Chapter Twelve - Digital twin: The industry use cases
Introduction
The emergence of software-defined cloud infrastructures and scores of integrated platforms along with a bevy of pioneering digital technologies such as machine and deep learning, streaming analytics, microservices architecture (MSA), container management solutions, the distributed and decentralized IoT architectures, fog or edge data analytics, 5G communication, etc., leads to a variety of digital disruption, innovation and transformation for the worldwide corporates and cities. The nations across the globe setting up and sustaining smarter cities are empowered with the faster maturity and stability of game-changing technologies and tools. With the continued advancements and accomplishments in the ICT (information and communication technologies) space, the speed and sagacity with which the establishment of smarter cities is really praiseworthy. The rising complexities due to the arrival and usage of heterogeneous and multiple technologies for realizing smart cities are on the climb. Therefore the adoption of complexity-mitigation and value-adding technologies helps planners, decision-makers and administrators come handy in surmounting those complications to quickly and easily bring forth people-centric, extensible, adaptive, knowledge-driven, innovation-filled, cloud-enabled, and safe cities.
Heavy industry machineries, scores of personal as well as professional devices, a bevy of humanoid robots and flying drones, a dazzling array of defense equipment, medical instruments, highly complicated machineries such as satellites, rocket launchers, earth movers, etc., the growing family of manufacturing and medical instruments, and consumer electronics are growing exponentially in widespread usage. Extra intelligence besides additional capacities and capabilities are being innately embedded into all kinds of machines and devices in order to be elegantly intelligent in their designated operations, offerings and outputs. The device ecosystem is continuously growing in order to bring in a litany of path-breaking automation for not only businesses but also for people in their everyday decisions, deals and deeds. With a number of popular miniaturized techniques, devices become slim and sleek, trendy and handy, and multi-faceted. A large number of modules are being attached with devices internally as well as externally in order to supply advanced services. There are single board computers (SBCs), which are embedded and networked.
Devices are becoming intelligent through purpose-specific and agnostic integration and orchestration. Devices are being presented as API-enabled services. Devices are being expressed and exposed as interoperable, publicly discoverable, network-accessible, and composable services. All device complexities due to the multiplicity and heterogeneity nature of devices get decimated with the service-enablement. The devices and their functionalities are hidden behind the service APIs. Device integration (seamless and spontaneous) with other devices in the vicinity and faraway cloud-based applications and data stores leads to the realization of context-aware applications.
For such devices and products, there are a couple of important goals to be fulfilled. First, it is mandatory to have a deeper and decisive glimpse of what they can do, and how, what sorts of internal as well as external risks involved in using them on day-to-day basis, how they act and react in different situations, what sort of benefits can be accrued if linked together, what is its performance level and health condition, etc., before they are actually produced. The second aspect is that manufacturers and end-users want to have the product state information continuously as the product data helps immensely in devising a workable and futuristic plan for the next version/release of the product. Multiple machines, a slew of data sources, different stakeholders, and distributed applications constantly interact with products in order to have a comprehensive and futuristic view of the products. Preventive and predictive maintenance of the products can be fulfilled through real-time data capture and crunch, which helps to extricate actionable insights in time. The remote monitoring, measurement, marketing, management and maintenance of devices can be realized.
Digital twins are the virtual replicas of physical devices [1] that data scientists and IT pros can use to run simulations before actual devices are physically built and deployed. Digital twin technology has moved beyond manufacturing and started to merge with some of the emerging technologies such as the Internet of Things, data lakes, artificial intelligence (AI) and data analytics. We primarily focus on the current and future use cases for this new technological paradigm.
Section snippets
A recap of digital twin
Digital transformation is definitely a buzzword these days. Worldwide enterprises are taking all that are needed to be succulently projected as digital enterprises. Governments across the world are seriously strategizing and precisely planning to have digital governments as a beneficial measure for their citizens. Even we hear, read and sometimes experience digital economy. Our city planners and administrators are keen to have digitally transformed cities. Thus, digitization and digitalization
Digital twin key drivers
The technologies and tools for accurate sensing, perception, and vision, ambient communication, data virtualization, integrated data analytics, predictive insights, knowledge discovery and dissemination, containerized cloud infrastructures, etc., are stabilizing and maturing fast. Therefore, the concept of digital twin is growing rapidly in order to remarkably and rewardingly support and sustain digital transformation.
