Ke Feng – författare

This book presents recent research developments and integrated methodologies for digital twin gear wear monitoring and remaining useful life prediction for rotating machinery. It describes a comprehensive framework for identifying wear mechanisms, developing dynamic gearbox models, and implementing online monitoring schemes that track the evolution of abrasive wear and fatigue pitting. The methodologies introduced allow for accurate assessment of tooth profile changes and surface integrity without requiring operational stoppage. Simulations and dynamic model implementations in this book are constructed using the MATLAB® and Simulink® software packages.Features:Gives a systematic investigation of vibration-based techniques to distinguish between fatigue pitting and abrasive wearDevelops an integrated monitoring and prediction framework using a dynamic gear model and wear modelIncludes a novel digital-twin approach that regularly updates model coefficients using measured vibration data to ensure prediction accuracyDiscusses the impact of macro- and micro-level wear on dynamic contact forces and vibration characteristicsProvides experimental validation through run-to-failure tests conducted under both dry and lubricated conditionsThis book is aimed at researchers and graduate students in mechanical engineering, signal processing, machine condition monitoring, and reliability engineering.

This book gathers the latest advances, innovations, and applications in the field of efficiency and performance engineering, as presented by leading international researchers and engineers at the TEPEN International Workshop on Fault Diagnostics and Prognostics (TEPEN-IWFDP), held in Qingdao, China, on May 8–11, 2024. Topics include machine and structural health monitoring, non-destructive testing and fault detection, diagnostic and prognostic for both operational and manufacturing processes, maintenance optimization and asset management, smart metamaterials and metastructures, artificial intelligent, and machine learning. The contributions, which are selected through a rigorous international peer-review process, share exciting ideas that spur novel research directions and foster new multidisciplinary collaborations.

This book gathers the latest advances, innovations, and applications in the field of efficiency and performance engineering, as presented by leading international researchers and engineers at the TEPEN International Workshop on Fault Diagnostics and Prognostics (TEPEN-IWFDP), held in Qingdao, China, on May 8–11, 2024. Topics include machine and structural health monitoring, non-destructive testing and fault detection, diagnostic and prognostic for both operational and manufacturing processes, maintenance optimization and asset management, smart metamaterials and metastructures, artificial intelligent, and machine learning. The contributions, which are selected through a rigorous international peer-review process, share exciting ideas that spur novel research directions and foster new multidisciplinary collaborations.

This book provides a comprehensive guide to using data-driven methods in reliability and safety engineering for industrial systems. It explores how modern technologies like data analytics, machine learning, and artificial intelligence can enhance decision-making, predict failures, and improve system resilience.In an era of increasingly complex industrial systems, traditional methods often fail to address reliability and safety challenges. This book highlights how integrating data-driven techniques can optimize system performance, reduce risks, and enhance safety outcomes. Key topics include predictive maintenance, risk assessment, AI integration, and the challenges of implementing these technologies in real-world environments. Case studies across industries like energy and manufacturing illustrate the practical applications of these methods.This book is aimed at professionals in reliability engineering, safety, risk management, and industrial systems, as well as researchers and students seeking to understand the role of data-driven methods in modern engineering practices.