Search

Rolling bearings in production practice usually serve in a healthy state. Some fault state labels are scarce or even no labels, resulting in unbalanced data categories. Meanwhile, frequent working condition switching results in significant differences in data distribution among working conditions, and labeled data in some working states cannot be fully utilized. To deal with the challenge of low fault identification accuracy caused by these practical factors, this paper proposed a novel adversarial unsupervised subdomain adaption multi-channel deep convolutional network (ASMDCN). Firstly, a parallel three-channel depth feature extraction module is built, and a multi-scale convolution kernel is used to fully extract the rich features of vibration signals under various working conditions. Secondly, a novel loss function is designed to adequately consider the classification difficulty of samples and the degree of class imbalance. Finally, the adversarial training strategy is used to force the feature extractor to extract the domain invariant features, and the Local Maximum Mean discrepancy (LMMD) is used to align the global and related subdomains of the source and target domains. The experimental results show that the designed feature extraction can fully extract the domain-invariant features of the rolling bearings under different working conditions. Under the proposed objective function optimization, the network model can fully align the features of multi-source and single-target domain under unbalanced data and has strong generalization performance.

This paper studies a class of quasi-cyclic LDPC (QC-LDPC) codes, i.e., Tanner (3, 23)-regular QC-LDPC codes of code length $23p$ with $p$ being a prime and $p \equiv 1 (\mathrm {mod} 69)$ . We first analyze the cycle structure of Tanner (3, 23)-regular QC-LDPC codes, and divide their cycles of lengths 4, 6, 8, and 10 into five equivalent types. We propose the sufficient and necessary condition for the existence of these five types of cycles, i.e., the polynomial equations in a 69th unit root of the prime field $\mathbb {F}_{p}$ . We check the existence of solutions for such polynomial equations by using the Euclidean division algorithm and obtain the candidate girth values of Tanner (3, 23)-regular QC-LDPC codes. We summarize the results and determine the girth distribution of Tanner (3, 23)-regular QC-LDPC codes.

With the advancement of the wood processing industry, the demand for the detection of surface defects in wood has become increasingly urgent. The application of automated production technology has enhanced the efficiency and precision of wood processing, which can significantly impact product quality and competitiveness. However, current methods for detecting surface defects in wood suffer from issues such as low detection accuracy, high computational complexity, and poor real-time performance. In response to these challenges, this paper proposes a high-precision, lightweight, real-time wood surface defect detection method based on YOLO(GBCD-YOLO) model. Firstly, the Ghost Bottleneck is introduced to improve the computational efficiency and inference speed of deep neural networks. Furthermore, the BiFormer is incorporated in the neck to enhance the performance of natural language processing tasks. Simultaneously, CARAFE is utilized as an upsampling replacement to enhance perceptual and capture abilities for details. In addition, the Dynamic Head is introduced to enhance the method’s flexibility and generalization ability, and the loss function is replaced with complete intersection over union (CIoU). The proposed method was evaluated using an optimized dataset and the YOLOv5s model was chosen as the baseline. The experimental results show that compared with the original YOLOv5s, the mAP (0.5) has been improved by 13.45%, reaching 88.72%. The mAP (0.5:0.95) increased by 11.95%, and FPS increased by 6.25%. In addition, the parameter of the improved model has been reduced by 15.49%. These results indicate that the proposed GBCD-YOLO improves the real-time detection performance of wood surface defects.

The increasing integration of distributed household photovoltaics (PVs) and electric vehicles (EVs) may further aggravate voltage violations and unbalance of low-voltage distribution networks (LVDNs). DC distribution networks can increase the accommodation of PVs and EVs and mitigate mutilple power quality problems by the flexible power regulation capability of voltage source converters. This paper proposes schemes to establish hybrid AC/DC LVDNs considering the conversion of the existing three-phase four-wire low-voltage AC systems to DC operation. The characteristics and DC conversion constraints of typical LVDNs are analyzed. In addition, converter configurations for typical LVDNs are proposed based on the three-phase four-wire characteristics and quantitative analysis of various DC configurations. Moreover, an optimal planning method of hybrid AC/DC LVDNs is proposed, which is modeled as a bi-level programming model considering the annual investments and three-phase unbalance. Simulations are conducted to verify the effectiveness of the proposed optimal planning method. Simulation results show that the proposed optimal planning method can increase the integration of PVs while simultaneously reducing issues related to voltage violation and unbalance.

