Designing health indicators (HIs) for aerospace composite structures that demonstrate their health comprehensively, including all types of damage that can be adaptively updated, is challenging, especially under complex conditions like impact and compression-fatigue loadings. This paper introduces a new AI-based approach to designing reliable HIs (fulfilling requirements—monotonicity, prognosability, and trendability—referred to as ’Fitness’) for single-stiffener composite panels under fatigue loading using acoustic emission sensors. It incorporates complete ensemble empirical mode decomposition with adaptive noise for feature extraction, semi-supervised base deep learner models made of long short-term memory layers for information fusion, and a semi-supervised paradigm to simulate labels inspired by the physics of progressive damage. In this way, nondifferentiable prognostic criteria are implicitly implemented into the learning process. Ensemble learning, especially using a semi-supervised network built with bidirectional long short-term memory, improves HI quality while reducing deep learning randomness. The Fitness function equation has been modified to provide a more trustworthy foundation for comparison and enhance the practical reliability of the standard in prognostics and health management. Ablation experiments are conducted, including variations in dataset division and leave-one-out cross-validation, confirming the generalizability of the approach.

@en

Data-driven methodologies have found increasing usage in the last decade for remaining useful life (RUL) prognostics of composite materials utilizing structural health monitoring (SHM) data. Of particular interest is the reliable RUL prediction in cases where the end-of-life is not in between the extreme values within the testing dataset. For example, when unexpected phenomena that severely compromise the structural integrity occur during the service life. Such cases are often referred as outliers and the RUL prognosis based on a data-driven model that learns from past data is often erroneous. This study addresses this challenge by proposing a new stochastic model; the Similarity Learning Hidden Semi Markov Model (SLHSMM), an extension of the Non-Homogenous Hidden Semi Markov Model (NHHSMM). Through the utilization of a nonparametric discrete distribution, which characterizes the similarity between the testing structure and the training structures, a dynamic re-estimation process is employed. This process assigns higher importance to the training structures that display greater similarity to the testing one. As a result, the estimated parameters effectively capture the specific characteristics of the testing structure. The training and testing SHM data sets consist of strain measurements collected from a case study where carbon–epoxy single-stringered panels, are subjected to constant, variable, and random amplitude fatigue loading until failure. RUL estimations from the SLHSMM, the NHHSMM, and the Gaussian Process Regression (GPR) are compared. The SLHSMM clearly outperforms its classical counterpart and GPR providing more accurate outlier and inlier prognostics, demonstrating its capability to adapt to unexpected phenomena and integrate unforeseen data into a prognostic platform.

@en

We present a generic methodology for developing a Health Indicator out of strain-based Structural Health Monitoring data suitable for implementation in prognostic tasks. For this purpose, an in-house test campaign is launched. Single-stringered composite panels are subjected to compression-compression fatigue with the strains being monitored with Fiber Bragg Grating sensors located along the stringers’ feet. Three different fatigue scenarios with increased complexity are investigated i.e. constant amplitude fatigue, variable amplitude fatigue and finally random amplitude (spectrum) fatigue. In this paper, we propose a fusion scheme based on Genetic Algorithms, with the resulted fused Health Indicator achieving high monotonicity and prognosability, both crucial attributes for an enhanced performance of prognostic algorithms. Finally, a popular machine learning algorithm, i.e. Gaussian Process Regression, is employed in order to predict the Remaining Useful Life of the panels in the test set. It is evidenced that the newly proposed fused Health Indicator predicts the Remaining Useful Life far more accurately as several popular performance metrics indicate. The methodology retains a data agnostic character able to be applied in Structural Health Monitoring data from different sensing technologies.

@en

In this paper we execute a complex test campaign to develop a novel methodology for the Remaining Useful Life (RUL) estimation of complex multi-stiffened composite aeronautical panels utilizing Machine Learning models trained with Structural Health Monitoring (SHM) data from hierarchically simpler elements, i.e., single-stiffened panels. Distributed Fiber Optical sensors (DFOS) are employed to monitor the panels’ behavior undergoing variable amplitude compression-compression fatigue after multiple impacts. A data processing methodology is first applied to the DFOS data, to both alleviate the effect of the variable loading conditions on the monitored strain and ease the computational burden. In this upscaling endeavor, an advanced strain-based Health Indicator (HI) based on Genetic algorithms, created and validated on the single-stiffened panel data, is utilized as the prognostic feature for the RUL estimations of the multi-stiffened panels. The HI displays favorable characteristics in terms of monotonicity and prognosability which are highly desirable for more accurate RUL estimations. For the prognostic task, standard machine learning models are trained using the historical degradation data of the single-stiffened panels and a similarity analysis is performed to enhance the accuracy when predicting the RUL of the multi-stiffened panels. Despite the increased structural complexity of the multi-stiffened panels, we demonstrate that the RUL is able to be predicted with reasonable accuracy. The present work paves the road for upscaling and applying prognostic methodologies to more complex structures beyond simple coupons or generic elements.

