“Mama look at that, the Barbie doll house that we were looking at on Amazon last night is 25% off now,” my 11-year old daughter said excitedly. Then, an ad popped up as I was doing some research on “digital twin.” As I turned my attention to the ad, I also saw other ads about books on “Personal branding”, which meant that Amazon knew my interests, preferences, likes, and dislikes. Knowing all this, helps Amazon provide me with a customized experience not only when I visit the site, but also when I’m away from it. My preferences, likes, and dislikes are all recorded in this digital world. I have created an online replica of myself – my digital twin.
Consider this concept applied to an industrial scenario. Consider a digital replica of a windmill, solar panel, or train locomotive which is paired with a physical one that is sensorized so it can send out data about itself to – its twin. This pairing of the physical and digital worlds makes it possible to analyze this data and fosters the visibility, predictive and preventive maintenance, and what-if analysis needed to understand the behavior of the assets by creating scenarios that are difficult to replicate in real life.
What is the digital twin?
A digital twin, according to Gartner, is a digital representation of a physical object. It includes the model of the physical object, data from the object, a unique one-to-one correspondence to the object, and the ability to monitor the object.
Digital twins have been around since 2002, but only gained momentum in 2017 when they became cost-effective thanks to an increase in the adoption of the Internet of Things (IoT) and cloud technologies, which enable low cost, high storage and compute, high throughput messaging, security, and more.
Every year, we pay around $20 billion dollars to maintain industrial machines, and we do so because they are critical to our operations. Digital twins put the right information in the right hands at the right time. This information can generate predictive insights to ensure that the industrial assets run more predictably, saving millions of dollars. Gartner predicts that by 2021, half of large industrial companies will use digital twins, resulting in those organizations gaining a 10% improvement in effectiveness.
Does this mean we have to build a digital twin? Not necessarily. IoT and analytics are the two great enablers of digital twins. Attaching IoT sensors to your products and assets gives us access to massive amounts of data about the products and the data collected serves as the foundation of the digital twins. There are, however, a few points to consider before investing in digital twins:
- Identify the purpose of the digital twin: what problem are we trying to solve? If the problem can be solved with sensor data, we may avoid having to build the digital twin.
- Weigh in the risks against the economic value: there are inherent risks associated with costs, security, privacy, and integration.
- Assess readiness: As the digital twin comes into the mainstream, job roles would change and we would need the capabilities to scientifically and physically simulate all the pieces working together as intended. Innovators must overcome traditional, siloed expert thinking.
Clearly, what is needed is a comprehensive portfolio that empowers the enterprise to excel at the fundamentals of digital twin by enhancing the core to create a culture of continuous improvement and innovation like never before.
Digital twins in industry 4.0
As we enter industry 4.0, digital twin is at the core of bringing in interoperability where machines and people can communicate with each other and foster transparency by creating a virtual copy of the physical world through sensor data.
The economic value of the future would involve scenarios such as:
- A field service engineer would be trained on a virtual machine, without having a dedicated trainer or simulator
- Artificial intelligence (AI) and machine learning would make machines autonomous, self-optimizing, and able to diagnose, heal, and repair themselves, thereby reducing human intervention
- For the twins to be effective, they must be connected to other components in the smart factory, software agents, unit of work, process, authentication, authorization, decisions, outliers, feedback, security, metrics, dependencies which can be considered as blocks spanning across domains in the blockchain paradigm. With digital twins, the data transferred between the blocks could be protected and made universally transparent applying the blockchain paradigm, leading to global digital transformation
- In the digital twin era, sub-units would be able to discover each other with embedded semantic properties to create a desired assembly.
With the advent of IoT, opportunities are knocking at our door, we just need to open it with prompt decisiveness. Digital twins are the bridge between the physical and the digital world and provide the catalyst for such prompt decisiveness. To take this discussion forward, connect with me via my profile or on social media.