Industry use of Digital Twins

Throughout this book, you will learn how to create your first industrial Digital Twin. Before we get started, though, it is essential to understand who the key stakeholders are that have an interest in the value of Digital Twins, as well as some of the high-level applications in different industries.

Digital Twin stakeholders

Let's distinguish two different high-level scenarios when using Digital Twins in industrial applications. The first scenario is where the asset that is twinned is a standalone product that's used by an end user. The specific model of an electric vehicle (EV), such as a Tesla Model 3, might be the product, while the consumer is the end user. The vehicle manufacturer will be the Original Equipment Manufacturer (OEM).

The second scenario is a manufacturing asset such as a smart factory, where the EV is produced. The Digital Twin is the factory itself and has different use cases and applications during the smart factory's life cycle phases. This production facility could also be a gold mine, an oil platform, a power distribution micro-grid, or a nuclear power plant.

For this scenario, the stakeholders include the owner/operator that commissions Engineering, Procurement, Construction, and Manufacture (EPCM) contractors to design and build these production facilities. OEMs provide equipment for facilities, and Operations and Maintenance service providers are often used by owners/operators to operate and maintain these facilities on their behalf.

Traditionally, OEMs did not have access to their products and their usage data after they left their factories, but OEMs are increasingly supplying their product Digital Twins with physical assets and, in process, aim to get access to real-time usage data. We are starting to see the reach of OEM Digital Twins extend beyond their own factories' boundaries.

Service providers for Digital Twins aim to extend their capabilities across the full life cycle of the product and facility's Digital Twins. This includes connectivity, compute, storage, integration, modeling, analytics, visualization, and workflows.

The following diagram shows the typical roles of stakeholders during the asset life cycle phases:

Figure 1.9 – Key stakeholders during the life cycle of an entity

All of these stakeholders have had a vested interest in Digital Twins at some stage during the product or facility's life cycle. Information or Digital Twin sharing between stakeholders increases as Digital Twin use cases start to span multiple stakeholders across multiple phases. It significantly increases the Digital Twins' business value, but it also increases complexity and leads to interoperability challenges. Some of these challenges will be addressed later in the book.

Industrial Digital Twin applications

Digital Twins exist across the whole life cycle of assets and products, as we saw earlier in this chapter. Let's look at a few examples of industrial Digital Twin use cases in different industries. This is not an exhaustive list, but it does provide examples that highlight some of the challenges that can be addressed by Digital Twins. This can help you decide on the type of Digital Twin you would like to build as your prototype.

Discrete manufacturing

• Optimize Overall Equipment Effectiveness (OEE) in real time during operations.
• Predictive quality improvement during operations to reduce the scrap rate and rework.
• Enhance product designs with insights from operations and maintenance data.

Process manufacturing

• Manage batch-based processes to "golden batch" in real time to improve product quality and process optimization.
• Predict equipment failure with machine learning models based on real-time operational data and models built on historical failure data.
• Monitor real-time compliance with safety and regulatory requirements for classified equipment during operations.

Energy (power)

• Predict the energy demand per consumer through dynamic machine learning models in an operations-planning Digital Twin.
• Improve grid distribution and management by utilizing simulation models based on real-time data input for Distributed Energy Resources (DERs).
• Improve solar array maintenance by detecting anomalous behavior that indicates dirty panels, for example.
• Predictive maintenance for wind farms to improve the "first-time fix rate" and reduce truck rolls and the spares inventory that's carried by the field service teams.

Oil and gas

• Perform real-time Finite Element Method (FEM) analytics to determine offshore oil platforms' structural integrity based on weather and oceanic data.
• Update subsurface reservoir models with drilling and exploration data to support investment decisions.
• Monitor rotating equipment (such as pumps and compressors) in real time to improve equipment availability and asset performance. This includes condition-based and predictive maintenance.

Mining and metals

• Improved recovery yields on mineral processing plants during operations such as gold recovery or coal washing.
• Monitor mine tailings and other environmental waste in real time and provide recommendations based on expert business rules.
• Provide real-time casting guidance to blast furnace operators based on real-time process parameters and metallurgical (physics) models.

Automotive

• The Digital Twins of vehicles provide feedback to manufacturers with usage data that is incorporated in design improvements.
• Real-time telemetry in the Digital Twin of a car enables manufacturers and their service agents to offer maintenance services based on condition monitoring and predictive analytics.
• The Digital Twins of autonomous vehicles opens up new business models for service providers, such as ride-share operators.

Life sciences and medical

• Reduce the risk of critical stock and logistics challenges with a real-time Digital Twin of the end-to-end supply chain.
• Reduce downtime on expensive High-Performance Liquid Chromatography (HPLC) systems with real-time conditioning monitoring and failure prediction.
• The Digital Twin of a patient providing a holistic view to improve the quality and efficacy of medical treatment (though this is currently challenged by privacy and security concerns).

Infrastructure

• Enable off-site and on-site pre-fabrication by updating the dimensional and structural data in design Digital Twins, through to additive manufacturing during the construction and delivery phases.
• Provide real-time insights and situational awareness during natural disasters and severe weather events.
• Provide real-time insights into foot traffic in retail infrastructures such as malls and shopping centers.

Aerospace

• Track and Trace Digital Twins provide insights into real-time material and supply chain management in aviation manufacturing.
• The predictive Digital Twin of aircraft landing gear extends the life of components and reduces maintenance costs.
• Airport Digital Twins with real-time aircraft movement improve bay utilization and cycle times, thereby increasing revenue.

Defense

• Improved equipment reliability and maintainability of complex military equipment with condition monitoring and predictive maintenance Digital Twins.
• Strategic warfare Digital Twins based on real-time situational data provide planning scenarios to tactical command and leadership.
• A Spatial Digital Twin with a single, dynamic dataset that represents the physical world with sufficient resolution to act as the reference point for all systems requiring mission data.

Other

The Digital Twin concept is increasingly used to model and manage less tangible entities. Some of these include the following:

• Digital Twin of the Earth
• Digital Twin of organizations
• Digital Twin of bushfires

These different examples show a diverse range of Digital Twin applications. There are many more that have not been included in this list. The range of potential applications is only limited by the imagination of those who are actively building these Digital Twins.

A key element of all these examples is that they have clear and measurable value to the stakeholders of the Physical Twin or entity.