12 factors that are increasing the popularity of digital twins and simulations


The concept of digital twins is a leading trend in corporate strategy. It gets its name from the way companies build virtual equivalents or twins of physical objects. These digital copies are becoming increasingly popular because they can control important simulations that were previously not possible.

Take a wind turbine as an example of where digital twin technology comes in handy. The turbine can be equipped with sensors that provide real-time data on the performance of the turbine, be it speed, energy output or weather conditions. This data can then be used to create a digital copy of the turbine, including a 3D digital representation. Machine learning and other models can be used to identify patterns in this turbine – for example, whether it is working optimally. The digital copy can be used to run simulations without disturbing the original turbine, and improvements can then be traced back to the original.

Simulation arouses interest in digital twins

Observers see a significant need for multi-physics simulations that offer a holistic view of different physical domains such as electronics, structures and heat. This is critical for areas such as noise and vibration. The top simulation techniques include Computational Fluid Dynamics (CFD), Multi-Body Systems (MBS) or Finite Element Analysis (FEA).

Simulation is becoming increasingly important in the manufacturing industry. Simulation software is an insurance policy for manufacturers, Michael Larner, senior analyst at ABI Research, told VentureBeat. There is an arms race in the provider community for the algorithms that can be used, he said. This “insurance” enables them to respond to rapid changes in consumer demand and interruptions in the supply chain, such as the chip scarcity that is currently hampering the auto industry. ABI predicts that simulation technologies for manufacturing could grow 7.1% to $ 2.6 billion by 2030.

Others expect that simulation advances will be used to improve various aspects of operations, particularly with the advent of what is known as the “omniverse” for rendering models – related to the use of things like VR and AR, automated data labeling, AI-assisted physics, and improved Supply chains.

12 Effects of Simulation Trends on Digital Twins

1. Omniverse for collaboration

“The most exciting development in simulation and modeling tools over the next three to five years will be the evolution of the omniverse,” said Michael Putz, CEO and co-founder of Blackshark. Some other exciting improvements include AI-assisted modeling for building reconstruction, live labeling, and AI frameworks. Top Omniverse Use Cases will combine simulation and collaboration for urban planning, location scouting, architecture acceptance, logistics, UAV flight planning and insurance.

2. Learning with less data

The generative AI techniques used in deep fakes are also getting better and better at refining and optimizing the simulation models for various digital twins. Chris Mattmann, Chief Technology and Innovation Officer of NASA JPL, told VentureBeat, “The key lies in balancing the need for labeled training data and realistic environmental simulations for the ground truth of the twin digital environment.” improve model accuracy and efficiency with less manual labeling.

3. Close gaps in physics

Modeling and simulation tools are improving with the use of AI to create physics models from live data captured from physical industrial processes. Faustino Gomez, CEO and co-founder of Nnaisense, told VentureBeat that digital twins from traditional physics models are too slow to be used for complex processes involving chemistry and fluid dynamics in real time. For example, together with EOS GmbH, Nnaisense developed a digital twin for modeling heat in additive manufacturing processes without explicit physics models. These models can predict key phenomena in real time rather than days. The most important AI algorithms that he sees as bridging the physical gap include geometric deep learning, neural ordinary differential equation (ODE) models, and contrastive learning.

4. Inference models simulate manufacturability

The simulation of digital twins has traditionally focused on simulating product performance characteristics. Improvements in sensors embedded in the manufacturing process enable inference models that can simulate manufacturability features that affect quality, cost, and ease of assembly. Jeff Kowalski, Tempo Automation’s chief product officer, said inference modeling techniques automate the process of generating digital twin models through direct observation. This reduces the human effort involved in manually creating the rules that go into a model. It also automatically updates models in response to changes in the environment.

5. Improvement of autonomous systems

Better digital twins could also improve models that control autonomous cars, ships, forklifts, and even factories. Jordan Reynolds, Director of Data Science at Kalypso, told VentureBeat, “Great advances in autonomous systems performance have come from Model Predictive Control (MPC), a digital twin methodology that simulates how a complex system reacts to operational inputs and changes in its environment reacts. ”These models are used to simulate dynamic system behavior and to autonomously control these systems in the physical world. MPC is also used to simulate the spread of COVID-19 and determine the optimal interventions to accelerate its decline.

