Two-dimensional Images Research Articles

Prognostic value of left atrial strain in patients with moderate to severe mitral stenosis

Abstract Background Mitral stenosis causes an inflow restriction during diastole and is characterized by an increase in left atrial (LA) pressure with reduced cardiac output. Pressure overload of the LA can lead to atrial fibrosis and remodeling, resulting in a loss of LA reservoir and compliance capacity that can lead to backward load on the pulmonary circulation. To date, there are limited studies evaluating the impact of LA strain on prognosis of mitral stenosis patients. Purpose The aim of this study was to assess the prognostic value of LA strain in patients with moderate to severe mitral stenosis using two-dimensional (2D) strain imaging. Methods This was a single-center retrospective study, 237 patients with moderate or severe mitral stenosis were enrolled from January 2010 to December 2022. Baseline clinical and echocardiographic parameters were collected, LA strain measurements with reference time point at end diastole for reservoir strain (LASr), conduit strain (LAScd) and contraction strain (LASct) were analyzed using TOMTEC software. The endpoint was a composite outcome of all-cause mortality, heart failure hospitalization and valve intervention (percutaneous transvenous mitral commissurotomy and surgical intervention). All the LA parameters were analyzed separately to avoid collinearity. Results A total of 237 patients were included in the study. The patients had a mean age was 66.56 ± 13.61 years-old and were predominantly female (67.9%) with median follow up duration is 4.54 years (IQR 1.44 – 6.44). Mean left ventricular ejection fraction (LVEF) was 56.86 ± 10.51%, mean left atrium volume index (LAVI) was 73.94 ± 55.46 ml/m2, mean for LASr, LAScd and LASct were 11.81 ± 8.89%, -6.19 ± 4.50%, and -5.58 ± 6.05% respectively. LASr with a cut-off < 15.8% was independently associated with the composite outcome of all-cause mortality, heart failure hospitalization and valve intervention on multivariable Cox regression analysis (HR 2.51, 95% CI 1.54 - 4.10, p < 0.001). LAScd, LASct and LA volume index did not demonstrate any significant association with the endpoint. Conclusion LASr was independently associated with all-cause mortality, heart failure hospitalization and valve intervention in patients with moderate to severe mitral stenosis.

OmicsFootPrint: a framework to integrate and interpret multi-omics data using circular images and deep neural networks.

The OmicsFootPrint framework addresses the need for advanced multi-omics data analysis methodologies by transforming data into intuitive two-dimensional circular images and facilitating the interpretation of complex diseases. Utilizing deep neural networks and incorporating the SHapley Additive exPlanations algorithm, the framework enhances model interpretability. Tested with The Cancer Genome Atlas data, OmicsFootPrint effectively classified lung and breast cancer subtypes, achieving high area under the curve (AUC) scores-0.98±0.02 for lung cancer subtype differentiation and 0.83±0.07 for breast cancer PAM50 subtypes, and successfully distinguished between invasive lobular and ductal carcinomas in breast cancer, showcasing its robustness. It also demonstrated notable performance in predicting drug responses in cancer cell lines, with a median AUC of 0.74, surpassing nine existing methods. Furthermore, its effectiveness persists even with reduced training sample sizes. OmicsFootPrint marks an enhancement in multi-omics research, offering a novel, efficient and interpretable approach that contributes to a deeper understanding of disease mechanisms.

Additively-manufactured shear tri-coaxial rocket injector mixing and combustion characteristics

A monolithic tri-coaxial propellant injection scheme for enhanced mixing of methane-oxygen in liquid-propellant rocket systems is enabled by additive manufacturing. Mixing and combustion characteristics of the tri-coaxial design are assessed experimentally from 1–69 bar using laser absorption tomography and chemiluminescence imaging, and are compared to a traditionally-manufactured bi-coaxial design. Quantitative two-dimensional images of temperature and carbon monoxide mole fraction are generated from the laser absorption spectroscopy methods, while OH* chemiluminescence provides an approximate metric for combustion heat release defining flame length and injector standoff distance. At similar pressures and oxidizer-to-fuel ratios, the tri-coaxial injector design is shown to enhance mixing and combustion progress, reducing characteristic mixing length scales and achieving improved combustion performance relative to more conventional bi-coaxial designs. Despite enhanced mixing, the tri-coaxial design exhibits more limited reduction in flame standoff distance from the injector face, suggesting that increased heat flux to the injector face can be managed. The tri-coaxial injector highlights the potential to leverage additive manufacturing to enhance performance and simplify the fabrication of liquid-propellant rocket engines.

