Search Results (46)

Despite the enormous amounts of waste textiles produced by the world’s textile industry’s explosive growth, resource utilization rates are still poor. Cotton/polyester blended waste fabrics make up a sizable share, and sorting them precisely is essential to increasing recycling value and promoting the circular economy in the textile industry. Traditional mechanical and human sorting techniques are ineffective and inaccurate; current spectral analysis algorithms mainly concentrate on quantitative composition prediction and are insufficiently capable of differentiating between waste fabrics with comparable content gradients. To address these challenges, this paper proposes an improved 1DCNN model (Dual-1DCNN-Residual-SE) integrated with Near-Infrared (NIR) hyperspectral imaging technology. This model takes raw spectral data and Savitzky-Golay (SG) smoothing data as dual-channel inputs, introducing residual connections to capture subtle spectral differences between similar fabric categories, and employs SE attention mechanisms to adaptively enhance key features. Comparative experiments with four traditional algorithms—KNN, RF, SVM, and PLS—demonstrate that the proposed model achieves a classification accuracy of 95.94%, surpassing the best traditional algorithm SVM (88.12%) by 7.82%. Ablation experiments confirm each enhanced module’s efficacy. This study achieves high-precision classification of cotton/polyester blended waste fabrics, providing technical support for intelligent sorting of industrial waste fabrics. Full article

With the explosive growth of data across various fields, effective data preprocessing has become increasingly critical. Evolutionary and swarm intelligence algorithms have shown considerable potential in feature selection. However, their performance often deteriorates in large-scale problems, due to premature convergence and limited exploration ability. To address these limitations, this paper proposes an algorithm named IHBOFS, a biomimetics-inspired optimization framework that integrates multiple adaptive strategies to enhance performance and stability. The introduction of the Good Point Set and Elite Opposition-Based Learning mechanisms provides the population with a well-distributed and diverse initialization. Furthermore, adaptive exploitation–exploration balancing strategies are designed for each subpopulation, effectively mitigating premature convergence. Extensive ablation studies on the CEC2022 benchmark functions verify the effectiveness of these strategies. Considering the discrete nature of feature selection, IHBOFS is further extended with continuous-to-discrete mapping functions and applied to six real-world datasets. Comparative experiments against nine metaheuristic-based methods, including Harris Hawk Optimization (HHO) and Ant Colony Optimization (ACO), demonstrate that IHBOFS achieves an average classification accuracy of 92.57%, confirming its superiority and robustness in high-dimensional feature selection tasks. Full article

Carbon fiber reinforced silicon carbide (C/SiC) composite material exhibits exceptional properties, including high strength, high stiffness, low density, outstanding high-temperature performance, and corrosion resistance. Consequently, they are widely used in aerospace, defense, and automotive engineering. However, their anisotropic, high hardness, and brittle characteristics make them a typical difficult-to-machine material. This paper focuses on achieving high-quality micro hole machining of C/SiC composite material via electrical discharge machining. It systematically investigates electrical discharge machining characteristics and innovatively develops a hollow internal flow helical electrode reaming process. Experimental results reveal four typical chip morphologies: spherical, columnar, blocky, and molten. The study uncovers a multi-mechanism cutting process: the EDM ablation of the composite involves material melting and explosive vaporization, the intact extraction and fracture of carbon fibers, and the brittle fracture and spalling of the SiC matrix. Discharge energy correlates closely with surface roughness: higher energy removes more SiC, resulting in greater roughness, while lower energy concentrates on m fibers, yielding higher vaporization rates. C fiber orientation significantly impacts removal rates: processing time is shortest at θ = 90°, longest at θ = 0°, and increases as θ decreases. Typical defects such as delamination were observed between alternating 0° and 90° fiber bundles or at hole entrances. Cracks were also detected at the SiC matrix–C fiber interface. The proposed hole-enlargement process enhances chip removal efficiency through its helical structure and internal flushing, reduces abnormal discharges, mitigates micro hole taper, and thereby improves forming quality. This study provides practical references for the EDM of C/SiC composite material. Full article

