KPG Scienchar
home Scienchar Home
KPG Journal > Digital Twin- For Better Processes, Improved Performance & Effective Product

Digital Twin- For Better Processes, Improved Performance & Effective Product

Meet Patel, Piyush Bhatia, Ankit Prajapati

Computer Science and Engineering, R. N. G. Patel Institute of Technology, Surat, India

Regarding present approaches to the development of manufacturing processes, the gaining of a satisfactory figure's basis of the relevant process information and successive development of possible design options needs 74 % of the total time-consumption. Digital twin is the ability to take a virtual illustration of the component and the pattern of how a component operates and work in the real world. Various new groundbreaking manufacturing strategies, such as Industrial Internet, Industry 4.0, cloud-based manufacturing is used to achieve smart manufacturing, resulting in the increasing number of newly designed production lines in both developed and developing countries. Particularly, more precise digital replicas of the manufactured component are important to seal the gap between design and manufacturing and to mirror the physical and simulation world.
Keywords- Digital Twin, semi-physicalsimulation, Industry 4.0, Big data.

INTRODUCTION

A digital twin is a cross-domain digital model that precisely denotes a product or performance of a product in operation.


The digital twin evolves and continuously updates to mirror any modification to the physical counterpart throughout the counterpart's lifecycle, generating a closed-loop of reaction in a simulated environment that offers the right process design for their products and manufacturing processes.


A digital twin is a simulated illustration of a real product, used to recognize and predict the physical counterpart's performance characteristics. Digital twins are generally used in entire product development to simulate, analyst, and improve the product and production system before financing in physical prototypes and assets.


By combining multi-physics simulation, data analytics, and machine learning capabilities, digital twins can regulate the outcome of design changes, usage scenarios, environmental conditions, and other limitless variables - eliminating the need for physical prototypes, reducing development time, and improving quality of the finalized product or process.[6]


To accurate modeling over the entire lifecycle of a product, digital twins use data from sensors situated on the physical part of the system to regulate the object's real-time performance, operating conditions, and changes in the system over time. By use of this data, the digital twin continuously updates to update any alteration to the physical part throughout the product cycle, generating a closed-loop of feedback in a simulated environment that empowers companies to continuously enhance their products, production, and performance at a nominal cost.


The application of digital twin depends on which stage of the product lifecycle it is used. Product, Production, and Performance are three types of Digital twin which are explained below. The digital thread is known as combining three digital twins. The term "thread" is used since it is woven into, and brings organized data from, all stages of the product and production lifecycles.[2]


Digital twins can be used to virtually validate product performance, while also showing how your products are currently acting in the physical world. This "product digital twin" provides a virtual-physical connection that lets you analyse how a product works under different circumstances and make updates in the simulated world to ensure that the next physical product will act as exactly as design in the field. All of this eliminates the need for various prototypes, reduces over-all development time, improves quality of the final manufactured product, and permits faster iterations in reply to customer comment.


HOW DOES A DIGITAL TWIN WORK?

Capabilities for detecting key characteristics of the real asset's state and behaviour. This typically implies sensors with corresponding processing capabilities for data quality improvement, such a tuning, filtering, time synchronization. Preserving the integrity of the specifications.


This can be specific end-to-end user applications for observing and control, it can be old applications for maintenance and asset management, or for pattern recognition and decision provision data flowing from twin feed to data analytics and machine learning models. The technology idea used in the sap predictive engineering insights is formed on the principle of annotations and stimulations. Observations are made by physical sensor measurements on a real structure. Actuator motions ruled by sensor measurement data are advantageous in a simulation model by stimulating the digital twin of the real system, as demonstrated in figure 1.[4]


Fig 1. | How Digital Twin works[4]

Sensors attached to the physical product gather data and send it back to the digital twin, and their interaction helps optimise the product's performance via a maintenance regime.


For example, sensors inside an aero-engine might sense when components require changing or fixing. Jet engine manufacturer Rolls-Royce at present uses Engine Health Management (EHM) to trace the health of thousands of engines, using onboard sensors and live satellite feeds. These data are used to lift maintenance regimes. Ultimately, they could be used in the original aero-engine design process.


