Damage detection in guided wave structural health monitoring using Gaussian process regression

This paper studies the effectiveness of joint compression and denoising strategies with realistic, long-term guided wave structural health monitoring data. We leverage the high correlation between nearby collections of guided waves in time to create sparse and low-rank representations. While compression and denoising schemes are not new, they are almost exclusively designed and studied with relatively simple datasets. In contrast, guided wave structural health monitoring datasets have much more complex operational and environmental conditions, such as temperature, that distort data and for which the requirements to achieve effective compression and denoising are not well understood. The paper studies how to optimize our data collection and algorithms to best utilize guided wave data for compression, denoising, and damage detection based on seven million guided wave measurements collected over 2 years.

Assessing the robustness of a sensor system and the related predictions is a key step in structural health monitoring (SHM). In this paper, the SHM system under consideration uses macro fiber composite (MFC) sensors to generate ultrasonic guided waves for inspection of a composite bolted joint. Bolt bearing failure is introduced to a target hole through tensile loading. The MFC sensor-actuators are configured in a circular array around the target hole and used to send and receive the ultrasonic waves from many different directions. This strategy facilitates a scattering matrix approach to identifying the most effective actuation and sensing angles for damage detection. Multiple interrogation wavelengths are also utilized to study the effect of the wavelength relative to the size of hole being monitored. However, various other factors are expected to impact the ultrasonic signal and therefore the damage detection results. Particularly, the position and orientation of each sensor is precisely measured through image processing techniques in order to quantify the effects of sensor misalignment. Finally, the sensitivity of the ultrasonic inspection technique to variation in each phenomenon is compared to better understand the most significant effects on damage detection performance.

The representation of structural dynamics in the absence of physics-based models, is often accomplished through the identification of parametric models, such as the autoregressive with exogenous inputs, e.g. ARX models. When the structure is amenable to environmental variations, parameter-varying extensions of the original ARX model can be implemented, allowing for tracking of the operational variability. Yet, the latter occurs in sufficiently longer time-scales (days, weeks, months), as compared to system dynamics. For inferring a “global”, long time-scale varying ARX model, data from a full operational cycle has to typically become available. In addition, when the sensor network comprises multiple nodes, the identification of long time-scale varying, vector ARX models grow in complexity. We address these issues by proposing a distributed framework for structural identification, damage detection and localization. Its main features are: (i) the individual estimation of local, single-input-single-output ARX models at every operational point; (ii) the long time-scale representation of each individual ARX coefficient via a Gaussian process regression, which captures dependency on varying Environmental and Operational Conditions (EOCs); (iii) the establishment of a distributed residual generation algorithm for damage detection, which produces time-series of well-defined stationary statistics, with detected discrepancies used for damage diagnosis; and, (iv) exploitation of ARX-inferred mode shape curvatures, obtained via ARX-inferred global state-space models, of the healthy and damaged states, for damage localization. The method is assessed via application on two numerical case studies of different complexity, with the results confirming its efficacy for diagnostics under varying EOCs.

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.

This study investigates the applicability of an emergent learning algorithm called Gaussian process regression (GPR) algorithm to predict damage in plate-like structures as an inverse problem. The presented method is based on static responses and static strain energy as input parameters to GPR model. The performance of the presented methods has been evaluated using two numerical examples, namely, four fixed and cantilever plates. Also, an examination has been performed in which only translational DOFs are selected as measured DOFs. In another work, the effect of noise in static data has been investigated. The model results were compared using mean square errors. The obtained results show the effectiveness of GPR in damage detection and estimation of plate-like structures using static data which may be noisy.

