Feature selection serves as a critical preprocessing step inmachine learning,focusing on identifying and preserving the most relevant features to improve the efficiency and performance of classification algorithms.Par...Feature selection serves as a critical preprocessing step inmachine learning,focusing on identifying and preserving the most relevant features to improve the efficiency and performance of classification algorithms.Particle Swarm Optimization has demonstrated significant potential in addressing feature selection challenges.However,there are inherent limitations in Particle Swarm Optimization,such as the delicate balance between exploration and exploitation,susceptibility to local optima,and suboptimal convergence rates,hinder its performance.To tackle these issues,this study introduces a novel Leveraged Opposition-Based Learning method within Fitness Landscape Particle Swarm Optimization,tailored for wrapper-based feature selection.The proposed approach integrates:(1)a fitness-landscape adaptive strategy to dynamically balance exploration and exploitation,(2)the lever principle within Opposition-Based Learning to improve search efficiency,and(3)a Local Selection and Re-optimization mechanism combined with random perturbation to expedite convergence and enhance the quality of the optimal feature subset.The effectiveness of is rigorously evaluated on 24 benchmark datasets and compared against 13 advancedmetaheuristic algorithms.Experimental results demonstrate that the proposed method outperforms the compared algorithms in classification accuracy on over half of the datasets,whilst also significantly reducing the number of selected features.These findings demonstrate its effectiveness and robustness in feature selection tasks.展开更多
Image registration within a solar photosphere sequence is crucial for observational solar physics studies requiring high spatial and temporal resolutions.Previously,we identified residual large-scale nonrigid distorti...Image registration within a solar photosphere sequence is crucial for observational solar physics studies requiring high spatial and temporal resolutions.Previously,we identified residual large-scale nonrigid distortions in high-resolution solar photosphere images from ground-based telescopes after high-resolution reconstruction.Because these distortions are not eliminated by conventional sequence correlation alignment,they can affect the analysis of small-scale activity in the solar photosphere.Here,we implemented an image registration model using deep learning(HCAM-Net)to solve the problem.Within an encoder-decoder framework,we introduced a hybrid attention mechanism to improve context information capture and extract accurate deformation fields.Analyzing solar photosphere images acquired by the New Vacuum Solar Telescope,we demonstrated that the proposed model effectively achieved highly accurate nonrigid image registration.Evaluation metrics and visualization results indicated that our model outperformed current state-of-the-art models,such as VoxelMorph and TransMorph,for nonrigid registration of solar photosphere images,with a structural similarity index measure of 0.965 and a coefficient of determination of 0.976.展开更多
Unmanned Aerial Vehicle(UAV)assisted federated learning enables on-edge model training,but its effectiveness depends on sustainable client participation through well-designed incentive mechanisms.Existing approaches b...Unmanned Aerial Vehicle(UAV)assisted federated learning enables on-edge model training,but its effectiveness depends on sustainable client participation through well-designed incentive mechanisms.Existing approaches based on economic models provide theoretical guarantees under restrictive assumptions,while Reinforcement Learning(RL)methods adapt to dynamics but lack provable incentive compatibility.We propose an adaptive privacy-aware incentive mechanism that integrates contract theory with Multi-Agent RL(MARL).The contract design provides a truthful initialization under privacy heterogeneity,while MARL adaptively refines incentives in dynamic environments.An Incentive Compatibility(IC)regularized optimization further ensures policy convergence and robustness.Experiments in UAV-assisted FL show that our method improves social welfare by up to 35%and participant engagement by 45%over state-of-the-art baselines,while maintaining strong privacy guarantees.展开更多
The flying foxes optimization(FFO)algorithm,as a newly introduced metaheuristic algorithm,is inspired by the survival tactics of flying foxes in heat wave environments.FFO preferentially selects the best-performing in...The flying foxes optimization(FFO)algorithm,as a newly introduced metaheuristic algorithm,is inspired by the survival tactics of flying foxes in heat wave environments.FFO preferentially selects the best-performing individuals.This tendency will cause the newly generated solution to remain closely tied to the candidate optimal in the search area.To address this issue,the paper introduces an opposition-based learning-based search mechanism for FFO algorithm(IFFO).Firstly,this paper introduces niching techniques to improve the survival list method,which not only focuses on the adaptability of individuals but also considers the population’s crowding degree to enhance the global search capability.Secondly,an initialization strategy of opposition-based learning is used to perturb the initial population and elevate its quality.Finally,to verify the superiority of the improved search mechanism,IFFO,FFO and the cutting-edge metaheuristic algorithms are compared and analyzed using a set of test functions.The results prove that compared with other algorithms,IFFO is characterized by its rapid convergence,precise results and robust stability.展开更多
Lithium-ion batteries(LIBs)are widely deployed,from grid-scale storage to electric vehicles.LIBs remain stationary most of their service life,where calendar aging degrades capacity.Understanding the mechanisms of LIB ...Lithium-ion batteries(LIBs)are widely deployed,from grid-scale storage to electric vehicles.LIBs remain stationary most of their service life,where calendar aging degrades capacity.Understanding the mechanisms of LIB calendar aging is crucial for extending battery lifespan.However,LIB calendar aging is influenced by multiple factors,including battery material,its state,and storage environment.Calendar aging experiments are also time-consuming,costly,and lack standardized testing conditions.This study employs a data-driven approach to establish a cross-scale database linking materials,side-reaction mechanisms,and calendar aging of LIBs.MELODI(Mechanism-informed,Explainable,Learning-based Optimization for Degradation Identification)is proposed to identify calendar aging mechanisms and quantify the effects of multi-scale factors.Results reveal that cathode material loss drives up to 91.42%of calendar aging degradation in high-nickel(Ni)batteries,while solid electrolyte interphase growth dominates in lithium iron phosphate(LFP)and low-Ni batteries,contributing up to 82.43%of degradation in LFP batteries and 99.10%of decay in low-Ni batteries,respectively.This study systematically quantifies calendar aging in commercial LIBs under varying materials,states of charge,and temperatures.These findings offer quantitative guidance for experimental design or battery use,and implications for emerging applications like aerial robotics,vehicle-to-grid,and embodied intelligence systems.展开更多
