We’ve heard for years how your refrigerator is going to send a shopping list to your grocery store, your car will make an appointment for an oil change, and the blinds on your windows will automatically close as dusk falls.
What about the Internet of Things in the workplace? It seems to me that far more people have an immediate need for the machines they work with every day on the job to supply them with specific information.
While I can appreciate that having an expensive lathe machine tell me that there is a problem with the calibration of one of the lathes, having that same piece of machinery provide me with safety warnings, a way to access operational information I may have forgotten, a name of a person to call to solve an immediate problem, or a checklist of compliance issues that need to be completed before I operate it would be far more useful. That’s the Internet of Smart Things.
In the shift to a learning economy, what role will managers play, particularly in companies in more manpower-intensive heavy industries like ports and container handling, mining, automotive and general manufacturing? Also, with relation to industrial jobs, in what ways is IosT an opportunity?
Managers who are currently responsible for providing on-the-spot reminders and remedial training would be free to perform more important managerial jobs. Learning becomes the responsibility of the workers who can find out what they need to know and do using their smart devices – phones, tablets, or Google Glass EE – connected to the machines. Managers’ role will be to enable workers to use the IosT.
Managers will also be able to look at the analytics the IosT returns and see where training is hitting or missing the mark, find out who is acting as a go-to expert for operations or repairs, check to make sure regulatory guidelines and maintenance are being met on time, and more. Managers responsible for training will be able to see what parts of the training are working and which areas need to be revisited and revised.
In your writings, you’ve said that the IosT humanizes the IoT? In what way?
It adds people back into the equation. It takes machines that can essentially talk to one another and gives them the capability to literally talk to the workers operating and maintaining them.
You’ve also mentioned that the return on investment is easier to see with the IosT. How so?
According to the 2016 Training Industry Report, the manufacturing sector alone spent more than $25 million on training that year. Current research informs us that we forget as much as 50% of that training in a matter of days or weeks. That means that every dollar spent returns only 50 cents in value. The IosT is an antidote to forgetting since it provides not only just-in-time information; it can be designed to provide just-for-me initialized training as well.
Safety direct and indirect costs from injuries and accidents in the workplace have been estimated by the Occupational Safety and Health Administration, or OSHA – an agency of the United States Department of Labor – to amount to almost $1 billion per week. This ranges from medical payments to repairs of damaged equipment. Smart machines, driven by the IosT, would dramatically cut down these costs by reinforcing safety training and providing safety alerts and instructions. By ensuring that machinery was properly operated and maintained the indirect costs would also be reduced.
What, in your opinion, do responsible developers of technology need to consider in developing IoT systems to make the IosT a reality?
“The value of having a smart machine talking to other smart machines has already proven to be valuable. Incorporating the people who work on those smart machines into the equation makes the IosT even more important.”
The human-machine interface. There is an entire ecosystem that needs to be accounted for. Machine-to-machine data sharing is one element of the ecosystem. Human-to-machine interaction and connection is the other. The value of having a smart machine talking to other smart machines has already proven to be valuable. Incorporating the people who work on those smart machines into the equation makes the IosT even more important. It’s a viewpoint that asks a simple question: How can this technology be used to make life better for the people who work with these interconnected machines every day?
David Grebow heads KnowledgeStar, a US-based consulting firm that provides Fortune 500 corporations, start-ups, NGOs and analyst agencies with insight about the intersection of digital technology and education. His latest book “Minds at Work” will be published in December, 2018 by ATD Press.The Internet of Smart Things™ is trademarked by KnowledgeStar, Inc.
Highlights from the Industry of Things World Report 2017
The Industry of Things World Survey Report 2017 sheds light on the state of the IoT market. Based on the views of over 1,100 cross-industry leaders, the focus point is now shifting towards real-world implementation and monetization of industrial IoT. According to Maria Relaki, Portfolio Director at we.CONECT Global Leaders, the organizer of Industry of Things World conference series, industrial IoT has moved from theory to application.