In high-temperature testing scenarios that rely on contact, fine-wire thermocouples demonstrate commendable dynamic performance. Nonetheless, their thermal inertia leads to notable dynamic nonlinear inaccuracies, including response delays and amplitude reduction. To mitigate these challenges, a novel dynamic error correction approach is introduced, which combines a Continuous Restricted Boltzmann Machine, Deep Belief Network, and Physics-Informed Neural Network (CDBN-PINN). The unique heat transfer properties of the thermocouple’s bimetallic structure are represented through an Inverse Heat Conduction Equation (IHCP). An analysis is conducted to explore the connection between the analytical solution’s ill-posed nature and the thermocouple’s dynamic errors. The transient temperature response’s nonlinear characteristics are captured using CRBM-DBN. To maintain physical validity and minimize noise amplification, filtered kernel regularization is applied as a constraint within the PINN framework. This approach was tested and confirmed through laser pulse calibration on thermocouples with butt-welded and ball-welded configurations of 0.25 mm and 0.38 mm. Findings reveal that the proposed method achieved a peak relative error of merely 0.83%, superior to Tikhonov regularization by −2.2%, Wiener deconvolution by 20.40%, FBPINNs by 1.40%, and the ablation technique by 2.05%. In detonation tests, the corrected temperature peak reached 1045.7 °C, with the relative error decreasing from 77.7% to 5.1%. Additionally, this method improves response times, with the rise time in laser calibration enhanced by up to 31 ms and in explosion testing by 26 ms. By merging physical constraints with data-driven methodologies, this technique successfully corrected dynamic errors even with limited sample sizes. Full article

The inversion of shallow underground vibration fields primarily relies on signals collected by numerous sensors deployed on the surface. However, the accuracy of inversion is affected by the spatial distribution of these sensors. Therefore, under limited measurement points, signal reconstruction at unknown locations remains a critical challenge. To address this problem, we developed an SC-Net-based self-supervised interpolation method for missing wavefield data in shallow subsurface applications. This study utilizes incomplete seismic data acquired in real-world scenarios to train a neural network for seismic data interpolation, thereby expanding the sampled signals required for inversion. Since available seismic data samples are often scarce in practice, we adopt a hybrid training strategy combining simulated and real data. Specifically, a large number of numerically simulated samples are jointly trained with a limited set of real-world measurements. Furthermore, to enhance the robustness of network outputs, we integrate the Mean Teacher model framework and propose a self-supervised learning approach for missing data. Additionally, to enable the network to effectively capture long-range dependencies in both frequency and spatial domains of seismic data, we introduce a dual-branch feature fusion network that jointly models channel-wise and spatial relationships. Finally, in our actual field explosion experiments conducted at the test site, we demonstrated improved accuracy of our method through comparative analysis with several typical interpolation neural networks. Three ablation studies are also designed to demonstrate the effectiveness of the proposed approach. Full article

Aluminum powder is the most commonly used metal fuel in the industry of explosives and propellants. The research progress in preparation technology, reactivity and application of nano-aluminum in explosives and propellants is systematically reviewed in this paper. The preparation technology of nano-aluminum powder includes mechanical pulverization technology (such as the ball milling method and ultrasonic ablation method, etc.), evaporation condensation technology (such as the laser induction composite heating method, high-frequency induction method, arc method, pulsed laser ablation method, resistance heating condensation method, gas-phase pyrolysis method, wire explosion pulverization method, etc.), chemical reduction technology (such as the solid-phase reduction method, solution reduction method, etc.) and the ionic liquid electrodeposition method, each of which has its own advantages. Some new preparation methods have emerged, providing important reference value for the large-scale production of high-purity, high-quality nano-aluminum powder. The reactivity differences between nano-aluminum powder and micro-aluminum powder are compared in the thesis. It is clear that the reactivity of nano-aluminum powder is much higher than that of micro-aluminum powder in terms of ignition performance, combustion performance and reaction completeness, and it has a stronger influence on the detonation performance of mixed explosives and the combustion performance of propellants. Nano-aluminum powder is highly prone to oxidation, which seriously affects its application efficiency. In addition, when aluminum powder oxidizes or burns, a surface oxide layer will be formed, which hinders the continued reaction of internal aluminum powder. In addition, nano-aluminum powder may deteriorate the preparation process of explosives or propellants. To improve these shortcomings, appropriate coating or modification treatment is required. The application of nano-aluminum powder in mixed explosives can improve many properties of mixed explosives, such as detonation velocity, detonation heat, peak value of shock wave overpressure, etc. Applying nano-aluminum powder to propellants can significantly increase the burning rate and improve the properties of combustion products. It is pointed out that the high reactivity of nano-aluminum powder makes the preparation and storage of high-purity nano-aluminum powder extremely difficult. It is recommended to increase research on the preparation and storage technology of high-purity nano-aluminum powder. Full article