The effect of handedness and biological sex on fingermark ridge height and volume as examined by 3D imaging.

For decades, detectives and forensic scientists have relied on friction ridge skin comparisons to identify individuals in criminal investigations. This method involves examining (latent) fingermarks, typically captured as two-dimensional (2D) images, and comparing them with known inked impressions or scans. The comparisons focus on general patterns, the location and orientation of minutiae, and additional characteristics like scars or pores. However, this common process overlooks other potentially valuable factors, such as handedness, biological sex, and the time since deposition, which could provide crucial investigative leads, especially in cases with partial or unclear ridge patterns. This study explored the potential of three-dimensional (3D) optical profilometry (OP) to observe changes in fingermarks ridge height and volume over 7 days while considering hand dominance and biological sex. The results indicated that all the assessed 3D metrics were generally consistent in detecting the effects of sex and handedness, mostly noticeable on aged fingermarks. Specifically, females and impressions from their non-dominant hand exhibited higher values. Additionally, the influence of time was evident, with fresh fingermarks showing significantly larger ridges in terms of height and volume. These findings suggest that 3D OP can enhance the probative value of fingermarks by inferring additional characteristics such as sex, handedness, and the age of the impression. These activity-level propositions could provide useful information in cases where only partial or poor-quality fingermarks are recovered, providing new data dimensions that could lead to more comprehensive forensic examinations.

Comparison of On-Sky Wavelength Calibration Methods for Integral Field Spectrograph

With advancements in technology, scientists are delving deeper in their explorations of the universe. Integral field spectrograph (IFS) play a significant role in investigating the physical properties of supermassive black holes at the centers of galaxies, the nuclei of galaxies, and the star formation processes within galaxies, including under extreme conditions such as those present in galaxy mergers, ultra-low-metallicity galaxies, and star-forming galaxies with strong feedback. IFS transform the spatial field into a linear field using an image slicer and obtain the spectra of targets in each spatial resolution element through a grating. Through scientific processing, two-dimensional images for each target band can be obtained. IFS use concave gratings as dispersion systems to decompose the polychromatic light emitted by celestial bodies into monochromatic light, arranged linearly according to wavelength. In this experiment, the working environment of a star was simulated in the laboratory to facilitate the wavelength calibration of the space integral field spectrometer. Tools necessary for the calibration process were also explored. A mercury–argon lamp was employed as the light source to extract characteristic information from each pixel in the detector, facilitating the wavelength calibration of the spatial IFS. The optimal peak-finding method was selected by contrasting the center of weight, polynomial fitting, and Gaussian fitting methods. Ultimately, employing the 4FFT-LMG algorithm to fit Gaussian curves enabled the determination of the spectral peak positions, yielding wavelength calibration coefficients for a spatial IFS within the range of 360 nm to 600 nm. The correlation of the fitting results between the detector pixel positions and corresponding wavelengths was >99.99%. The calibration accuracy during wavelength calibration was 0.0067 nm, reaching a very high level.

Fault diagnosis method of automobile rolling bearing based on transfer learning and improved DenseNet

Aiming at the problems caused by ignoring the time series characteristics, the scarcity of labeled data and the long diagnosis time in the fault diagnosis of one-dimensional vibration signals of automobile bearings, a new method combining improved DenseNet and transfer learning is proposed in this study. This method uses Recurrent Plot (RP) technology to convert one-dimensional vibration data into two-dimensional images to fully tap the potential value of time series. By optimizing the DenseNet network structure, the fault features are extracted effectively. Lightweight network design and MobileViT Attention mechanism are used to reduce the number of parameters and improve computing efficiency. With the help of transfer learning technology, the fault features in the source domain are transferred to the target domain, which solves the problem of cross-condition diagnosis and greatly reduces the diagnosis time. The experimental results show that the proposed method can improve the accuracy of fault identification and diagnosis efficiency, and achieve accurate classification.

Deep Learning-Based Reconstruction of 3D Morphology of Geomaterial Particles from Single-View 2D Images.

