Digital Twins and Virtual Environments
Engineers utilize the concept of digital twins for centuries. You design an apparatus, then track its performance on paper, find points you can enhance, and then make the necessary tweaks to processes or components. Digitization and advancements in computer sciences now allow all these processes to be automated using sensors while algorithms generate insights. This is the core concept of digital twins. Leonardo would have built a copter if he had gained access to a working digital twin of his copter designs. Unfortunately, he lacked sensors to install in crucial joints and had no measuring devices to assess the performance of his mechanical parts.
IBM’s Chris O’Connor explains on their company blog: “Digital twin is a virtual/digital representation of a physical entity or system. It involves connected “things” generating real-time data. That data is analyzed in the cloud, and combined with other data related to the thing / context around it. It is then presented to people in a variety of roles, so they can remotely understand its status, its history, its needs, and interact with it to do their jobs.”
(Image Source: Deloitte University Press)
Digital Twins Replicate Complex Systems
Unlike command and control centers, the digital twin is just a virtual replica of a real machine or system. The core idea behind this is not to manage the system remotely, but to analyze its behavior, design strengths and weaknesses, and get insights on the enhancements you can introduce to the system.
A virtual twin may be applied literally to any system or machine. In reality, you need digital twins only when complex systems are concerned, not to analyze a simple lever system. The emerging Internet of Things networks are perfect examples of a system you can optimize using digital twins. Those are hundreds and millions of connected devices where you need all cross-connections assessed and overall network efficiency evaluated using sensors and input-output gauging devices. You need to measure bandwidths and evaluate the combined computing power of an IoT network to reap off the benefits.
Digital Twins Are Not Easy to Implement
The same applies to industrial systems where the potential application of the digital twins concept can result in savings worth billions of dollars due to improved manufacturing efficiency. Gartner experts put digital twins on their list of the top 10 technology trends for 2017, but this potential is only achievable in case future systems feature self-optimizing capabilities in a manufacturing ecosystem comprising a digital twin.
This is quite a task even for large multinationals. You need to design and implement sophisticated systems where a complex physical machine and its digital replica are able to communicate crucial data at planning, production, and order processing level, as well as utilize the results at the lowest machine level.
In theory, you can have an identical manufacturing platform and its virtual twin from the very beginning, thus being able to alter and enhance the machine design before implementation in practice. Then you collect data from sensors and introduce further enhancements, resulting in an almost perfect production efficiency, minimum errors, and minimized rejects level. You can test any possible machine configuration on the digital version first, having the ability to select the optimum one.
The opportunities are endless provided that you have access to resourceful computer systems able to process a vast amount of data and store it for further use. You can perform these resource-consuming computing tasks in the cloud, yet you still need a powerful software platform to make the most out of a very complicated digital twin.
One of the most promising features of an advanced digital twin is it can use the very same data streams to serve the needs of different stakeholders – from design engineers to floor technicians to product designers and marketers. All within a single IoT platform that connects a reliable computer system to physical machinery and operations, paving the way for the next industrial revolution.
By Kiril V. Kirilov
Kiril V. Kirilov is a content strategist and writer who is analyzing the intersection of business and IT for nearly two decades. Some of the topics he covers include SaaS, cloud computing, artificial intelligence, machine learning, IT startup funding, autonomous vehicles and all things technology. He is also an author of a book about the future of AI and Big Data in marketing.