Slug flow represents one of the most critical and operationally challenging regimes in oil-gas-water multiphase pipelines.To advance both mechanistic understanding and predictive capability,this study integrates physi...Slug flow represents one of the most critical and operationally challenging regimes in oil-gas-water multiphase pipelines.To advance both mechanistic understanding and predictive capability,this study integrates physical analysis with data-driven modeling to elucidate the conditions governing slug formation and to enable its rapid and accurate prediction.A systematic review of existing research is first undertaken to clarify the mechanisms responsible for slug initiation.The influences of gas superficial velocity,liquid velocity,liquid viscosity,liquid surface tension,and the axial component of gravity are examined to characterize their roles in interfacial instability and flow transition.Then,the effects of temperature,total flow rate,water cut,gas-liquid ratio,and pipeline inclination angle are quantitatively assessed,revealing the dominant trends that promote or inhibit slug development.Building on this foundation,a comprehensive three-phase oil-gas-water flow model is constructed.Numerical simulations are performed for 243 operating conditions encompassing a broad range of temperatures,water cuts,gas-liquid ratios,liquid flow rates,and inclination angles.These simulated cases constitute the training dataset for nine machine learning algorithms.To evaluate generalization performance,108 additional randomly generated operating conditions are predicted,covering temperatures of 80–150◦C,water cuts of 40–90%,gas-liquid ratios of 3–30,liquid flow rates of 100–200 t/d,and inclination angles of 5–15.Comparative validation reveals marked differences in predictive accuracy.The BP neural network achieves the highest accuracy,95%,substantially outperforming XGBoost,83.3%,Random Forest and Decision Tree,81.5%,Logistic Regression and Support Vector Machine,80.6%,K-Nearest Neighbor and Naive Bayes 78.7%,and K-Means,63%.Overall,the BP neural network demonstrates superior robustness and precision in predicting previously unseen operating conditions,effectively combining the physical consistency of mechanistic modeling with the efficiency and adaptability of machine learning approaches.展开更多
To investigate the complex relationship between rolling process parameters and mechanical properties of AZ31 magnesium alloy rolled sheets,the Leave-One-Out Cross-Validation(LOOCV)and parameter tuning were applied to ...To investigate the complex relationship between rolling process parameters and mechanical properties of AZ31 magnesium alloy rolled sheets,the Leave-One-Out Cross-Validation(LOOCV)and parameter tuning were applied to optimizing hyper-parameters for the four(BPNN,SVR,RF,and KNN)machine learning models.An interpretable prediction model based on machine learning and SHapley Additive exPlanations(SHAP),as well as an analytical method combining the SHAP model and the Pearson Correlation Coefficient(PCC),were proposed.The results showed that among the four models,the SVR model was able to simultaneously and accurately predict the ultimate tensile strength(UTS)and elongation(EL).According to the combination analysis of PCC and the magnesium alloy rolling forming mechanism,it was found that strain rate and reduction displayed a negative and positive correlation with UTS,respectively,while rolling temperature and reduction illustrated a positive and negative correlation with EL,respectively.Through the SHAP method,which could interpret the output results of the SVR machine learning model,it was deduced that reduction and strain rate played an important role in the SVR model of the outputs of the UTS and EL,respectively.Combining SHAP with PCC,it was found that strain rate and reduction had a greater influence on the UTS than rolling temperature,whereas strain rate and rolling temperature had more influence on the EL compared to reduction.展开更多
The distributed permutation flow shop scheduling problem(DPFSP)has received increasing attention in recent years.The iterated greedy algorithm(IGA)serves as a powerful optimizer for addressing such a problem because o...The distributed permutation flow shop scheduling problem(DPFSP)has received increasing attention in recent years.The iterated greedy algorithm(IGA)serves as a powerful optimizer for addressing such a problem because of its straightforward,single-solution evolution framework.However,a potential draw-back of IGA is the lack of utilization of historical information,which could lead to an imbalance between exploration and exploitation,especially in large-scale DPFSPs.As a consequence,this paper develops an IGA with memory and learning mechanisms(MLIGA)to efficiently solve the DPFSP targeted at the mini-malmakespan.InMLIGA,we incorporate a memory mechanism to make a more informed selection of the initial solution at each stage of the search,by extending,reconstructing,and reinforcing the information from previous solutions.In addition,we design a twolayer cooperative reinforcement learning approach to intelligently determine the key parameters of IGA and the operations of the memory mechanism.Meanwhile,to ensure that the experience generated by each perturbation operator is fully learned and to reduce the prior parameters of MLIGA,a probability curve-based acceptance criterion is proposed by combining a cube root function with custom rules.At last,a discrete adaptive learning rate is employed to enhance the stability of the memory and learningmechanisms.Complete ablation experiments are utilized to verify the effectiveness of the memory mechanism,and the results show that this mechanism is capable of improving the performance of IGA to a large extent.Furthermore,through comparative experiments involving MLIGA and five state-of-the-art algorithms on 720 benchmarks,we have discovered that MLI-GA demonstrates significant potential for solving large-scale DPFSPs.This indicates that MLIGA is well-suited for real-world distributed flow shop scheduling.展开更多
As one of the most seismically active regions,Sichuan Basin is a key area of seismological studies in China.This study applies a neural network model with attention mechanisms,simultaneously picking the P-wave arrival...As one of the most seismically active regions,Sichuan Basin is a key area of seismological studies in China.This study applies a neural network model with attention mechanisms,simultaneously picking the P-wave arrival times and determining the first-motion polarity.The polarity information is subsequently used to derive source focal mechanisms.The model is trained and tested using small to moderate earthquake data from June to December 2019 in Sichuan.We apply the trained model to predict first-motion polarity directions of earthquake recordings in Sichuan from January to May 2019,and then derive focal mechanism solutions using HASH algorithm with predicted results.Compared with the source mechanism solutions obtained by manual processing,the deep learning method picks more polarities from smaller events,resulting in more focal mechanism solutions.The catalog documents focal mechanism solutions of 22 events(M_(L) 2.6–4.8)from analysts during this period,whereas we obtain focal mechanism solutions of 53 events(M_(L) 1.9–4.8)through the deep learning method.The derived focal mechanism solutions for the same events are consistent with the manual solutions.This method provides an efficient way for the source mechanism inversion of small to moderate earthquakes in Sichuan region,with high stability and reliability.展开更多
Microseismic monitoring technology is widely used in tunnel and coal mine safety production.For signals generated by ultra-weak microseismic events,traditional sensors encounter limitations in terms of detection sensi...Microseismic monitoring technology is widely used in tunnel and coal mine safety production.For signals generated by ultra-weak microseismic events,traditional sensors encounter limitations in terms of detection sensitivity.Given the complex engineering environment,automatic multi-classification of microseismic data is highly required.In this study,we use acceleration sensors to collect signals and combine the improved Visual Geometry Group with a convolutional block attention module to obtain a new network structure,termed CNN_BAM,for automatic classification and identification of microseismic events.We use the dataset collected from the Hanjiang-to-Weihe River Diversion Project to train and validate the network model.Results show that the CNN_BAM model exhibits good feature extraction ability,achieving a recognition accuracy of 99.29%,surpassing all its counterparts.The stability and accuracy of the classification algorithm improve remarkably.In addition,through fine-tuning and migration to the Pan Ⅱ Mine Project,the network demonstrates reliable generalization performance.This outcome reflects its adaptability across different projects and promising application prospects.展开更多
