Shengnan Wu – författare

Fault diagnosis is useful for technicians to detect, isolate, identify faults, and troubleshoot. Bayesian network (BN) is a probabilistic graphical model that effectively deals with various uncertainty problems. This model is increasingly utilized in fault diagnosis.This unique compendium presents bibliographical review on the use of BNs in fault diagnosis in the last decades with focus on engineering systems. Subsequently, eleven important issues in BN-based fault diagnosis methodology, such as BN structure modeling, BN parameter modeling, BN inference, fault identification, validation, and verification are discussed in various cases.Researchers, professionals, academics and graduate students will better understand the theory and application, and benefit those who are keen to develop real BN-based fault diagnosis system.

This book systematically examines performance evaluation, reliability modeling, and risk analysis for offshore well control equipment, integrating multidisciplinary approaches from petroleum, safety, mechanical, and artificial intelligence engineering. It employs reliability modeling, dynamic Bayesian networks, and machine learning to assess key devices such as subsea safety systems and blowout preventers, with emphasis on lifecycle and risk evaluation. The study addresses practical challenges including imperfect testing, degradation, and time-varying failures, and analyzes equipment behavior under special operational conditions. Providing theoretical tools and research insights, this work supports enhanced safety in deep-sea oil and gas operations. It is intended for undergraduates, graduates, and researchers interested in offshore drilling equipment and risk assessment technologies.

This book is a compilation of over a decade's worth of insights from the authors' research group on dynamic risk assessment and intelligent early warning systems. Highly technical approaches are provided to address the engineering requirements for the safe operation of complex systems in oil and gas production. These involve various methods and techniques using real-time process monitoring parameters, images, texts, and line-of-sight tracking technology to develop intelligent early warning systems to mitigate risks in complex oil and gas production systems. The book arms readers with practical safety management guidelines through the examination of real case applications for petroleum refining systems, unconventional oil and gas fracturing systems, and offshore oil and gas exploitation.This book begins with a discussion of the main risk factors and features of oil and gas production systems, and reviews the state-of-art research and practice on the industry's existing early warning systems. Following this, different approaches of intelligent early-warning technology are developed based on various data sources including real-time monitoring of process parameters through shale gas fracturing construction; infrared thermal imaging video surveillance of oil and gas exploration equipment; text records on historical accidents and incidents; and operator eye movement data (for behavioral safety tracking). Lastly, this book discusses the practical applications of early risk warnings in shale gas fracturing systems, multi-level correlation early warning in refining and chemical plants, and early warnings for abnormal events in deepwater oil and gas exploitation.