期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到229篇文章
< 1 2 … 12 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Multi-source errors evaluation of machine tools:from research gaps to methodologies and applications 认领 引用 被引量：1
1
作者 Jingang Sun Yanbin Zhang +14 位作者 Xiao Ma Benkai Li Min Yang Liandi Xu Haiyuan Xin Qinglong An Lida Zhu Qingfeng Bie Xianxin Yin Shouhai Chen Guanqun Li Yusuf Suleiman Dambatta Rui Xue Zhenwei Yu Changhe Li 《International Journal of Extreme Manufacturing》 SCIE EI CAS CSCD 2026年第2期44-96,共53页
Multi-source errors,as critical obstacles limiting the accuracy retention and machining performance of machine tools,hold fundamental and strategic significance for achieving high-precision,high-efficiency,and high-re... Multi-source errors,as critical obstacles limiting the accuracy retention and machining performance of machine tools,hold fundamental and strategic significance for achieving high-precision,high-efficiency,and high-reliability machining in modern manufacturing systems.However,these errors typically exhibit complex characteristics such as strong coupling,time-variance,and nonlinearity,which challenge traditional methods of error identification,modeling,and compensation in terms of adaptability,real-time capability,and integration.Therefore,it is imperative to establish a systematic and intelligent multi-source error control framework.Firstly,this work systematically reviews typical error sources and their evolution mechanisms,evaluates multi-scale detection technologies including laser interferometry,double ball-bar systems,multi-sensor fusion,and vision-based systems,and constructs an intelligent error identification and evaluation framework.Next,it reviews classical modeling methods such as homogeneous transformation matrices,screw theory,thermal equilibrium models,finite element analysis,and modal analysis,compares physical modeling,data-driven,and hybrid modeling strategies,and develops an integrated multi-source error modeling architecture centered on digital twin technology and artificial intelligence.Furthermore,key technologies,including geometric error mapping and real-time compensation,online thermal error prediction and active temperature control,dynamic error suppression,and adaptive control,are summarized.A multi-level integrated error compensation architecture is proposed by combining physical models,data models,and cyber-physical synchronization.This architecture encompasses core processes such as error traceability and decoupling,dynamic prediction,real-time compensation,and closed-loop optimization,emphasizing engineering implementation mechanisms based on cyber-physical collaboration,multi-physics coupling,and multi-scale fusion,thereby effectively enhancing accuracy stability and control robustness under complex operating conditions.Finally,frontier challenges such as constructing high-fidelity coupled models from heterogeneous multi-source data,edge-cloud collaborative control,and cross-platform interoperability are discussed.The application prospects of multi-source error evaluation are also envisioned,providing theoretical foundations and technical support for the precise management and optimization of the entire lifecycle accuracy of machine tools. 展开更多
关键词 multi-source error evaluation error coupling integrated error modeling traceability and decoupling hybrid prediction closed-loop error compensation
暂未订购 下载PDF
A review on research of system dynamics and multi-source fault diagnosis of key components in high-speed train 认领 引用
2
作者 Baosen Wang Yongqiang Liu +4 位作者 Qilan Li Min Wang Qiaoying Ma Yingying Liao Shaopu Yang 《Chinese Journal of Mechanical Engineering》 SCIE EI CAS CSCD 2026年第1期496-507,共12页
As China's high-speed railway technology advances,high-speed trains have emerged as a pivotal mode of transportation,instrumental in facilitating passenger and freight mobility while fostering robust regional eco-... As China's high-speed railway technology advances,high-speed trains have emerged as a pivotal mode of transportation,instrumental in facilitating passenger and freight mobility while fostering robust regional eco-nomic and trade interactions.Nonetheless,the safety of train operations remains a paramount concern,prompting extensive research into the dynamic behavior of critical components,which is essential to ensuring seamless and secure transportation services.This article commences by comprehensively reviewing the current landscape and evolutionary trajectory of dynamic model analysis