This study explores the consensus of multi-agent systems in the presence of ambient noise using intermittent Brownian noise stabilization. Firstly, the research provides a mathematical explanation of multi-agent systems and intermittent stochastic noise, and establishes a sufficient condition for multi-agent systems to achieve consensus using intermittent stochastic noise control input. Secondly, a consensus criterion is proposed for a class of multi-agent systems that are affected by ambient noise. Finally, the simulation results demonstrate that the intermittent stochastic noise stabilization technique can facilitate the establishment of consensus in multi-agent systems.

Accurately classifying tree species in urban forests remains a major challenge due to the limitations of existing methods. While hyperspectral imaging is capable of capturing detailed spectral information, it struggles with the issue of ‘similar reflectance curves for different species’. On the other hand, the intensity frequency curve also has the problem of ‘similar intensity frequency curves for different species’. To overcome these challenges, a new method is proposed in this study. The method combines UAV LiDAR intensity frequency features (IF) and hyperspectral features (HF) to accurately identify tree species, abbreviated as HICM. The results of the study demonstrate that HICM can accurately identify 16 common urban tree species with an overall accuracy (OA) of 92.0% and kappa of 91.2%. Compared with using only IF or HF for identification, HICM improves OA by 16.9% and 12%, and kappa by 21.6% and 10.1%, respectively. This shows that HF and IF have complementarity, and the combination of these two features effectively addresses the problems of “same species different frequency” and “same species different spectrum”.

NASA's (National Aeronautics and Space Administration) ICESat-2 with a Photon Counting LiDAR (Light Detection And Ranging) Sensor sensitively detects signal photons at high speed with an advanced detection system called the Advanced Topographic Laser Altimeter System (ATLAS). However, the sensor also extracts a large amount of background photon noise coming from the atmosphere, ground, sun, or other radiation. This condition is particularly evident in forest areas. This study proposes an automatic machine learning approach to utilize data for forestry applications to improve data availability compared to NASA's official product. Our method uses only a very limited number (10%) of sample points for training, ensuring operational efficiency and training accuracy. We conclude that the integrated learning performance generally outperforms single models, and the mean F1 score of all tests is approximately 0.9. The mean F1 score of the Stacked Ensembles model is 0.957 ahead of the other models. The top three variables used in training models are kNNdist5, kNNdist10, and h. These three variables could explain 51.6% of the components of the models. Over the regions tested, the proposed method could improve the proportion of signals correctly identified by 6.4%, 12.2%, 2.7%, 9.3%, and 1.4% in five datasets. The model performs better in low signal-to-noise (SNR) datasets less than 7.5. The method would be largely unaffected by differences in topography, noise distribution, and SNR. The classifiers could correct misclassified labels in ATL08 products and show good stability in different conditions.

Internal discharges in composite insulators often cause abnormal heating, interface failure and erosion of the core rod. However, the mechanism and the exact process of the degradation of HTV shed and FRP core rod caused by internal discharges are still unclear. In this work, abnormal heating insulator samples are taken from an AC 500 kV extra-high voltage (EHV) transmission line. Macro- and micro-scopic morphological observation, hardness tests, industrial CT tests and chemical property tests are applied on the samples. The cause of heating and the deterioration mechanism of each part of insulators is further explored. Cavities and air holes are found in the HTV skirts in this batch of insulators, which are generated during manufacturing. These cavities lead to the distortion of electrical field and become the origin of the discharges. Decomposition of polydimethylsiloxane leads to the hardening and chalking of the HTV shed. It is also found that the adhesive in the rod-housing interface fails during operation. Epoxy resin in core rod decomposes in a multi-factor aging environment, leading to the decay-like aging of the core rod surface. As the aging progress develops inward, the insulator will eventually lose its mechanical properties. It is inferred that the internal discharge is the main reason of heating and deterioration of composite insulators. Moreover, long-term discharge will lead to the decay-like aging of core rods.

