Digital twins are virtual replicas of physical devices that data scientists and IT pros can use to run simulations before actual devices are built and deployed. Digital twins can also take real-time IoT data and apply AI and data analytics to optimize performance.
Digital twin technology has moved beyond manufacturing and into the merging worlds of Internet of Things, artificial intelligence and data analytics and more complex things become connected, with the ability to produce data, having a digital equivalent gives data scientists and other IT professionals the ability to optimize deployments for peak efficiency and create other what-if scenarios.
What is a digital twin?
A digital twin refers to a virtual model of a process, product or service. It is a bridge between the physical and digital world. In other words, a digital twin is a digital or virtual copy of physical assets or products.
The term digital twin was originally coined by Dr. Michael Grieves in 2002. NASA was one of the first to use this technology for space exploration missions. This pairing of the virtual and physical worlds allows analysis of data and monitoring of systems to identify problems before they even occur, prevent downtime, develop new opportunities, and even plan for the future by using simulations.
Why use a digital twin?
Digital twins are used in a variety of applications like anomaly detection, asset management, and fleet management. These common applications drive the intended use of the digital twins. In a characteristic smart connected system topology as shown below, the digital twins could be executed on the smart asset, at the edge, or on the IT/OT layers depending on the response time that the application requires.For example, predictive maintenance generally would require making real-time or time-sensitive decisions. When you implement multiple digital twins for different applications, you can deploy each one differently into the system topology.
How does Digital twin work?
Digital twins connect the real and virtual world by collecting real time data from the installed sensors. The collected data is either locally decentralized or centrally stored in a cloud.The data is then evaluated and simulated in a virtual copy of the assets. After receiving the information from the simulation the parameters are applied to real assets. This integration of data in real and virtual representation helps in optimizing the performance of real assets.Digital twin can be used in various industries such as manufacturing, automotive, construction, utilities and healthcare. Hence we can say the digital twin is the next big thing in fourth industrial revolution for the development of new products and processes.
How to Design Digital Twins?
A digital twin design is made by gathering data and creating computational models to test it. This can include an interface between the digital model and an actual physical object to send and receive feedback and data in real time.
A digital twin requires data about an object or process in order for a virtual model to be created that can represent the behaviours or states of the real world item or procedure. This data may relate to the lifecycle of a product and include design specifications, production processes or engineering information. It can also include production information including equipment, materials, parts, methods and quality control. Data can also be related to operation, such as real-time feedback, historical analysis and maintenance records. Other data used in digital twin design can include business data or end-of-life procedures.
Once the data has been gathered it can be used to create computational analytical models to show operating effects, predict states such as fatigue, and determine behaviours. These models can prescribe actions based on engineering simulations, physics, chemistry, statistics, machine learning, artificial intelligence, business logic or objectives. These models can be displayed via 3D representations and augmented reality modelling in order to aid human understanding of the findings.
The findings from digital twins can be linked to create an overview, such as by taking the findings of equipment twins and putting them into a production line twin, which can then inform a factory-scale digital twin. By using linked digital twins in this way it is possible to enable smart industrial applications for real world operational developments and improvements.
What kinds of types of digital twins are there?
IBM offers a categorization scheme based not on specific industries but on the complexity of what’s being twinned. This provides a useful way to think about the needs in specific use cases and gives a look at the broad spectrum of what digital twins can do:
- Component or part twinssimulate the smallest example of a functioning component.
- Asset twinssimulate two or more components working together and let you study the interactions between them.
- System or unit twinslet you see how multiple systems assets work together, simulating an entire production line, for instance.
- Process twinstake the absolute top-level view of systems working together, letting you figure out how an entire factory might operate.
Where is it Used?
Digital twins are used in a wide variety of industries for a range of applications and purposes. Some notable examples include:
“Digital twins can make manufacturing more productive and streamlined while reducing throughput times.”
One example of where digital twins are used in the automotive industry is to gather and analyse operational data from a vehicle in order to assess its status in real time and inform product improvements.
Outside of manufacture and industry, digital twin is used in the retail sector to model and augment the customer experience, whether at the level of a shopping centre or for individual stores.
The medical sector has benefitted from digital twin in areas such as organ donation, surgery training and de-risking of procedures. Systems have also modelled the flow of people through hospitals and track where infections may exist and who may be in danger through contact.
Global climate change has had an impact across the world in recent years, yet digital twin can help to combat this by the informed creation of smarter infrastructures, emergency response plans and climate change monitoring.
Digital twin can also be used to help cities become more economically, environmentally and socially sustainable. Virtual models can guide planning decisions and offer solutions to the many complex challenges faced by modern cities. For example, real time responses to problems can be informed by real time information from digital twins to allow assets such as hospitals to react to a crisis.
Digital Twin concept represents the convergence of the physical and the virtual world where every industrial product will get a dynamic digital representation. Throughout the product development life cycle, right from the design phase to the deployment phase, organizations can have a complete digital footprint of their products. These ‘connected digital things’ generate data in real time, and this helps businesses better analyze and predict the problems in advance or give early warnings, prevent downtime, develop new opportunities and even plan better products for the future at lower costs by using simulations. All these will have a greater impact on delivering a better customer experience in business as well. Digital Twins which incorporates Big Data, Artificial Intelligence (AI), Machine Learning (ML) and Internet of Things are key in Industry 4.0 and are predominantly used in the Industrial Internet of Things, engineering, and manufacturing business space. The widespread reach and usage of the Internet of Things have made the Digital Twins more cost-effective and accessible for the business world.