for both traditional bearings and axle box bearings.Emphasis is placed on elucidating the profound influence of diverse bearing fault types on the system's kinematic state,alongside delving into the research methodologies employed in developing multi-physics field coupling models.Subsequently,it expounds on the content of investigations focusing on various wheel and track impairments,grounded in the dynamic modeling of the bearing vehicle coupling system.Concurrently,the intricate interplay between wheel-rail excitation and axle box bearing faults on the system's performance is elucidated.Concludingly,the article underscores the inadequacy of current multi-source fault diagnosis meth-odologies in tackling the intricacies of complex train operating environments,thereby highlighting its sig-nificance as a pressing and vital research agenda for the future. 展开更多
关键词 High-speed train Axle box bearing Dynamic model Wheel rail excitation Multi-source fault
暂未订购 下载PDF
High-precision classification of benthic habitat sediments in shallow waters of islands by multi-source data 认领 引用
3
作者 Qiuhua TANG Ningning LI +4 位作者 Yujie ZHANG Zhipeng DONG Yongling ZHENG Jingjing BAO Jingyu ZHANG 《Journal of Oceanology and Limnology》 SCIE CAS CSCD 2026年第1期99-108,共10页
Benthic habitat mapping is an emerging discipline in the international marine field in recent years,providing an effective tool for marine spatial planning,marine ecological management,and decision-making applications... Benthic habitat mapping is an emerging discipline in the international marine field in recent years,providing an effective tool for marine spatial planning,marine ecological management,and decision-making applications.Seabed sediment classification is one of the main contents of seabed habitat mapping.In response to the impact of remote sensing imaging quality and the limitations of acoustic measurement range,where a single data source does not fully reflect the substrate type,we proposed a high-precision seabed habitat sediment classification method that integrates data from multiple sources.Based on WorldView-2 multi-spectral remote sensing image data and multibeam bathymetry data,constructed a random forests(RF)classifier with optimal feature selection.A seabed sediment classification experiment integrating optical remote sensing and acoustic remote sensing data was carried out in the shallow water area of Wuzhizhou Island,Hainan,South China.Different seabed sediment types,such as sand,seagrass,and coral reefs were effectively identified,with an overall classification accuracy of 92%.Experimental results show that RF matrix optimized by fusing multi-source remote sensing data for feature selection were better than the classification results of simple combinations of data sources,which improved the accuracy of seabed sediment classification.Therefore,the method proposed in this paper can be effectively applied to high-precision seabed sediment classification and habitat mapping around islands and reefs. 展开更多
关键词 Wuzhizhou Island marine remote sensing coastal mapping multi-spectral remote sensing shallow water reef seabed sediment classification benthic habitat mapping multi-source data fusion random forest(RF)
暂未订购 下载PDF
Multi-source hydrocarbon accumulation in the faulted and deeply depressed Tangdong area,Qikou Sag,Bohai Bay Basin 认领 引用
4
作者 Xiugang Pu Guochao Xia +6 位作者 Jiangchang Dong Zhannan Shi Wenzhong Han Qianru Shi Wei Zhang Yueqi Dong Xiongying Dong 《Energy Geoscience》 EI CAS CSCD 2026年第2期85-100,共16页
Based on organic geochemical analysis data,this study examined the characteristics of multi-source hydrocarbon accumulation in the Tangdong area of Qikou Depression,Bohai Bay Basin.The results indicate that the Tangdo... Based on organic geochemical analysis data,this study examined the characteristics of multi-source hydrocarbon accumulation in the Tangdong area of Qikou Depression,Bohai Bay Basin.The results indicate that the Tangdong area contains four source rock sequences:the third member of the Dongying Formation(Ed3),the middle and lower sub-members of the first and third member of Shahejie Formation(Es 1M,Es 1L,Es 3).Both the salinity of sedimentary water bodies and the contribution of bacteria in the four source rock sequences gradual increase in the order of Es 3,Es 1M,Es 1L and Ed3,as indicated by the Ga/C30H,ETR,sterane/C30 hopane,C24TeT/C26TT,C23TT/C30H,and the carbon isotope data of group components.Additionally,certain quantities of 4-methylsterane have been detected in