The aero engine's digital twin would specify this new data, which seems on the manufacturer's product lifecycle management (PLM) system. Some manufacturers, such as power tool maker Black & Decker, have extended the digital twin concept to involve digitally modelling assembly lines and other factory systems, helping manufacturers lift productivity and efficiency.


WHY IS DIGITAL TWIN TECHNOLOGY IMPORTANT?

Digital twins are robust masterminds to drive innovation and performance. Imagine it as your most talented product technicians with the most advanced monitoring, analytical, and predictive abilities at their fingertips. By 2018, companies who invest in digital twin technology will see a 30% improvement in cycle times of critical processes, predicts IDC.


There will be billions of things signified by digital twins within the next five years. These changes of the physical world will lead to new alliance opportunities among physical world product experts and data scientists whose jobs are to recognize what data tells us about operations.


Digital twin technology helps companies improve the customer experience by well understanding customer needs, advance enhancements to existing products, operations, and services, and can even help drive the innovation of new business.


For example, GE's "digital wind farm" opened up new ways to enhance productivity. GE uses the digital environment to inform the configuration of each wind turbine in advance of construction. Its goal is to produce 20% increases in efficiency by analysing the data from each turbine that is fed to its simulated equivalent.


"For every physical asset in the world, we have a virtual copy running in the cloud that gets better off with every second of operative data," says Ganesh Bell, chief digital officer and general manager of Software & Analytics at GE Power & Water.


All indications seem to predict we are on the point of a digital twin technology explosion. More companies will learn of real-world and pilot program success stories and will want to install their very own digital twins to achieve a competitive advantage.


Digital Twin Technology aids to produce a copy of the physical assets of a product or service in an industry. It is a clone of the physical product just in digital form. More probably, a simulated model of the physical process, this technology helps in investigating the data, lends a platform to check the functioning formerly to develop a resolution for any potential problems. It also provides an insight into the stimulations with the help of real-time data thereby joining the product digitally with its own design.


APPLICATIONS AND IMPORTANCE

A comprehensive collaboration of artificial intelligence, machine learning, and data analytics, digital twin predicts the issue before it occurs in the physical machine. It is like knowing the future and having the ability to meld it.


With digital twin technology, minimum time and capital are devoted to undertaking any issue. There are comparatively minor downtimes and overhead expenditures. It is an integrated way to optimize and monitor performance virtually.


Innovation in business accompanied by consistent customer services is so far another application of digital twin. It manages customer operations and understands their needs. It is gradually finding its applications in aircraft engines, locomotives, wind turbines, buildings and HVAC control systems, healthcare and retail.


Internet of things acts as a base for the digital twin technology. Hence, soon, most of the IoT platforms will adopt digital twin technology. GE uses the digital environment to inform the configuration of each wind turbine prior to construction. It has implemented over 500,000 digital twins. German packaging systems manufacturer, Optima, digitally planned and observed its transport system using digital twin technology by Siemens. The Singapore government, in association with the 3D design software giant Dassault Systems, is building a simulated model of the country with an aim to optimize and enhance the town planning process.


For every asset and product, there is a simulated model of the same made functional via cloud services which consistently promote the operational data to produce better results and provide extra insights. It won't be long that more and more companies would accept adigital twin to exist in the competitive market and have advantageous business outcomes.


APPLICATIONS AND IMPORTANCE

GES digital wind farm is moving wind industry decades in to the future by combining the smartest most advanced hardware with the power and flexibility of the industrial Internet it begins with GES revolutionary megawatt modular turbine individually configurable to optimize performance across the farm then each software-defined machine is connected to the digital infrastructure powered by predicts get connected get connected get insights get optimized in real-timeall from the palm of your hand with the digital wind farm tomorrow is today.


Few people embody the backyard inventor better than Charles Brush. In 1887, he built behind his mansion in Cleveland, Ohio, a 4-ton wind generator with 144 blades and a comet-like tail and used it to power a set of batteries in his basement. Although by today's standards the huge, 60-foot machine was massively inefficient, it started a new industry that pushed generations of engineers to make it better. Now GE has decided to go further and improve on the entire wind farm in one fell swoop.


