Pradeep Agarwal, senior director, ERP Cloud, Oracle talks to Dataquest about the role played by digital twin technology in the Indian IT industry, and some challenges associated with it.
What is the role of the digital twin in the Indian IT landscape?
India is a burgeoning economy, for which the next decade of manufacturing will focus on adopting cognitive solutions that infuse intelligence into all processes – from a factory’s floor to the finished product. Digitalisation of the industries can optimise them, but the deployment of digital twins has the potential to improve scalability, reduce the cost of production, minimise production defects, and reduce production time.
In process-driven functions, digital twins constantly receive data feeds from interconnected machines, helping in predictive maintenance and running the business as usual without downtime. Many key industry verticals in India will benefit from this.
What challenges does the industry face in linking technologies like IoT, AI, ML with a digital twin?
One, there is a clear gap between technical skills and digital dexterity. Two, there are concerns around data security. Three, handling data growth is something organisations often grapple with. As more companies become dependent on AI usage, they will be faced with more data that is being generated at a faster pace and presented in multiple formats. To wade through these vast amounts of data, AI algorithms need to be able to combine data that might be of different types and time-frames.
The deployment of digital twins can be revolutionary in tackling these issues. Predictive maintenance solutions powered by digital twins help in precise monitoring and timely recognising potential anomalies within a system. For instance, a predictive twin offered under Oracle IoT Intelligent Applications can detect future problems or the state of a machine and can determine trends and patterns from contextual machine data. With this information, problems like potential security can be addressed in advance to prevent loss of time.
In which sectors can businesses refine their operations by implementing digital twin technology?
The application of digital twins is versatile and can work for various industry sectors including automotive, food and beverages, pharmaceuticals, power utilities, transportation and logistics, aerospace and defense, and data centers, to name a few.
How is data core to digital twin technology and how does it help in delivering value and unlock data insights?
Data is indeed at the core of digital twin technology. Two-way communication between the physical and digital is essential for digital twins. Data flows from the physical asset to the digital twin and vice versa. That data is leveraged using data science, whether that’s AI, ML, or basic data analysis. Insights derived from this data helps provide better decision-making resulting in interventions that are fed back to the physical asset, providing better outcomes. The more that machine-to-machine data exchanges are used, the better the results are.
How is the digital twin vital to the expansion of IoT technology?
A digital twin is essentially a virtual model of a physical device. It is used by IoT developers, for running simulations without an actual physical device. In one way or another, digital twins can be credited for the burgeoning growth of IoT. An IoT device takes its place like a physical object in the concrete world. A digital twin on the other hand is the virtual representation of the same IoT device which exists within a system. It basically replicates the physical dimensions, capabilities, and functionalities of the IoT device in a virtual environment. Hence, there is an intrinsic connection between the two.
What kind of solutions is Oracle offering around this new technology?
Oracle IoT Intelligent Applications core offering includes key digital twin elements including virtual twin, predictive twin, and twin projections. In a virtual twin, Oracle’s device virtualisation feature creates a virtual representation of a physical device or an asset in the cloud to retrieve a last known status or to control the operation states of an asset. In a predictive twin, the digital twin implementation builds an analytical or statistical model for prediction by using a machine-learning technique.