The soybean futures market in China occupies an important position in the agricultural product futures market. The research on the fluctuation of soybean futures price and the prediction of the future price trend has always been the focus of extensive attention in the field of agricultural economics. This paper proposes an EEMD-NAGU hybrid prediction model for soybean futures price based on Ensemble Empirical Mode Decomposition (EEMD) and New Attention Gate Unit (NAGU). The model first uses EEMD to process soybean futures price data into multiple Intrinsic Mode Functions (IMFs) and residual sequence. Then calculates the sample entropy of each IMF and reconstructed the IMF into three components of low-frequency, medium-frequency, and high-frequency, according to the size of the sample entropy. NAGU is formed by embedding the Attention mechanism (Attention) into the Gate Recurrent Unit (GRU) structure, further improving the learning capability of the model. NAGU splits the original reset gate and update gate, sets up two-stage respectively, and uses different activation functions to capture the information in historical data better. Soybean futures price data is complex nonlinearities and contain more noise. In this model, EEMD plays denoises the time series data and fixes the model input. NAGU can perform differential learning on data and finally produce prediction results. EEMD-NAGU is compared with thirteen other prediction models (Support Vector Regression (SVR), LSTM, GRU, NAGU, EEMD-LSTM, EEMD-GRU, EEMD-NGU, Attention-LSTM, Attention-GRU, Attention-NGU, EEMD-Attention-LSTM, EEMD-Attention-GRU, and EEMD-Attention-NGU). The evaluation indexes of the experiment are Mean Absolute Error (MAE), Mean Square Error (MSE), and R Squared ( $R^{2}$ ). The experimental results show that the EEMD-NAGU model outperforms other models with better prediction performance. The model can be widely used to predict the price of wheat, corn, gold, oil, and other time series data.

Background and objective: Significant variability in the quality of healthcare supplied by hospitals is drawing broad attention from the United States Centers for Medicare and Medicaid Services. The primary issue is to evaluate hospital performance based on patient outcomes. Generalized linear random-effects models are a promising analytical tool for evaluating hospital performance. However, hospital compare data often violate the classical assumptions of normality on random effects and linearity representation on transformed conditional mean structures in these models. Methods: In this article, we proposed and tested the performance of a class of hospital compare models that embraces nonparametric mean structures with semi-nonparametric hospital random effects. Such models were further improved and integrated into a zero-inflated model. $\mathtt {SAS}$ programs to implement these newly proposed hospital compare models were thoroughly developed. The $\mathtt {SAS}$ programs are freely available via a GitHub (https:\\www.GitHub.com) repository. Results: We demonstrate the robustness of the proposed hospital compare models by conducting intensive empirical studies. Flexible semi-nonparametric random effects and functional fixed-effects mean structure were used to analyze patient mortality in a large-scale intensive care unit data set. After applying the proposed models to assess standardized modality rates and address patient-mix variability across hospitals, we detected those underperforming hospitals with higher mortality rates. Conclusions: Our research findings highlight how constructing advanced assessment tools for hospital performance could support better decision-making at the administrative and public levels. The proposed hospital compare models are comprehensive in their capacity to identify patterns of hospital random effects and to convey the variability in healthcare quality with powerful accuracy and interpretability.

Electric power fittings are the link between conductors and transmission towers, and it is essential to improve their ability to withstand damage. To obtain the actual load of electric power fittings and study the stress of each electric power fitting under the actual load, a transmission line model of catenary-shaped and an integral model of tension insulator string are established in this paper. Then, conductors with a uniform thickness of ice coating and ice shedding process are simulated by changing density method. The results show that the maximum dynamic tension of the conductor of the isolated span transmission line is greater than the static tension of conductor icing only when the length of the ice-shedding section is small. Under any ice-shedding condition, the maximum dynamic tension of the conductor of the multi-span transmission line will be close to or greater than the static tension after conductor icing. When the form conductor tension is loaded on the tension insulator string, it can be found that the most dangerous fitting in the tension insulator string is found, and the stress analysis is carried out on the key connecting fittings, which provides a reference for the design and optimization of electric power fitting.