"Every wind farm has a unique profile, like DNA or a fingerprint," says Keith Longtin, general manager for wind products at GE Renewable Energy. "We thought if we could capture data from the machines about how they interact with the landscape and the wind, we could build a digital twin for each wind farm inside a computer, use it to design the most efficient turbine for each pad on the farm, and then keep optimizing the whole thing."


Fig. 2. | A GE wind turbine and its digital twin[8]

"The world's electricity demand will grow by 50 percent over the next 20 years, and people want to get there by using reliable, affordable, and sustainable power," says Steve Bole, president and CEO of GE Power & Water. "This is the perfect example of using big data, software and the Industrial Internet to drive down the cost of renewable electricity."


The Industrial Internet is a digital network connecting, collecting and analysing machine data. GE believes that the Industrial Internet could add $10 to $15 trillion to global GDP in efficiency gains over the next two decades.


Each digital wind farm begins life as a digital twin, a cloud-based computer model of a wind farm at a specific location. The model allows engineers to pick from as many as 20 different turbine configurations - from pole height to rotor diameter and turbine output - for each pad at the wind farm and design its most efficient real-world doppelganger. "Right now, wind turbines come in given sizes, like T-shirts," says Ganesh Bell, chief digital officer at GE Power & Water. "But the new modular designs allow us to build turbines that are tailor-made for each pad."


But that's only half of the story. Just like Apple's Siri and other machine learning technologies, the digital twin will keep crunching data coming from the wind farm and providing suggestions for making operations even more efficient, based on the software's insights. Longtin says that operators will be even able to use data to control noise. "If there is a house near the wind farm, we will be able to change the rotor speed depending on the wind direction to stay below the noise threshold," he says.


The data comes from dozens of sensors inside each turbine monitoring everything from the yaw of the nacelle to the torque of the generator and the speed of the blade tips. The digital twin, which can optimize wind equipment of any make, not just GE's, gobbles it up and sends back tips for improving performance. "This is a real-time analytical engine using deep data science and machine learning," Bell says. "There is a lot of physics built into it. We get a picture that feels real, just like driving a car in a new video game. We can do things because we understand the physics - we build turbines - but also because we write software."


The digital wind farm is built on Predix, a software platform that GE developed specifically for the Industrial Internet. Predix can accommodate any number of apps designed for specific wind farm tasks - from responding to grid demand to maximizing and predicting power output. Says Bell: "This is the start of a big journey for the wind industry."[8]


COMPARISON OF DIGITAL TWIN AND BIG DATA IN MANUFACTURING

TABLE 1 | BIG DATA AND DIGITAL TWIN COMPARISION[8]

CONCLUSIONS

Over the last decade, dramatic advances have been placed in the capabilities and technologies of the data collection for the physical product as well as the design and presentation of the digitalproduct. the connection between the two data sources has lagged far behind their development, which hinders the applicability of the digital twin to various activities in industry and manufacturing. According to this need, this paper presents agooddesign framework that focuses on connecting the physical product and virtual product. It is most useful for the repetitive redesign of an existing product instead of a completely new product. Never-the less, it unnecessarily means that DTPD cannot be adapted for designing completely new products, which is one direction of future work


REFERENCES

  1. Qinglin Qi, Fei Tao, "Digital Twin and Big Data Towards Smart Manufacturing and Industry 4.0: 360 Degree Comparison"
  2. HAO ZHANG, QIANG LIU, XIN CHEN , DING ZHANG, AND JIEWU LENG Key Laboratory of Computer Integrated Manufacturing System, Guangdong University of Technology, Guangzhou 510006, China
  3. https://www.essentracomponents.com
  4. http://www.fedem.com
  5. https://www.analyticsinsight.net
  6. https://www.forbes.com
  7. https://ieeexplore.ieee.org/document/8258937
  8. https://www.ge.com/reports/post/119300678660/wind-in-the-cloud-how-the-digital-wind-farm-will-2
arrow_downward Download PDF