source rocks in the Es 3,Es 1M,and Ed3,suggesting the special contribution of dinoflagellates to these source rocks.Based on biomarker parameters and carbon isotope data,the crude oil can be categorized into classes A to D,which show complex multi-source accumulation characterized by different sources in the same well and even in the same layer.Class A crude oil occurring in the higher part of the Ed3 originates from source rocks in the Es 1L and Es 3.Class B oil existing in the lower part of the Ed3 is derived from source rocks in the Ed3.Class C oil found in the Es 1U is sourced from source rocks in the Es 1M.Class D oil present in the Es 1L is contributed indigenously by the source rocks in the Es 1L,establishing this unit as a lithologic hydrocarbon reservoir with source rocks and reservoirs in the same layer.Under the guidance of the understanding of multi-source hydrocarbon accumulation,currently,three wells have been drilled,all yielding satisfactory outcomes. 展开更多
关键词 Oil-source rock correlation Multi-source hydrocarbon accumulation Petroleum geochemistry Source rock Deeply depressed area Qikou sag Exploration well emplacement
暂未订购 下载PDF
Multi-source remote sensing unveils hydrological dynamics and drought escalation in Central Asia's arid regions 认领 引用
5
作者 WANG Yuhao ZHENG Zhijie +13 位作者 ZHU Guofeng HUANG Enwei MENG Gaojia LU Siyu QIU Dongdong CHEN Longhu LI Rui JIAO Yinying ZHAO Ling QI Xiaoyu WANG Qinqin LI Wenmin MIAO Yuxin WANG Qingyang 《Journal of Geographical Sciences》 SCIE CSCD 2026年第5期1105-1129,共25页
Despite the reported“warming-wetting”trend,Central Asia faces severe water insecurity due to climate shifts and anthropogenic activities.This study integrates multi-source remote sensing data(GRACE,TRMM,MODIS)with m... Despite the reported“warming-wetting”trend,Central Asia faces severe water insecurity due to climate shifts and anthropogenic activities.This study integrates multi-source remote sensing data(GRACE,TRMM,MODIS)with machine learning to analyze drought dynamics from 2003 to 2022 using the Water Storage Deficit Index(WSDI).Results reveal significant declines in terrestrial water storage(TWS)particularly in the Tianshan Mountains(–10.20 mm/yr)and the Central Desert(–6.19 mm/yr).Drought severity has intensified since 2014,with 67%of subregions transitioning to moderate drought.Random Forest modeling indicates that drought is no longer solely climate-driven but is increasingly dominated by anthropogenic factors(GDP,urbanization,cropland),which explain over 85%of the variability.Furthermore,the WSDI outperformed traditional indices by identifying 12 major drought events linked to deep aquifer depletion—a“hidden”structural deficit often overlooked by surface-based metrics.These findings challenge the optimistic“warming-wetting”narrative,highlighting the urgent need for storage-based management strategies to address anthropogenic groundwater depletion. 展开更多
关键词 Central Asia’s arid regions drought dynamics multi-source remote sensing GRACE hydrometeorological drivers Random Forest
暂未订购 下载PDF
Drive-by spatial offset detection for high-speed railway bridges based on fusion analysis of multi-source data from comprehensive inspection train 认领 引用
6
作者 Chuang Wang Jiawang Zhan +4 位作者 Nan Zhang Yujie Wang Xinxiang Xu Zhihang Wang Zhen Ni 《Railway Engineering Science》 EI 2026年第1期128-148,共21页
The spatial offset of bridge has a significant impact on the safety,comfort,and durability of high-speed railway(HSR)operations,so it is crucial to rapidly and effectively detect the spatial offset of operational HSR ... The spatial offset of bridge has a significant impact on the safety,comfort,and durability of high-speed railway(HSR)operations,so it is crucial to rapidly and effectively detect the spatial offset of operational HSR bridges.Drive-by monitoring of bridge uneven settlement demonstrates significant potential due to its practicality,cost-effectiveness,and efficiency.However,existing drive-by methods for detecting bridge offset have limitations such as reliance on a single data source,low detection accuracy,and the inability to identify lateral deformations of bridges.This paper proposes a novel drive-by inspection method for spatial offset of HSR bridge based on multi-source data fusion of comprehensive inspection train.Firstly,dung beetle optimizer-variational mode decomposition was employed to achieve adaptive decomposition of non-stationary dynamic signals,and explore the hidden temporal relationships in the data.Subsequently,a long short-term