About this Research Topic
The so-called smart manufacturing or industry 4.0, is credited to the continuous evolution of technologies in the fields of communication, networking, storage, and computing. These have been applied to the more traditional world of industrial automation to increase productivity and quality of workers’ lives, and define new business opportunities in modern ‘smart factories’. Smart factories integrate information generated by the different actors in the production process (e.g., human operators, industrial machines, information systems) for monitoring and forecasting purposes.
The representation of physical entities in the virtual world can be stored in a factory data space together with other information, e.g. data available from the company and production history, worker suggestions, and preferences. These digital entities or digital twins (DTs), could yield large volumes of data with a variety of high-velocity updates. Big data management techniques are a key ingredient for ensuring interoperability while generating insights from the available data and pushing Industry 4.0 research.
The factory data space is heterogeneous in their nature from the employed schema (or its absence), the employed vocabulary, and the access technology point of view. It can include relational and no-SQL databases or unstructured sources such as spurious files of the factory information system. Due to such heterogeneity, existing data management techniques for smart manufacturing applications struggle to capture the whole production goal semantic and mainly focus on specific interoperability aspects. Furthermore, existing data modeling frameworks for DTs (either commercial or open-source) do not provide full support for simulation and prediction. DTs can expose services, modify, monitor, and predict the state of their wrapped objects and their data are a fundamental part of a factory data space.
The goal of this Research Topic is to understand how data management methods and technologies can be employed in consistent architectures for smart manufacturing, including, but not limited to (1) heterogeneity of a smart factory data space; (2) modeling frameworks that provide support for analytics, simulation, and prediction; (3) integration methods that can provide a unified view over the factory data space.
We welcome papers that address, but are not limited to the following topics:
● Data Management for Cyber-physical systems
● Data-centric middleware
● Data modeling for digital twin interoperability
● Analytics for Industry 4.0, simulation, and prediction models Data Exchange
● Data Integration
● Cloud-based solutions
The article types below are accepted for submission. Please refer to https://www.frontiersin.org/journals/big-data#article-types
● Original Research
● Methods
● Review
● Systematic Review
● Policy and Practice Reviews
● Conceptual Analysis
● Data Report
● Opinion
● Technology and Code
The representation of physical entities in the virtual world can be stored in a factory data space together with other information, e.g. data available from the company and production history, worker suggestions, and preferences. These digital entities or digital twins (DTs), could yield large volumes of data with a variety of high-velocity updates. Big data management techniques are a key ingredient for ensuring interoperability while generating insights from the available data and pushing Industry 4.0 research.
The factory data space is heterogeneous in their nature from the employed schema (or its absence), the employed vocabulary, and the access technology point of view. It can include relational and no-SQL databases or unstructured sources such as spurious files of the factory information system. Due to such heterogeneity, existing data management techniques for smart manufacturing applications struggle to capture the whole production goal semantic and mainly focus on specific interoperability aspects. Furthermore, existing data modeling frameworks for DTs (either commercial or open-source) do not provide full support for simulation and prediction. DTs can expose services, modify, monitor, and predict the state of their wrapped objects and their data are a fundamental part of a factory data space.
The goal of this Research Topic is to understand how data management methods and technologies can be employed in consistent architectures for smart manufacturing, including, but not limited to (1) heterogeneity of a smart factory data space; (2) modeling frameworks that provide support for analytics, simulation, and prediction; (3) integration methods that can provide a unified view over the factory data space.
We welcome papers that address, but are not limited to the following topics:
● Data Management for Cyber-physical systems
● Data-centric middleware
● Data modeling for digital twin interoperability
● Analytics for Industry 4.0, simulation, and prediction models Data Exchange
● Data Integration
● Cloud-based solutions
The article types below are accepted for submission. Please refer to https://www.frontiersin.org/journals/big-data#article-types
● Original Research
● Methods
● Review
● Systematic Review
● Policy and Practice Reviews
● Conceptual Analysis
● Data Report
● Opinion
● Technology and Code
Keywords: Analytics and machine learning, digital twin, data integration, data-centric middleware, cloud computing, industry 4.0, big data managment
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