Task-oriented medical dialogue systems face two fundamental challenges: the explosion of state-action space caused by numerous diseases and symptoms and the sparsity of informative signals during interactive diagnosis. These issues significantly hinder the accuracy and efficiency of automated clinical reasoning. To address these problems, we propose MA-HRL, a multi-agent hierarchical reinforcement learning framework that decomposes the diagnostic task into specialized agents. A high-level controller coordinates symptom inquiry via multiple worker agents, each targeting a specific disease group, while a two-tier disease classifier refines diagnostic decisions through hierarchical probability reasoning. To combat sparse rewards, we design an information entropy-based reward function that encourages agents to acquire maximally informative symptoms. Additionally, medical knowledge graphs are integrated to guide decision-making and improve dialogue coherence. Experiments on the SymCat-derived SD dataset demonstrate that MA-HRL achieves substantial improvements over state-of-the-art baselines, including +7.2% diagnosis accuracy, +0.91% symptom hit rate, and +15.94% symptom recognition rate. Ablation studies further verify the effectiveness of each module. This work highlights the potential of hierarchical, knowledge-aware multi-agent systems for interpretable and scalable medical diagnosis. Full article

With the rapid development of smart devices and the Internet of Things (IoT), the explosive growth of data has placed increasingly higher demands on real-time processing and intelligent decision making. Cloud-edge collaborative computing has emerged as a mainstream architecture to address these challenges. However, in sky-ground integrated systems, the limited computing capacity of edge devices and the inconsistency between cloud-side fusion results and edge-side detection outputs significantly undermine the reliability of edge inference. To overcome these issues, this paper proposes a cloud-edge collaborative model adaptation framework that integrates deep reinforcement learning via Deep Q-Networks (DQN) with local feature transfer. The framework enables category-level dynamic decision making, allowing for selective migration of classification head parameters to achieve on-demand adaptive optimization of the edge model and enhance consistency between cloud and edge results. Extensive experiments conducted on a large-scale multi-view remote sensing aircraft detection dataset demonstrate that the proposed method significantly improves cloud-edge consistency. The detection consistency rate reaches 90%, with some scenarios approaching 100%. Ablation studies further validate the necessity of the DQN-based decision strategy, which clearly outperforms static heuristics. In the model adaptation comparison, the proposed method improves the detection precision of the A321 category from 70.30% to 71.00% and the average precision (AP) from 53.66% to 53.71%. For the A330 category, the precision increases from 32.26% to 39.62%, indicating strong adaptability across different target types. This study offers a novel and effective solution for cloud-edge model adaptation under resource-constrained conditions, enhancing both the consistency of cloud-edge fusion and the robustness of edge-side intelligent inference. Full article

With the rapid development of the Internet, the speed and scope of sudden public events disseminating in cyberspace have grown significantly. Current methods of quantifying public opinion heat often neglect emotion-driven factors and user interaction behaviors, making it difficult to accurately capture fluctuations during dissemination. To address these issues, first, this study addressed the complexity of interaction behaviors by introducing an approach that employs the information gain ratio as a weighting indicator to measure the “interaction heat” contributed by different interaction attributes during event evolution. Second, this study built on SnowNLP and expanded textual features to conduct in-depth sentiment mining of large-scale opinion texts, defining the variance of netizens’ emotional tendencies as an indicator of emotional fluctuations, thereby capturing “emotional heat”. We then integrated interactive behavior and emotional conflict assessment to achieve comprehensive heat index to quantification and dynamic evolution analysis of online public opinion heat. Subsequently, we used Hodrick–Prescott filter to separate long-term trends and short-term fluctuations, extract six key quantitative features (number of peaks, time of first peak, maximum amplitude, decay time, peak emotional conflict, and overall duration), and applied K-means clustering algorithm (K-means) to classify events into three propagation patterns, which are extreme burst, normal burst, and long-tail. Finally, this study conducted ablation experiments on critical external intervention nodes to quantify the distinct contribution of each intervention to the propagation trend by observing changes in the model’s goodness-of-fit ($R^2$) after removing different interventions. Through an empirical analysis of six representative public opinion events from 2024, this study verified the effectiveness of the proposed framework and uncovered critical characteristics of opinion dissemination, including explosiveness versus persistence, multi-round dissemination with recurring emotional fluctuations, and the interplay of multiple driving factors. Full article

