Manufacturing, energy and transportation companies are increasingly benefiting from Industry 4.0 applications after years of hype. The emergence of digital twins is one of the main reasons engineering and design teams are realizing these benefits for their businesses.

What is a digital twin?

A digital twin is a real-time digital representation of an actual physical asset in operation that reflects the current state of the asset and provides relevant historical data. Businesses can leverage digital twins to analyze real-time performance, optimize operations, predict future behavior, or fine-tune control of its assets, such as pumps, motors, power plants, manufacturing lines, or machinery. vehicle fleets.

Why use a Digital Twin?

There are many ways for engineering teams to design and deploy digital twins to bring value to their businesses and optimize future operations.

Asset history

Digital twins capture the history of the physical asset and are periodically updated to represent the current state of the real asset. Over time, these past states become the history of the asset. The type of information included in this history differs depending on how the digital twin is used and what is captured in the current state. For example, a digital twin used for fault classification will capture a history that includes operational data for a specific pump from its healthy and faulty state. In the future, engineers can then compare this pump’s operational data to digital twin histories of other pumps to understand how they performed in the face of similar faults and the effect on fleet efficiency.

Interview Strategies

The ability to monitor an entire fleet using digital twins brings benefits to planning operational events and improving maintenance strategies.

For example, when a specific pump is about to fail, digital twins can assess how this will affect fleet efficiency and potential costs. This informs the company when making the decision between ordering a new part and waiting for it to arrive or paying more for expedited shipping to get the part as soon as possible.

Simulate future scenarios

Companies can use digital twins to simulate future scenarios to see how factors like weather, fleet size, or different operating conditions affect performance. This approach helps manage assets and optimize operations by informing maintenance schedules or notifying expected breakdowns in advance.

Digital twins can be leveraged by businesses for a variety of applications, including anomaly detection, operations optimization, and predictive maintenance.

Anomaly detection

The digital twin model works in parallel with real assets and signals in real time operational behavior that deviates from expected behavior. For example, an oil company can stream sensor data from continuously operating offshore oil rigs while the digital twin model looks for anomalies in operational behavior to flag potential damage to equipment.

Optimization of operations

Companies can apply variables such as weather, fleet size, energy costs, or performance factors to trigger hundreds or thousands of simulations to assess readiness or necessary adjustments to endpoints. current system setpoints. This approach allows you to optimize system operations to mitigate risk, reduce costs, or gain efficiency. For example, Mathworks worked with a beverage and food producer to create a digital twin that not only supports design optimization, but also failure testing and predictive maintenance.

Predictive maintenance

In automation and industrial machinery applications, companies can use digital twin models to determine the remaining useful life and the best time to service or replace equipment.

In a typical smart connected system topology, as shown in Fig. 1, Digital Twins can be run on the smart asset, edge, or IT/OT layers depending on the required response time of the application. For example, predictive maintenance, a common Industry 4.0 application, typically requires making real-time or time-critical decisions, which means the digital twin must be embedded directly into the asset or at the edge.

digital twins
Figure 1: A typical smart connected system topology and where digital twins should be deployed. © 1984–2020 MathWorks, Inc.

How does a Digital Twin work?

The following example describes a company that has three well sites in different locations where it operates multiple pumps to extract oil and gas from the ground and wants to apply predictive maintenance to a digital twin on its multiple pumps.

Engineers can create a digital model that is updated with incoming data from sensors and current pump operating conditions. As shown in Fig. 2, the digital twin model takes these readings and outputs the current status of the pump which is analyzed by company personnel to unlock several benefits including:

  • Reduced equipment downtime: Each pump contains valuable components such as valves, seals and plungers. The digital twin helps reduce downtime by enabling staff to prevent breakdowns by predicting them in advance.
  • Inventory management: Engineers can also leverage the digital twin to identify developing faults and gain insight into parts that may need repair or replacement, enabling better parts inventory management.
  • Fleet management, what-if simulations and operational planning: In all three well locations, all pumps can have similar functionality; however, each location has different environmental factors, such as temperature, that affect pump operation. The digital twin allows the company to monitor the entire fleet, simulate future scenarios and make comparisons to identify ways to increase efficiency and improve operational planning.
digital twins
Figure 2: Sensor measurements and operating conditions are sent from the pump to the model, and the model outputs the current status of the pump. © 1984–2020 MathWorks, Inc.

How to build a digital twin

Engineers will increasingly be called upon to develop digital twins for their business given the above advantages. Here are three methods design teams should keep in mind when preparing, building, and applying their digital twin models.

Data-driven model

A company looking to optimize maintenance schedules by estimating remaining useful life (RUL) will use a data-driven model, as the type of asset data will determine which model teams will use. Similarity models can be used if the company has complete histories of similar machines. If only failure data is available, survival models can be used, and if failure data is not available, but the safety threshold is known, a degradation model can be used. If failure data is not available but you know a safe threshold, you can use degradation models to estimate RUL. In this RUL scenario, the degradation model is constantly updated using pump data measured by different sensors such as pressure, flow, and vibration.

Physics-based model

If a company wants to simulate future scenarios and monitor the behavior of the fleet in those scenarios, it will use a physics-based model, which is created by connecting mechanical and hydraulic components. This model is fed with data from an asset, and its parameters are estimated and adjusted with this incoming data to keep the model up to date. Engineers can then inject different types of faults and simulate the behavior of the pump under different fault conditions.

How to apply digital twins

Design teams should create a unique digital twin for each individual asset. This means that for each asset in a different location, teams must create a unique digital twin that has been initialized with the specific asset’s settings. The total number of unique twins will depend on the application. If teams are modeling a system of systems, they may or may not need a twin for each system of components depending on the level of precision required. For example, if the intent is to perform failure prediction and failure classification, design teams should create different models that meet these different goals.

Delivering Value with the Digital Twin

The flexibility and various potential benefits of digital twins make them a top priority for companies transitioning to Industry 4.0. Having an up-to-date representation of actual operational assets enables engineering and design teams to unlock data insights to optimize, improve efficiency, automate and assess future performance, while reducing costs and shortening development times.