memory neural network was developed to achieve feature fusion of multi-source signal and accurate prediction of spatial settlement of HSR bridge.A dataset of track irregularities and CRH380A high-speed train responses was generated using a 3D train-track-bridge interaction model,and the accuracy and effectiveness of the proposed hybrid deep learning model were numerically validated.Finally,the reliability of the proposed drive-by inspection method was further validated by analyzing the actual measurement data obtained from comprehensive inspection train.The research findings indicate that the proposed approach enables rapid and accurate detection of spatial offset in HSR bridge,ensuring the long-term operational safety of HSR bridges. 展开更多
关键词 High-speed railway bridge Drive-by inspection Spatial offset Multi-source data fusion Deep learning
暂未订购 下载PDF
In-situ monitoring of layer-wise process quality and signal analysis for laser powder bed fusion using multi-source optical signal 认领 引用
7
作者 Di Wang Tao Tang +10 位作者 Tingyi Wang Renwu Jiang Xiaoqiang Zheng Long Zhou Laizhu Chen Wenlong Chen Pan Wang Zhiguang Zhou Ying Ma Yongqiang Yang Linqing Liu 《Additive Manufacturing Frontiers》 CAS CSCD 2026年第2期59-77,共19页
Laser powder bed fusion is a key metal additive manufacturing technology capable of fabricating geometrically complex parts,yet its reliable industrial adoption is hindered by the inherent complexity and stochastic de... Laser powder bed fusion is a key metal additive manufacturing technology capable of fabricating geometrically complex parts,yet its reliable industrial adoption is hindered by the inherent complexity and stochastic defect formation of the process.Current quality assessment is constrained by the inherent latency of offline methods and the diagnostic limitations of single-sensor monitoring.To address these challenges,this study developed a multi-source optical signal monitoring system integrating coaxial photodiodes and an off-axis industrial camera to achieve simultaneous powder spreading detection and radiation signal monitoring during LPBF layer-wise process quality monitoring.Based on the successful identification and analysis of typical detectable features,the YOLOv5s deep learning model was employed to achieve rapid and accurate detection of lack-of-powder defects during the printing process.The training results indicated that the model exhibited good performance metrics.The relationships between process parameters,typical defects,and multi-channel monitoring data were also investigated.The monitoring system achieved a spatial resolution of 300μm for in-process monitoring and demonstrated high accuracy in detecting various defect types,including lack of powder,pores,warping,stitching seams,and printing failures.Furthermore,the algorithm-detected signal anomalies exhibited good spatial correlation with the actual surface defects.Simultaneously,wavelet time-frequency analysis was employed to evaluate molten pool dynamic stability under different process parameters and to analyze energy distribution for different defects.Furthermore,3D model reconstruction from signals enabled effective correlation with actual part defects.Based on the signal-driven process optimization,complex conformal cooling molds were successfully fabricated with a grafting accuracy error of less than 0.12 mm on high-performance substrates,demonstrating the practical efficacy of the developed monitoring methodology.This study provides both a technological and a theoretical foundation for intelligent quality control in LPBF and its practical implementation in industry. 展开更多
关键词 Laser powder bed fusion Multi-source optical signal Signal analysis Layer-wise quality monitoring
暂未订购 下载PDF
A Survey of Key Technologies for Multi-source Heterogeneous Data in Intelligent Manufacturing 认领 引用
8
作者 Minghao Zhu Pengfei Yang +2 位作者 Bo Gao Xuehan Li Letian Wang 《Instrumentation》 2026年第1期26-39,共14页
