Damage localization for composite structure using guided wave signals with Gramian angular field image coding and convolutional neural networks

A hybrid structural health monitoring (SHM) system, consisting of a piezoelectric transducer and fiber optic sensors (FOS) for generating and monitoring Lamb waves, was investigated to determine their potential for damage detection and localization in composite aerospace structures. As part of this study, the proposed hybrid SHM system, together with an in-house developed algorithm, was evaluated to detect and localize two types of damage: a through thickness damage (hole of 2 mm in diameter) and a surface damage (2 mm diameter bore hole with a depth of 0.65 mm) located on the backside of the plate. The experiments were performed using an aircraft representative composite plate skin, manufactured from carbon fiber reinforced polymer (CFRP).

Distinguishing pericarpium citri reticulatae of different origins using terahertz time-domain spectroscopy combined with convolutional neural networks

Carbon fiber composite laminates, consisting of highly anisotropic ply layers, are widely used in aerospace structures due to their good strength to weight ratio. However, due to poor interlaminar strength, composite components are prone to barely visible impact damage during aircraft operation. Sparse array guided wave imaging, using a network of distributed sensors, is an important Structural Health Monitoring (SHM) tool for the detection and localization of in-service damage in composite structures. However, the anisotropy of composite laminates influences guided wave scattering, impacting imaging performance. Defect characterization can be improved by considering the scattering characteristics of various damage types for the sparse array signal processing. Guided wave scattering (A0 Lamb wave mode) was investigated around an artificial insert delamination in a quasi-isotropic carbon fiber reinforced polymer (CFRP) panel. Permanent magnets, mounted on an undamaged region of the plate, were also used as scattering targets and compared to the delamination case. Full 3D Finite Element (FE) simulations were performed for both the delamination and magnet cases and compared to wavefield data obtained from non-contact laser measurements. Good agreement was found between the experimental measurements and simulations. Scattered guided wave amplitudes around each damage type show strong directional dependency with energy focusing along the fiber directions of the outer ply layers of the laminate. Distinct scattering behavior was observed for each damage type. A forward scattered wave was observed for the delamination, whereas the magnet blocked forward wave transmission. Implications of anisotropy and angular scattering on sparse array SHM of different defect types are discussed.

Understanding the learning mechanism of convolutional neural networks in spectral analysis

Among the many deep learning methods, the convolutional neural network (CNN) model has an excellent performance in image recognition. Research on identifying and classifying image datasets using CNN is ongoing. Animal species recognition and classification with CNN is expected to be helpful for various applications. However, sophisticated feature recognition is essential to classify quasi-species with similar features, such as the quasi-species of parrots that have a high color similarity. The purpose of this study is to develop a vision-based mobile application to classify endangered parrot species using an advanced CNN model based on transfer learning (some parrots have quite similar colors and shapes). We acquired the images in two ways: collecting them directly from the Seoul Grand Park Zoo and crawling them using the Google search. Subsequently, we have built advanced CNN models with transfer learning and trained them using the data. Next, we converted one of the fully trained models into a file for execution on mobile devices and created the Android package files. The accuracy was measured for each of the eight CNN models. The overall accuracy for the camera of the mobile device was 94.125%. For certain species, the accuracy of recognition was 100%, with the required time of only 455 ms. Our approach helps to recognize the species in real time using the camera of the mobile device. Applications will be helpful for the prevention of smuggling of endangered species in the customs clearance area.

