If you're involved in IoT-related industries, you've seen a lot of activity around the idea of digital twins. The concept of digital twins is not a new concept - the term has been in existence since 2003, and you can see examples of applying its pairing technology at NASA's Apollo Mission Center. However, until recently, technical barriers that made it difficult to create true digital twins were broken. Today, large asset companies and other companies are using technological breakthroughs to plan or implement digital twin products or manufacturing processes. We can expect this interest and growth to continue: Gartner predicts that by 2021, half of all industrial companies worldwide will use digital twins and the average efficiency will increase by 10%.
The simplest definition of digital twins is to reflect the real-time state of an object by stabilizing the flow of data from the connected sensor output. The data stream that connects objects and data is called a digital thread. In some cases, digital twins not only reflect the current state of the object, but also store the historical state of the object.
How can we exaggerate the importance of digital twins in many industries, especially for manufacturing equipment and manufacturing processes that require close interaction between machines and humans. Two key reasons are: visualization and collaboration.
If you want to measure the bandwidth of human senses, vision will be the highest. Therefore, people's decision-making relies on being able to fully understand the situation and take the necessary actions. This is why the factory manager usually has a place to overlook the factory. Nowadays, as manufacturing equipment and machines become more complex, the advantages of being able to see the process have largely disappeared. Instead, today's computerized systems provide data to shop floor managers so they can make decisions through data sheets or basic charts.
Digital twins can combine the two to present accurate, visual data to decision makers in real time, including information that was previously unavailable (such as temperature or internal wear). In fact, digital twins improve the efficiency of visualization by removing non-critical information, processing the basic information into a more understandable format, and providing a more flexible (eg 360-degree or micro/macro) view.
Finally, visualization also helps to benchmark and compare historical data or best-in-class data immediately. The potential in this area is enormous because it identifies areas for improvement, shows the areas of greatest concern, and enables rapid decision making in real time.
The second important aspect of digital twins is the ability to share a digital view of the machine with the viewer anywhere. Therefore, this enables people to view, track and install devices on a global scale. This capability also eliminates the delay in reporting alerts to management, eliminates single points of failure due to human error, and makes it easier to seek expert help.
Digital Twins expands the range of workshops used by product managers, designers and data scientists. By a new understanding of how processes and machines work or not, they can design better products and more efficient processes, and anticipate problems earlier than before, saving time and reducing the waste of building physical models. They can also see the gap between expectations and reality and conduct root cause analysis.
So, what should companies considering using digital twins consider? The first thing they ask is, “What do I need to know about my manufacturing business to make me make decisions?” This determines what kind of data to acquire and what kind of visualization system to build. The question to be asked later is "What are the tasks that my business mainly wants to accomplish with digital twins?" The answer to this question can effectively clarify what conclusions will be drawn from the data obtained from the digital twins. By definition, digital twins are tailored to the object of use to ensure that only relevant data is displayed, reducing visual clutter. The final step is to develop a gradual roadmap so that digital twins become more powerful over time. This can be done by adding more relevant data sets to existing images or by accessing more roles in the business. A good example of how Google Maps builds incremental digital twins. Today's Google Maps simulates location and traffic data in more detail and more accurately than it did a decade ago. It is constantly evolving in terms of data richness and usability.
These benefits will be worth the advance planning of digital twins. As digital twins offer better products, higher efficiency and faster release cycles (from product conception to market), industrial companies with digital twins will be able to create sustainable competitive advantages. Therefore, the key now is to start investing in digital twins even in smaller projects and continue investing in the near future to create better and more complete systems.