The third annual Industry of Things World Survey investigates the opinions of over 1,100 Internet of Things (IoT) and Industry 4.0 managers working in industries such as manufacturing, information and communication technologies, automotive and transportation, healthcare, chemicals and many more. Conducted online from January to March 2017, the survey covers the current state of the worldwide IoT market.
“The results indicate that IoT is now considered essential to business and not just theory or something that is good to have. Eighty-eight percent of the respondents found industrial IoT critical to their organization’s future success,” comments Maria Relaki, Portfolio Director at we.CONECT Global Leaders. “A key finding is that Industrial IoT has already become mainstream: According to our respondents, adoption of industrial internet is at 91 percent. This means that companies are moving beyond the theoretical planning phase, and they are able to discuss how they are going to roll out their plans or even what they have already achieved with IIoT,” she explains.
Trends and phenomena
Relaki points out that the increasing percentage of use of digital technology—up from last year’s 82% to 91% this year—supports the notion that digital transformation really is the way to go. According to her, moving to the implementation phase means that there is a lot going on in the world of IoT because this stage has so many steps. In addition to the overarching theme of digital transformation, among the hot topics discovered in this year’s survey results are monetization strategies, data analytics, platforms, and improved operating performance. “People have had enough of ‘This is the next big thing’. Now, businesses are expecting results,” says Relaki.
However, some themes remain equally important from year to year. “Forecasting demand, cybersecurity, and interoperability have not lost importance,” Relaki notes. For example, over half of the respondents (55%) think regulation, governance, and security play a very important role in digital transformation, while almost two thirds (62%) found cybersecurity and privacy a hurdle that must be overcome in pursuing digital transformation. The lack of industry standards for interoperability and interconnectivity was the second most significant hurdle (39%) from the respondents’ perspective.
Challenges and opportunities
“Businesses have identified the opportunities of IIoT technologies, and they are now looking for specific solutions to answer their needs.”
The survey identified some of the challenges and opportunities of industrial IoT. “Based on the responses to our open-ended questions, businesses have identified the opportunities of IIoT technologies, and they are now looking for specific solutions to answer their needs,” she says. For example, the majority of respondents expected IIoT to yield new revenue streams and business models (66%) as well as new products and services (66%). The biggest potential IIoT improvement areas were found in plant operating performance through improved maintenance and asset uptime (58%) or through improved execution (48%).
The challenge lies in recognizing innovation and integrating it into business. For instance, when it comes to digital transformation, only four percent of respondents found their company as having both vision and execution in place.
Industry of Things World 2017
Industry of Things World 2017 is a strategic conference that brings together stakeholders from a variety of industries, all with the aim of defining the future of the fourth industrial revolution. Organized by we.CONECT Global Leaders, the event is scheduled to take place in Berlin, Germany, from September 18 to 19, 2017. According to Relaki, approximately 1,000 participants representing over 40 different nationalities are expected to attend.
Key themes of the two-day program include, among others, overcoming integration challenges of industry 4.0 in running businesses, monetizing the IIoT in an industrial setting, the impact of AI, machine learning, and robotics on productivity, and the implications of the convergence of IT and OT in terms of security. “This year, the emphasis is shifting from ideas and intentions to implementation. There will be presentations of actual projects demonstrating real-world applications of IIoT technologies and sessions dedicated to the integration of innovation in companies,” shares Relaki.
Among the conference’s 80-plus speakers are Kevin Ashton, a renowned expert in digital transformation and the one who coined the term “the Internet of Things;” Nigel Upton, Worldwide Director and General Manager IoT and Global Connectivity Platforms at Hewlett Packard Enterprise; Eric Schaeffer, Senior Managing Director at Accenture; and Tanja Rueckert, President IoT and Digital Supply Chain at SAP.
To find out more about the agenda and speakers of Industry of Things World 2017, visit www.industryofthingsworld.com/en/ .
Download the full survey report here.
Maria Relaki works as Portfolio Director at we.CONECT Global Leaders and is responsible for the Industry of Things World global event series.