The morphology of particles formed in different environments contains critical information. Thus, the rapid and effective reconstruction of their three-dimensional (3D) morphology is crucial. This study reconstructs the 3D morphology from two-dimensional (2D) images of particles using artificial intelligence (AI). More than 100,000 particles were sampled from three sources: naturally formed particles (desert sand), manufactured particles (lunar soil simulant), and numerically generated digital particles. A deep learning approach based on a voxel representation of the morphology and multi-dimensional convolutional neural networks was proposed to rapidly upscale and reconstruct particle morphology. The trained model was tested using the three particle types and evaluated using different multi-scale morphological descriptors. The results demonstrated that the statistical properties of the morphological descriptors were consistent for the real 3D particles and those derived from the 2D images and the model. This finding confirms the model's validity and generalizability in upscaling and reconstructing diverse particle samples. This study provides a method for generating 3D numerical representations of geological particles, facilitating in-depth analysis of properties, such as mechanical behavior and transport characteristics, from 2D images.

Assembly method for curved porous circular workpieces based on multidimensional information fusion: Grid electrode component

To tackle the problems related to the complexities of obtaining depth information for circular workpiece with arc surface and holes, a novel vision guidance method has been introduced to precisely gauge interlayer spacing. The process includes the acquisition and preprocessing of point cloud depth information, along with matching and edge processing. The depth coordinates of the point cloud are subsequently determined. Two-dimensional image processing technology is employed to extract the coordinates of the center of the surface circular hole in the curved porous circular workpiece. The 3D coordinates are generated for guiding the assembly by integrating these datasets. Experiments on grid parts in aviation propulsion systems demonstrate that this method maintains dot matrix spacing within 0.5–1.2 mm, ensures the coaxiality of the center hole, and meets assembly standards. The results confirm the method’s effectiveness for automated assembly of curved porous round workpieces.

3D reconstruction and depth estimation method for local anomalies of rail surface based on multi-view stereo matching

Abstract Detecting rail surface anomalies has become crucial for ensuring the safety of train operations. However, manual detection methods are time-consuming and labor-intensive. Although traditional detection models based on one-dimensional signals or two-dimensional images can effectively identify the existence of defects, they are difficult to use to obtain local depth characteristic information, leading to difficulties in accurately assessing the extent of damage in abnormal regions. Rail track maintenance strategies are typically developed based on the detected different depth ranges of defects. To address this issue, this paper proposes a local depth estimation method based on the point cloud of the target rail surface reconstructed by PatchmatchNet. Firstly, according to the acquisition method of multi-view images and the sampling environment at the site, a practical data collection protocol is established for generating a multi-view dataset of rail surface. Next, dense point cloud of the target rail surface were reconstructed by PatchmatchNet. Subsequently, a method for estimating the local anomaly depth is developed based on the point cloud. Experimental results demonstrate that the proposed method achieves a minimum error of approximately 5.5% within a maximum depth range of 0.35mm, when compared to depth measurements obtained using a structured light camera. Finally, this paper presents a more comprehensive three-dimensional representation of the local abnormal physical structure, surpassing traditional one-dimensional and two-dimensional forms. This enhanced representation offers richer information for the effective determination of whether the anomalies constitute defects and aids in distinguishing true defects from other surface irregularities. Such advancement significantly improves the precision of defect assessment and supports the development of highly precise repair strategies.

Two-point statistics in non-homogeneous rotating turbulence

Time-resolved two-dimensional two-component particle image velocimetry measurements with high spatial resolution are carried out in a water tank agitated by four blades rotating at constant speed. Different blade geometries and rotation speeds are tested for the purpose of modifying turbulent flow conditions. In all cases where no baffles are used to break the rotation, the Zeman length is an order of magnitude smaller than the Taylor length. Compared with the cases with baffles which break the rotation, in the unbaffled cases turbulence production and/or mean advection are significant and the turbulence nonlinearity is dramatically reduced for the horizontal (i.e. normal to the axis of rotation) two-point turbulence fluctuating velocities. This nonlinearity reduction is manifest not only in the interscale turbulent energy transfer but also in the interspace turbulent energy transfer, which nearly vanishes. However, the nonlinearity is not reduced for the vertical two-point turbulence fluctuating velocities: the corresponding interscale turbulent transfer rate is in fact intensified, and its dependence on the two-point separation distance, as well as that of the corresponding interspace turbulent transfer rate, which does not vanish, is significantly modified. Even though non-homogeneities are very different for different blades and rotation speeds in the unbaffled cases, the horizontal fluctuating velocity's second-order structure function collapses with scalings which resemble predictions for homogeneous turbulence subject to strong rotation. The vertical fluctuating velocity's second-order structure function does not collapse for different blade geometries by neither these nor the Kolmogorov predictions.