6. Simulation orchestration

Simulation containers promise to build on the success of application containers that underpin agile software development and deployment practices. Maurizio Galardo, Aveva’s chief technologist at XR, expects simulation tools to evolve from fine-tuning products designed to solve specific tasks to a container of capabilities that allow users to quickly synthesize entire product designs. These simulation microservices can be reused in various design, simulation and production workflows.

7. Generative design of systems

Generative design techniques automate design proposals from a number of initial specifications. PTC Vice President of Product Management Paul Sagar said that engineers have traditionally used generative design to create and optimize individual parts. He expects improvements in algorithms and processing capacity to solve broader problems in simulating complete assemblies, such as the performance of a carburetor using a digital twin of the complete car.

8. Engineering business products

Improvements in computing power and interoperability lead to digital twins that combine business and engineering simulation techniques. Scott Buchholz, National Research Director for Emerging Technologies at Deloitte Consulting, said, “Digital twins can be very useful for simulating things like switching from selling widgets to selling as a service.” For example, Bridgestone uses digital twins to measure cost per mile to optimize the maintenance and tire selection of fleets. This helps business teams sell tire miles as a service and align technical decisions with longevity and maintenance strategies to improve this new business model.

9. Cooperation in the supply chain

Simulation tool providers such as Synopsys find ways to simulate the chip design and the software running on it. This promises to improve collaboration on products such as automotive chips, which have faced significant bottlenecks due to the integration challenges of more modern chip designs. Tom De Schutter, Vice President of Engineering of the Synopsys Verification Group, sees great opportunities in the development of scalable digital threads that are operated across the entire supply chain in order to map individual components through complete system products. This includes digital twins of individual hardware designs, systems on a chip, electronic subsystems and overall systems. But that also requires new infrastructure to capture, share, and track the fine-grained data that powers these hybrid digital twins.

10. Smaller models

AI can also be refined to create smaller models that require less data and computational power than traditional approaches known as reduced order models, said Brett Chouinard, Altair’s chief technology officer. He anticipates this will increasingly support the deployment of sophisticated digital twin models on remote devices such as edge gateways and devices. These smaller digital twins will increasingly add value to new products and services. Chouinard said, “While this is already happening, newer applications that build on it only bring it more focus, creating more complexity and a demand for more capacity on the fringes.”

11. Digital twins with multiple domains

Simulation integration techniques also open up possibilities for multi-domain simulations. These build on multi-physics and integration techniques to support work across domains such as security and physical infrastructures such as power grids and gas pipelines, said Dr. Rajive Bagrodia, CEO and Founder of Scalable Network Technologies. In the power grid, for example, attacks that delay control of a circuit breaker or falsify the reporting of the sensor load can cause a number of cascading effects with potentially catastrophic consequences for a regional power grid. Multi-domain digital twins coupling physical system simulators with network emulators could improve resilience, detection, and response to these types of scenarios.

12. Democratization of simulation

The democratization of simulation could open up new planning and development possibilities for less technical users. Today, the simulation market is primarily aimed at industrial designers and engineers in R&D departments. More accessible tools will lower the barriers to adoption for business users, purchasing departments and subject matter experts. “Design decisions will be much smarter because new products are selected based not only on aesthetics or performance, but on a variety of factors,” said Roger Assaker, president of Hexagon Manufacturing Intelligence’s MSC Software Division.


VentureBeat’s mission is to be a digital marketplace for technical decision makers to gain knowledge about transformative technologies and transactions. Our website provides essential information on data technologies and strategies to help you run your organization. We invite you to become a member of our community to gain access:

  • current information on the topics of interest to you
  • our newsletters
  • closed thought leadership content and discounted access to our award-winning events such as Transform 2021: Learn more
  • Network functions and more

become a member


Leave A Reply