An inspiring example is given below. An engineer's job is to design and test
Digital twins for the intelligent IoT era
It is going to be the connected and cognitive era. Every commonly found and cheap thing in our everyday environments (homes, offices, hotels, hospitals, shopping malls, training halls, entertainment plazas, food joints, car parking areas, pathways, etc.) gets methodically digitized through a slew of digitization and edge technologies. Digitized items (stylishly termed as connected entities/IoT artifacts/smart objects/sentient materials) are capable of participating in mainstream computing. They
The levels of digital twin (DT) maturity model
There are multiple levels for digital twins. The levels typically depend on various things such as the number of sensors and actuators getting attached with physical twins and the number of different applications, services and data sources getting integrated with digital twins.
- •
Partial—At this level, the digital twin typically is connected with a limited number of data sources and sensors such as pressure, temperature and device state. This kind of twin is useful to capture a key metric or state
Digital twin industry domains
As we see, there are significant impressions and improvisations through digitization and digitalization techniques, tenets and tips. A myriad business, technology and cultural transformations across a host of industry verticals ranging from healthcare, manufacturing, retail, utility, logistics, supply chain, etc., are being realized through adoption and adaptation of digital technologies. It is predicted by leading market watchers, analysts, and researchers that there will be trillions of
Enterprise-scale digital twins
General Electric (GE), without any iota of doubt, is the industry pioneer in embracing and escalating the DT idea. The Digital Twin collects data from its manufacturing, maintenance, operations, and operating environments and uses this data to create a unique model of each specific asset, system, or process, while focusing on a key behaviour such as life, efficiency and flexibility). Powerful and real-time analytics is applied on the collected and cleansed data in order to uncover patterns in
Digital twin (DT) industry use cases
Any new technology is being comprehensively weighed based on its broader and deeper impacts. The DT technology is gathering momentum with the praiseworthy advancements in the allied technologies such as IoT, knowledge visualization, sensing technology, artificial intelligence, data virtualization and analytics, etc. DT is being primarily used to design, test, and build next-generation intelligent systems. Any worthwhile physical entity has its corresponding virtual/logical/cyber representation,
Digital twin applications
With a deeper understanding, the usage of this captivating discipline is spreading and rising. For example, the digital twin (DT) of an automobile prototype is a digital and 3D representation of every part of the vehicle. This is just replicating the physical vehicle so accurately that a human could virtually operate the car exactly as he or she would do in the physical world and get the same responses, digitally simulated. Not only systems but also processes are being digitally twinned. As
Digital twin benefits
All kinds of complicated and consolidated systems are bound to have their own digital replicas to gain and use a lot of complexity-mitigation tips. Not only product design and development but also product operations get simplified and streamlined to a larger extent. Digital twin vividly articulates and accentuates the various features, functionalities, and fallacies of any product, which is getting implemented. DT emerges as the centralized and converged source off actual truth adequately
A digital twin-centric approach for driver-intention prediction and traffic congestion-avoidance
The road traffic is steadily growing due to continued growth in people and vehicle population. The connectivity infrastructure (read roads, expressways, bridges, tunnels, etc.) is not growing correspondingly and hence the research endeavors for optimal resource allocation and utilization of connectivity resources has gained a lot these days. Therefore insights-driven real-time traffic management is turning out to be an important aspect in establishing and sustaining smarter cities across the
The solution architecture description
Following are the principal ingredients for enabling congestion discovery and dispersal, avoidance and prediction.
- 1.
Gathering Situational Information in real time—The current road and vehicle data through fog or edge data analytics
- 2.
Gaining Driver History, behavior and Intention through machine learning (ML) and Deep Learning (DL)
- 3.
Data lake at Cloud for stocking historical information
- 4.
Intelligent Transport System (ITS)
- 5.
The Virtual Vehicle (VV) model—Digital Twin
- 6.
Blockchain as a Service for Vehicles
The
Edge analytics-based virtual vehicle (VV) networks
To address the traffic challenges, here is a viable proposal. With the availability of powerful cameras and sensors along the roads, bridges, expressways, tunnels, signals, etc., a massive amount of real-time as well as historical data get captured, collected, cleaned, and stocked in order to be crunched. One of the decision-enabling factors for proactively and pre-emptively avoid traffic congestion and snarl is to get the drive intention. Fig. 2 vividly illustrates how the driver intention is
The future
Digital twin (DT) use cases have moved out of the conceptual stage to deliver real-world impacts across enterprises, which are currently executing their digital transformation initiatives. The faster proliferation of industrial IoT (IIoT) products have laid down a stimulating foundation for the widespread interest in this captivating phenomenon. That is, multiple sensors and actuators get lavishly attached with industry machineries and instruments. Further on, other purpose-specific and
Conclusion
A digital twin is a dynamic virtual representation of any digitized entity. Mechanical and electrical systems are being digitized with the systematic application of edge and IoT technologies. Consumer, automotive and industry electronics, avionics, robotics, and other electronic systems are the natural products to have their own digital twin.