Currently,most enterprises have adopted information software and digital equipment and gradually established digital factories.They conduct enterprise data collection and decision-support activities,generating large v... Currently,most enterprises have adopted information software and digital equipment and gradually established digital factories.They conduct enterprise data collection and decision-support activities,generating large volumes of multi-source heterogeneous data across all stages of the product life cycle.However,current data utilization methods remain simplistic,and the goal of leveraging multi-source heterogeneous data to drive manufacturing value has yet to be fully realized.To address this issue,this study first defines the concept and characteristics of multi-source heterogeneous data in intelligent manufacturing,based on an analysis of its relationship with industrial big data.Then,integrating principles from data science,a technological framework for multi-source heterogeneous data is proposed.The key technologies involved in each stage of data processing are investigated,and typical applications of such data in intelligent manufacturing are discussed.Finally,this paper analyzes the challenges and future development directions of multi-source heterogeneous data processing in intelligent manufacturing.The goal is to provide theoretical and technical support for integrating intelligent manufacturing with data science. 展开更多
关键词 intelligent manufacturing multi-source heterogeneous data feature fusion data system technological framework
暂未订购 下载PDF
Hybrid Deep Learning for Hydraulic Cylinder Fault Diagnosis under Complex Conditions via Multi-Source Signal Fusion 认领 引用
9
作者 Chen Yang Jianwen Yan +2 位作者 Yixiong Feng Lei Li Jianrong Tan 《Instrumentation》 2026年第1期40-56,共17页
Hydraulic presses are indispensable in automotive and aerospace manufacturing,with hydraulic cylinders serving as key components for operational safety and product quality.Internal leakage faults in hydraulic cylinder... Hydraulic presses are indispensable in automotive and aerospace manufacturing,with hydraulic cylinders serving as key components for operational safety and product quality.Internal leakage faults in hydraulic cylinders are difficult to diagnose due to the scarcity of labeled data,the complexity of fault mechanisms,and the limited representation capability of single-signal methods under variable operating conditions.To address these issues,a hybrid deep learning feature fusion model based on displacement error and pressure signal,including convolutional autoencoder,multi-head attention mechanism,residual network and bidirectional long short time series neural network(CAEMRAB),is proposed for the diagnosis and classification of leakage faults in hydraulic cylinders.A hydraulic cylinder test system simulates heavy load,variable speed,and nonlinear motion under actual operating conditions.Through the all-round deep feature decoupling of the proposed model,the multi-source signal representation ability in complex and multi-noise environments is enhanced,effectively extracting the local and global features of displacement error and pressure signal fault data and achieving efficient classification.Experimental results indicate that the proposed model achieves at least a 3.95%improvement in diagnostic accuracy compared with ablation models.In addition,it exhibits high diagnostic stability across other models,single-signal diagnosis,varying sample sizes,and complex noise conditions.These experiments fully validate the superior performance of the proposed method in terms of diagnostic accuracy,reliability,and robustness. 展开更多
关键词 hydraulic cylinder feature fusion multi-source signal hybrid deep learning deep feature decoupling
暂未订购 下载PDF
Optimizing Energy Efficiency in Tunnel Boring Machine Rock Breaking via Multi-source Data Fusion 认领 引用 被引量：1
10
作者 Xiaojun Yan Wencong Qi +4 位作者 Chuan Qu Minghui Ma Shanglin Liu Qian Zhang Xuesong Cheng 《Acta Mechanica Solida Sinica》 SCIE EI CSCD 2026年第4期481-493,共13页
The era of big data has profoundly transformed mechanics research,with data-driven approaches playing a vital role in modeling and optimization.This study focuses on tunnel boring machine(TBM),where the thrust-torque ... The era of big data has profoundly transformed mechanics research,with data-driven approaches playing a vital role in modeling and optimization.This study focuses on tunnel boring machine(TBM),where the thrust-torque ratio is a key determinant of their tunneling energy efficiency.However,due to the complexity of experiments and the testing requirements,obtaining sufficient high-quality data under varying geological conditions remains a major challenge in optimizing the tunneling energy efficiency of TBM.To address this,multi-cutter rotary cutting machine experiments and numerical simulations were conducted on 22 different rock types.Comprehensive datasets of normal and rolling forces were systematically collected.Using specific energy(SE)as the rock-breaking efficiency metric,we integrated physical and numerical data through a CatBoost-based