Real-Time 3D Imaging and Inhibition Analysis of Human Serum Amyloid A Aggregations Using Quantum Dots.

Serum amyloid A (SAA) is one of the most important precursor amyloid proteins discovered during the study of amyloidosis, but its underlying aggregation mechanism has not yet been well elucidated. Since SAA aggregation is a key step in the pathogenesis of AA amyloidosis, amyloid inhibitors can be used as a tool to study its pathogenesis. Previously, we reported a novel microliter-scale high-throughput screening (MSHTS) system for screening amyloid β (Aβ) aggregation inhibitors based on quantum dot (QD) fluorescence imaging technology. In this study, we report the aggregation of human SAA (hSAA) in phosphate-buffered saline, in which we successfully visualized hSAA aggregation by QD using fluorescence microscopy and confocal microscopy. Two-dimensional and three-dimensional image analyses showed that most aggregations were observed at 40 μM hSAA, which was the optimal aggregation concentration in vitro. The accuracy of this finding was verified by a Thioflavin T assay. The transmission electron microscopy results showed that QD uniformly bound to hSAA aggregation. hSAA aggregation inhibitory activity was also evaluated by rosmarinic acid (RA). The results showed that RA, which is a compound with high inhibitory activity against Aβ aggregation, also exhibited high inhibitory activity against 40 μM hSAA. These results indicate that the MSHTS system is an effective tool for visualizing hSAA aggregation and for screening highly active inhibitors.

Describing the musculature of mystacial pads in harbour seals (Phoca vitulina) using diceCT.

Pinnipeds have long, sensitive, moveable mystacial vibrissae. In other mammals, intrinsic muscles contribute to protracting the vibrissae. However, the mystacial muscles of pinnipeds have not yet been systematically described. Using traditional histological methods provides us with two-dimensional muscle images, but having the ability to visualise these structures in three dimensions would allow for a more comprehensive understanding of pinniped vibrissal anatomy, especially given the challenges posed by their large and extremely curved mystacial pad. We predicted that harbour seals would have large, regular intrinsic muscles due to their well-organised, moveable vibrissae. We adopted diffusible iodine contrast-enhanced computer tomography (diceCT) to describe, for the first time, the three-dimensional architecture of the mystacial vibrissal muscles found in harbour seals. Our observations show that their vibrissae are organised into grids within the mystacial pad. We identified both sling-shaped and oblique intrinsic muscles that connect one vibrissae to the next in the same row. We also identified extrinsic muscles, including the m. nasolabialis, m. maxillolabialis, m. levator nasolabialis and m. orbicularis oris. Contrary to our prediction, the intrinsic muscles were not very large, although they were regularly distributed throughout the pad. Rather, the extrinsic muscles, particularly the m. nasolabialis and m. maxillolabialis were large, deep and well-defined, running throughout the length of the mystacial pad. Therefore, we suggest that these extrinsic muscles, the m. nasolabialis and m. maxillolabialis, are responsible for driving vibrissal protraction underwater. These findings demonstrate the importance of three-dimensional visualisation techniques in advancing our understanding of mystacial anatomy and function in pinnipeds.

Isothermal Flow Field Characterization of a Full-Scale Sector Combustor at Elevated Pressures

Abstract An experimental investigation in a sector (20 deg) of full-scale annular gas turbine combustor is performed. The sector combustor is optically accessible for the flow and flame visualization of the primary and exit zones of the combustor. The distinctive feature of the experimental setup is that it preserves the geometrical details of an annular combustor that includes the casing, dome and combustor liner. The combustor design features a series of primary and secondary dilution holes with multiple film cooling strips on the outer and inner liner. In the present study, the combustor is operated at inlet Mach numbers of 0.02–0.3 at operating absolute pressures of 1–5 bar. Static pressure measurements are performed at multiple locations in the rig to characterize the pressure drop across the combustor. Two-dimensional particle image velocimetry (PIV) is performed to measure the velocity fields of the primary and exit zones of the combustor simultaneously. The results show the presence of a central recirculation zone (CRZ), high-velocity annular jets, and a pair of dilution jets in the primary zone of the combustor. The steady-state flow structures are invariant of inlet Mach number and pressures. The relationship between the relative pressure drop across the combustor and the combustor inlet condition is obtained. Mass flowrate and momentum flux are calculated for the flow through the swirler, central recirculation zone, the primary dilution jets, and the exit zone. The paper shows how the flow structures in a realistic combustor change with variations in global combustor parameters.