Image credit: Industry of Things World
Update: Kevin Ashton, who first coined the term ”Internet of Things” talks about the next phase of the Industrial Internet. Video was filmed at the event venue in Berlin.
— IndIntNow (@IndIntNow) September 22, 2017
How Industrial IoT enables the factory of the future
Trillion-dollar projections on the expanding size of the market are urging companies to capitalize on the Industrial IoT. For many, however, it remains unclear how industries should apply IIoT to begin making the hyper-efficient and agile factory of the future a reality. Fabio Bottacci, founder and CEO of VINCI Digital and Industrial IoT Expert Contributor at the World Economic Forum and at the Brazilian Development Bank (BNDES), shares his insights on how Industrial IoT is already increasing operational efficiency, saving time and reducing cost.
As the Fourth Industrial Revolution transforms manufacturing and material handling, enterprises continue to look for ways to create value from converging technologies. But what are the steps that companies need to take to put together an effective agenda of action? Fabio Bottacci finds it essential that the implementation of industrial internet is incorporated into the company’s strategy and business development. In other words, chief executives must embrace change. “In order to advance decision-making on the correct level, CEOs must be included from the very beginning, possibly as initiative main sponsor. IT officers alone cannot drive real digital transformation,” says Bottacci.
Bottacci advises manufacturers to initiate the transformation by defining a specific set of goals, to be assessed and validated initially on a pilot project, before the implementation at scale of an end-to-end Industrial IoT solution. The next step is to deploy an industrial internet pilot in one facility, or on a specific production line, which will be used as a case study for learning how IoT works in this particular industrial environment. The pilot facility is then reworked and developed according to observations. After the test phase, it is easy for a company to apply the same principles, with proper adjustments, at scale to other facilities.
Bottacci uses the concept of flexible infrastructure to refer to how transformation can be simpler in certain contexts. “It is easier to justify large investments in industrial internet in environments where industrial internet is incorporated into production by transitioning directly to automated, advanced IIoT environments. The transition phase is less complicated when the existing infrastructure is light, because there are fewer things that must be accounted for in applying new solutions,” he explains.
A case in point is Romania, where the internet infrastructure is now top of the class in Europe. The Romanian infrastructure was created rather recently compared to more affluent European countries, and therefore, the entire web is more modern than that in Finland, for example.
Industrial internet in practice
“IIoT coupled with AI or ML turns maintenance into a dynamic, rapid and automated task.”
Bottacci emphasizes that applications of industrial IoT are already a reality. According to him, there are dozens of different use cases of IIoT in enterprises. “Companies are already developing IoT applications that work, and they have started making a difference. For example, transportation and warehousing benefit from automated vehicles and asset tracking. In manufacturing, predictive maintenance and asset performance management are key areas where industrial internet boosts value creation.”
Predictive maintenance keeps assets up and running, decreasing operational costs and saving companies millions of dollars. Data from IIoT-enabled systems – sensors, cameras, and data analytics enabled by powerful artificial intelligence (AI) or machine learning (ML) algorithms – helps to better plan maintenance, allowing manufacturers to service equipment before problems occur. “Data streaming from sensors and devices can be used to quickly assess current conditions, recognize warning signs, deliver alerts and automatically trigger appropriate maintenance processes. IIoT coupled with AI or ML thus turns maintenance into a dynamic, rapid and automated task,” Bottacci explains.
“Other potential advantages include increased equipment lifetime, increased plant safety and fewer accidents with negative impact on environment,” he adds.
The importance of edge analytics
“Companies have been proactive in moving the processing of IIoT to cloud services,” Bottacci notes. However, in his opinion, it is not necessarily a wise move to have everything in the cloud. During critical stages of the manufacturing process it is crucial that decisions can be made instantaneously. Here, manufacturers can benefit from edge analytics.