fusion framework.The predictive model was initially trained on simulation data to capture the relationships among penetration,uniaxial compressive strength,tensile strength,and SE,and was subsequently fine-tuned with experimental data to develop the final fused model.Compared to models trained solely on experimental or simulated data,the fused model reduced RMSE by 37.1%and 58.6%,respectively,and improved R2by 19.0%and 44.6%,thereby enhancing both prediction accuracy and generalization capability.Furthermore,Bayesian optimization was employed to minimize SE and identify the optimal penetration.The results indicate that as rock strength increases,the optimal penetration decreases,while the corresponding minimal SE increases.These findings provide theoretical and engineering insights for improving TBM energy efficiency and parameter optimization,while establishing a robust data fusion framework for mechanical data analysis. 展开更多
关键词 Multi-source data fusion CatBoost Tunnel boring machine Multi-cutter rock-breaking Energy efficiency
暂未订购 下载PDF
Monitoring of agricultural drought based on multi-source remote sensing data in Heilongjiang Province,China 认领 引用
11
作者 Chenfa Jiang Changhui Ma +4 位作者 Sibo Duan Xiaoxiao Min Youzhi Zhang Dandan Li Xia Zhang 《Journal of Integrative Agriculture》 SCIE CAS CSCD 2026年第4期1716-1730,共15页
Agriculture is the foundation of socio-economic development and is highly influenced by weather and climate conditions.Drought is one of the most significant threats to agricultural development and food security.Curre... Agriculture is the foundation of socio-economic development and is highly influenced by weather and climate conditions.Drought is one of the most significant threats to agricultural development and food security.Currently,in-situ drought monitoring based on weather stations and based on remote sensing data has limitations,including infrequent updates,limited coverage,and low accuracy.This study leverages multi-source remote sensing data to monitor agricultural drought in Heilongjiang Province,China.We developed multi-source composite drought indices(MCDIs)at various timescales(3,6,9,and 12 months)by integrating precipitation,land surface temperature,soil moisture,and vegetation indices.Utilizing remote sensing data from various sources,we calculated a series of single drought indices,which are the precipitation condition index,soil moisture condition index,vegetation condition index,and temperature condition index.These are then integrated into MCDIs using a multivariable linear regression approach.The analysis reveals that MCDIs correlate more with standardized precipitation evapotranspiration index(SPEI)than single drought indices.When examining the correlation between different MCDIs and the affected area of crops and major grain production,MCDI-9 showed the highest correlation with the affected area of crops,while MCDI-12 showed the highest correlation with grain production.This suggests that these two MCDIs at different timescales are better indicators of agricultural drought.The spatio-temporal analysis of MCDI indicates that drought in Heilongjiang Province primarily occurs in early spring,gradually spreading from the Greater Khingan Mountains region to the southeastern plains.The drought gradually alleviates during the summer,ending by the autumn harvest period.Therefore,the MCDIs constructed in this study can serve as effective methods and indicators for drought monitoring in Heilongjiang Province and similar regions. 展开更多
关键词 agricultural drought spatio-temporal monitoring multi-source remote sensing data SPEI Heilongjiang Province
暂未订购 下载PDF
CCDNN:A Novel Deep Learning Architecture for Multi-Source Data Fusion 认领 引用
12
作者 Zhiwen Chen Siwen Mo +4 位作者 Haobin Ke Steven X.Ding Zhaohui Jiang Chunhua Yang Weihua Gui 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2026年第3期555-567,共13页