Summary Gas-liquid flow is one of the most observed in nature and in many industrial applications. The presence of dense gas is a special case (i.e., a flow with a liquid/gas viscosity ratio of 10 or even less). Dense-gas/liquid flow is found in the Brazilian offshore production scenario, which is characterized by subsea lines operating under reservoir pressures typically ranging from 100 bar to 500 bar, temperatures around 60°C, and high CO2 content, while upstream of the choke valve pressures commonly range between 30 bar and 160 bar. Despite its relevance, the technical literature shows significant gaps. Although some studies employ dynamic pressure signals to analyze two-phase flows, most rely on numerical simulations or high-frequency experimental systems. Consequently, the analysis and classification of dense-gas/liquid flow using low-frequency differential pressure signals that are precisely the most widely available measurements in offshore operations have not been addressed. Likewise, there are no approaches that integrate multiple signal-to-image encoding techniques with advanced hybrid deep learning architectures for flow-pattern characterization from pressure-gradient signals. To address these gaps, we introduce a methodology that transforms low-frequency pressure-gradient time series into multivariate images using four complementary encoding techniques. Gramian angular fields (GAFs) [Gramian angular summation field (GASF)/Gramian angular difference field (GADF)] capture temporal correlations and angular relationships; recurrence plots (RPs) reveal recurrence patterns and nonlinear dynamic structures; and Markov transition fields (MTF) model state-transition probabilities while preserving the statistical structure of the signal. These representations are integrated into a unified 2 × 2 mosaic, generating a final image of size 2m × 2n. In addition, a hybrid deep learning model convolutional neural network (CNN)-transformer with coordinated attention is proposed, designed to leverage both local features and global dependencies. The convolutional modules extract fine spatial patterns, the Swin Transformer blocks learn long-range relationships through hierarchical self-attention, and the coordinated attention module preserves directional information by recalibrating feature responses along the horizontal and vertical axes. This combination enables the model to capture rapid local variations in the pressure gradient as well as global hydrodynamic trends, both essential in complex multiphase systems. By relying exclusively on low-frequency pressure-gradient signals, which are typically available in offshore monitoring systems, the proposed method offers strong industrial applicability. The results show that the hybrid model achieves 99% accuracy in classifying dense-gas/liquid flow patterns, significantly outperforming traditional approaches based on physical correlations or statistical analysis. These advancements position the methodology as a significant contribution to multiphase-flow characterization in the oil and gas industry.

Accurately identifying epileptogenic zone (EZ) using high-frequency oscillations (HFOs) is a challenge that must be mastered to transfer HFOs into clinical use. We analyzed the ability of a convolutional neural network (CNN) model to distinguish EZ and non-EZ HFOs. Nineteen medically intractable epilepsy patients with good surgical outcomes 2 years after surgery were studied. Five-minute interictal intracranial electroencephalogram epochs of slow-wave sleep were selected randomly. Then 5 s segments of ripples (80–200 Hz) and fast ripples (FRs, 200–500 Hz) were detected automatically. The EZs and non-EZs were identified using the surgery resection range. We innovatively converted all epochs into four types of images using two scales: original waveforms, filtered waveforms, wavelet spectrum images, and smoothed pseudo Wigner–Ville distribution (SPWVD) spectrum images. Two scales were fixed and fitted scales. We then used a CNN model to classify the HFOs into EZ and non-EZ categories. As a result, 7,000 epochs of ripples and 2,000 epochs of FRs were randomly selected from the EZ and non-EZ data for analysis. Our CNN model can distinguish EZ and non-EZ HFOs successfully. Except for original ripple waveforms, the results from CNN models that are trained using fixed-scale images are significantly better than those from models trained using fitted-scale images (p < 0.05). Of the four fixed-scale transformations, the CNN based on the adjusted SPWVD (ASPWVD) produced the best accuracies (80.89 ± 1.43% and 77.85 ± 1.61% for ripples and FRs, respectively, p < 0.05). The CNN using ASPWVD transformation images is an effective deep learning method that can be used to classify EZ and non-EZ HFOs.

