Big Data Mining and Intelligent Analytics for Industrial Systems Under Uncertainty

Modern industrial systems generate large volumes of heterogeneous data from sensors, control systems, maintenance records, simulations, and operational logs. These data provide important opportunities for process monitoring, state estimation, fault diagnosis, performance prediction, and operational decision-making. However, practical industrial environments are often affected by uncertain operating conditions, incomplete or noisy measurements, changing process dynamics, limited fault labels, equipment degradation, and interactions among multiple physical processes. These factors make conventional data-mining methods difficult to apply directly and reliably.This Research Topic aims to bring together recent advances in big-data mining and intelligent analytics for industrial systems operating under uncertainty. Particular attention will be given to methods that can extract useful and trustworthy knowledge from incomplete, imbalanced, multimodal, and dynamically changing industrial data. The Topic welcomes both methodological studies and practical applications in energy, manufacturing, nuclear engineering, chemical processes, transportation, and other complex industrial sectors.Relevant themes include, but are not limited to:- Industrial big-data mining and representation learning;- Uncertainty modelling and uncertainty-aware learning;- State estimation, process prediction, and fault diagnosis;- Learning with incomplete, noisy, imbalanced, or weakly labelled data;- Multimodal fusion of sensor data, physical models, images, text, and expert knowledge;- Physics-informed and knowledge-guided machine learning;- Transfer learning, domain adaptation, and few-shot learning for changing operating conditions;- Digital twins and intelligent monitoring of industrial equipment;- Interpretable, robust, and trustworthy artificial intelligence;- Intelligent decision support and risk assessment for complex industrial processes.The purpose of this Research Topic is to provide a platform for researchers from artificial intelligence, data mining, industrial informatics, control, and engineering disciplines to share new methods, datasets, applications, and practical experience. We particularly encourage work that addresses real industrial uncertainty and demonstrates clear engineering value. Topic editors: CHAOYU GONG, Yanlin Li Source: https://www.frontiersin.org/research-topics/85558/big-data-mining-and-intelligent-analytics-for-industrial-systems-under-uncertainty