“Edge computing enables real-time analytics. Edge analytics is an approach to data collection and analysis where automated analytical computation is performed on data at a sensor, network switch or other device instead of waiting for the data to be sent back to a centralized data store. IIoT can be supplemented with Arduino-based, open-source computer hardware and software applications that allow some of the processing to take place on site, at the edge of the network and near the source of the data. Edge computing helps ensure that the right processing takes place at the right time, in the right place,” Bottacci explains. “Edge computing is a preferable option for the cloud in terms of security, as proprietary data is kept within the company firewall. Moreover, edge computing becomes vital when you need real-time analysis and automated action to save critical-mission production lines or facilities from potential heavy damages.”
Creating value with Industrial IoT
“There’s no value in the data without advanced algorithms of machine learning.”
Bottacci says that value can be created in surprisingly simple ways by putting data to work. As an example of enhancing safety and efficiency in material handling, he refers to a fleet management system in Silicon Valley. “Peloton Tech’s truck platooning system is a case study that illustrates how IIoT is already creating value. The system uses vehicle-to-vehicle communication to connect the braking and acceleration between two trucks. The lead truck controls the simultaneous acceleration and braking of the whole fleet, reacting faster than a human or even a sensor system could. What follows is a reduction in aerodynamic drag, which leads to companies saving around seven per cent in fuel cost. In terms of annual savings, this is a remarkable number,” says Bottacci.
In Europe, trucking companies such as Scania and Volvo Trucks have adopted IIoT fleet thinking. “It still takes courage to adopt innovations like these,” Bottacci admits. However, he recommends getting started quickly by building a case study of industrial internet and then working towards expanding IIoT to cover more and more of the industrial realm. “Companies should start seeing emerging technology like Industrial IoT not as a threat but as the only way to survive in a matter of a few years. That’s two or three years if you are an optimist, five to ten if you are more conservative,” estimates Bottacci.
In Bottacci’s view, the simple capacity of devices to seize data is not what the Industrial Internet of Things is essentially about. “Even if you have all the infrastructure and the technology to get the data – sensors, WiFi, the gateway, the cloud – and the capacity of analyzing the data, there’s no value in it without AI, more specifically advanced algorithms of machine learning.”
“IIoT is about AI or ML analyzing data in real time so as to make decisions and act, most of the times several days or even weeks before a potential issue. This process results in actual business outcomes,” Bottacci states. “Prescriptive analytics react autonomously, real-time: In a mission-critical situation, a prescriptive system will autonomously decide what to do. This is where edge analytics is imperative,” he explains. “My point is: You can’t consider industrial internet standalone. The real value comes from how companies use AI and ML-enabled IIoT solutions in analyzing and processing data.”
Fabio Bottacci works as an independent advisor. He is founder and CEO of VINCI Digital and an Industrial IoT Expert Contributor at the World Economic Forum and at BNDES, the Brazilian Development Bank.
Unifying industrial IoT technologies with monitoring
While the majority of industrial companies have multiple systems and technologies managing various components of their operations, only a few have been able to aggregate the data from all of these systems together to drive business prosperity. When brought together, the data from these disparate systems can produce insights across all aspects of the business.
“The teams and upper management of these industrial organisations could – with a unified monitoring tool – see every link in the supply chain and their products’ evolution from early stages right through to delivery,” Paessler AG’s APAC sales director Andrew Timms told IoT Hub. Besides operations-wide oversight, monitoring tools can also be used for the management of particular components of the value chain.
Read more about aggregating data from RFID, SCADA, IT and other sources at: https://www.iothub.com.au/news/unifying-industrial-iot-technologies-with-monitoring-458258
The need to connect legacy devices to the IIoT
Pre-internet assets lack the connectivity of newer pieces of equipment. These legacy devices, however, still have years of remaining value if they can be linked to the cloud, enabling their data to be analyzed and revealing actionable insights that could perhaps potentially transform business. Wael Elrifai, Sr. Director of Enterprise Solutions at Pentaho, offers insights on how older systems can be made to work with current ones, and talks about the human side of machine learning.
Businesses that have operated for a considerable amount of time will have accumulated several legacy systems over that period. While they have long life-spans, few of these machines will be immediately compatible with one another. The cost of replacing these pre-internet assets to facilitate communication could easily outweigh foreseeable production benefits. What steps must plant managers then take to combine AI capabilities with legacy infrastructure?
