Structural Health Monitoring: A Statistical Pattern Recognition Approach is the first book that addresses this emerging field of applied engineering research. This book approaches the structural health monitoring problem in a unique manner by casting this problem in the context of statistical pattern recognition paradigm. Such a paradigm can be described as a four-part process: (1) Operational Evaluation, (2) Data Acquisition, Fusion and Cleansing, (3) Feature Extraction and Information Condensation, and (4) Statistical Model Development for Feature Discrimination. First, the statistical pattern recognition paradigm is described in general terms. Then, the four parts of the process are explained in detail. Numerical and experimental studies of laboratory test specimens and in-situ structures are used to provide the reader further insight into each part of this paradigm. Throughout the book emphasis is placed on taking an integrated approach to the development of structural health monitoring solutions by coupling the measurement hardware portion of the problem directly with the data interrogation algorithms.
* Unique in addressing structural health monitoring in the context of statistical pattern recognition paradigm * Emphasises the importance of coupling sensing technologies with data interrogation algorithms in an integrated manner * Demonstrates how the areas of machine learning, statistical pattern recognition, multivariate statistical analysis as well as classical probability and statistics can be used to enhance the application of this technology to aerospace, civil and mechanical engineering structural health monitoring problems * Introduces and defines the topic of Damage Prognosis - forecasting remaining system life by quantifying the current state of structural health, estimating the future loading environments for that system, and predicting through simulation and past experience the remaining useful life of the system