Industrial Big Data and Artificial Intelligence

Dear Colleagues,

Industrial platforms now generate vast, heterogeneous, and fast-evolving data—from high-frequency sensor streams and control logs to imagery, text, and graphs. This Topic seeks contributions that convert such data into trustworthy intelligence for analysis, optimization, and decision support across industrial settings. We welcome advances in scalable spatiotemporal learning; multimodal fusion and vision–time-series co-modeling; streaming/real-time and on-device analytics; robust anomaly detection under distribution shift; AI for quality assurance, process tuning, scheduling, and control; hybrid and physics-aware modeling; causal inference, uncertainty quantification, and governance for safe, auditable AI; privacy-preserving collaboration (e.g., federated or split learning); synthetic data and simulation-validated methods; and human-in-the-loop tools and visualization. Submissions may present algorithms, system architectures, datasets and benchmarks, reproducible case studies, surveys, or best-practice guidelines. Emphasizing reliability, safety, and cost-aware scalability, this Topic aims to bridge lab-grade methods and real-world deployment across manufacturing, energy and power, process industries, robotics, logistics, and smart infrastructure.

Prof. Dr. Chun Yin
Dr. Jiusi Zhang
Dr. Quan Qian
Dr. Tenglong Huang
Topic Editors