@en

During the service of composite airframes, damage initiates and accumulates due to the manufacturing imperfections, impact damage and cyclic loadings, leading to the degradation in its load-bearing capacity. The nature of the degradation process is complicated due to the multi-mode damage propagation and complexity in the structural details of airframes. In the condition-based health management of airframe structures, the degradation is expressed in the concept of remaining useful life (RUL). Online prognostic health management is an emerging field dedicated to the timely prediction of RUL using onboard sensors. This work presents a mechanics-informed approach to the prognosis of a typical airframe element, stiffened CFRP composite panel, under compression-compression fatigue. The fatigue degradation of axial stiffness is monitored by Lamb wave velocity and utilised for online RUL prediction via particle filter.

@en

Prognosis of the Remaining Useful Life (RUL) of a structure from Structural Health Monitoring data is the ultimate level in the SHM hierarchy. Reliable prognostics are key to a Condition Based Maintenance paradigm for aerospace systems and structures. In the present work, we propose a methodology for RUL prognosis of generic aeronautical elements i.e. single stringered composite panels subjected to compression/compression fatigue. Strain measurements are utilized in this direction via FBG sensors bonded to the stiffener feet. The strain data collected during the fatigue life are processed and used for the RUL prognosis. In order to accomplish this task, it is essential to produce Health Indicators (HIs) out of raw strain that can properly capture the degradation process. To create such HIs a new pre/post-processing technique is employed and a variety of different HIs are developed. The quality of the HIs can enhance the performance of the prognostic algorithms, hence a fusion methodology is proposed using genetic algorithms. The resulted fused HI is used for the RUL estimation of the SSCPs. Gaussian processes and Hidden Semi Markov Models are employed for RUL prognosis and their performance is compared. Despite the complexity the raw data we demonstrate the feasibility of successful RUL prognostics in a SHM-data driven approach.

@en

A digital twin representative of a typical composite stiffened panel is utilized to monitor skin-to-stringer disbonds. A validated finite element model of the composite panel estimates the longitudinal strains of the pristine state, at the exact location where integrated fiber Bragg grating sensors are permanently installed. Experimental strains are acquired and compared to those provided by the digital twin in order to reveal the presence of disbonds. The integrated sensor grid is used in a manner that some sensors identify the load acting on the panel, leveraging on the digital twin baseline, whilst the remaining ones are dedicated for diagnostic purposes. Two damaged single-stringer panels are tested under compression-compression fatigue conditions. Static strains are received during quasi-static test intervals among the fatigue cycles. The historical strain data are analyzed in a near real-time manner to detect and localize the induced damage throughout the test span.

@en

To move towards a condition-based maintenance practice for aircraft structures, design of reliable health management methodologies is required. Development of diagnostic methodologies is commonly realised on simplified sample structures with assumptions that methodologies can be adapted for application to realistic aircraft structures under in-service conditions. Yet such actual applications are not conducted. In this work, we study the development of diagnostic methodologies to training structures and their application to dissimilar testing structures. A heterogeneous population is considered, consisting of single-stiffener composite panels for methodology development and training and a multi-stiffener composite panel for application and testing. Characteristics as its composite material, lay-up, and temperature condition are constant while topologies and applied loads differ between the dissimilar structures. Damage in the structural panels is monitored on multiple diagnostic levels using a variety of structural health monitoring (SHM) techniques, including acoustic emission and distributed strain sensing. Specifically, we develop diagnostic methods for localising and monitoring disbond growth after impact using strain data collected during fatigue testing of multiple single-stiffener panels and apply these for disbond monitoring in an upscaled version of a multi-stiffener panel. In this manner, this study aids in the maturement and application of SHM methodologies to realistic aircraft structures.