Gut Analysis Toolbox - automating quantitative analysis of enteric neurons.

The enteric nervous system (ENS) consists of an extensive network of neurons and glial cells embedded within the wall of the gastrointestinal (GI) tract. Alterations in neuronal distribution and function are strongly associated with GI dysfunction. Current methods for assessing neuronal distribution suffer from undersampling, partly due to challenges associated with imaging and analyzing large tissue areas, and operator bias due to manual analysis. We present the Gut Analysis Toolbox (GAT), an image analysis tool designed for characterization of enteric neurons and their neurochemical coding using two-dimensional images of GI wholemount preparations. GAT is developed in Fiji, has a user-friendly interface, and offers rapid and accurate segmentation via custom deep learning (DL)-based cell segmentation models developed using StarDist, as well as a ganglia segmentation model in deepImageJ. We apply proximal neighbor-based spatial analysis to reveal differences in cellular distribution across gut regions using a public dataset. In summary, GAT provides an easy-to-use toolbox to streamline routine image analysis tasks in ENS research. GAT enhances throughput, allowing rapid unbiased analysis of larger tissue areas, multiple neuronal markers and numerous samples.

Assessment of fetal cardiac function in pregnant women with anemia: prospective case-control study.

To compare fetal cardiac function in pregnant women with iron deficiency anemia (IDA) vs healthy pregnant controls. This was a single-center, prospective, case-control study conducted in a tertiary hospital between November 2022 and September 2023. Women diagnosed with IDA who attended as outpatients at the pregnancy follow-up clinic at 30-34 weeks' gestation or who were hospitalized for intravenous iron treatment owing to profound anemia were included. The control group consisted of randomly selected gestational-age-matched pregnant women with no obstetric complications or comorbidities and who did not have anemia. Patients underwent two-dimensional imaging, followed by pulsed-wave Doppler and M-mode and tissue Doppler imaging (TDI) to evaluate fetal cardiac function. A fetal cardiac score was calculated using systolic, diastolic and global hemodynamic function parameters, and was compared between patients with IDA and those without. The fetal cardiac score was also assessed according to the severity of anemia in the IDA group. A total of 150 patients, comprising 50 patients with IDA and 100 healthy pregnant women at 30-34 weeks' gestation, were included in the study. Of the patients with IDA, 20 had mild, 18 had moderate and 12 had severe anemia. The fetal myocardial performance index and isovolumetric relaxation time were significantly higher in the IDA group compared with the control group (P < 0.0001 for both), while isovolumetric contraction time was similar. Among the fetal tricuspid and mitral valve diastolic parameters, the E, A and E/A values were significantly lower in the IDA group (P < 0.05 for all). Mitral (MAPSE) and tricuspid (TAPSE) annular plane systolic excursions were significantly lower in the IDA group (P < 0.05 for both). The IDA group also had significantly lower values for the TDI parameters mitral and tricuspid E', A', S' and E'/A' ratio and a significantly higher E/E' ratio (P < 0.05 for all). Among the IDA subgroups, a significant decrease was observed in the tricuspid and mitral A, E and E/A ratio in fetuses whose mothers had severe anemia (P = 0.001). M-mode Doppler analysis revealed significantly lower fetal TAPSE and MAPSE in the patient group with severe maternal anemia (P = 0.001 for both). According to the subgroup comparison of TDI findings, the fetuses of mothers with severe anemia had significantly lower tricuspid and mitral E', A', S' and E'/A' ratio values and a significantly higher E/E' ratio (P < 0.05 for all). The fetal cardiac score was significantly higher in the maternal IDA group compared with the control group (P < 0.001). A significant negative correlation was found between maternal hemoglobin level and fetal cardiac score (P < 0.001). We observed differences in fetal systolic and diastolic cardiac function in pregnancies with maternal IDA. Fetal cardiac function was affected more among patients with severe anemia. This study found an increased E/E' ratio in the fetuses of pregnant women with IDA, suggesting decreased fetal heart maturation. Prenatal fetal cardiac evaluation, especially in women with severe anemia, can facilitate a more seamless transition to the postnatal period for these newborns. © 2024 International Society of Ultrasound in Obstetrics and Gynecology.