Digital twin is typically a software package or library getting hosted and managed in cloud infrastructures. Digital twin is continuously empowered as it
Pethuru Raj working as the Chief Architect in the Site Reliability Engineering (SRE) division, Reliance Jio Infocomm Ltd. (RJIL), Bangalore. The previous stints are in IBM Cloud Center of Excellence (CoE), Wipro Consulting Services (WCS), and Robert Bosch Corporate Research (CR). In total, I have gained more than 18 years of IT industry experience and 8 years of research experience. Finished the CSIR-sponsored PhD at Anna University, Chennai and continued with the UGC-sponsored postdoctoral
References (3)
- ...
Cited by (16)
Digital transformation and business intelligence for a SME: systems thinking action research using PrOH modelling
2024, Procedia Computer ScienceHarnessing blockchain-digital twin fusion for sustainable investments
2024, Harnessing Blockchain-Digital Twin Fusion for Sustainable InvestmentsEmerging trends and innovations in blockchain-digital twin integration for green investments: A case study perspective
2024, Harnessing Blockchain-Digital Twin Fusion for Sustainable InvestmentsSurvey on open-source digital twin frameworks–A case study approach
2024, Software - Practice and ExperienceData integration for digital twins in the built environment based on federated data models
2023, Proceedings of the Institution of Civil Engineers: Smart Infrastructure and Construction
Pethuru Raj working as the Chief Architect in the Site Reliability Engineering (SRE) division, Reliance Jio Infocomm Ltd. (RJIL), Bangalore. The previous stints are in IBM Cloud Center of Excellence (CoE), Wipro Consulting Services (WCS), and Robert Bosch Corporate Research (CR). In total, I have gained more than 18 years of IT industry experience and 8 years of research experience. Finished the CSIR-sponsored PhD at Anna University, Chennai and continued with the UGC-sponsored postdoctoral research in the Department of Computer Science and Automation, Indian Institute of Science, Bangalore. Thereafter, I was granted a couple of international research fellowships (JSPS and JST) to work as a Research Scientist for 3.5 years in two leading Japanese universities. Published more than 30 research papers in peer-reviewed journals such as IEEE, ACM, Springer-Verlag, Inderscience, etc. Have authored and edited 20 books thus far and focus on some of the emerging technologies such as IoT, Cognitive Analytics, Blockchain, Digital Twin, Docker-enabled Containerization, Data Science, Microservices Architecture, fog/edge computing, Artificial intelligence (AI), etc. Have contributed 35 book chapters thus far for various technology books edited by highly acclaimed and accomplished professors and professionals.
Chellammal Surianarayanan is an Assistant Professor of Computer Science at Bharathidasan University Constituent Arts and Science College, Tiruchirappalli, Tamil Nadu, India. She earned doctorate in Computer Science by developing computationally optimized techniques for discovery and selection of semantic services. She has published research papers in Springer Service-Oriented Computing and Applications, IEEE Transactions on Services Computing, International Journal of Computational Science, Inderscience, and the SCIT Journal of the Symbiosis Centre for Information Technology, etc. She has produced book chapters with IGI Global and CRC Press. Recently she produced books on Cloud computing with Springer and on MicroServices Architecture with CRC Press. She has been a life member of several professional bodies such as the Computer Society of India, IAENG, etc. Before coming to academic service, Chellammal Surianarayanan served as Scientific Officer in the Indira Gandhi Centre for Atomic Research, Department of Atomic Energy, Government of India, Kalpakkam, Tamil Nadu, India. She was involved in the research and development of various embedded systems and software applications. Her remarkable contributions include the development of an embedded system for lead shield integrity assessment, portable automatic air sampling equipment, the embedded system of detection of lymphatic filariasis in its early stage, the and development of data logging software applications for atmospheric dispersion studies. In all she has more than 20 years of academic and industrial experience