— IndIntNow (@IndIntNow) June 1, 2017
Wael Elrifai, Sr. Director of Enterprise Solutions at Pentaho, begins with this premise. “I usually like to remind people that we talk as though data was not generated in the past on these systems. Remember, however, that there’s a lot of robotics involved already, and these systems have sensors that have been producing data for decades. The truth of the matter is that systems such as PLCs (programmable logic controllers) and SCADA (Supervisory Control and Data Acquisition) have already been capturing that data. What you need to do now is to pull the data off those systems. Things like data integration tools are built for that,” he says.
According to Elrifai, predictive maintenance – a technology that drives value in modern manufacturing – isn’t new either. “The difference today is, because the cost of computing and the cost of storage have dramatically reduced, you can do more with it. It’s been a nice positive feedback cycle: Where you can capture more data, you can do more computing work – applied mathematics, machine learning and AI, among others. This then makes capturing data more valuable.”
Conversely, in situations where it’s entirely mechanical and no data or robotics are involved, he suggests looking for proxies for that data. Elrifai adds that while some retrofitting may be required, from his experience a lot of data is already there and is not being used, so it would be best to begin with that.
IIoT implementation across industries
Some industries are more advanced when it comes to IIoT implementation, while others lag. To convince traditional manufacturing companies of the economic benefits of AI investments, Elrifai offers the following examples.
“The ports industry is already using complex machine learning techniques. The most common one for logistics companies is simulated annealing, a method for schedule optimization that sees to it that cranes are doing the right thing at the right time, and containers are moved according to the right schedule.” Elrifai believes that for some container terminals, it’s mostly about the integration of the larger supply chain.
On the other hand, he recalls a visit to a steel factory that wanted to improve its efficiency. “A couple of times a day, they experienced a very specific kind of failure. This cost about 10 percent of their productivity, and in the steel industry that figure is enormous,” Elrifai explains. Furthermore, the way they knew there was a problem was rather unusual: The control room would start shaking.
While the company wanted to reduce this through predictive maintenance techniques, what they didn’t know was that they were capturing all this data already. Elrifai says like many other companies, this particular steel factory would only look at five, ten or 20 variables, the ones that were in their SCADA system.
“What they didn’t do is integrate this with thousands of other sources. The statistical techniques that factories are doing today are low-dimensionality ones,” he continues, adding that trying to convince groups to do more is a matter of explaining to them that it’s just an evolution of what they are already doing.
Where humans fit in
Another dimension to machine learning and AI is the human factor. As far as the supply chain is concerned, Elrifai is of this opinion. “If you are talking about supervised learning – just prediction, basically – oftentimes the baseline data that you use to train these systems is from humans. And you want these systems to evolve, because systems evolve, factories evolve,” he says. “I think humans are always going to be there, helping to state what the ground truth is. Or, at least for the foreseeable future, they will be doing that.”
In addition, Elrifai points out that in certain cases in factories, several different algorithms are voting whether something is going to fail or not, and a human expert is doing that as well.
“With these kinds of methods – ensembles, if you will – you end up with better outcomes. For instance, the machine by itself might produce 75% accuracy and the human on his or her own might produce 68% accuracy. When you put them together, you end up with greater performance, say 80% or 85%,” he states. “I think there’s still a lot of room for cooperation. I don’t think the algorithms are taking over just yet.”
How to solve new problems
“The common problem people have with technology is that they search for problems. That makes no sense. Solution? Start with use cases.”
Finally, Elrifai – with his background in data science – offers this essential piece of advice to companies that plan to connect legacy equipment to the IIoT. “The common problem people have with technology is that they search for problems. That makes no sense,” he emphasizes. His solution? Start with use cases.
