Model‐Based Statistical Signal Processing for Change and Damage Detection

Abstract

Handling parameterized models for monitoring structures or processes is a natural approach to damage or fault detection and diagnosis. Modeling damages and faults as deviations in the parameter vector with respect to its nominal value in safe conditions calls for the use of statistical change detection and isolation methods. Such methods share the ability of handling noises and uncertainties with other statistical approaches. The purpose of this article is to describe the key elements in the design of change detection algorithms. Basic concepts (likelihood ratio, estimation, and innovation) are introduced. These tools involve a number of familiar operations (integration, averaging, sensitivity, adaptive thresholds, and windows). It is suggested that a statistical framework enlightens the meaning and increases the power of those operations. Vibration‐based structural health monitoring is addressed within this framework.