PART OF: IEEE Big Data 2018
** There is a 1-day registration option **
Digital twins are dynamic digital or virtual software replications of physical assets, products, and systems. Popular applications areas include areas such as Manufactured products (i.e. cars, wind turbines, airplanes, ships), Industrial processes (Energy systems, Power plants, Smart Grids, Oil & Gas production), and Buildings and Infrastructures (Smart Buildings, Intelligent Transportation Systems, bridge monitoring).
Digital twins have moved from concept to reality very rapidly in recent years. IDC predicts that by 2020, 30% of global 2000 companies will use data from digital twins of IoT-connected products and assets to improve product-innovation success rates and organizational productivity, achieving gains of up to 25%.In October 2017 Gartner added digital twins to its top 10 strategic technology trends for 2018. With an estimated 21 billion connected sensors and endpoints by 2020, digital twins could exist for billions of things in the near future. Potentially billions of dollars of savings in maintenance repair and operation and optimized IoT asset performance are expected.
However, the huge potential of digital twin technology is currently mainly reflected in the better design of an asset, based on the extensive simulations in various conditions, requiring huge computing resources (usually HPC). On the other hand, the explosion of (I)IoT has introduced advanced sensing of an industrial asset (product, process, system) that is enriched with the real-time perception of surrounding environment in order to enable real-time management of an asset. Real-world data enables a new quality in interpreting the model. This capability enables more efficient (run-time) operation of an asset through increased real-world situational awareness. By delivering a quantitative foundation, big data analytics enables digital twins to empower enterprises to both rapidly identify new improvement opportunities and diagnose and correct problems before they reach a critical level.
Consequently, new industry challenges call for a tight integration of the simulation and data analytics approaches:
Therefore, exploiting the full potential of Digital Twins will depend on the further interaction of two key technologies: Big Data for exploring the value of created data including HPC/Processing facilities to support processing and simulations. This goal will require at least two types of innovations related to hybridization of the models and data:
Formatting Instructions 8.5" x 11" (DOC, PDF)
LaTex Formatting Macros
Prof. Dr. David Maier, Portland State University, Portland, Oregon
Dr. Lea Shanley, Southwest Big Data Hub, Raleigh, North Carolina
Dr. Jukka Nurminen, VTT Technical Research Centre of Finland Ltd, Finland
Dr. Ruben Costa, UNINOVA-INSTITUTO DE DESENVOLVIMENTO DE NOVAS TECNOLOGIAS-ASSOCIACAO, Portugal
Dr. Aníbal Reñones, Fundación Cartif, Spain
Roberta Turra, CINECA - Consorzio Interuniversitario, Italy
Dr. Dominik Riemer, FZI FORSCHUNGSZENTRUM INFORMATIK AM KARLSRUHER INSTITUT FUR TECHNOLOGIE, Germany
Dr. Arne J. Berre (SINTEF)
Dr. Ljiljana Stojanovic (Fraunhofer IOSB)
Dr. Nenad Stojanovic (NISSATECH)