Structural health monitoring (SHM) plays a pivotal role in ensuring the safety, reliability and service life of engineering structures. In smart structures, networks of active-response materials (e.g. piezoelectric films, magnetostrictive patches, or fibre-optic cables), which convert mechanical and thermal stimuli into electrical or optical signals and act as the primary interface for continuous condition assessment. A persistent challenge is the influence of environmental and operational variability (EOV), particularly temperature changes, which can distort sensor measurements and either obscure or mimic genuine indicators of structural damage. Although numerous methodologies have been proposed to address this issue across various sensing platforms, a comprehensive comparative assessment across methodological categories remains lacking. This review critically examines 3 principal approaches developed to mitigate EOV: direct baseline compensation, adaptive and multi-baseline strategies, and reference-free techniques, including recent advances in transfer learning and hybrid physics-informed machine learning frameworks. A structured literature search spanning Scopus, Web of Science, IEEE Xplore and ScienceDirect underpins the analysis. Each approach is systematically evaluated, highlighting key benefits, limitations and suitability for varying operational scenarios. In addition, emerging trends, gaps and future research directions are identified, emphasising the need for hybrid models, real-time reference-free methodologies, robust uncertainty quantification and scalable population-based SHM solutions. The synthesis is intended to inform the design of next-generation smart, adaptable SHM systems regardless of sensing modality and their seamless integration into intelligent structures operating under complex real-world environmental conditions.
Artificial Neural Networks (ANNs) have rapidly emerged as a promising tool to solve damage identification and localization problem, according to a Structural Health Monitoring approach. Finite Element (FE) Analysis can be extremely helpful, especially for reducing the laborious experimental campaign costs for the ANN development and training phases. The aim of the present work is to propose a guided wave-based ANN, developed through the use of the Finite Element Method, to determine the position of damages. The paper first addresses the development and assessment of the modeling technique. The FE model accuracy was proven through the comparison of the predicted results with experimental and analytical data. Then, the ANN was developed and trained on an aluminum plate and subsequently verified in a composite plate, as well as under different damage configurations. According to the results herein proposed, the ANN allowed to detect and localize damages with a high level of accuracy in all cases of study.
The aim of this work is to propose a numerical methodology based on the finite element (FE) method to investigate the dispersive behavior of guided waves transmitted, converted, and reflected by reinforced aluminum and composite structures, highlighting their differences. The dispersion curves of such modes can help designers in improving the damage detection sensitivity of Lamb wave based structural health monitoring (SHM) systems. A preliminary phase has been carried out to assess the reliability of the modelling technique. The accuracy of the results has been demonstrated for aluminum and composite flat panels by comparing them against experimental tests and semi-analytical data, respectively. Since the good agreement, the FE method has been used to analyze the phenomena of dispersion, scattering, and mode conversion in aluminum and composite panels characterized by a structural discontinuity, as a stiffener. The research activity allowed emphasizing modes conversion at the stiffener, offering new observations with respect to state of the art. Converted modes propagate with a slightly slower speed than the incident ones. Reflected waves, instead, have been found to travel with the same velocity of the incident ones. Moreover, waves reflected in the composite stiffened plate appeared different from those that occurred in the aluminum one for the aspects herein discussed.
In the condition monitoring of rotating systems, overfitting is a common challenge due to limited data history, which reduces the effectiveness of fault detection frameworks; this limitation often leads to unreliable diagnostics, resulting in unexpected machine failures and increased operational costs in industrial applications. Advances in deep learning suggest using simulated data to address this issue, but operational variabilities still cause significant data distribution shifts, affecting model accuracy. This article presents a new vibration-based monitoring framework that improves fault detection in rotary machines by effectively managing these shifts. It features a novel fine-tuning approach within sequential domain adaptation, requiring only a limited number of observations from the target domain for accurate model adjustment. The domain adaptation process is elucidated through a novel visualization of internal activation patterns within the sequential network. This method is further enhanced by a hybrid algorithm that combines wavelet transformation, a multi-layer perceptron, and a transformer encoder, followed by domain-specific fine-tuning. The framework’s effectiveness is demonstrated through experimental data from two different rotor systems, validated by sensitivity and comparative analyses, highlighting its robustness, generalizability, and practical applicability as a baseline in industrial fault detection scenarios.