Guest Editorial: Data-Driven Management of Complex Systems Through Plant-Wide Performance Supervision

Abstract

The fourteen papers in this special section focus on data-drive management of complex systems via plant-wide performance supervision. Currently, massive amounts of data are continuously being produced by social and industrial activities. Consequently, data-driven techniques have received considerable attention both in industry and academia in recent years, aiding scientists to manage and interpret the available data. The reasons behind such popularity of data-driven techniques are twofold. On the one hand, advanced data processing and information acquisition technologies have been developed to the extent that large amounts of data in different forms are available for big data analysis from descriptive to prescriptive. On the other hand, with the help of machine learning methodologies, the supervision and management systems can provide effective decisions for plant-wide optimal performance. Compared to the conventional model-based techniques, the data-driven ones can not only save the costly modeling procedures but also extract valuable information from available process data for real-time analysis and management. However, there are many complex and challenging problems in the data-driven supervision and management techniques, such as data-driven supervision on the safety, security, and robustness, as well as the performance-supervised management and their distributed designs. The papers in this section target recent results, trends, and practical developments in the data-driven methodologies of plant-wide performance supervision and management for complex systems, especially those related to process monitoring and machine learning activities with their industrial applications.