Unveiling Trends and Predictions in Digital Factories
Σοφία Καραγιώργου, Georgios Vafeiadis, Dimitris Ntalaperas, Nikolaos Lykousas, Danai Vergeti, Δ. Αλεξάνδρου · 2019
The emergence of the Industrial Internet of Things paves the way for enhancing the real-time monitoring capabilities of contemporary manufacturing enterprises through the extensive utilization of physical and virtual sensors. This paradigm enables the detection of early warning signals concerning systems' degradation and facilitates the prompt decision making and actions performed ahead of time. Currently, even large manufacturing companies have not yet developed a complete Predictive Maintenance strategy and appropriate sensor-driven, real-time systems in order to utilize these benefits. In this paper, we propose a failure prediction system for complex IT systems in the steel industry. The novelty of our work lies in the exploitation of Deep Learning techniques from streaming operational sensor data, enabling earlier failure predictions through a Neural Networks approach. To evaluate the proposed framework, real-life data are collected and analyzed based on daily operational and maintenance activities within the production line. We further demonstrate the framework's potential by presenting some early results in modeling and predicting the complex and dynamic behavior in the manufacturing settings.