With the rapid development of Industrial 4.0 and Industrial Internet of Things,the data collection with multisource has significantly improved.How to effectively fuse these data for various engineering applications is... With the rapid development of Industrial 4.0 and Industrial Internet of Things,the data collection with multisource has significantly improved.How to effectively fuse these data for various engineering applications is still an open and challenge issue.To this end,we propose the canonical correlation guided deep neural network(CCDNN),a novel deep learning architecture,to learn a correlated representation for multi-source data fusion.Unlike the linear canonical correlation analysis(CCA),kernel CCA and deep CCA,in the proposed method,the optimization formulation is not restricted to maximize correlation,instead we make canonical correlation as a constraint,which preserves the correlated representation learning ability and focuses more on the engineering tasks endowed by optimization formulation,such as reconstruction,classification and prediction.Furthermore,to reduce the redundancy induced by correlation,a redundancy filter is designed.We illustrate its data fusion ability via correlated representation learning and superior performance on various engineering tasks.In experiments on MNIST dataset,the results show that CCDNN has better reconstruction performance in terms of mean squared error and mean absolute error than deep CCA and deep canonically correlated autoencoders(DCCAE).Also,we present the application of the proposed network to industrial fault diagnosis and remaining useful life cases for the classification and prediction tasks accordingly.The proposed method demonstrates approving performance in both tasks when compared to existing methods.Extension of CCDNN to much more deeper with the aid of residual connection is also presented in Appendix. 展开更多
关键词 Canonical correlation analysis(CCA) correlated representation learning deep learning fault diagnosis multi-source data fusion remaining useful life
暂未订购 下载PDF
EDTM:Efficient Domain Transition for Multi-Source Domain Adaptation 认领 引用
13
作者 Mangyu Lee Jaekyun Jeong +2 位作者 Yun Wook Choo Keejun Han Jungeun Kim 《Computer Modeling in Engineering & Sciences》 SCIE EI 2026年第2期955-970,共16页
Domain adaptation aims to reduce the distribution gap between the training data(source domain)and the target data.This enables effective predictions even for domains not seen during training.However,most conventional ... Domain adaptation aims to reduce the distribution gap between the training data(source domain)and the target data.This enables effective predictions even for domains not seen during training.However,most conventional domain adaptation methods assume a single source domain,making them less suitable for modern deep learning settings that rely on diverse and large-scale datasets.To address this limitation,recent research has focused on Multi-Source Domain Adaptation(MSDA),which aims to learn effectively from multiple source domains.In this paper,we propose Efficient Domain Transition for Multi-source(EDTM),a novel and efficient framework designed to tackle two major challenges in existing MSDA approaches:(1)integrating knowledge across different source domains and(2)aligning label distributions between source and target domains.EDTM leverages an ensemble-based classifier expert mechanism to enhance the contribution of source domains that are more similar to the target domain.To further stabilize the learning process and improve performance,we incorporate imitation learning into the training of the target model.In addition,Maximum Classifier Discrepancy(MCD)is employed to align class-wise label distributions between the source and target domains.Experiments were conducted using Digits-Five,one of the most representative benchmark datasets for MSDA.The results show that EDTM consistently outperforms existing methods in terms of average classification accuracy.Notably,EDTM achieved significantly higher performance on target domains such as Modified National Institute of Standards and Technolog with blended background images(MNIST-M)and Street View House Numbers(SVHN)datasets,demonstrating enhanced generalization compared to baseline approaches.Furthermore,an ablation study analyzing the contribution of each loss component validated the effectiveness of the framework,highlighting the importance of each module in achieving optimal performance. 展开更多
关键词 Multi-source domain adaptation imitation learning maximum classifier discrepancy ensemble based classifier EDTM
暂未订购 下载PDF
Temporal and spatial variations in evapotranspiration on the northern slope of the Kunlun Mountains based on multi-source datasets 认领 引用
14
作者 YuanYuan Zhang MingJun Zhang +2 位作者 ShiQin Xu CunWei Che QinQin Du 《Research in Cold and Arid Regions》 CAS CSCD 2026年第1期59-70,共12页