Searching Method for Three-Dimensional Puncture Route to Support Computed Tomography-Guided Percutaneous Puncture.

In CT-guided percutaneous punctures-an image-guided puncture method using CT images-physicians treat targets such as lung tumors, liver tumors, renal tumors, and intervertebral abscesses by inserting a puncture needle into the body from the exterior while viewing images. By recognizing two-dimensional CT images prior to a procedure, a physician determines the least invasive puncture route for the patient. Therefore, the candidate puncture route is limited to a two-dimensional region along the cross section of the human body. In this paper, we aim to construct a three-dimensional puncture space based on multiple two-dimensional CT images to search for a safer and shorter puncture route for a given patient. If all puncture routes starting from a target in the three-dimensional space were examined from all directions (the brute-force method), the processing time to derive the puncture route would be very long. We propose a more efficient method for three-dimensional puncture route selection in CT-guided percutaneous punctures. The proposed method extends the ray-tracing method, which quickly derives a line segment from a given start point to an end point on a two-dimensional plane, and applies it to three-dimensional space. During actual puncture route selection, a physician can use CT images to derive a three-dimensional puncture route that is safe for the patient and minimizes the puncture time. The main novelty is that we propose a method for deriving a three-dimensional puncture route within the allowed time in an actual puncture. The main goal is for physicians to select the puncture route they will use in the actual surgery from among the multiple three-dimensional puncture route candidates derived using the proposed method. The proposed method derives a three-dimensional puncture route within the allowed time in an actual puncture. Physicians can use the proposed method to derive a new puncture route, reducing the burden on patients and improving physician skills. In the evaluation results of a computer simulation, for a 3D CT image created by combining 170 two-dimensional CT images, the processing time for deriving the puncture route using the proposed method was approximately 59.4 s. The shortest length of the puncture route from the starting point to the target was between 20 mm and 22 mm. The search time for a three-dimensional human body consisting of 15 CT images was 4.77 s for the proposed method and 2599.0 s for a brute-force method. In a questionnaire, physicians who actually perform puncture treatments evaluated the candidate puncture routes derived by the proposed method. We confirmed that physicians could actually use these candidates as a puncture route.

Ghost Removal from Forward-Scan Sonar Views near the Sea Surface for Image Enhancement and 3-D Object Modeling

Underwater sonar is the primary remote sensing and imaging modality within turbid environments with poor visibility. The two-dimensional (2-D) images of a target near the air–sea interface (or resting on a hard seabed), acquired by forward-scan sonar (FSS), are generally corrupted by the ghost and sometimes mirror components, formed by the multipath propagation of transmitted acoustic beams. In the processing of the 2-D FSS views to generate an accurate three-dimensional (3-D) object model, the corrupted regions have to be discarded. The sonar tilt angle and distance from the sea surface are two important parameters for the accurate localization of the ghost and mirror components. We propose a unified optimization technique for improving both the measurements of these two parameters from inexpensive sensors and the accuracy of a 3-D object model using 2-D FSS images at known poses. The solution is obtained by the recursive updating of sonar parameters and 3-D object model. Utilizing the 3-D object model, we can enhance the original images and generate synthetic views for arbitrary sonar poses. We demonstrate the performance of our method in experiments with the synthetic and real images of three targets: two dominantly convex coral rocks and a highly concave toy wood table.