BackgroundNasopharyngeal carcinoma (NPC), an endemic malignancy in Southeast Asia and southern China, necessitates precise delineation of the gross tumor volume (GTV) for radiotherapy to optimize patient prognosis. Positron emission tomography (PET) imaging offers valuable metabolic insights to guide radiotherapy planning but is hampered by manual GTV segmentation, which is labor-intensive and prone to inter- and intra-observer variability. Conventional segmentation methods are inherently limited, and comparative evaluations of deep learning (DL) frameworks for PET-based primary NPC lesion segmentation remain scarce. Thus, this study aimed to optimize the delineation of primary NPC radiotherapy target volumes by leveraging PET-image-based DL segmentation technology, with the goal of enhancing both the precision and efficiency of lesion delineation.MethodsResearchers retrospectively collected PET imaging data from 212 NPC patients at the Affiliated Hospital of Guangdong Medical University. The patients were randomly divided into training (170 patients) and testing (42 patients) datasets. A radiation oncologist and a nuclear medicine physician collaboratively delineated the cancer lesion boundaries through consensus. After data preprocessing, three DL models (Res-Unet, Nn-Unet, and Nn-Former) were used to automatically segment the lesions. Training was based on the training dataset. During evaluation, the models’ segmentation performance was comprehensively assessed using Dice similarity coefficient (DSC) and Hausdorff distance (HD). A visual analysis of the results was also conducted to intuitively understand the models’ segmentation capabilities.ResultsIn the training set, Nn-Unet achieved the highest DSC of 0.869, whereas in the testing set, its DSC was 0.833. The DSC for Nn-Former hovered around 0.8 in both the training and testing sets. In contrast, Res-Unet demonstrated the lowest DSC values among the three models, particularly in the testing set (DSC =0.794). Statistical analysis revealed that the DSC of Nn-Unet was significantly higher than that of both Res-Unet and Nn-Former in the training set (P<0.01 for both comparisons). Regarding the 95% HD and average surface distance (ASD) values, Nn-Unet outperformed the other two models in both the training and testing sets. However, Res-Unet exhibited a much higher HD value in the testing set compared to the training set. The Loss curves for all models gradually decreased as training progressed, indicating that the models were learning relevant features of NPC lesions. The final Loss value for Res-Unet was approximately 0.7, whereas Nn-Unet and Nn-Former had final Loss values below 0.8.ConclusionsThe PET-image-based automatic segmentation model for the primary tumor of NPC established in this study demonstrates the clinical potential of Nn-Unet in primary lesion of NPC segmentation tasks.

Elevated temperatures can cause significant changes in guided-wave (GW) propagation and transduction for structural health monitoring (SHM). This work focuses on GW SHM using surface-bonded piezoelectric wafer transducers in metallic plates for the temperature range encountered in internal spacecraft structures (20—150°C). First, studies done to determine a suitable bonding agent are documented. This is then used in controlled experiments to examine changes in GW propagation and transduction using PZT-5A piezoelectric wafers under quasi-statically varying temperature (also from 20 to 150°C). Modeling efforts to explain the experimentally observed increase in time-of-flight and change in sensor response peak-to-peak magnitude with increasing temperature are detailed. Finally, these results are used in detection and location of mild and moderate damage using the pulse-echo GW testing approach within the temperature range.

A wide range of vibrating structures are characterized by variable structural dynamics resulting from changes in environmental and operational conditions, posing challenges in their identification and associated condition assessment. To tackle this issue, the present contribution introduces a stochastic modeling methodology via Gaussian Process (GP) time-series models. In the presently introduced approach, the vibration response is represented by means of a random coefficient time-series model, whose coefficients comply with a GP regression on the environmental and operational parameters. The approach may be implemented in conjunction to any type of linear-in-the-parameters time-series model, ranging from simple AR models to more complex non-linear or non-stationary time-series models. The obtained GP time-series modeling approach provides an effective and compact global representation of the vibrational response of a structure under a wide span of environmental and operational conditions. The effectiveness of the postulated GP time-series models is demonstrated through two case studies: the first involves the identification of the vertical vibration response of the Humber bridge, evaluated over a period of three years; the second considers the long-term simulated vibration response of a wind turbine featuring non-stationary dynamics stemming from the rotor speed. In both cases, the variation of the average wind speed is the main driver of uncertainty, while, through application of the proposed GP time-series models, it is possible to track the resulting variation in modal quantities.

