In the era of Internet of Things and dynamically interconnected systems, real time data becomes a new industrial asset, used to create new opportunities for operations improvement and to increase industrial value through the capitalisation of immaterial assets. In the smart factory, big data acquisition, analysis and visualisation pave the way to the manufacturing servitization, defined as the strategic innovation of organisations capabilities and processes to shift from product offering to an integrated ``product plus service'' offering. According to this vision, interconnected physical systems are associated with a cyber twin, where innovative services for big data management should be provided. In this paper, we propose an interactive data exploration framework, that poses a service-oriented perspective on the smart factory. Large amounts of data are incrementally collected from physical systems, organized and analysed on the cloud and new services are provided to enable data exploration. Such services implement novel data summarisation techniques, based on clustering, to manage data abundance, and data relevance evaluation techniques, aimed to focus the attention on relevant data that is being explored. Services are based on a multi-dimensional model, that is suited for supporting the iterative and multi-step exploration of Big Data.
Interactive Data Exploration as a Service for the Smart Factory
Bagozi A.;Bianchini D.
;De Antonellis V.;Ragazzi D.
2017-01-01
Abstract
In the era of Internet of Things and dynamically interconnected systems, real time data becomes a new industrial asset, used to create new opportunities for operations improvement and to increase industrial value through the capitalisation of immaterial assets. In the smart factory, big data acquisition, analysis and visualisation pave the way to the manufacturing servitization, defined as the strategic innovation of organisations capabilities and processes to shift from product offering to an integrated ``product plus service'' offering. According to this vision, interconnected physical systems are associated with a cyber twin, where innovative services for big data management should be provided. In this paper, we propose an interactive data exploration framework, that poses a service-oriented perspective on the smart factory. Large amounts of data are incrementally collected from physical systems, organized and analysed on the cloud and new services are provided to enable data exploration. Such services implement novel data summarisation techniques, based on clustering, to manage data abundance, and data relevance evaluation techniques, aimed to focus the attention on relevant data that is being explored. Services are based on a multi-dimensional model, that is suited for supporting the iterative and multi-step exploration of Big Data.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