As the group-buying model shows significant progress in attracting new users,enhancing user engagement,and increasing platform profitability,providing personalized recommendations for group-buying users has emerged as...As the group-buying model shows significant progress in attracting new users,enhancing user engagement,and increasing platform profitability,providing personalized recommendations for group-buying users has emerged as a new challenge in the field of recommendation systems.This paper introduces a group-buying recommendation model based on multi-head attention mechanisms and multi-task learning,termed the Multi-head Attention Mechanisms and Multi-task Learning Group-Buying Recommendation(MAMGBR)model,specifically designed to optimize group-buying recommendations on e-commerce platforms.The core dataset of this study comes from the Chinese maternal and infant e-commerce platform“Beibei,”encompassing approximately 430,000 successful groupbuying actions and over 120,000 users.Themodel focuses on twomain tasks:recommending items for group organizers(Task Ⅰ)and recommending participants for a given group-buying event(Task Ⅱ).In model evaluation,MAMGBR achieves an MRR@10 of 0.7696 for Task I,marking a 20.23%improvement over baseline models.Furthermore,in Task II,where complex interaction patterns prevail,MAMGBR utilizes auxiliary loss functions to effectively model the multifaceted roles of users,items,and participants,leading to a 24.08%increase in MRR@100 under a 1:99 sample ratio.Experimental results show that compared to benchmark models,such as NGCF and EATNN,MAMGBR’s integration ofmulti-head attentionmechanisms,expert networks,and gating mechanisms enables more accurate modeling of user preferences and social associations within group-buying scenarios,significantly enhancing recommendation accuracy and platform group-buying success rates.展开更多
The growing demand for carbon neutrality has heightened the focus on CO_(2)hydrogenation as a viable strategy for transforming carbon dioxide into valuable chemicals and fuels.Advanced machine learning(ML)approaches i...The growing demand for carbon neutrality has heightened the focus on CO_(2)hydrogenation as a viable strategy for transforming carbon dioxide into valuable chemicals and fuels.Advanced machine learning(ML)approaches integrate materials science with artificial intelligence,enabling scientists to identify hidden patterns in datasets,make informed decisions,and reduce the need for labor-intensive,repetitive experimentation.This review provides a comprehensive overview of ML applications in the thermocatalytic hydrogenation of CO_(2).Following an introduction to ML tools and workflows,various ML algorithms employed in CO_(2)hydrogenation are systematically categorized and reviewed.Next,the application of ML in catalyst discovery is discussed,highlighting its role in identifying optimal compositions and structures.Then,ML-driven strategies for process optimization,particularly in enhancing CO_(2)conversion and product selectivity,are examined.Studies modeling descriptors,spanning catalyst properties and reaction conditions,to predict catalytic performance are analyzed.Consequently,ML-based mechanistic studies are reviewed to elucidate reaction pathways,identify key intermediates,and optimize catalyst performance.Finally,key challenges and future perspectives in leveraging ML for advancing CO_(2)hydrogenation research are presented.展开更多
Various and intricate varieties of lung disease have made it challenging for computer aided diagnosis to appropriately segment lung lesions utilizing computed tomography(CT)images.This study integrates transfer learni...Various and intricate varieties of lung disease have made it challenging for computer aided diagnosis to appropriately segment lung lesions utilizing computed tomography(CT)images.This study integrates transfer learning with the attention mechanism to construct a deep learning model that can automatically detect new coronary pneumonia on lung CT images.In this study,using VGG16 pre-trained by ImageNet as the encoder,the decoder was established utilizing the U-Net structure.The attention module is incorporated during each concatenate procedure,permitting the model to concentrate on the critical information and identify the crucial components efficiently.The public COVID-19-CT-Seg-Benchmark dataset was utilized for experiments,and the highest scores for Dice,F1,and Accuracy were 0.9071,0.9076,and 0.9965,respectively.The generalization performance was assessed concurrently,with performance metrics including Dice,F1,and Accuracy over 0.8.The experimental findings indicate the feasibility of the segmentation network proposed in this study.展开更多
The hot deformation behavior of magnesium(Mg)alloys is significantly governed by the multi-physics coupling effects of temperature(T),strain rate(ε)and strain(ε),resulting in flow behavior that exhibits pronounced n...The hot deformation behavior of magnesium(Mg)alloys is significantly governed by the multi-physics coupling effects of temperature(T),strain rate(ε)and strain(ε),resulting in flow behavior that exhibits pronounced nonlinearity and multi-scale complexity.This study systematically investigates the hot deformation behavior of Mg-Y-Nd-(Sm)-Zr alloys.Sm alloying promotes recrystallization.The flow stress of Sm-containing alloys declines sharply towards a steady state after reaching its peak value.To overcome the limitations of the Arrhenius-type constitutive(AC)model in predicting complex nonlinear flow behavior,the AC and data hybrid informed neural network(ACINN)model is developed.This approach enhances the predictive accuracy and extends the applicability of the traditional AC model.The evolution of microstructure and recrystallization behavior under hot deformation conditions are investigated based on results from electron backscatter diffraction(EBSD)and transmission electron microscopy(TEM).The relationship between the power dissipation factor(η)and recrystallization behavior is further examined using K-means clustering analysis.The results demonstrate that dynamic recrystallization(DRX)behavior varies with theηvalue,comprising four distinct regimes:dynamic recovery(DRV),discontinuous dynamic recrystallization(DDRX)dominance,continuous dynamic recrystallization(CDRX)dominance and complete dynamic recrystallization.This analysis presents a new perspective for studying the hot deformation processes of Mg alloys.展开更多
The rapid growth of Internet of things devices and the emergence of rapidly evolving network threats have made traditional security assessment methods inadequate.Federated learning offers a promising solution to exped...The rapid growth of Internet of things devices and the emergence of rapidly evolving network threats have made traditional security assessment methods inadequate.Federated learning offers a promising solution to expedite the training of security assessment models.However,ensuring the trustworthiness and robustness of federated learning under multi-party collaboration scenarios remains a challenge.To address these issues,this study proposes a shard aggregation network structure and a malicious node detection mechanism,along with improvements to the federated learning training process.First,we extract the data features of the participants by using spectral clustering methods combined with a Gaussian kernel function.Then,we introduce a multi-objective decision-making approach that combines data distribution consistency,consensus communication overhead,and consensus result reliability in order to determine the final network sharing scheme.Finally,by integrating the federated learning aggregation process with the malicious node detection mechanism,we improve the traditional decentralized learning process.Our proposed ShardFed algorithm outperforms conventional classification algorithms and state-of-the-art machine learning methods like FedProx and FedCurv in convergence speed,robustness against data interference,and adaptability across multiple scenarios.Experimental results demonstrate that the proposed approach improves model accuracy by up to 2.33%under non-independent and identically distributed data conditions,maintains higher performance with malicious nodes containing poisoned data ratios of 20%–50%,and significantly enhances model resistance to low-quality data.展开更多
