How 'digital twins' will revolutionize product software development
Imagine a world where your car drops you off to work in the morning, transforms into a self-driving taxi service for the day, and then comes back in the evening to pick you up. Imagine hospitals prescribing personalized care to patients based on the patient’s biophysical and lifestyle information gathered over time, instead of generic medicine for all patients with similar illness.
These scenarios may seem like science fiction. But the Internet of Things (IoT) is already making them a reality – enterprises like NASA already use mirrored systems to design futuristic aircrafts, where they alter, test and learn the implications of small changes before deploying at scale.
Enter the world of digital twin.
Simply put, digital twin is a connection between the physical and virtual worlds. Digital twin integrates big data, artificial intelligence (AI), machine learning (ML) and IoT with data to create living digital simulation models that update and change as their physical counterpart changes. Like an avatar of the actual product.
Digital twin enables the creator to visualize the status and condition of a product that may be thousands of miles away. It can provide new insights into how products can be better designed, manufactured, operated and serviced. Once you understand the role digital twin plays, the next question is: how can your business use it?
Here are some examples.
Digital twin is poised to change the current face of manufacturing sector. Some of the manufacturing companies have built digital twins of heavy machinery components. These twins predict the business outcomes associated with remaining life of these components. Regular maintenance or replacements of spare parts can be scheduled based on the analyzed results.
Furthermore, a problem that arises in one factory can be identified and controlled not only in that factory, but also implemented across all factories across the globe.
Digital twins can be used in the automobile sector for creating virtual models of a connected vehicle. Data is constantly being transmitted back and forth from the car to the factory. If a driver, for instance, has a rattle in the door of his car, sensor data from the door is transferred to its digital twin. The issue can be analyzed and fixed on the Digital Twin; the repair on the actual car door is handled via software download to adjust the hydraulics.
Retailers and CPG companies can create digital twins of consumers by combining detailed transaction data with insights from social media and usage data from IoT-enabled devices. Combining data with machine learning algorithms and non-transactional knowledge such as family size and makeup, time spent away from home on a vacation, local travel to work, etc., allow companies to establish a reliable model of individual consumers. This allows retailers to predict timing and frequency of purchases. Digital twin also helps them understand the point at which a unique customer is likely approaching “reorder point” – the ideal time to present them with an offer.
In a smart city, all the physical objects (i.e. things) will have embedded computing and communication capabilities, which can sense the environment and work with each other - IoT. Some of the important services domains in a smart city are smart water, smart energy, smart home and waste management. Here, physical systems collect sensory information from the real world and send them to the digital twin computation modules. These modules process data and notify the physical systems on findings, sometimes sending control commands to make necessary changes in the physical world.
Whether it is for better prediction, improved visibility into the operations of machines, performing root cause analysis, and/or what-if analysis, Digital twins provide a sandbox environment to analyze, evaluate and implement changes. The key here is cutting down the inherent risk of loss/sunk cost as a result false alarms or recall.
I believe that within 10 years, the use of digital twins in business will be commonplace. The question in the coming days should not be, “Should I invest in IoT and digital twins?,” but rather, “Where should I start and how soon can I start investing in IoT and digital twins to reap the benefits and stay competitive?”