“I think there’s a sense that this is extremely expensive to do. However, all you really are doing is putting up a basic data engineering or basic machine learning infrastructure – this is low-cost. There’s a lot of automation available now around machine learning,” states Elrifai. “In the data world, when you try to build models, about 80-90% of the effort that is put in is made up of data engineering, feature engineering, preparing data, filtering – all the easy stuff.”
Elrifai believes that a lot of the data prep for data engineering can be done in an automated fashion. “I don’t think people recognize that. They are trying to use old tools to solve new problems,” he concludes.
Wael Elrifai is an author and speaker. He works as Sr. Director of Enterprise Solutions at Pentaho, a data integration and business analytics company with an enterprise-class, open source-based platform for diverse big data deployments.
Keys to effective IIoT design
How does the IIoT change the way industrial products and services are designed? What types of opportunities should companies seize and which challenges should they expect to tackle? Petri Asikainen, Director of Core Technology Development at Konecranes, shares his insights.
Machines report on their usage and condition. Maintenance interaction data is combined with equipment engineering information. Remote-controlled cranes. Logistics chains are truly transparent, as each link is programmed to anticipate the next steps, optimizing flow across the entire chain.
As low-cost sensors and powerful software turn the IIoT from buzzword to reality, the opportunities for new product and service design seem endless. But where should companies start?
Focus on customer value
“The starting point for successful design is a deep understanding of the client’s processes and needs.”
According to Petri Asikainen, Director of Product Development at Konecranes, the key to great IIoT design involves taking a step back from all the cool things that technology can do, and focusing on where it can offer clients the most value.
“Buyers in industrial companies are usually highly rational. Most of them do not care for fancy new gadgets or features just for the novelty of it,” says Asikainen. “The starting point for successful design is a deep understanding of the client’s processes and needs. What is essential and useful for them? Can you make significant improvements in efficiency or work safety? How can you make their life easier?”
Sometimes the solution might not be selling new equipment, but rather retrofitting old equipment with sensors that connect it to intelligent networks to extend its lifespan. Or, it may not mean new sensors but developing software to utilize the sensor data already available in a new way.
“When you have a solid understanding of the user environment, there’s quite a lot you can do by developing the software instead of adding new hardware or sensors – and it’s often more cost-effective too,” he continues.
Design products that communicate
It’s important to note that in the IIoT environment, your products are just small pieces of a larger network. To offer real value, they must fit into, communicate with and improve the client’s existing system.
“With any type of new product, you need to ask the basic questions: How will it communicate with its surroundings and other intelligent systems like enterprise resource planning software? What type of data should it gather and for what end?” explains Asikainen.
Not all data is equally useful either. With increasing amounts of automation, and more smart machines and programs being used at industrial sites, the human operators’ ability to handle new information is often already at its limit. As Asikainen points out, “Especially in user interface design, you should be careful to present only the most crucial information at each given moment.”
Another aspect concerns the high demand for data security in the industrial setting.
“Unlike on the consumer side, you cannot monetize customer data by sharing it with third parties,” Asikainen says. “Data security is a huge issue in IIoT design, as the possible risks with data breaches are often severe.”
Use data to deepen understanding of client needs
“With a clear focus and insight into client operations, IIoT solutions can produce tangible gains for most industrial clients.”
While there are challenges in designing for the IIoT environment, there are also huge opportunities. For one, the influx of new information allows designers to form a deeper understanding of clients’ real needs and to offer them optimized solutions.
“Before, we had an incomplete view into how clients actually use our equipment and services. Now, we can start the design process from facts and real-life data. That is a great advantage for both sales forces and product development.”
In practice, this can mean creating new service concepts or equipment models that fit the clients’ use patterns more precisely. Or it could include offering complementary services that improve safety and quality such as staff training sessions on how to use the equipment efficiently.
The good news, says Asikainen, is that with a clear focus and insight into client operations, IIoT solutions can produce tangible gains for most industrial clients.
“In heavy industrial settings where production volumes and material flows are large, optimizing equipment and tweaking processes with the help of new data can bring in significant savings,” concludes Asikainen.
Petri Asikainen works as Director of Core Technology Development at Konecranes.