Accurate prediction of rockburst intensity levels is crucial for ensuring the safety of deep hard rock engineering construction.This paper introduced an expert system for rockburst intensity level prediction that empl...Accurate prediction of rockburst intensity levels is crucial for ensuring the safety of deep hard rock engineering construction.This paper introduced an expert system for rockburst intensity level prediction that employs machine learning algorithms as the basis for its inference rules.The system comprises four modules:a database,a repository,an inference engine,and an interpreter.A database containing 1114 rockburst cases was used to construct 357 datasets that serve as the repository for the expert system.Additionally,19 types of machine learning algorithms were used to establish 6783 micro-models to construct cognitive rules within the inference engine.By integrating probability theory and marginal analysis,a fuzzy scoring method based on the SoftMax function was developed and applied to the interpreter for rockburst intensity level prediction,effectively restoring the continuity of rockburst characteristics.The research results indicate that ensemble algorithms based on decision trees are more effective in capturing the characteristics of rockburst.Key factors for accurate prediction of rockburst intensity include uniaxial compressive strength,elastic energy index,the maximum principal stress,tangential stress,and their composite indicators.The accuracy of the proposed rockburst intensity level prediction expert system was verified using 20 engineering rockburst cases,with predictions aligning closely with the actual rockburst intensity levels.展开更多
Graph Federated Learning(GFL)has shown great potential in privacy protection and distributed intelligence through distributed collaborative training of graph-structured data without sharing raw information.However,exi...Graph Federated Learning(GFL)has shown great potential in privacy protection and distributed intelligence through distributed collaborative training of graph-structured data without sharing raw information.However,existing GFL approaches often lack the capability for comprehensive feature extraction and adaptive optimization,particularly in non-independent and identically distributed(NON-IID)scenarios where balancing global structural understanding and local node-level detail remains a challenge.To this end,this paper proposes a novel framework called GFL-SAR(Graph Federated Collaborative Learning Framework Based on Structural Amplification and Attention Refinement),which enhances the representation learning capability of graph data through a dual-branch collaborative design.Specifically,we propose the Structural Insight Amplifier(SIA),which utilizes an improved Graph Convolutional Network(GCN)to strengthen structural awareness and improve modeling of topological patterns.In parallel,we propose the Attentive Relational Refiner(ARR),which employs an enhanced Graph Attention Network(GAT)to perform fine-grained modeling of node relationships and neighborhood features,thereby improving the expressiveness of local interactions and preserving critical contextual information.GFL-SAR effectively integrates multi-scale features from every branch via feature fusion and federated optimization,thereby addressing existing GFL limitations in structural modeling and feature representation.Experiments on standard benchmark datasets including Cora,Citeseer,Polblogs,and Cora_ML demonstrate that GFL-SAR achieves superior performance in classification accuracy,convergence speed,and robustness compared to existing methods,confirming its effectiveness and generalizability in GFL tasks.展开更多
Deep learning attentionmechanisms have achieved remarkable progress in computer vision,but still face limitations when handling images with ambiguous boundaries and uncertain feature representations.Conventional atten...Deep learning attentionmechanisms have achieved remarkable progress in computer vision,but still face limitations when handling images with ambiguous boundaries and uncertain feature representations.Conventional attention modules such as SE-Net,CBAM,ECA-Net,and CA adopt a deterministic paradigm,assigning fixed scalar weights to features without modeling ambiguity or confidence.To overcome these limitations,this paper proposes the Fuzzy Attention Network Layer(FANL),which integrates intuitionistic fuzzy set theory with convolutional neural networks to explicitly represent feature uncertainty through membership(μ),non-membership(ν),and hesitation(π)degrees.FANLconsists of four coremodules:(1)feature dimensionality reduction via global pooling,(2)fuzzymodeling using learnable clustering centers,(3)adaptive attention generation through weighted fusion of fuzzy components,and(4)feature refinement through residual connections.A cross-layer guidance mechanism is further introduced to enhance hierarchical feature propagation,allowing high-level semantic features to incorporate fine-grained texture information from shallow layers.Comprehensive experiments on three benchmark datasets—PathMNIST-30000,full PathMNIST,and Blood MNIST—demonstrate the effectiveness and generalizability of FANL.The model achieves 84.41±0.56%accuracy and a 1.69%improvement over the baseline CNN while maintaining lightweight computational complexity.Ablation studies show that removing any component causes a 1.7%–2.0%performance drop,validating the synergistic contribution of each module.Furthermore,FANL provides superior uncertainty calibration(ECE=0.0452)and interpretable selective prediction under uncertainty.Overall,FANL presents an efficient and uncertaintyaware attention framework that improves both accuracy and reliability,offering a promising direction for robust visual recognition under ambiguous or noisy conditions.展开更多
To ensure the safe and stable operation of rotating machinery,intelligent fault diagnosis methods hold significant research value.However,existing diagnostic approaches largely rely on manual feature extraction and ex...To ensure the safe and stable operation of rotating machinery,intelligent fault diagnosis methods hold significant research value.However,existing diagnostic approaches largely rely on manual feature extraction and expert experience,which limits their adaptability under variable operating conditions and strong noise environments,severely affecting the generalization capability of diagnostic models.To address this issue,this study proposes a multimodal fusion fault diagnosis framework based on Mel-spectrograms and automated machine learning(AutoML).The framework first extracts fault-sensitive Mel time–frequency features from acoustic signals and fuses them with statistical features of vibration signals to construct complementary fault representations.On this basis,automated machine learning techniques are introduced to enable end-to-end diagnostic workflow construction and optimal model configuration acquisition.Finally,diagnostic decisions are achieved by automatically integrating the predictions of multiple high-performance base models.Experimental results on a centrifugal pump vibration and acoustic dataset demonstrate that the proposed framework achieves high diagnostic accuracy under noise-free conditions and maintains strong robustness under noisy interference,validating its efficiency,scalability,and practical value for rotating machinery fault diagnosis.展开更多
Lithology identificationwhile drilling technology can obtain rock information in real-time.However,traditional lithology identificationmodels often face limitations in feature extraction and adaptability to complex ge...Lithology identificationwhile drilling technology can obtain rock information in real-time.However,traditional lithology identificationmodels often face limitations in feature extraction and adaptability to complex geological conditions,limiting their accuracy in challenging environments.To address these challenges,a deep learning model for lithology identificationwhile drilling is proposed.The proposed model introduces a dual attention mechanism in the long short-term memory(LSTM)network,effectively enhancing the ability to capture spatial and channel dimension information.Subsequently,the crayfishoptimization algorithm(COA)is applied to optimize the model network structure,thereby enhancing its lithology identificationcapability.Laboratory test results demonstrate that the proposed model achieves 97.15%accuracy on the testing set,significantlyoutperforming the traditional support vector machine(SVM)method(81.77%).Field tests under actual drilling conditions demonstrate an average accuracy of 91.96%for the proposed model,representing a 14.31%improvement over the LSTM model alone.The proposed model demonstrates robust adaptability and generalization ability across diverse operational scenarios.This research offers reliable technical support for lithology identification while drilling.展开更多
基金supported by National Natural Science Foundation of China(62106092)Natural Science Foundation of Fujian Province(2024J01822,2024J01820,2022J01916)Natural Science Foundation of Zhangzhou City(ZZ2024J28).
