How IoT powers next-generation Enterprise Asset Management
Enterprise Asset Management (EAM) has a significant impact on an organisation’s ability to overcome challenges and compete in the global market. EAM can result in significant cost savings and growth thanks to its ability to positively affect planning and budgeting, strategic alignment, Maintenance, Repair, and Operations (MRO), risk management, compliance, and organisational harmonisation.
By: Dr. Cierrah Perrin, Principal Business Architect, Digital Asset Performance at DXC Technology.
At the core of our vision for next-gen EAM is the rapidly emerging network of physical devices, vehicles, appliances, and other items embedded with electronics, sensors, actuators, and network connectivity called the Internet of Things (IoT).
EAM is entering the connected era
As enterprises evolve and enterprise assets become increasingly more interconnected, EAM must evolve as well. The size of the IoT market is expected to balloon up to 20 billion units by 2020. A large portion of this number is predicted to come from the IIoT, which focuses on embedded devices and objects in an enterprise setting that contain technology to sense, communicate, and interact with the external environment.
The massive amounts of data generated by both IoT and IIoT represent a tremendous opportunity for all forward-thinking and asset-intensive enterprises to more efficiently design, construct, commission, operate, maintain, decommission, and replace physical assets. However, for the data to be of any value, enterprises need the ability to make sense of it by turning countless individual data points into easy-to-understand trend charts and statistics.
Predictive maintenance with Big Data analytics
Many enterprises now produce such a large volume of data that traditional data processing application software is inadequate to deal with them. In the recent years, new techniques have emerged, allowing enterprises to collect, store, and analyse data from a variety of sources, including traditional business transactions as well as the information coming from industrial sensors or machine-to-machine communication.
These new techniques are collectively known as big data analytics, and their goal is to uncover hidden patterns, correlations, trends, and other useful insights to help enterprises make more-informed business decisions. Even though the term big data was first used in the mid-1990s, it has become well-known only in recent years, since data scientists, predictive modelers, and statisticians have been busy analysing data from the IoT and the IIoT.
Next-gen EAM relies on big data analysis of data from IoT and IIoT to predict when equipment failure might occur and when maintenance should be performed. This practice, called predictive maintenance, gives enterprises a crystal ball, potentially enabling them to see how and when a failure might unfold unless they take the necessary steps to prevent it.
As such, predictive maintenance helps enterprises avoid expensive equipment malfunctions, improve production quality and reliability, optimise resource management, schedule maintenance at the least disruptive time to operations, predict warranty claims, and inform customers about upcoming issues to increase their satisfaction, among many other things.
For example, a machine dispensing thermal paste could continuously analyse production data coming from industrial sensors to detect when it can no longer reach the target temperature. The machine could then automatically consult the quality database and identify the most suitable parameter set to restore itself into a working order.
Historically, enterprises used to repair their equipment only after a failure had already occurred, causing their production to slow down or come to a halt. This is called corrective (or fail-and-fix) maintenance. Many enterprises today rely on preventive maintenance (or frequency-based maintenance), which is a time-based method where the equipment is maintained proactively according to a fixed schedule while the equipment is still working.
“Predictive maintenance (PdM), also known as condition-based maintenance, has been proposed as a new method to overcome the disadvantages of both corrective and preventive maintenance. The basic idea of PdM is to perform maintenance at the right time, i.e., right before failures. Among the three practices, PdM is the most cost-effective and yet the most challenging because finding that right time is usually a formidable task,” stated an article published in Emerging Technology and Factory Automation (ETFA).
Thanks to big data analytics and the data coming from IoT and IIoT, next-gen EAM makes the task of finding the right time for maintenance effortless. Machinery can automatically send a message to technicians to alert them about a brewing problem, reducing unplanned downtime and saving costs.
This fundamentally changes the nature of the relationship technicians have with machinery. Our vision of next-generation EAM replaces traditional technicians with so-called smart technicians, who are in part skilled analysts capable of intelligently scheduling maintenance to minimise disruption and costs using insights provided by the machinery itself.
Digital twin and its role in next-gen EAM strategies
Digital twins are commonly described as dynamic digital representations of industrial assets. Digital twins enable enterprises to better understand and predict the performance of their machines and find new revenue streams, and change the way they operate.
In practice, digital twins are used to optimise machines with the use of 3D modeling to create digital companions for the physical objects combined with big data analysis of information coming from various industrial sensors to create living digital simulation models that update and change as their physical counterparts do.
“The ultimate vision for the digital twin is to create, test and build our equipment in a virtual environment,” said John Vickers, NASA’s Leading Manufacturing Expert and Manager of NASA’s National Center for Advanced Manufacturing. “Only when we get it to where it performs to our requirements do we physically manufacture it. We then want that physical build to tie back to its digital twin through sensors so that the digital twin contains all the information that we could have by inspecting the physical build.”
By pairing digital twins with mixed reality smart glasses, which make it possible to engage with digital content as if it were part of the real world, smart technicians could soon do their jobs faster, smarter, and safer. The pairing could result in easier access to detailed schematics, training videos, quality assurance checklists, and, above all, digital twins of industrial assets.
Here at DXC, we have developed and piloted a Smart Technician solution on ODG R-7 Smart Glass technology, complete with integrated Intelligent Checklist and Visual Remote Guidance apps, and using voice commands to step through mantenance and repair operations, digitally overlaying instructions onto physical equipment.
We also worked with a major chemical treatment and distribution company to develop an augmented reality solution that guides the company’s sales people through an assessment of a customer’s storage site, to ensure the safety of delivery before delivering dangerous chemicals to the site. DXC created an augmented reality application on Microsoft HoloLens to provide a much more realistic form of training and assessment at much less cost.
It is expected that billions of things will be represented by digital twins within three to five years. By using data provided by physical, Internet-connected sensors and combining it with software simulations and analysis, enterprises will be able to quickly respond to changes, improve operations and increase value across the entire lifecycle of an asset.
The total enterprise investment into digital twin technology is predicted to grow significantly during the upcoming years, and the enterprises that invest in the digital twin technology could see a 30% improvement in cycle times of critical processes by 2018.
This, coupled with the benefit of predictive maintenance and smart technicians, is our vision for next-gen Enterprise Asset Management. As enterprises embrace technologies that rely on enormous amounts of data and in-depth analytics, they will naturally move away from working in silos toward connected, data-driven models that reduce costs and inefficiencies, address uncertainties, improve productivity, and do so much more.