Bimetals—materials composed of two metal components with dissimilar standard reduction–oxidation (redox) potentials—offer unique electronic, optical, and catalytic properties, surpassing monometallic systems. These materials exhibit not only the combined attributes of their constituent metals but also new and novel properties arising from their synergy. Although many reviews have explored the synthesis, properties, and applications of bimetallic systems, none have focused exclusively on iron (Fe)- and aluminum (Al)-based bimetals. This systematic review addresses this gap by providing a comprehensive overview of conventional and emerging techniques for Fe-based and Al-based bimetal synthesis. Specifically, this work systematically reviewed recent studies from 2014 to 2023 using the Scopus, Web of Science (WoS), and Google Scholar databases, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, and was registered under INPLASY with the registration number INPLASY202540026. Articles were excluded if they were inaccessible, non-English, review articles, conference papers, book chapters, or not directly related to the synthesis of Fe- or Al-based bimetals. Additionally, a bibliometric analysis was performed to evaluate the research trends on the synthesis of Fe-based and Al-based bimetals. Based on the 122 articles analyzed, Fe-based and Al-based bimetal synthesis methods were classified into three types: (i) physical, (ii) chemical, and (iii) biological techniques. Physical methods include mechanical alloying, radiolysis, sonochemical methods, the electrical explosion of metal wires, and magnetic field-assisted laser ablation in liquid (MF-LAL). In comparison, chemical protocols covered reduction, dealloying, supported particle methods, thermogravimetric methods, seed-mediated growth, galvanic replacement, and electrochemical synthesis. Meanwhile, biological techniques utilized plant extracts, chitosan, alginate, and cellulose-based materials as reducing agents and stabilizers during bimetal synthesis. Research works on the synthesis of Fe-based and Al-based bimetals initially declined but increased in 2018, followed by a stable trend, with 50% of the total studies conducted in the last five years. China led in the number of publications (62.3%), followed by Russia, Australia, and India, while Saudi Arabia had the highest number of citations per document (95). RSC Advances was the most active journal, publishing eight papers from 2014 to 2023, while Applied Catalysis B: Environmental had the highest number of citations per document at 203. Among the three synthesis methods, chemical techniques dominated, particularly supported particles, galvanic replacement, and chemical reduction, while biological and physical methods have started gaining interest. Iron–copper (Fe/Cu), iron–aluminum (Fe/Al), and iron–nickel (Fe/Ni) were the most commonly synthesized bimetals in the last 10 years. Finally, this work was funded by DOST-PCIEERD and DOST-ERDT. Full article

The deployment density of surface sensors can significantly impact the accuracy of subsurface shallow seismic field energy inversion. With finite budget constraints, it is often not feasible to deploy a large number of sensors, resulting in limited seismic signal acquisition that hinders accurate inversion of the shallow subsurface explosions. To address the challenge of insufficient sensor signals needed for inversion, we conducted a study on a subsurface shallow wavefield data interpolation method based on transfer learning. This method is designed to increase the overall signal acquisition by interpolating signals at target locations from limited measurement points. Our research employs neural networks to interpolate real seismic data, supplementing the sampled signals. Given the lack of extensive samples from actual data collection, we devised a training approach that combines numerically simulated signals with real collected signals. Initially, we performed conventional interpolation training using a deep interpolation network with complete synthetic gather images obtained from numerical simulations. Subsequently, the feature extraction part was frozen, and the interpolation network was transferred to real datasets, where it was trained using incomplete gather images. Finally, these incomplete gather images were re-input into the trained network to obtain interpolated results at the target locations. Our study demonstrates the superiority of our method by comparing it with two other interpolation networks and validating the effectiveness of transfer learning through four sets of ablation experiments in the actual test. This method can also be applied to other shallow geological structures to generate a large number of seismic signals for energy inversion. Full article

Aerial images are commonly used for detecting insulators in transmission lines to ensure their safe operation. However, each capture session generates thousands of insulator images, requiring manual collection, organization, and analysis. Therefore, to achieve automation in insulator state detection, this paper proposes a method based on deep learning for insulator state detection in transmission lines. Firstly, an insulator state detection model is built based on YOLOv7, and the model is improved using a bi-level routing attention mechanism and a content-aware up-sampling operator. Then, combined with dataset augmentation, including cropping, flipping, rotating, scaling, and splicing and a bounding box loss function incorporating a dynamic non-monotonic focus mechanism, 4000 visible images from different voltage levels of transmission lines are used for training. Finally, using a confusion matrix combined with comparative and ablation experiments, the results of insulator state detection are analyzed. Experimental results show that the proposed method achieves a detection accuracy of 97.1%. The detection accuracies for insulators exhibiting self-explosion, damage, flashover, and insulator strings are 93.5%, 98.6%, 97.5%, and 98.9%, respectively. Analysis results demonstrate that the proposed method can effectively realize insulator status detection. Full article