文摘Feature selection serves as a critical preprocessing step inmachine learning,focusing on identifying and preserving the most relevant features to improve the efficiency and performance of classification algorithms.Particle Swarm Optimization has demonstrated significant potential in addressing feature selection challenges.However,there are inherent limitations in Particle Swarm Optimization,such as the delicate balance between exploration and exploitation,susceptibility to local optima,and suboptimal convergence rates,hinder its performance.To tackle these issues,this study introduces a novel Leveraged Opposition-Based Learning method within Fitness Landscape Particle Swarm Optimization,tailored for wrapper-based feature selection.The proposed approach integrates:(1)a fitness-landscape adaptive strategy to dynamically balance exploration and exploitation,(2)the lever principle within Opposition-Based Learning to improve search efficiency,and(3)a Local Selection and Re-optimization mechanism combined with random perturbation to expedite convergence and enhance the quality of the optimal feature subset.The effectiveness of is rigorously evaluated on 24 benchmark datasets and compared against 13 advancedmetaheuristic algorithms.Experimental results demonstrate that the proposed method outperforms the compared algorithms in classification accuracy on over half of the datasets,whilst also significantly reducing the number of selected features.These findings demonstrate its effectiveness and robustness in feature selection tasks.
基金funded by the Strategic Priority Research Program of the Chinese Academy of Sciences(XDB0560000)the National Natural Science Foundation of China(12473054)+1 种基金the Basic Research on Fund Projects in Yunnan Province(2019FA001)the Yunnan Province Science Foundation Project(202105AC160085).
文摘Image registration within a solar photosphere sequence is crucial for observational solar physics studies requiring high spatial and temporal resolutions.Previously,we identified residual large-scale nonrigid distortions in high-resolution solar photosphere images from ground-based telescopes after high-resolution reconstruction.Because these distortions are not eliminated by conventional sequence correlation alignment,they can affect the analysis of small-scale activity in the solar photosphere.Here,we implemented an image registration model using deep learning(HCAM-Net)to solve the problem.Within an encoder-decoder framework,we introduced a hybrid attention mechanism to improve context information capture and extract accurate deformation fields.Analyzing solar photosphere images acquired by the New Vacuum Solar Telescope,we demonstrated that the proposed model effectively achieved highly accurate nonrigid image registration.Evaluation metrics and visualization results indicated that our model outperformed current state-of-the-art models,such as VoxelMorph and TransMorph,for nonrigid registration of solar photosphere images,with a structural similarity index measure of 0.965 and a coefficient of determination of 0.976.
基金supported by the National Natural Science Foundation of China(No.62361003)the Guangxi Science and Technology Base and Talent Special Project(Nos.AD25069071 and AD24010061).
文摘Unmanned Aerial Vehicle(UAV)assisted federated learning enables on-edge model training,but its effectiveness depends on sustainable client participation through well-designed incentive mechanisms.Existing approaches based on economic models provide theoretical guarantees under restrictive assumptions,while Reinforcement Learning(RL)methods adapt to dynamics but lack provable incentive compatibility.We propose an adaptive privacy-aware incentive mechanism that integrates contract theory with Multi-Agent RL(MARL).The contract design provides a truthful initialization under privacy heterogeneity,while MARL adaptively refines incentives in dynamic environments.An Incentive Compatibility(IC)regularized optimization further ensures policy convergence and robustness.Experiments in UAV-assisted FL show that our method improves social welfare by up to 35%and participant engagement by 45%over state-of-the-art baselines,while maintaining strong privacy guarantees.
基金support from the Ningxia Natural Science Foundation Project(2023AAC03361).
文摘The flying foxes optimization(FFO)algorithm,as a newly introduced metaheuristic algorithm,is inspired by the survival tactics of flying foxes in heat wave environments.FFO preferentially selects the best-performing individuals.This tendency will cause the newly generated solution to remain closely tied to the candidate optimal in the search area.To address this issue,the paper introduces an opposition-based learning-based search mechanism for FFO algorithm(IFFO).Firstly,this paper introduces niching techniques to improve the survival list method,which not only focuses on the adaptability of individuals but also considers the population’s crowding degree to enhance the global search capability.Secondly,an initialization strategy of opposition-based learning is used to perturb the initial population and elevate its quality.Finally,to verify the superiority of the improved search mechanism,IFFO,FFO and the cutting-edge metaheuristic algorithms are compared and analyzed using a set of test functions.The results prove that compared with other algorithms,IFFO is characterized by its rapid convergence,precise results and robust stability.
基金supported by the National Key Research and Development Program of China(2024YFE0213000)the Postdoctoral Innovative Talents Support Program(BX20240232)+1 种基金the Natural Science Foundation of China for Young Scholars(72304031)the Fundamental Research Funds for the Central Universities(FRF-TP-22-024A1).
文摘Lithium-ion batteries(LIBs)are widely deployed,from grid-scale storage to electric vehicles.LIBs remain stationary most of their service life,where calendar aging degrades capacity.Understanding the mechanisms of LIB calendar aging is crucial for extending battery lifespan.However,LIB calendar aging is influenced by multiple factors,including battery material,its state,and storage environment.Calendar aging experiments are also time-consuming,costly,and lack standardized testing conditions.This study employs a data-driven approach to establish a cross-scale database linking materials,side-reaction mechanisms,and calendar aging of LIBs.MELODI(Mechanism-informed,Explainable,Learning-based Optimization for Degradation Identification)is proposed to identify calendar aging mechanisms and quantify the effects of multi-scale factors.Results reveal that cathode material loss drives up to 91.42%of calendar aging degradation in high-nickel(Ni)batteries,while solid electrolyte interphase growth dominates in lithium iron phosphate(LFP)and low-Ni batteries,contributing up to 82.43%of degradation in LFP batteries and 99.10%of decay in low-Ni batteries,respectively.This study systematically quantifies calendar aging in commercial LIBs under varying materials,states of charge,and temperatures.These findings offer quantitative guidance for experimental design or battery use,and implications for emerging applications like aerial robotics,vehicle-to-grid,and embodied intelligence systems.
基金funded by the Hubei Provincial Department of Education Science and Technology Plan Project(Young and Middle-aged Talent Program)(https://jyt.hubei.gov.cn/),grant number Q20241308the National Natural Science Foundation of China(https://www.nsfc.gov.cn/),grant number 52174064.