Evaluation for coarse aggregate distribution of asphalt mixtures based on the two-dimensional digital image analysis

Meso-structure is one of the major sources of macro-performance in asphalt mixtures. The research on aggregate distribution state is of great significance for the further improvement of asphalt mixture macro-performance. However, the variations of research methods among prior works hamper the deduction of the holistic potential and promising directions of coarse aggregate distribution analysis from current research findings. This work comprehensively verified the quantifying ability of aggregate distribution state indices and their correlation with rutting performance under an advanced digital image processing technique and a wide range of asphalt mixture types, and aims to provide a reference of the holistic potential and promising directions of coarse aggregate distribution analysis for subsequent research. To this end, eleven typical asphalt mixtures’ aggregate distribution state and rutting performance were measured, quantified, and correlated. The results show that Kpe nears or more than 0.56 can be the sign of coarse aggregates effectively interlocked while it nears or less than 0.26 is the opposite; Uarea nears or less than 2 % can be the sign of reaching a coarse aggregate distribution equilibrium; Δorien approaches 6.21 can be the sign of reaching a coarse aggregate orientation equilibrium; mixtures with a nominal maximum aggregate size of 10 mm are disabled in gathering contact chains. Moreover, these coarse aggregate distribution state quantifying indices proposed in existing research can indeed describe the meso-structural features of asphalt mixtures to a certain extent. However, these indices fail to capture the underlying meso-structural features relating to rutting performance and lead to limited applicability. Furthermore, the poor performance of these coarse aggregate distribution state quantifying indices in the global fitting mainly comes from their incompatibility with changes in nominal maximum aggregate size.

Batch channel normalized-CWGAN with Swin Transformer for imbalanced data fault diagnosis of rotating machinery

Abstract In real scenarios, rotating machinery is mainly operated in optimal condition, leading to fault data scarce and difficult to collect. This issue results in imbalanced data, significantly limiting the effectiveness of intelligent fault diagnosis methods. To address this issue, a novel fault diagnosis method for rotating machinery is proposed in this paper, which combines the batch channel normalized conditional wasserstein generative adversarial network (BCN-CWGAN) with Swin Transformer. Firstly, the one-dimensional vibration signal is preprocessed into two-dimensional feature images using a symmetrized dot pattern (SDP). Subsequently, self-attention mechanism and deep feature learning module constructed by DenseNet are integrated into the generator of GAN to acquire more discriminative feature information. Meanwhile, the discriminator of GAN is combined with batch channel normalization strategy, which further enhances the generalization ability. Besides, a two time-scale update rule strategy enhances training stability and convergence speed by updating model parameters at different time scales. Then, the data augmentation capability of BCN-CWGAN is used to generate high-quality fault samples to augment the imbalanced dataset. Finally, Swin Transformer is combined to achieve accurate fault diagnosis. The performance enhancement of the proposed method is verified through comparison and diagnosis results of two engineering experiments, demonstrating its substantial value for research in engineering practice. With the proposed data augmentation method, the average accuracy of A1, B1, C1, and D1 datasets in experiment 1 reached 99.24%, 98.85%, 96.78%, and 96.04%, respectively. Meanwhile, the proposed method achieved the best accuracy in experiment 2.

A fault diagnosis method for bearings and gears in rotating machinery based on data fusion and transfer learning

Abstract Rotating machinery is a crucial component of industrial equipment, and the fault diagnosis of bearings and gears, as vital elements of rotating machinery, is essential since they often fail under harsh working conditions, leading to significant property losses and serious personal safety problems. However, fault data for gears and bearings are often sparse in actual condition, and it is a challenge to ensure the reliability and stability of fault diagnosis results by extracting the features of a single data. To solve the above problems, this paper proposes a fault diagnosis method that combines Transfer Learning and data fusion techniques. Firstly, in this method, two kinds of fault signals are transformed into Gramian Angular Difference Fields and Recurrence Plot. Next, a U-shaped feature fusion dual discriminator generative adversarial network is used to fuse two-dimensional images from multiple sensor data. Its feature fusion module deeply integrates the features of the two images, thereby solving the impact of single data on the reliability and stability of fault diagnosis. Moreover, open-source datasets are used for Transfer Learning training to tackle the small sample problem. Finally, a decision-level information fusion classifier, the Dual-Branch Dempster-Shafer Classifier (DB-DSC), classifies the fused images. This classifier incorporates an improved soft threshold function and D-S evidence theory to achieve adaptive gradient changes and improve the robustness and accuracy of classification results. The experimental results show the effectiveness and stability of the proposed method, and the generated images get high score in several metrics. The average classification accuracy of the classification network reaches 93% and 92.5% on the two datasets, Therefore, the proposed method exhibits strong fault diagnosis capabilities under the small sample conditions of bearings and gears.