Big Data Exploration for Smart Manufacturing Applications

摘要

Industrial Big Data management is gaining momentum as a relevant research topic for the development of innovative smart manufacturing applications. Big data technologies enable the collection, management and analysis of large amount of data from Cyber Physical Systems. In this context, data exploration is becoming a fundamental facility to let users/operators learn from collected data and take decisions. Exploration has to be performed according to different perspectives, spreading over all the hierarchy levels of the smart factory asset (from each device up to the fully connected enterprise and its products) and covering the entire life cycle value stream, from development to production stages. In this paper, we propose a model-based approach to represent data exploration scenarios, by abstracting from implementation details and taking into account different perspectives of the Reference Architectural Model for Industry 4.0 (RAMI 4.0). In particular, each scenario is related to the relevance of data to be explored and different user/operator requirements. A framework based on the approach and experiments in a real Industry 4.0 case study are also described.