@en

An increasing interest for Structural Health Monitoring has emerged in the last decades. Acoustic emission (AE) is one of the most popular and widely studied methodologies employed for monitoring, due to its capabilities of detecting, locating and capturing the evolution of damage. Most literature so far, has employed AE for characterizing damage mechanisms and monitoring propagation, while only a few employ it for real time monitoring and even fewer for Remaining Useful Life (RUL) prognosis. In the present work, we demonstrate a methodology for leveraging AE recordings for prognostics of composite aerospace structures. Single stiffened CFRP panels are subjected to a variety of compressive fatigue loadings, while AE sensors monitor the panels’ degradation in real time. Several AE features, both from the time and frequency domains, are utilized to identify features capable of capturing the degradation and used as Health Indicators for RUL prognosis. The choice of Health Indicators is predominantly made based on three prognostic attributes, i.e. monotonicity, trend and prognosability, which can overall affect the prognostic performance. RUL prediction of the panels is performed by employing two prominent machine learning algorithms, i.e. Gaussian Process Regression and Artificial Neural Networks. It is evidenced that the proposed AE-based methodology is highly capable to be utilized for RUL prediction of composite structures under variable loading conditions.

@en

In this study, a multi-level Structural Health Monitoring methodology for stiffened composite panels is introduced. A digital twin (DT), that is, a three-dimensional finite element (FE) model, representing the pristine state baseline of the test article, is developed and verified for compressive loading in the post-buckling regime. The detailed FE model is utilized to train a surrogate model with respect to exogenous input, that is, axial load magnitude. The surrogate assists the DT concept that would allow prediction of the load acting on the structure based on an influx of strain data, acquired from fiber Bragg grating sensors permanently attached along the stringer feet. For this purpose, we leverage on the observation that remote from the damage, the strain field remains virtually unaltered with regard to the pristine state. The load is estimated by a sensor placed far from the damage whilst the diagnostic actions are performed by exploiting measurements from the remaining sensing locations. A health indicator, which compares the experimentally received strains with those from the surrogate representing the pristine state, is utilized to (1) detect, (2) localize, and (3) characterize the damage. As damage, we consider either skin-to-stringer disbond or initial impact damage propagation as well as overall stiffness degradation during thousands or millions of fatigue cycles. The sensors that have detected a disbond are dedicated to evaluating the potential propagation of it, while the remaining sensors evaluate the overall stiffness degradation. The proposed methodology is tested for one artificially disbonded and two impacted single-stringer panels subjected to block loading compression-compression fatigue.

@en

Health management methodologies for condition-based maintenance are often developed using sensor data collected during experimental tests. Most tests performed in laboratories focus on a coupon level or flat panels, while structural component testing is less commonly seen. As researchers, we often consider our experimental tests to be representative of a structure in a final application and consider the developed methodologies to be transferrable to these real-life structures. Yet, structures in their final applications such as wind turbines or aircraft are often larger, more complex, might contain various assembly details, and are loaded in complex conditions. These factors might influence the performance of developed diagnostic and prognostic methodologies and should therefore not be ignored. In our work, we consider the aspects of upscaling structural health monitoring (SHM) methodologies for stiffened composite panels with the design of the panels inspired by an aircraft wing structure. For this, we examine two levels of panels, namely a single- and multi-stiffener composite panel, where we consider the single-stiffener panel to be a representative lower-level version of the multi-stiffener panel. Multiple SHM sensors (acoustic emission, Lamb waves, strain sensing) were installed on both composite panels to monitor damage propagation during testing. We identify and analyse challenges and further discuss considerations that must be taken during upscaling of diagnostics and prognostics, and with that, aid in the development of health management methodologies for condition-based maintenance.@en

The development of health indicators (HI) of diagnostic and prognostic potential from generally uninformative raw sensor data is both a challenge and an essential feature for data‐driven diagnostics and prognostics of composite structures. In this study, new damage‐sensitive features, developed from strains acquired with Fiber Bragg Grating (FBG) and acoustic emission (AE) data, were investigated for their suitability as HIs. Two original fatigue test campaigns (constant and variable amplitude) were conducted on single‐stringer composite panels using appropriate sensors. After an initial damage introduction in the form of either impact damage or artificial disbond, the panels were subjected to constant and variable amplitude compression–compression fatigue tests. Strain sensing using FBGs and AE was employed to monitor the damage growth, which was further verified by phased array ultrasound. Several FBGs were incorporated in special SMARTapes™, which were bonded along the stiffener’s feet to measure the strain field, whereas the AE sensors were strategically placed on the panels’ skin to record the acoustic emission activity. HIs were developed from FBG and AE raw data with promising behaviors for health monitoring of composite structures during service. A correlation with actual damage was attempted by leveraging the measurements from a phased array camera at several time instances throughout the experiments. The developed HIs displayed highly monotonic behaviors while damage accumulated on the composite panel, with moderate prognosability.

