Two heads are better than one
The concept ‘digital twins’ was coined in a presentation by Grieves in 2003 according to the white paper (Grieves, M. (2014). Digital twin: manufacturing excellence through virtual factory replication. White paper)
Digital twin is digital representation of a physical objects such as devices, people, processes, or systems. Digital twins are advanced simulation and analytical capabilities that can establish links to live data.
Digital twins mirror the operation and predict the state for the physical entity employing advanced technologies to improve the performance of a physical entity. Digital Twin is not a specific technique but a scheme, in which the modelling methods and purposes depend on the usage scenario.
The communication between physical and digital replica is bi-direction, and it is a critical feature for distinguishing between the digital model, digital shadow and digital twin. The fidelity of digital twins depends on its intended purpose.
DT is dynamic since it evolves with the physical entity by feeding the data in the product life cycle (PLC).
Production characteristics and constraints information of products can be added to the digital model. Geometric models only represent the static information of the model. Operations of a physical entity can be modelled by simulation techniques. Besides, another class of modelling methods, called the rule-based method, is used to extract knowledge and rules from historical data, expert knowledge to predict the behavior of the physical entities. In rule-based methods, statistical methods and machine learning models are used to extract rules, and ontology methods are used to describe rules. Digital twins are dynamic, and model evolution techniques update the models according to the feedback of the physical twin to mirror the physical objects. Model verification and validation are critical to keeping the model fidelity and accuracy, which is quite critical to its performance.
Product Digital Twins
They are virtual representations of a product over its lifecycle that combine data from multiple sources to improve the design, manufacturing, and support of products and services. Product Digital Twin helps manufacturers improve performance throughout the equipment lifecycle.
Process Digital Twins
They enhances the Product Digital Twin beyond a single machine to encompass the entire production environment. Process Digital Twins enhance the benefits of a Product Digital Twin as well as enable advanced scenarios in three areas of the manufacturing process – at the machine level, the factory level, and the supply chain level.
Organizational Digital Twin
This is a model of any organization that integrates operational and contextual data to understand how an organization operationalizes its business model, connects with its current state, responds to changes, deploys resources and delivers customer value.
Achieve the operational excellence of Industry 4.0 Manufacturers can gain efficiencies by applying the principles of Industry 4.0, a vision of an interconnected factory where equipment is online, intelligent, and capable of collaborating in a vertically integrated organization.
Companies in many different industries are already capturing real value and they have very high potential to apply digital twin for their product development, manufacturing, and through-life support. Accelerates the pace of product development while simultaneously reducing development costs.
Based on the experience of companies that have already adopted the approach, digital-twin technologies can drive a revenue increase of up to 10 percent, accelerate time to market by as much as 50 percent, and improve product quality by up to 25 percent. Digital-twin technology is becoming a significant industry. Current estimates indicate that the market for digital twins in Europe alone will be around €7 billion by 2025, with an annual growth rate of 30 to 45 percent. The global digital twin market size was valued at $3 billion in 2020 and is estimated to reach $73.5 billion by 2027.