Aimed at solving the problems of frequent handover and large overheads for positioning in 6G, this paper proposes a reinforcement learning (RL)-based visible light positioning (VLP) handover scheme by means of a stereo camera system in which a lower handover rate and higher positioning accuracy were achieved simultaneously. Because of the randomness of the distribution location of indoor light sources and obstacles, even if the parameters of light sources and receivers are consistent, users cannot rely on unitary and invariable parameters to determine whether to change the access point (AP) in the process of moving, especially in some special locations. The proposed scheme, which decomposed the user’s moving track at different speeds in a VLP system to optimize selecting the AP by using RL at each step, was exhibited and tested. Experimental results show that the proposed scheme achieved millimeter-level positioning accuracy, improved the normalized reward by over 40% and reduced the handover rate by 87% and 78% compared to the immediate handover (IHO) and dwell handover (DHO) methods concurrently.

3D reconstruction is the transformation of real objects into mathematical models. By using 3D models, we can observe the shape and measure the parameters, and help us to analyze the properties of objects. For the problems of incompleteness and inefficiency in the reconstruction of object 3D point clouds, a fast and automated system for panoramic 3D point cloud reconstruction of objects was proposed. First, we designed an automatic platform, which could acquire RGB image sequences of objects in two directions. Then we adopted the Structure From Motion (SFM) algorithm to generate point clouds. For the problem of different scales of point clouds, we obtained the scaling by calculating the length ratio of the axes of the oriented bounding box, and scaled the point clouds to a uniform scale. In addition, markers were placed around the object and used to acquire the rotation matrix of the object point cloud in two directions. Finally, we verified the point cloud models of different objects generated by the system, and found that the relative error didn’t exceed 6.67%. According to the results, the system proposed could reconstruct the panoramic 3D point cloud of the object better and provide a reference for related research.

Based on a developed three-layerair–ice–water reflection model, this article simulates the evolution of reflection coefficient versus elevation angle. Due to the interference between the signal components from the air–ice and ice–water interfaces, the reflection coefficient experiences an oscillating pattern versus elevation angle so that detecting sea ice using the power or amplitude of the reflected global navigation satellite system (GNSS) signal has to choose a suitable satellite to reduce the influence of the oscillating pattern. A sea ice surface is more stable and presents higher correlation than a dynamic ocean surface, this article explores the potential of detecting and measuring sea ice using the coherency of reflected GNSS signal for coastal scenario. Experimental results show that phase coherency can significantly detect sea ice without strictly limiting elevation and azimuth angle. This article also is to is to explore the potential of retrieving sea ice thickness using the oscillating phase pattern versus elevation angle. The phase compensation and the dual-polarization observation are proposed to remove the delay phase between the direct and reflected signal from the estimated phase of the reflected GNSS signal. The results show that the amplitude and frequency of the oscillating phase pattern, respectively, have an inversely proportional and positively linear relationship with sea ice thickness. Simulation shows that, compared to the oscillating amplitude, the oscillating frequency is a better choice to measure sea ice thickness. The frequency of the dual-polarization oscillating pattern could provide the measurement performance with a root-mean-square error of 0.05 m.

