The capabilities of detection and localization of damage in a structure, using a guided wave-based structural health monitoring (GWSHM) system, depend on the damage location and the chosen sensor array setup. This paper presents a novel approach to assess the reliability of an SHM system enabling to quantify localization accuracy. A two-step technique is developed to combine multiple paths to generate one probability of detection (POD) curve that provides information regarding the detection capability of an SHM system at a defined damage position. Moreover, a new method is presented to analyze localization accuracy. Established probability-based diagnostic imaging using a signal correlation algorithm is used to determine the damage location. The resultant output of the localization accuracy analysis is the smallest damage size at which a defined accuracy level can be reached at a determined location. The proposed methods for determination of detection probability and localization accuracy are applied to a plate-like CFRP structure with an omega stringer with artificial damage of different sizes at different locations. The results show that the location of the damage influences the sensitivity of detection and localization accuracy for the used detection and localization methods. Localization accuracy is enhanced as it becomes closer to the array’s center, but its detection sensitivity deteriorates.

The continuous monitoring of structural integrity is crucial, as imperceptible damage may appear at any point throughout a structure's lifespan. Several Structural Health Monitoring (SHM) technologies have been developed so far to detect and assess defects in structures. Deep Learning is a common tool for processing data obtained with SHM systems. Although many artificial intelligence-based SHM technologies exist already for damage detection, only a few are focused on damage localization. Existing localization approaches are limited through them being applied on defined simple structures and requiring a large amount of data, which is usually unavailable in practical applications. In this work, measured data from guided ultrasonic wave propagation is used to determine the location of damage in a composite stiffened structure representative of fuselage segments. A novel artificial intelligencebased approach for damage localization is presented and tested with a feed-forward as well as a convolutional neural network. Both architectures show that localization is possible. The accuracy is then analyzed with the probability of localization method and compared to existing non-artificial intelligence-based approaches. These results make it possible to define the minimum damage that can be correctly localized.

The growing adoption of carbon composite materials in the aviation industry necessitates robust SHM systems to mitigate the risks associated with BVID. Among various SHM techniques, Acoustic Emission results particularly effective to pinpoint impact events accurately. This paper aims to optimize impact localization by introducing innovative refinements to the classic Δ𝑇 mapping method and evaluating them alongside modern Machine Learning techniques applied to both complex aluminum and carbon-fiber composite plates. The traditional Δ𝑇 methodology is improved by integrating nearest sensor logic and domain regions to refine spatial predictions. To rigorously assess and benchmark the reliability of the enhanced Δ𝑇 methods against ML algorithms, a Probability of Localization statistical framework is implemented. This approach focuses on the 𝐸90|95 index, which defines the boundary radius within which an acoustic event is successfully located with a 95% statistical confidence level. Experimental validations, demonstrate that the refinement applied to Δ𝑇 method significantly outperforms classical approaches. On a flat composite plate, the enhanced logic reduces the localization error to 11.90mm, yielding an improvement of approximately 50% in the internal area. By leveraging the POL metric, it is possible to observe a 40% improvement in localization capabilities across the entire plate by using the ML-based algorithm.

Translating classical parametric Probability of Detection (POD) analysis 1:1 from Non Destructive Testing (NDT) to Structure Health Monitoring (SHM) systems is not applicable. As a result, over the last two decades, several methods have been developed to assess the reliability of SHM systems such as Length-at-Detection (LaD), Random Effects Model (REM), and Model-Assisted Probability of Detection (MAPOD) methods. Among these, MAPOD method is particularly promising, as it uses simulations to generate statistically independent datasets for the calculation of POD curves, using the same procedure as the classical parametric POD analysis described in the handbook MIL-HDBK 1823A. Although simulation tools are highly effective in accounting for and simulating structural uncertainties, they fall short in representing system, operational and environmental uncertainties. As a result, simulation-based POD analyses lack full representativeness of real-world conditions. In addition, the classical parametric POD analysis assumes a linear relationship between damage size $a$ and its corresponding damage indicator. Furthermore, due to the statistical dependence of repeated measurements, the parametric POD procedure, as described in MIL-HDBK 1823A, cannot be directly applied to monitoring scenarios.To address these limitations, this paper proposes a novel Augmented Probability of Detection (A-POD) method. This method augments simulated datasets, which account for structural uncertainties, with experimental datasets from real Guided Wave Structural Health Monitoring (GWSHM) systems including environmental, operational and system uncertainties. Unlike classical parametric methods, A-POD does not require a predefined relationship between damage size $a$ and the damage indicator, allowing it to be applied to any damage growth trends. The performance and validity of the A-POD method is demonstrated using data obtained from a transducer-based GWSHM system exciting the fundamental torsional T(0,1) mode in a steel pipe. Different sizes of corrosion damage are simulated, including structural uncertainties. This data is augmented with experimental baseline data of an undamaged existing pipe. For validation purposes, artificial damage is introduced to this pipe structure and modelled. The validation of the A-POD method reveals that A-POD and MAPOD method agree well when the damage indicator is linear with damage size $a$. Moreover, comparing the POD analysis between the experimental and simulation datasets reveals very close results when comparing the $a_{90|95}$ values. Finally, the results show the capability of the A-POD method in assessing the reliability of GWSHM systems when the dataset does not exhibit a linear relationship, underscoring its flexibility and versatility.

The Model-Assisted Probability of Detection (MAPOD) technique employs extensive simulations to generate statistically independent datasets for assessing the reliability of Structural Health Monitoring (SHM) systems via Probability of Detection (POD) curves. While MAPOD follows the classical POD procedure described in MIL-HDBK-1823A, simulation tools, though effective in representing structural uncertainties, struggle to capture system, operational, and environmental variations—limiting the realism of simulation-based POD analyses. Moreover, the standard POD approach assumes a linear relationship between damage size $a$ and its indicator and cannot be directly applied to monitoring scenarios with statistically dependent measurements. This paper introduces a novel method that combines simulated damage scenarios with experimental data from Guided Wave Structural Health Monitoring (GWSHM) systems to account for all uncertainties and allow for the integration of the individual fingerprint of an SHM system. The proposed Augmented POD (A-POD) method removes the need for a predefined relationship between damage size $a$ and its indicator, making it applicable to any damage growth trend. The A-POD method is validated using data from a PZT-based GWSHM system exciting the fundamental torsional mode in a steel pipe. Simulated corrosion damage data are merged with experimental baseline data, and artificial defects are introduced for validation. The A-POD and MAPOD results agree well for linear trend growth cases, while the A-POD demonstrates strong reliability and adaptability, when the dataset lacks linearity.