Structural Health Monitoring Using Emerging Signal Processing Approaches with Artificial Intelligence Algorithms

Structural health monitoring is a powerful tool across civil, mechanical, automotive, and aerospace engineering, allowing the assessment and measurement of physical parameters in real time. Processing changes in the vibration signals of a dynamic system can detect, locate, and quantify any damage existing in the system. This book presents a comprehensive state-of-the-art review of the applications in time, frequency, and time-frequency domains of signal-processing techniques for damage perception, localization, and quantification in various structural systems. Experimental investigations are illustrated, including the development of a set of damage indices based on the signal features extracted through various signal-processing techniques to evaluate sensitivity in damage identification. Chapters summarize the application of the Hilbert–Huang transform based on three decomposition methods such as empirical mode decomposition, ensemble empirical mode decomposition, and complete ensemble empirical mode decomposition with adaptive noise. Also, the chapters assess the performance and sensitivity of different approaches, including multiple signal classification and empirical wavelet transform techniques in damage detection and quantification. Artificial neural networks for automated damage identification are introduced. This book suits students, engineers, and researchers who are investigating structural health monitoring, signal processing, and damage identification of structures.