Remote sensing images acquired by the FY4 satellite are crucial for regional cloud monitoring and meteorological services. Inspired by the success of deep learning networks in image super-resolution, we applied image super-resolution to FY4 visible spectrum (VIS) images. However, training a robust network directly for FY4 VIS image super-resolution remains challenging due to the limited provision of high resolution FY4 sample data. Here, we propose a super-resolution and transfer learning model, FY4-SR-Net. It is composed of pretraining and fine-tuning models. The pretraining model was developed using a deep residual network and a large number of FY4 A 4 and 1 km resolution VIS images as the training data. The knowledge derived from 4 km to 1 km resolution images was incorporated into FY4 B 1 km to 0.25 km resolution VIS images. The FY4-SR-Net is fine-tuned by incorporating limited 1 km and 0.25 km resolution panchromatic images, and then producing 1km super-resolution VIS images of the FY4 satellite. Using the one-day FY4 test dataset for qualitative and quantitative evaluations, the FY4-SR-Net outperformed the classic bicubic interpolation approach with a 16.12% reduction in root-mean-square error and a 2.97% rise in peak signal-to-noise ratio averages. The structural similarity value average increased by 0.0026. This article provides a new precedent for improving the spatial resolution of FY4 series meteorological satellites, which has important scientific significance and application properties.

Few-shot object detection (FSOD) aims to localize and recognize potential objects of interest only by using a few annotated data, and it is beneficial for remote sensing images (RSIs) based applications, such as urban monitoring. Previous RSIs-based FSOD works often try to convert the support images from class-agnostic features to class-specific vectors, and then perform feature attention operations on query image features to be tested. However, such methods still face two critical challenges: 1) They ignore the spatial similarity of support-query features, which is indispensable for RSIs detection; 2) They perform the feature attention operation in a unidirectional manner, which means that the learned support-query relations are asymmetric. In this article, to address the challenges above, we design a few-shot object detector, which can quickly and accurately generalize to unseen categories with only a small amount of data. The proposed approach contains two components: 1) the self-adaptive global similarity module that preserves the internal context information to calculate the similarity map between the objects in support and query images, and 2) the two-way foreground stimulator module that can apply the similarity map to the detailed embeddings of support and query images at the same time to make full use of support information, further strengthening the foreground objects and weakening the unconcerned samples. Experiments are conducted on DIOR and NWPU VHR-10 datasets and their results demonstrate the superiority of the proposed method compared with several state-of-the-art methods.

The Y field of view of an off-axis optical system is generally less than 1°. Scholars usually use a freeform surface to achieve a rectangular field of view imaging. However, it adds to the difficulty of processing, testing, assembling, and adjusting, and at the same time has the drawbacks of high manufacturing costs and long processing cycles. In view of the above problems, this paper presents a computational imaging design method for expanding the Y field of view of an off-axis optical system. This method analyzes the aberration characteristics of the optical system, creates a point spread function model based on the wavefront aberration theory and Zernike polynomials, and processes images using a spatial variation deconvolution algorithm. In this paper, we used this method to simulate an off-axis three-mirror optical system with a focal length of 260 mm, the f-number of 2.5, and a field of view of 8° × 1° and compare the images before and after processing. The results show that the processed images have a clear outline, the overall image quality is improved, the field of view is improved to 8° × 6°, and the modulation transfer function of the entire field of view is above 0.4. The off-axis optical system rectangular field of view imaging is realized without using a freeform surface.

A GaN Reverse-Conducting HEMT (RC-HEMT) is proposed and fabricated on the GaN/AlGaN/GaN platform. It features an integrated Schottky barrier diode (SBD) to realize reverse conduction and the double-heterojunction to enhance breakdown voltage (BV). Compared with the inherent reverse conduction capability of the conventional HEMT (Con. HEMT), the built-in SBD exhibits a low reverse turn-on voltage ( $V_{\text{RT}}$ ) and its $V_{\text{RT}}$ is independent of the threshold voltage and gate bias. At the off-state, the fixed positive and negative polarization charges form the polarization superjunction (PSJ). Therefore, the depletion region is extended and more uniform E-field distribution is obtained. Experimental results show that the RC-PSJ-HEMT achieves a low $V_{\text{RT}}$ of 0.68 V, which decreases 69.1% compared with that of the Con. HEMT. The BV of the RC-PSJ-HEMT (with $7.5 \mu \text{m}$ $V_{\text{GD}}$ ) is increased to 723 V from 202 V of the Con. HEMT.