文摘Slug flow represents one of the most critical and operationally challenging regimes in oil-gas-water multiphase pipelines.To advance both mechanistic understanding and predictive capability,this study integrates physical analysis with data-driven modeling to elucidate the conditions governing slug formation and to enable its rapid and accurate prediction.A systematic review of existing research is first undertaken to clarify the mechanisms responsible for slug initiation.The influences of gas superficial velocity,liquid velocity,liquid viscosity,liquid surface tension,and the axial component of gravity are examined to characterize their roles in interfacial instability and flow transition.Then,the effects of temperature,total flow rate,water cut,gas-liquid ratio,and pipeline inclination angle are quantitatively assessed,revealing the dominant trends that promote or inhibit slug development.Building on this foundation,a comprehensive three-phase oil-gas-water flow model is constructed.Numerical simulations are performed for 243 operating conditions encompassing a broad range of temperatures,water cuts,gas-liquid ratios,liquid flow rates,and inclination angles.These simulated cases constitute the training dataset for nine machine learning algorithms.To evaluate generalization performance,108 additional randomly generated operating conditions are predicted,covering temperatures of 80–150◦C,water cuts of 40–90%,gas-liquid ratios of 3–30,liquid flow rates of 100–200 t/d,and inclination angles of 5–15.Comparative validation reveals marked differences in predictive accuracy.The BP neural network achieves the highest accuracy,95%,substantially outperforming XGBoost,83.3%,Random Forest and Decision Tree,81.5%,Logistic Regression and Support Vector Machine,80.6%,K-Nearest Neighbor and Naive Bayes 78.7%,and K-Means,63%.Overall,the BP neural network demonstrates superior robustness and precision in predicting previously unseen operating conditions,effectively combining the physical consistency of mechanistic modeling with the efficiency and adaptability of machine learning approaches.
基金supported by the National Natural Science Foundation of China(Nos.52471132,52475356,52071139,U21A20130)the National Social Science Fund of China(No.21BJL075)+1 种基金the Natural Science Foundation of Fujian Province for Distinguished Young Scholars,China(No.2024J010031)the Natural Science Foundation of Chongqing,China(No.CSTB2023NSCQ-MSX0886)。
文摘To investigate the complex relationship between rolling process parameters and mechanical properties of AZ31 magnesium alloy rolled sheets,the Leave-One-Out Cross-Validation(LOOCV)and parameter tuning were applied to optimizing hyper-parameters for the four(BPNN,SVR,RF,and KNN)machine learning models.An interpretable prediction model based on machine learning and SHapley Additive exPlanations(SHAP),as well as an analytical method combining the SHAP model and the Pearson Correlation Coefficient(PCC),were proposed.The results showed that among the four models,the SVR model was able to simultaneously and accurately predict the ultimate tensile strength(UTS)and elongation(EL).According to the combination analysis of PCC and the magnesium alloy rolling forming mechanism,it was found that strain rate and reduction displayed a negative and positive correlation with UTS,respectively,while rolling temperature and reduction illustrated a positive and negative correlation with EL,respectively.Through the SHAP method,which could interpret the output results of the SVR machine learning model,it was deduced that reduction and strain rate played an important role in the SVR model of the outputs of the UTS and EL,respectively.Combining SHAP with PCC,it was found that strain rate and reduction had a greater influence on the UTS than rolling temperature,whereas strain rate and rolling temperature had more influence on the EL compared to reduction.
基金supported in part by the National Key Research and Development Program of China under Grant No.2021YFF0901300in part by the National Natural Science Foundation of China under Grant Nos.62173076 and 72271048.
文摘The distributed permutation flow shop scheduling problem(DPFSP)has received increasing attention in recent years.The iterated greedy algorithm(IGA)serves as a powerful optimizer for addressing such a problem because of its straightforward,single-solution evolution framework.However,a potential draw-back of IGA is the lack of utilization of historical information,which could lead to an imbalance between exploration and exploitation,especially in large-scale DPFSPs.As a consequence,this paper develops an IGA with memory and learning mechanisms(MLIGA)to efficiently solve the DPFSP targeted at the mini-malmakespan.InMLIGA,we incorporate a memory mechanism to make a more informed selection of the initial solution at each stage of the search,by extending,reconstructing,and reinforcing the information from previous solutions.In addition,we design a twolayer cooperative reinforcement learning approach to intelligently determine the key parameters of IGA and the operations of the memory mechanism.Meanwhile,to ensure that the experience generated by each perturbation operator is fully learned and to reduce the prior parameters of MLIGA,a probability curve-based acceptance criterion is proposed by combining a cube root function with custom rules.At last,a discrete adaptive learning rate is employed to enhance the stability of the memory and learningmechanisms.Complete ablation experiments are utilized to verify the effectiveness of the memory mechanism,and the results show that this mechanism is capable of improving the performance of IGA to a large extent.Furthermore,through comparative experiments involving MLIGA and five state-of-the-art algorithms on 720 benchmarks,we have discovered that MLI-GA demonstrates significant potential for solving large-scale DPFSPs.This indicates that MLIGA is well-suited for real-world distributed flow shop scheduling.
基金the National Key R&D Program of China(2021YFC3000701)for the financial support。
文摘As one of the most seismically active regions,Sichuan Basin is a key area of seismological studies in China.This study applies a neural network model with attention mechanisms,simultaneously picking the P-wave arrival times and determining the first-motion polarity.The polarity information is subsequently used to derive source focal mechanisms.The model is trained and tested using small to moderate earthquake data from June to December 2019 in Sichuan.We apply the trained model to predict first-motion polarity directions of earthquake recordings in Sichuan from January to May 2019,and then derive focal mechanism solutions using HASH algorithm with predicted results.Compared with the source mechanism solutions obtained by manual processing,the deep learning method picks more polarities from smaller events,resulting in more focal mechanism solutions.The catalog documents focal mechanism solutions of 22 events(M_(L) 2.6–4.8)from analysts during this period,whereas we obtain focal mechanism solutions of 53 events(M_(L) 1.9–4.8)through the deep learning method.The derived focal mechanism solutions for the same events are consistent with the manual solutions.This method provides an efficient way for the source mechanism inversion of small to moderate earthquakes in Sichuan region,with high stability and reliability.
基金supported by the Key Research and Development Plan of Anhui Province(202104a05020059)the Excellent Scientific Research and Innovation Team of Anhui Province(2022AH010003)support from Hefei Comprehensive National Science Center is highly appreciated.
文摘Microseismic monitoring technology is widely used in tunnel and coal mine safety production.For signals generated by ultra-weak microseismic events,traditional sensors encounter limitations in terms of detection sensitivity.Given the complex engineering environment,automatic multi-classification of microseismic data is highly required.In this study,we use acceleration sensors to collect signals and combine the improved Visual Geometry Group with a convolutional block attention module to obtain a new network structure,termed CNN_BAM,for automatic classification and identification of microseismic events.We use the dataset collected from the Hanjiang-to-Weihe River Diversion Project to train and validate the network model.Results show that the CNN_BAM model exhibits good feature extraction ability,achieving a recognition accuracy of 99.29%,surpassing all its counterparts.The stability and accuracy of the classification algorithm improve remarkably.In addition,through fine-tuning and migration to the Pan Ⅱ Mine Project,the network demonstrates reliable generalization performance.This outcome reflects its adaptability across different projects and promising application prospects.
基金supported by the Key Research and Development Program of Heilongjiang Province(No.2022ZX01A35).