In multivariate and multistep time series prediction research, we often face the problems of insufficient spatial feature extraction and insufficient time-dependent mining of historical series data, which also brings great challenges to multivariate time series analysis and prediction. Inspired by the attention mechanism and residual module, this study proposes a multivariate time series prediction method based on a convolutional-residual gated recurrent hybrid model (CNN-DA-RGRU) with a two-layer attention mechanism to solve the multivariate time series prediction problem in these two stages. Specifically, the convolution module of the proposed model is used to extract the relational features among the sequences, and the two-layer attention mechanism can pay more attention to the relevant variables and give them higher weights to eliminate the irrelevant features, while the residual gated loop module is used to extract the time-varying features of the sequences, in which the residual block is used to achieve the direct connectivity to enhance the expressive power of the model, to solve the gradient explosion and vanishing scenarios, and to facilitate gradient propagation. Experiments were conducted on two public datasets using the proposed model to determine the model hyperparameters, and ablation experiments were conducted to verify the effectiveness of the model; by comparing it with several models, the proposed model was found to achieve good results in multivariate time series-forecasting tasks. Full article

This study proposes a method based on image segmentation for accurately identifying liquid aluminum leakage during deep well casting, which is crucial for providing early warnings and preventing potential explosions in aluminum processing. Traditional DeepLabV3+ models in this domain encounter challenges such as prolonged training duration, the requirement for abundant data, and insufficient understanding of the liquid surface characteristics of casting molds. This work presents an enhanced DeepLabV3+ method to address the restrictions and increase the accuracy of calculating liquid surface areas for casting molds. This algorithm substitutes the initial feature extraction network with ResNet-50 and integrates the CBAM attention mechanism and transfer learning techniques. The results of ablation experiments and comparative trials demonstrate that the proposed algorithm can achieve favorable segmentation performance, delivering an MIoU of 91.88%, an MPA of 96.53%, and an inference speed of 55.05 FPS. Furthermore, this study presents a technique utilizing OpenCV to accurately measure variations in the surface areas of casting molds when there are leakages of liquid aluminum. In addition, this work introduces a measurement to quantify these alterations and establish an abnormal threshold by utilizing the Interquartile Range (IQR) method. Empirical tests confirm that the threshold established in this study can accurately detect instances of liquid aluminum leakage. Full article

The Weilasituo Li–polymetallic deposit, located on the western slope of the southern Great Xing’an Range in the eastern Central Asian Orogenic Belt, is hosted by quartz porphyry with crypto-explosive breccia-type Li mineralisation atop and vein-type Sn-Mo-W-Zn polymetallic mineralisation throughout the breccia pipe. This study introduces new data on multistage quartz and mica in situ trace elements; the study was conducted using laser ablation inductively coupled plasma mass spectrometry and ⁴⁰Ar/³⁹Ar dating of zinnwaldite to delineate the metallogenic age and genesis of Li mineralisation. Zinnwaldite yields a plateau age of 132.45 ± 1.3 Ma (MSWD = 0.77), representing Early Cretaceous Li mineralisation. Throughout the magmatic–hydrothermal process, quartz trace elements showed Ge enrichment. Li, Al, and Ti contents decreased, with Al/Ti and Ge/Ti ratios increasing, indicating increased magmatic differentiation, slight acidification, and cooling. Mica’s rising Li, Rb, Cs, Mg, and Ti contents and Nb/Ta ratio, alongside its falling K/Rb ratio, indicate the magma’s ongoing crystallisation differentiation. Fractional crystallisation primarily enriched Li, Rb, and Cs in the late melt. Mica’s high Sc, V, and W contents indicate a high f_O2 setting, with a slightly lower f_O2 during zinnwaldite formation. Greisenisation observed Zn, Mg, and Fe influx from the host rock, broadening zinnwaldite distribution and forming minor Zn vein orebodies later. Late-stage fluorite precipitation highlights a rise in F levels, with fluid Sn and W levels tied to magma evolution and F content. In summary, the Weilasituo Li–polymetallic deposit was formed in an Early Cretaceous extensional environment and is closely related to a nearby highly differentiated Li-F granite. During magma differentiation, rare metal elements such as Li and Rb were enriched in residual melts. The decrease in temperature and the acidic environment led to the precipitation of Li-, Rb-, and W-bearing minerals, and the increased F content in the late stage led to Sn enrichment and mineralisation. Fluid metasomatism causes Zn, Mg, and Fe in the surrounding rock to enter the fluid, and Zn is enriched and mineralised in the later period. Full article