@en

Conducting damage diagnostics on stiffened panels is commonly performed using a single SHM technique. However, each SHM technique has both its strengths and limitations. Rather than straining the expansion of single SHM techniques going beyond their intrinsic capacities, these strengths and limitations should instead be considered in their application. In this work, we propose a novel fusion-based methodology between data from two SHM techniques in order to surpass the capabilities of a single SHM technique. The aim is to show that by considering data fusion, a synergy can be obtained, resulting in a comprehensive damage assessment, not possible using a single SHM technique. For this purpose, three single-stiffener carbon–epoxy panels were subjected to fatigue compression after impact tests. Two SHM techniques monitored damage growth under the applied fatigue loads: acoustic emission and distributed fiber optic strain sensing. Four acoustic emission sensors were placed on each panel, thereby allowing for damage detection, localization, type identification (delamination), and severity assessment. The optical fibers were adhered to the stiffener feet’ surface, and its strain measurements were used for damage detection, disbond localization, damage type identification (stiffness degradation and disbond growth), and severity assessment. Different fusion techniques are presented in order to integrate the acoustic emission and strain data. For damage detection and severity assessment, a hybrid health indicator is obtained by feature-level fusion while a complementary and cooperative fusion of the diagnostic results is developed for damage localization and type identification. We show that damage growth can be monitored up until final failure, thereby performing a simultaneous damage assessment on all four SHM levels. In this manner, we demonstrate that by proposing a fusion-based approach toward SHM of composite structures, the intrinsic capacity of each SHM technique can be utilized, leading to synergistic effects for damage diagnostics.@en

Real-time Structural Health Monitoring (SHM) of aeronautical structural components is a technology persistently investigated the last years by researchers and engineers to potentially reduce the cost and/or implementation of scheduled maintenance tasks. To this end, various types of sensors have been proposed to serve this role, e.g. piezoelectric, acoustic emission, and strain sensors. In the present paper, a strain-based SHM methodology is proposed for skin/stringer disbond propagation health monitoring. Fiber-optic strain sensors with engraved Bragg gratings are utilized in order to evaluate the propagation of artificially-induced disbonds at single-stringered composite panels. The specimens are subjected to a block loading compression-compression fatigue spectrum. Longitudinal static strains are periodically acquired during quasi-static loadings every 500 cycles. A Health Indicator (HI), based on strains received from the stringer’s feet, is proposed and utilized to monitor the disbond growth. The evolution of this indicator is experimentally monitored throughout the lifespan of the specimens. The present paper verifies and consolidates via actual fatigue experiments the potential of the proposed static-strain based HI developed from numerical data in our previous work.

@en

In order to reduce aircraft downtimes Condition-Based-Maintenance (CBM) is a topic gaining increased popularity in recent years. However, to apply such maintenance policies reliable health monitoring techniques should be implemented. Two state of the art monitoring techniques, namely Fiber Bragg Gratings (FBG) and Acoustic Emission (AE) are used to monitor the fatigue behavior of single stiffened composite panels (SSCPs) subjected to variable amplitude compression-compression (C-C) fatigue. Advanced features, called Health indicators (HIs) are extracted from the raw sensor data to monitor the degradation behavior. It is crucial to have robust and reliable HIs that capture the degradation of the structures. This work focuses on providing capable HIs for monitoring degradation of composite structures.

@en

A case study is presented in which the first steps are made towards the development of a structural health monitoring (SHM) data fusion framework. For this purpose, a composite single-stiffener panel is subjected to compression-compression fatigue loading (R = 10). The carbon-epoxy panel contains an artificial disbond of 30 mm, which was created using a Teflon insert during manufacturing and placed between the skin and the stiffener foot. Under the applied fatigue load, the disbond is expected to grow and its propagation is monitored using two SHM techniques, namely acoustic emission (AE) and Rayleigh-scattering based distributed fiber optic strain sensing. Four AE sensors are placed on the skin, thereby allowing for disbond growth detection and localization. On each stiffener foot, fiber optic sensors are surface-bonded to monitor the growth of the disbond under the applied fatigue loading. The distributed strain measurements are used to localize and monitor the disbond growth. The strength of each technique is utilized by fusing the data from the AE sensors and the fiber optic sensors. In this manner, a data-driven approach is presented in which a data fusion of the different techniques allows for monitoring the damage in the stiffened panel on multiple SHM levels, including disbond growth detection and localization.

@en