Efficient wind energy harvesting becomes more and more important as a consequence of the increasing interest in renewable energy in the European Union [1]. This leads to growing sizes of wind turbines (WTs), and with it, larger WT blades (WTBs). The structural designs of these WTBs are created to optimize the potential energy output, where low mass is a key requirement. However, high flexibilities and lower buckling capacities are further results of these developments [2], thus certain damage scenarios become significant. Intelligently designed structural health monitoring (SHM) systems can help to reduce the associated operations and maintenance costs. Even though, several techniques are already developed for structural damage detection (SDD) in WTBs, the majority of these methods is not suitable for inservice measurements. This paper presents a SDD and structural damage localization (SDL) method based on the partial autocorrelation function (PACF) of vibration responses. The approach is applied to a numerical model of a large WTB, where the acceleration responses are obtained from transient dynamic simulations with a simplified aerodynamic loading approach. The novel damage sensitive feature (DSF) is developed as the Mahalanobis distance between a baseline and current vector of PACF coefficients. First, numerical modal analysis of the finite element (FE) WTB model is performed in order to estimate the effect of a disbonding damage scenario on the vibration characteristics. Second, the behaviour of the PACF for time series of the healthy system is discussed. Third, the SDD results on the basis of statistical hypothesis testing are assessed for two selected sensor locations and increasing damage extents. Finally, the performance of the proposed DSF with respect to SDL is illustrated for multiple locations on the WTB’s surface. This study demonstrated the efficiency of a DSF based on the PACF for SDD and SDL, which is promising for future developments of vibration-based SHM techniques in WTBs.

Fault isolating and grading for li-ion battery packs based on pseudo images and convolutional neural network

Damage localization in plate-like structures using time-varying feature and one-dimensional convolutional neural network

Convolutional Neural Networks (CNNs) have demonstrated impressive performance in complex machine learning tasks such as classification and regression problems. A reliable neural network structure plays a decisive role in CNN studies. Through comparing and analyzing the structure of neural networks, a model structure for better visualization performance has been discovered, and such a method supports the development of deep learning research. These studies are of particular importance in end-to-end systems for autonomous driving to imitate human driving, where the interpretability of the system is limited. Because of the uncertainty of the ground truth, for the determination of human steering in an image, it is difficult to accurately compare the visualization performance of different CNN models or different visualization methods. For practical applications, however, an objective and quantitative measure for assessing visualization performance is necessary. Therefore, a method to evaluate the visualization performance of CNN models using a driver model instead of human drivers is proposed, to generate a data set which can be used to determine the decisional point (ground truth) in the input image. Then, an exclusive method is also put forth, to quantitatively calculate the relationship between the decisional point (ground truth) and the visualization results produced by CNN models. In this paper, five CNN models as an autonomous steering controller are designed based on PilotNet, and the visualization abilities of each CNN models is compared by three evaluation indicators. By comparing the visualization performance of five different CNN models, it is shown that the proposed method can successfully assess the visualization level of the CNN model.

BACKGROUND AND AIM: Outdoor ultrafine particles (UFP; 100 nm) and black carbon (BC) vary greatly within cities and may have adverse impacts on human health such as cardiovascular mortality and brain tumour incidence. Traditional regression methods for estimating spatial distributions of ambient air pollution depend on extensive, curated geospatial information system databases. This has resulted in a disparity wherein little is known about local air pollution in the data-sparse settings of low- and middle- income countries. We used a hybrid approach to develop new models to estimate within-city spatial variations in outdoor UFP and BC concentrations across Bucaramanga, Colombia. METHODS: We conducted a large-scale mobile monitoring campaign over twenty days in 2019. Land use regression (LUR) models were developed using land use parameters from curated and open-source databases. Convolutional Neural Network (CNN) models were developed using Google Maps satellite view and street view images. Combined models were developed by combining predictions from the LUR and CNN models. After training in the training and validation sets, predictions were generated in the test set and compared to measured values. RESULTS:The combined UFP model (R2=0.54) outperformed the CNN (R2=0.47) and land use regression (LUR) models (R2=0.47) on their own. Similarly, the combined BC model also outperformed the CNN and LUR BC models (R2 = 0.51 vs 0.43 and 0.45 respectively). Spatial variations in model performance were more stable for the CNN and combined models compared to the LUR models suggesting that the combined approach may be less likely to contribute to differential exposure measurement error in epidemiological studies. CONCLUSIONS:Estimates from these models can then be applied to population-based cohorts in order to evaluate population health risks. Additionally, our findings demonstrated that satellite and street-level images can be combined with a traditional LUR modelling approach to improve predictions of within-city spatial variations in outdoor UFP and BC concentrations. KEYWORDS: Ultrafine particles, Black Carbon, Deep learning, Images, Land use regression