文摘As the group-buying model shows significant progress in attracting new users,enhancing user engagement,and increasing platform profitability,providing personalized recommendations for group-buying users has emerged as a new challenge in the field of recommendation systems.This paper introduces a group-buying recommendation model based on multi-head attention mechanisms and multi-task learning,termed the Multi-head Attention Mechanisms and Multi-task Learning Group-Buying Recommendation(MAMGBR)model,specifically designed to optimize group-buying recommendations on e-commerce platforms.The core dataset of this study comes from the Chinese maternal and infant e-commerce platform“Beibei,”encompassing approximately 430,000 successful groupbuying actions and over 120,000 users.Themodel focuses on twomain tasks:recommending items for group organizers(Task Ⅰ)and recommending participants for a given group-buying event(Task Ⅱ).In model evaluation,MAMGBR achieves an MRR@10 of 0.7696 for Task I,marking a 20.23%improvement over baseline models.Furthermore,in Task II,where complex interaction patterns prevail,MAMGBR utilizes auxiliary loss functions to effectively model the multifaceted roles of users,items,and participants,leading to a 24.08%increase in MRR@100 under a 1:99 sample ratio.Experimental results show that compared to benchmark models,such as NGCF and EATNN,MAMGBR’s integration ofmulti-head attentionmechanisms,expert networks,and gating mechanisms enables more accurate modeling of user preferences and social associations within group-buying scenarios,significantly enhancing recommendation accuracy and platform group-buying success rates.
文摘The growing demand for carbon neutrality has heightened the focus on CO_(2)hydrogenation as a viable strategy for transforming carbon dioxide into valuable chemicals and fuels.Advanced machine learning(ML)approaches integrate materials science with artificial intelligence,enabling scientists to identify hidden patterns in datasets,make informed decisions,and reduce the need for labor-intensive,repetitive experimentation.This review provides a comprehensive overview of ML applications in the thermocatalytic hydrogenation of CO_(2).Following an introduction to ML tools and workflows,various ML algorithms employed in CO_(2)hydrogenation are systematically categorized and reviewed.Next,the application of ML in catalyst discovery is discussed,highlighting its role in identifying optimal compositions and structures.Then,ML-driven strategies for process optimization,particularly in enhancing CO_(2)conversion and product selectivity,are examined.Studies modeling descriptors,spanning catalyst properties and reaction conditions,to predict catalytic performance are analyzed.Consequently,ML-based mechanistic studies are reviewed to elucidate reaction pathways,identify key intermediates,and optimize catalyst performance.Finally,key challenges and future perspectives in leveraging ML for advancing CO_(2)hydrogenation research are presented.
基金the Natural Science Foundation of Zhejiang Province(No.LQ20F020024)。
文摘Various and intricate varieties of lung disease have made it challenging for computer aided diagnosis to appropriately segment lung lesions utilizing computed tomography(CT)images.This study integrates transfer learning with the attention mechanism to construct a deep learning model that can automatically detect new coronary pneumonia on lung CT images.In this study,using VGG16 pre-trained by ImageNet as the encoder,the decoder was established utilizing the U-Net structure.The attention module is incorporated during each concatenate procedure,permitting the model to concentrate on the critical information and identify the crucial components efficiently.The public COVID-19-CT-Seg-Benchmark dataset was utilized for experiments,and the highest scores for Dice,F1,and Accuracy were 0.9071,0.9076,and 0.9965,respectively.The generalization performance was assessed concurrently,with performance metrics including Dice,F1,and Accuracy over 0.8.The experimental findings indicate the feasibility of the segmentation network proposed in this study.
基金supported by the National Natural Science Foundation of China(nos.52201119,52371108)Frontier Exploration Project of Longmen Laboratory,China(no.LMQYTSKT014)The Joint Fund of Henan Science and Technology R&D Plan of China(no.242103810056).
文摘The hot deformation behavior of magnesium(Mg)alloys is significantly governed by the multi-physics coupling effects of temperature(T),strain rate(ε)and strain(ε),resulting in flow behavior that exhibits pronounced nonlinearity and multi-scale complexity.This study systematically investigates the hot deformation behavior of Mg-Y-Nd-(Sm)-Zr alloys.Sm alloying promotes recrystallization.The flow stress of Sm-containing alloys declines sharply towards a steady state after reaching its peak value.To overcome the limitations of the Arrhenius-type constitutive(AC)model in predicting complex nonlinear flow behavior,the AC and data hybrid informed neural network(ACINN)model is developed.This approach enhances the predictive accuracy and extends the applicability of the traditional AC model.The evolution of microstructure and recrystallization behavior under hot deformation conditions are investigated based on results from electron backscatter diffraction(EBSD)and transmission electron microscopy(TEM).The relationship between the power dissipation factor(η)and recrystallization behavior is further examined using K-means clustering analysis.The results demonstrate that dynamic recrystallization(DRX)behavior varies with theηvalue,comprising four distinct regimes:dynamic recovery(DRV),discontinuous dynamic recrystallization(DDRX)dominance,continuous dynamic recrystallization(CDRX)dominance and complete dynamic recrystallization.This analysis presents a new perspective for studying the hot deformation processes of Mg alloys.
基金supported by State Grid Hebei Electric Power Co.,Ltd.Science and Technology Project,Research on Security Protection of Power Services Carried by 4G/5G Networks(Grant No.KJ2024-127).
文摘The rapid growth of Internet of things devices and the emergence of rapidly evolving network threats have made traditional security assessment methods inadequate.Federated learning offers a promising solution to expedite the training of security assessment models.However,ensuring the trustworthiness and robustness of federated learning under multi-party collaboration scenarios remains a challenge.To address these issues,this study proposes a shard aggregation network structure and a malicious node detection mechanism,along with improvements to the federated learning training process.First,we extract the data features of the participants by using spectral clustering methods combined with a Gaussian kernel function.Then,we introduce a multi-objective decision-making approach that combines data distribution consistency,consensus communication overhead,and consensus result reliability in order to determine the final network sharing scheme.Finally,by integrating the federated learning aggregation process with the malicious node detection mechanism,we improve the traditional decentralized learning process.Our proposed ShardFed algorithm outperforms conventional classification algorithms and state-of-the-art machine learning methods like FedProx and FedCurv in convergence speed,robustness against data interference,and adaptability across multiple scenarios.Experimental results demonstrate that the proposed approach improves model accuracy by up to 2.33%under non-independent and identically distributed data conditions,maintains higher performance with malicious nodes containing poisoned data ratios of 20%–50%,and significantly enhances model resistance to low-quality data.