Validation of the performance of guided wave structural health monitoring systems is vital if they are to be widely deployed; testing the damage detection ability of a system by introducing different types of damage at varying locations is very costly and cannot be performed on a system in operation. Estimating the damage detection ability of a system solely by numerical simulations is not possible as complex environmental effects cannot be accounted for. In this study, a methodology was tested and verified that uses finite element simulations to superimpose defect signals onto measurements collected from a defect-free structure. These signals are acquired from the structure of interest under varying environmental and operational conditions for an initial monitoring period. Measurements collected in a previous blind trial of an L-shaped pipe section, onto which a number of corrosion-like defects were introduced, were utilised during this investigation. The growth of three of these defects was replicated using finite element analysis and the simulated reflections were superimposed onto signals collected on the defect-free test pipe. The signal changes and limits of reliable detection predicted from the synthetic defect reflections superimposed on the measurements from the undamaged complex structure agreed well with the changes due to real damage measured on the same structure. This methodology is of great value for any structural health monitoring system as it allows for the minimum detectable defect size to be estimated for specific geometries and damage locations in a quick and efficient manner without the need for multiple test structures while accounting for environmental variations.

Guided waves using spatially distributed piezoelectric transducers are being applied to many structural health monitoring applications. These surface-mounted transducers, which are typically lead zirconate titanate, are generally assumed to be both undamaged and properly bonded to the host structure during usage. However, this assumption may not be valid, particularly after long-term operation under realistic environmental conditions. The transducer integrity becomes even more critical for aerospace applications because of the inevitably harsh operational conditions. In this study, a methodology for piezoelectric transducer diagnosis is developed to identify both damaged and poorly bonded transducers by quantifying the degree of signal reciprocity for guided waves propagating between pairs of surface-mounted transducers. The proposed method does not require direct comparison of signals to baselines, and it is independent of structural complexities such as geometrical features and boundaries. The method is also insensitive to environmental and operational conditions, such as temperature and applied loads, and is therefore not susceptible to false alarms caused by such variations. The efficacy of the proposed diagnostic technique is evaluated via two-dimensional simulations followed by experiments under varying environmental and operational conditions for piezoelectric transducers mounted on an aluminum plate.

Technology can give industries the ability to create products/materials/services that meet customer needs and comply with applicable regulatory obligations. In this context, an automatic damage detection system is proposed for sandwich panels. Instead of relying on manual inspection, the system is based on artificial vision and operates with high accuracy in an industrial environment, ensuring traceability in product quality, reducing the percentage of returns caused by imperfections. The adaptive thresholding method seeks to identify the pixel intensities found on the surface of the sandwich panel. Unlike existing methods, the proposed algorithm is based on an adaptive threshold that uses the local characteristics of an image to segment and classify damage on the surfaces of sandwich panels, seeking to reject or accept a product according to the quality levels defined by the standard. The experimental results propose to generate a comparison with a sandwich panel damage detection method based on a convolutional neural network. The results of the experiment show that the proposed thresholding-based method has better accuracy and F1Score than deep learning methods. Moreover, this system is able to improve the industrial standards of sandwich panel manufacturing according to the standard, which limits the allowable imperfections, pointing out only the maximum admissible value of manufacturing imperfections to obtain a quality product.KeywordsDamage identificationDeep learningFeature extractionComputer vision

The accuracy of frequency prediction is markedly affected by the nonlinearity and model degradation caused by multiple environmental conditions, which may hinder the prediction accuracy and detectability of damage. Therefore, this paper proposes a local correlation model (LCM) between multiorder bridge frequencies and multiple environmental factors for early warning of abnormal frequencies. First, partial least-squares analysis was conducted to extract several environmental principal components sensitive to modal frequencies. The most relevant local data set for each online environmental sample was selected according to similarity measurements based on Euclidean distance metrics. On this basis, more accurate environment–frequency relation models were formed using relatively simple local linear regression models. To filter out the residual environmental variability not suppressed by the LCM and to enlarge slightly abnormal frequency variation, a warning index (i.e., the weighted Mahalanobis distance) was defined using the residual subspatial reconstruction of principal component analysis. Finally, the validity of the proposed method was verified on a cable-stayed bridge. The results show that in contrast to conventional methods, the proposed LCM can accurately describe complicated frequency variations under changing environmental conditions by considering both the nonlinearity of environmental conditions and the time-varying properties of relation models. The detectability of frequency anomalies induced by sudden events can be effectively improved.