Methods to quantification of precursor damage in carbon fiber reinforced polymer (CFRP) composite structures are reported herein. These techniques include coda wave interferometry (CWI) and nonlinear ultrasonics (NLU). Since low-frequency Lamb wave propagation is insensitive to the early-stage material degradation, it is shown that decoding the information in coda wave can overcome this well-known limitation. To conclude this possibility, CWI technique is cross verified with a traditional high-frequency ultrasound method. To achieve this goal, a tensile–tensile fatigue experiment was designed for CFRP composite specimens. By inducing controlled fatigue damage in these structures, material states are assessed using low-frequency (&amp;lt;500 kHz) ultrasonic guided wave and high-frequency (&amp;gt;10 MHz) P-wave. Stretching guided coda wave is utilized to quantify the precursor damage as a unique approach in this article. However, such method could be illuded by the changes in the signals due to bonds and contacts. To verify if the CWI is successful, and to evaluate the precursor damage in composite structures, additional nonlinear analysis of ultrasonic signals from both guided waves and P-waves is performed. Higher order nonlinearities in both low-frequency guided wave and high-frequency P-wave propagation demonstrate the growth of precursor damage in CFRP composite structures. So does the CWI of low-frequency guided wave data. Accuracy of these ultrasonic techniques is validated with experimentally obtained remaining strengths of the fatigue specimens. With this verification it is envisioned that both CWI and NLU together could quantify the precursor damage in composite structures.

This study leveraged Convolutional Neural Network (CNN) models to estimate canopy height in Southeast Australian forests before and after the 2019–2020 bushfire event, using inputs from Sentinel-1, Sentinel-2, spectral indices, and terrain features and GEDI canopy height (rh99) as target variables. Our research consisted of three primary objectives: (1) an evaluation of GEDI rh99 canopy height in relation to an nDSM derived from airborne LiDAR, (2) the development of two CNN models for pre- and post-fire scenarios, and (3) utilizing the trained CNN models to generate pre- and post-fire canopy height maps and canopy height change maps across the continuous landscape. GEDI rh99 accuracy analysis revealed R 2 = 0.85, RMSE = 7.25 m and nRMSE = 0.23 for pre-fire GEDI and R 2 = 0.78, RMSE = 10.1 m and nRMSE = 0.3 for post-fire GEDI. The pre-fire CNN model achieved R 2 = 0.75, RMSE = 7.29 m and nRMSE = 0.22, and post-fire CNN model achieved R 2 = 0.62, RMSE = 11.67 m, and nRMSE = 0.34 when validated against nDSM. Bias analysis was conducted, revealing that GEDI rh99 underestimated nDSM across all canopy height ranges, and slope has no significant impact on GEDI accuracy. Notably, post-fire GEDI rh99 exhibited significant underestimation in high to extreme fire severity. The CNN models’ prediction displayed overestimation in short forests < 20 m and increasing underestimation in taller forests > 20 m and underestimation in high and extreme fire severity. Subsequent investigation indicated that canopy layer thinning in high fire severity conditions resulted in weak GEDI waveform signals and consequent bias. Additionally, the GEDI rh99 bias was propagated to the CNN models, together with insensitivity of spectral band values to canopy height in dense and burnt forests potentially contributed to models’ bias. Finally, we demonstrated CNN models’ ability to monitor forest recovery by generating canopy height maps spanning East Gippsland from 2019 to 2023.

Lamb wave-based damage detection of composite structures using deep convolutional neural network and continuous wavelet transform