Can digital twins model the post-pandemic recovery?

Digital twin technology, once the domain of the industrial sector, is entering the mainstream. It will be an essential component in modeling recovery post-pandemic by optimizing projects, building up resilience and helping to reduce costs.

A digital twin is a computer-generated virtual model of a process, product or service that uses real-world data to create simulations and predict how a product or process will perform in real time. This allows enterprises to harvest valuable insights into performance or spot potential issues.

Digital twins can be integrated into industry 4.0, analytics and, more recently, artificial intelligence (AI) and machine learning (ML). It further enhances output by including monitoring, process control and dynamic virtual testing. A digital twin can be as complicated or as simple as a project requires and is dependent on the data it is fed. This data is usually harvested from a network of sensors.

Digital twins go way beyond the simulation capabilities provided in computer-aided design. The huge take-up of IoT sensors is what has made digital twins increasingly possible for smaller projects. Combined with the Internet of Things (IoT), digital twins can be constructed to receive data in real time to enable the user to see how products or processes are changing as data is delivered.

The aerospace and defense industries have been trailblazers in digital twin technology. As the technology's price has reduced, it has been further adopted by the manufacturing and energy industries. More recently, its potential has been spotted by retail and financial services. Why? Because digital twin technology can allow business leaders to virtualize their organizations to improve productivity, optimize processes and increase resilience in the face of a crisis. Digital twins can contribute to economic recovery by designing self-healing supply chains or healthier and enhanced workflows in healthcare, for example.

Digital twins go mainstream

While the concept of digital twins has been around since 2002 when Michael Grieves at Michigan University first coined the term, IoT platforms have made the technology affordable and easily accessible. Gartner estimates that next year, over two-thirds of enterprises utilizing IoT will have deployed at least one digital twin in production. The global digital twin market is currently worth $6 billion across all industry sectors and will grow at a 40% CAGR to $16 billion by 2023.

Can digital twins model the post-pandemic recovery?

According to Gartner, digital twins are being adopted by all kinds of organizations, including healthcare, automotive, smart cities, retail and asset management. For example, French start-up ExactCure is looking to become a world leader in personalized health bio-modeling using digital twins. The company has been using digital twins to accurately prescribe drugs based on a patient’s unique characteristics and data. It is estimated that in the UK alone there are 237 million drug errors a year that could be avoided using ExactCure’s technology.

The patient’s digital twin simulates the impact of the medicines on the body. AI is used to assess personal characteristics such as age, weight, sex and so on. ML algorithms can be continuously adjusted based on qualitative feedback of patients.

The road to recovery

COVID-19 has been a catalyst for accelerating digitization. Digital twins can be a crucial tool in speeding up efforts to pinpoint stress points and represent scenarios from product creation and operations to effective asset utilization and risk, for example. They can also help in managing uncertainty and preserving business continuity.

The post-pandemic touchless society will have a significant impact on service levels. Contactless delivery of products and services will be paramount. Digital twins can help everyone, from manufacturers to healthcare providers, mitigate the unnecessary risk of contact or draw up contingency plans for disrupted supply chains.

As well as providing predictive modeling, greater transparency and insight into product behaviors, digital twins can also be used to create what-if scenarios and enable data-driven decision making. Businesses will be able to understand the impacts and trade-offs and make informed decisions in terms of capacity and inventory in supply chains, for example. As well as helping with immediate business demands, digital twins can help enterprises future-proof their operations and build more resilient contingency plans long term.

Considerations in adopting digital twins

As with any new emerging technology, enterprises need to understand the business needs for employing it alongside the benefits and challenges.

Digital twins have an enormous scope because they can model everything from individual components right up to entire processes and product lifecycles. But there are challenges to consider in terms of data security, the necessity for robust, real-time connectivity, specific technical skills, and the deployment and maintenance of sensor networks that allow the digital twin to capture environmental and operational data.

The next frontier

Adding artificial intelligence (AI) and machine learning (ML) makes smart digital twins. For example, digital twins can be trained to predict upcoming machinery failure months in advance, allowing manufacturing plants to plan for downtime. ML can enable designers to create models of products based on observed behaviors.

In the future, digital twins may make the promise of personalized medicine a reality. This will enable doctors to try out medication on a digital twin to find the patient's optimum treatment. For example, Siemens Healthineers has created a digital twin that simulates the physiological processes of a patient’s heart.

Going forward, we will see digital twin technology getting more and more sophisticated, bridging our virtual and physical worlds and providing unique insights into ourselves and our surroundings.

Read this blog on how digital twins can reduce the cost of real-world prototyping and this article on digitizing physical value chains in manufacturing, transport and logistics.