Understanding the interaction between polymers and proteins is of interest for researchers in medicine, biology, food science, and water treatment, among other fields. The goal may be to create strong interactions with enzymes to improve their catalytic stability, while in nanomedicine and biomedical engineering, the focus is often on reducing protein adsorption on polymer surfaces. Researchers have developed libraries of polymers with various monomer combinations and tested their binding to different proteins to better understand these interactions. In this work, we aimed to identify the polymer with the highest or lowest binding affinity to all proteins, respectively, using Gaussian Process Regression (GPR). However, incorporating categorical features such as the type of monomer has not been widely applied in GPR. Here we compare a range of process models, which were coined Multiplicative kernel, Additive kernel, Easy to interpret Gaussian Process model (EzGP), Latent Variable Gaussian Processes (LVGP), and the Latent Map Gaussian Processes (LMGP) by their developers. The LVGP model was found to perform best on the polymer-protein data set, where the output for binding strength was given by Förster resonance energy transfer (FRET), which can be used to help generate large data sets for machine learning (ML). The polymer that had the highest affinity to glucose oxidase (GOx), uricase (Uri), casein (Cas), trypsin (Trp), carbonic anhydrase (CAn) and bovine serum albumin (BSA) carried positive charges as well as hydrophobic benzyl groups. Negatively charged monomers dominated the polymer that rejected the most proteins intermixed with some cationic units, reminiscent of zwitterionic polymers.

In this article, we analyze the near-infrared (NIR) spectra of fifty-eight (58) commercial tablets of 500 mg of paracetamol from different origins (that is, with different batch numbers) in the local markets in Bamako. The NIR spectra were recorded in the spectral range 930 nm-1700 nm. The samples are divided into forty-eight (48) samples forming the set of calibration (training set) and ten (10) samples used as the validation or test set. To perform multivariate calibration, we apply-three nonlinear regression techniques (Gaussian processes regression (GPR), Random Forest (RF), Support vector machine (KSVM)), along with the traditional linear partial least-squares regression (PLSR) to several data pretreatments of the 58 samples. The results show that the three nonlinear regression calibrations have better prediction performance than PLS as far as RMSE is concerned. To decide the best regression model, we avoid R2 since this quantity is not a good parameter for this purpose. We will instead consider RMSE when comparing the different multivariate models. Additionally, to assess the impact of data preprocessing, we apply the above regression techniques to the original data, Multi-scattering correction (MSC), standard variate normalization (SNV) correction, smoothing correction, first derivative (FD), and second derivative correction (SD). The overall results reveal that Gaussian Processes Regression (GPR) applied to smooth correction gives the lowest RMSEP = 2.303053e-06 for validation (prediction) and RMSEC = 2.112316e-06 for calibration. In our investigation, one also notices that the developed GPR model is more accurate and exhibits enhanced behavior no matter which data preprocessing is used. All in all, GPR can be seen as an alternative powerful regression tool for NIR spectra of paracetamol samples. The statistical parameters of the proposed model are compared to the results of some other models reported in the literature.

Phased array beamsteering is an effective damage detection and assessment method in the guided wave structural health monitoring system. Monolithic piezoceramic (PZT) actuators have been widely utilized for beamsteering by assuming omnidirectional point sources for each actuator. However, this assumption can lead to erroneous results for a phased array of actuators with anisotropic actuation, such as MacroFiber Composites (MFC). The MFC actuators are investigated in this research for beamsteering considering the main lobe bandwidth, main lobe magnitude, and side lobe levels and compared to equivalently sized PZT actuators. Analytical models of the MFC and PZT actuators attached to an isotropic plate structure are presented. With the analytical model, the genetic algorithm is used to determine the optimal timing sequences of the phased array elements for beamforming enhancement. Experiments using the PZT and MFC phased arrays on an aluminum plate are also performed and compared to the analysis results. The experiment results closely match to the analysis results.