This book introduces recent developments and trends of S-T abnormality diagnosis for industrial distributed parameter systems (DPSs). As a typical representative of industrial processes, DPSs widely exist in both process and discrete manufacturing and operations, such as the snap curing oven in chip manufacturing, the tubular reactor in chemical manufacturing, the soft robots in special operations, etc. With the increasing development of industrial distributed parameter systems (especially the electrical vehicles and hybrid electric vehicles), spatio-temporal (S-T) abnormality diagnosis has become a pain in the neck and has attracted a great amount of attention in recent years. Moreover, the rapid development of machine learning and big data techniques has shed new insights on data-driven fault diagnosis and promoted the enthusiasm for studying the industrial distributed parameter systems. However, nearly no book has addressed this issue well and most existing research only consider traditional actuator/sensor fault while neglecting the spatio-temporal distributed characteristic of abnormality for DPSs. The main contents of this book include: 1) Model-based abnormality diagnosis and identification for completely-known industrial DPSs (“white box”); 2) Combined model-based and data-driven abnormality detection and localization for partially-known industrial DPSs (“grey box”); 3) Purely data-driven modeling and diagnosis for completely-unknown DPSs(“black box”). In conclusion, this book summarizes the authors’ works on both model-based and data-driven perspectives for S-T abnormality diagnosis of industrial DPSs. To be more precise, this book mainly focuses on the following challenges: space-time couple characteristics, limited sensing in space, and the dynamically varying abnormality in space. This book aims at post-graduate students, researchers, and engineers with background knowledge of industrial systems modeling and monitoring. Interesting readers can obtain state-of-the-art methods systematically in the last 5 years and have a general overview of recent developments and the future direction of this specific research field. This book introduces recent developments and trends of S-T abnormality diagnosis for industrial distributed parameter systems (DPSs). As a typical representative of industrial processes, DPSs widely exist in both process and discrete manufacturing and operations, such as the snap curing oven in chip manufacturing, the tubular reactor in chemical manufacturing, the soft robots in special operations, etc. With the increasing development of industrial distributed parameter systems (especially the electrical vehicles and hybrid electric vehicles), spatio-temporal (S-T) abnormality diagnosis has become a pain in the neck and has attracted a great amount of attention in recent years. Moreover, the rapid development of machine learning and big data techniques has shed new insights on data-driven fault diagnosis and promoted the enthusiasm for studying the industrial distributed parameter systems. However, nearly no book has addressed this issue well and most existing research only consider traditional actuator/sensor fault while neglecting the spatio-temporal distributed characteristic of abnormality for DPSs. The main contents of this book include: 1) Model-based abnormality diagnosis and identification for completely-known industrial DPSs (“white box”); 2) Combined model-based and data-driven abnormality detection and localization for partially-known industrial DPSs (“grey box”); 3) Purely data-driven modeling and diagnosis for completely-unknown DPSs(“black box”). In conclusion, this book summarizes the authors’ works on both model-based and data-driven perspectives for S-T abnormality diagnosis of industrial DPSs. To be more precise, this book mainly focuses on the following challenges: space-time couple characteristics, limited sensing in space, and the dynamically varying abnormality in space. This book aims at post-graduate students, researchers, and engineers with background knowledge of industrial systems modeling and monitoring. Interesting readers can obtain state-of-the-art methods systematically in the last 5 years and have a general overview of recent developments and the future direction of this specific research field. Yun Feng received the B.E. degree in automation and the M.S. degree in control theory and control engineering from the Department of Automation, Wuhan University, Wuhan, China, in 2014 and 2017, respectively, and the Ph.D. degree from the Department of Systems Engineering and Engineering Management, City University of Hong Kong, Hong Kong, in 2020. From July to November 2019, he was a Visiting Student with the Institute for Automatic Control and Complex Systems (AKS), University of Duisburg Essen, Duisburg, Germany. He is currently an Associate Professor with the School of Artificial Intelligence and Robotics and the National Engineering Research Center for