Structural Health Monitoring - A Machine Learning Perspective

The process of implementing a damage detection strategy for aerospace, civil and mechanical engineering infrastructure is referred to as structural health monitoring (SHM). The SHM process involves the observation of a system over time using periodically sampled dynamic response measurements from an array of sensors, the extraction of damage-sensitive features from these measurements and the statistical analysis of these features to determine the current state of system health. This process can encompass either physical modelling or data-driven methodologies to SHM, but is most powerful when it underpins the latter and is based on pattern recognition. There are increasing demands to develop and deploy SHM systems on various aerospace, civil, and mechanical systems, which have been driven by the tremendous economical and life-safety benefits that such technologies have the potential to provide.§Structural Health Monitoring: A Machine Learning Perspective provides a comprehensive overview of SHM formulated in terms of a statistical pattern recognition paradigm that is implemented with machine learning algorithms. This book is the result of almost twenty years work by the authors, who are widely regarded as the architects of the pattern recognition approach to SHM.§Key features:§First comprehensive account of the pattern recognition approach to SHM§Provides detailed background on machine learning and pattern recognition fundamentals as they apply to the SHM problem§Includes comprehensive appendices covering necessary signal processing theory and linear structural dynamics§Contains numerical and experimental studies of laboratory test specimens and in-situ structures§Structural Health Monitoring: A Machine Learning Perspective is a must-have for researchers and practicing engineers within the field of SHM, and is a comprehensive reference for graduate and advanced undergraduate students.