In the last years, scientific and industrial communities have put a lot of efforts into the development of a new framework for the assessment of structural integrity, generally known as Structural Health Monitoring (SHM), which should allow real-time, automatic evaluations of the state of the structures based on a network of permanently installed sensors. In the context of mechanical, aerospace and civil structures, several approaches have been proposed to address the SHM problem, yet, it remains often difficult to diagnose damages and estimate the structural health when dealing with varying operating and environmental conditions. Particle Filters have already been proposed as a time-domain-based method in the field of SHM, showing promising results as estimators of hidden, not directly observable states, such as those typically related to damages. At the same time, neural networks-based autoencoders have been proposed for structural damage detection, demonstrating to be capable of capturing damage-related features from vibration measurements. This work aims at exploiting the individual advantages offered by the two approaches by combining them in a novel algorithm for structural damage detection and localization, robust with respect to changing environmental conditions. The algorithm is further equipped with a fault indicator module stemming from the introduction of an automatic threshold and both deterministic and probabilistic fault indicators, thus offering a complete, valuable tool for supporting decision making with limited human intervention. The method is demonstrated with reference to a numerical MDOF system whose parameters are taken from a literature benchmark case study.

在过去的几年里，科学界和工业界付出了很多努力来开发一种新的结构完整性评估框架，通常称为结构健康监测 (SHM)，它应该允许实时、自动评估结构完整性。基于永久安装的传感器网络的结构状态。在机械、航空航天和土木结构的背景下，已经提出了几种方法来解决 SHM 问题，但是，在处理不同的操作和环境条件时，诊断损坏和估计结构健康状况通常仍然很困难。粒子滤波器已经被提出作为 SHM 领域中一种基于时域的方法，作为隐藏状态的估计器显示出有希望的结果，而不是直接可观察的状态，例如那些通常与损坏相关的状态。同时，基于神经网络的自动编码器已被提出用于结构损伤检测，证明能够从振动测量中捕获与损伤相关的特征。这项工作旨在通过将这两种方法结合到一种新颖的结构损伤检测和定位算法中来利用这两种方法提供的各自优势，该算法对不断变化的环境条件具有鲁棒性。该算法还配备了一个故障指示器模块，该模块源于自动阈值以及确定性和概率性故障指示器的引入，从而提供了一个完整的、有价值的工具，用于在有限的人工干预下支持决策制定。该方法参考数值 MDOF 系统进行演示，该系统的参数取自文献基准案例研究。