基金Project(42077244)supported by the National Natural Science Foundation of ChinaProject(2020-05)supported by the Open Research Fund of Guangdong Provincial Key Laboratory of Deep Earth Sciences and Geothermal Energy Exploitation and Utilization,China。
文摘Accurate prediction of rockburst intensity levels is crucial for ensuring the safety of deep hard rock engineering construction.This paper introduced an expert system for rockburst intensity level prediction that employs machine learning algorithms as the basis for its inference rules.The system comprises four modules:a database,a repository,an inference engine,and an interpreter.A database containing 1114 rockburst cases was used to construct 357 datasets that serve as the repository for the expert system.Additionally,19 types of machine learning algorithms were used to establish 6783 micro-models to construct cognitive rules within the inference engine.By integrating probability theory and marginal analysis,a fuzzy scoring method based on the SoftMax function was developed and applied to the interpreter for rockburst intensity level prediction,effectively restoring the continuity of rockburst characteristics.The research results indicate that ensemble algorithms based on decision trees are more effective in capturing the characteristics of rockburst.Key factors for accurate prediction of rockburst intensity include uniaxial compressive strength,elastic energy index,the maximum principal stress,tangential stress,and their composite indicators.The accuracy of the proposed rockburst intensity level prediction expert system was verified using 20 engineering rockburst cases,with predictions aligning closely with the actual rockburst intensity levels.
基金supported by National Natural Science Foundation of China(62466045)Inner Mongolia Natural Science Foundation Project(2021LHMS06003)Inner Mongolia University Basic Research Business Fee Project(114).
文摘Graph Federated Learning(GFL)has shown great potential in privacy protection and distributed intelligence through distributed collaborative training of graph-structured data without sharing raw information.However,existing GFL approaches often lack the capability for comprehensive feature extraction and adaptive optimization,particularly in non-independent and identically distributed(NON-IID)scenarios where balancing global structural understanding and local node-level detail remains a challenge.To this end,this paper proposes a novel framework called GFL-SAR(Graph Federated Collaborative Learning Framework Based on Structural Amplification and Attention Refinement),which enhances the representation learning capability of graph data through a dual-branch collaborative design.Specifically,we propose the Structural Insight Amplifier(SIA),which utilizes an improved Graph Convolutional Network(GCN)to strengthen structural awareness and improve modeling of topological patterns.In parallel,we propose the Attentive Relational Refiner(ARR),which employs an enhanced Graph Attention Network(GAT)to perform fine-grained modeling of node relationships and neighborhood features,thereby improving the expressiveness of local interactions and preserving critical contextual information.GFL-SAR effectively integrates multi-scale features from every branch via feature fusion and federated optimization,thereby addressing existing GFL limitations in structural modeling and feature representation.Experiments on standard benchmark datasets including Cora,Citeseer,Polblogs,and Cora_ML demonstrate that GFL-SAR achieves superior performance in classification accuracy,convergence speed,and robustness compared to existing methods,confirming its effectiveness and generalizability in GFL tasks.
文摘Deep learning attentionmechanisms have achieved remarkable progress in computer vision,but still face limitations when handling images with ambiguous boundaries and uncertain feature representations.Conventional attention modules such as SE-Net,CBAM,ECA-Net,and CA adopt a deterministic paradigm,assigning fixed scalar weights to features without modeling ambiguity or confidence.To overcome these limitations,this paper proposes the Fuzzy Attention Network Layer(FANL),which integrates intuitionistic fuzzy set theory with convolutional neural networks to explicitly represent feature uncertainty through membership(μ),non-membership(ν),and hesitation(π)degrees.FANLconsists of four coremodules:(1)feature dimensionality reduction via global pooling,(2)fuzzymodeling using learnable clustering centers,(3)adaptive attention generation through weighted fusion of fuzzy components,and(4)feature refinement through residual connections.A cross-layer guidance mechanism is further introduced to enhance hierarchical feature propagation,allowing high-level semantic features to incorporate fine-grained texture information from shallow layers.Comprehensive experiments on three benchmark datasets—PathMNIST-30000,full PathMNIST,and Blood MNIST—demonstrate the effectiveness and generalizability of FANL.The model achieves 84.41±0.56%accuracy and a 1.69%improvement over the baseline CNN while maintaining lightweight computational complexity.Ablation studies show that removing any component causes a 1.7%–2.0%performance drop,validating the synergistic contribution of each module.Furthermore,FANL provides superior uncertainty calibration(ECE=0.0452)and interpretable selective prediction under uncertainty.Overall,FANL presents an efficient and uncertaintyaware attention framework that improves both accuracy and reliability,offering a promising direction for robust visual recognition under ambiguous or noisy conditions.
基金supported in part by the National Natural Science Foundation of China under Grants 52475102 and 52205101in part by the Guangdong Basic and Applied Basic Research Foundation under Grant 2023A1515240021+1 种基金in part by the Young Talent Support Project of Guangzhou Association for Science and Technology(QT-2024-28)in part by the Youth Development Initiative of Guangdong Association for Science and Technology(SKXRC2025254).
文摘To ensure the safe and stable operation of rotating machinery,intelligent fault diagnosis methods hold significant research value.However,existing diagnostic approaches largely rely on manual feature extraction and expert experience,which limits their adaptability under variable operating conditions and strong noise environments,severely affecting the generalization capability of diagnostic models.To address this issue,this study proposes a multimodal fusion fault diagnosis framework based on Mel-spectrograms and automated machine learning(AutoML).The framework first extracts fault-sensitive Mel time–frequency features from acoustic signals and fuses them with statistical features of vibration signals to construct complementary fault representations.On this basis,automated machine learning techniques are introduced to enable end-to-end diagnostic workflow construction and optimal model configuration acquisition.Finally,diagnostic decisions are achieved by automatically integrating the predictions of multiple high-performance base models.Experimental results on a centrifugal pump vibration and acoustic dataset demonstrate that the proposed framework achieves high diagnostic accuracy under noise-free conditions and maintains strong robustness under noisy interference,validating its efficiency,scalability,and practical value for rotating machinery fault diagnosis.
基金supported by the National Key Research and Development Program for Young Scientists,Chin(Grant No.2021YFC2900400)the Sichuan-Chongqing Science and Technology Innovation Cooperation Program Project,China(Grant No.2024TIAD-CYKJCXX0269)the National Natural Science Foundation of China,China(Grant No.52304123).
文摘Lithology identificationwhile drilling technology can obtain rock information in real-time.However,traditional lithology identificationmodels often face limitations in feature extraction and adaptability to complex geological conditions,limiting their accuracy in challenging environments.To address these challenges,a deep learning model for lithology identificationwhile drilling is proposed.The proposed model introduces a dual attention mechanism in the long short-term memory(LSTM)network,effectively enhancing the ability to capture spatial and channel dimension information.Subsequently,the crayfishoptimization algorithm(COA)is applied to optimize the model network structure,thereby enhancing its lithology identificationcapability.Laboratory test results demonstrate that the proposed model achieves 97.15%accuracy on the testing set,significantlyoutperforming the traditional support vector machine(SVM)method(81.77%).Field tests under actual drilling conditions demonstrate an average accuracy of 91.96%for the proposed model,representing a 14.31%improvement over the LSTM model alone.The proposed model demonstrates robust adaptability and generalization ability across diverse operational scenarios.This research offers reliable technical support for lithology identification while drilling.
