| Resumo: | Industrial automation platforms are experiencing a paradigm shift. With the new technol-ogies and strategies that are being applied to enable a synchronization of the digital and real world, including real-time access to sensorial information and advanced networking capabilities to actively cooperate and form a nervous system within the enterprise, the amount of data that can be collected from real world and processed at digital level is growing at an exponential rate. Indeed, in modern industry, a huge amount of data is coming through sensorial networks em-bedded in the production line, allowing to manage the production in real-time. This dissertation proposes a data collection framework for continuously collecting data from the device to the cloud, enabling resources at manufacturing industries shop floors to be handled seamlessly. The framework envisions to provide a robust solution that besides collecting, transforming and man-aging data through an IoT model, facilitates the detection of patterns using collected historical sensor data. Industrial usage of this framework, accomplished in the frame of the EU C2NET project, supports and automates collaborative business opportunities and real-time monitoring of the production lines.
|
|---|