By combining eight types of evapotranspiration datasets,the spatial and temporal variations in the evapotranspiration(ET)on the northern slope of the Kunlun Mountains were analyzed in uninhabited areas that lack obser... By combining eight types of evapotranspiration datasets,the spatial and temporal variations in the evapotranspiration(ET)on the northern slope of the Kunlun Mountains were analyzed in uninhabited areas that lack observational data.The order of the average annual ET was ERA5_Land(312.32 mm/a)>CR(239.80 mm/a)>MOD16STM(211.87 mm/a)>GLADS(119.02 mm/a)>ETM(111.88 mm/a)>EB-ET(109.90 mm/a)>GLEAM(100.84 mm/a)>MERRA-2(100.81 mm/a).The ET value from the ERA5_Land dataset was three times higher than that of the other five datasets.The ET values of the CR and MOD16STM datasets were twice that of the other five datasets.In terms of time,the correlation coefficient between the GLEAM and MERRA-2 datasets was the highest(R?0.82).In terms of space,GLDAS and MERRA-2 had the highest multi-year average ET correlation coefficient(R?0.80).The reduction in spatial scale resulted in clear differences in the multi-year average ET correlations among different products in the same region.In terms of time,the average annual ET of the basins on the northern slope of the Kunlun Mountains exhibited an overall increasing trend for all data sources,and the overall annual average change in the study area estimated by the eight datasets was 1.09 mm/a.The most rapid rates of increase were obtained from GLDAS(1.38 mm/a)and GLEAM(1.38 mm/a).In the CR,ERA5_Land,GLEAM,GLDAS,MERRA-2,ETM,MOD16STM,and EB-ET datasets,46.46%,41.47%,87.30%,40.30%,49.10%,47.13%,57.16%,and 45.12%of the watersheds,respectively,showed a significantly increasing trend.The ET value of the Yarkand River Basin showed a significantly increasing trend for all eight data sources.The results of this study provide a scientific reference for the allocation of water resources on the northern slope of the Kunlun Mountains. 展开更多
关键词 North slope basin of Kunlun Mountains Evapotranspiration Multi-source data Climate change
暂未订购 下载PDF
WAFDect:A Malware Detection Model Based on Multi-Source Feature Fusion 认领 引用
15
作者 Xian Wu Liang Wan +1 位作者 Jingxia Ren Bangfeng Zhang 《Computers, Materials & Continua》 SCIE EI 2026年第7期1183-1202,共20页
Traditional malware detection models rely on a single feature source for detection,resulting in high false positive or false negative rates due to incomplete information.In addition,conventional models depend on manua... Traditional malware detection models rely on a single feature source for detection,resulting in high false positive or false negative rates due to incomplete information.In addition,conventional models depend on manual feature engineering,which is inefficient and hard to adapt to new malware variants.To address these challenges,this paper proposes a malware detection model called WAFDect based on a self-attention mechanism with multi-source feature fusion.The model consists of two key designs.First,we construct a multi-source feature extraction model that analyzes multi-source data such as API call sequences,registry operation logs,file operation logs,and network behavior logs,capturing malware characteristics at multiple abstraction levels and building a global representation of maliciousness,thereby overcoming the problem of single feature sources in traditional models.Second,to address the heterogeneity of multi-source features in terms of dimension,scale,and semantics,we design a feature alignment module based on attention weights.This module can dynamically learn the association strength between different feature modalities and achieve semantic alignment and adaptive fusion of cross-modal features through a weighting allocation mechanism,effectively reducing the reliance on manual feature engineering in traditional methods.The experimental results indicate that WAFDect achieved excellent detection performance on the Speakeasy(trainset)and Avast-CTU_Small datasets,with accuracies of 0.9229 and 0.9878,respectively.Compared with traditional detection models,this method shows significant improvements in key metrics such as accuracy and F1 score,thereby validating its effectiveness. 展开更多
关键词 Malware detection multi-source feature fusion dynamic analysis self-attention mechanism
暂未订购 下载PDF
An Optimized Ensemble Learning Framework for Energy Efficiency Assessment in Low-Voltage Distribution Networks Using Multi-Source Data Integration 认领 引用
16
作者 Yujie Shi Guoxing Wu +2 位作者 Qingwei Wang Xieli Fu Wenfeng Yang 《Energy Engineering》 EI 2026年第9期350-375,共26页
This study proposes an optimized ensemble learning framework for energy-efficiency assessment in low-voltage distribution networks by integrating multiple data sources.The framework integrates heterogeneous data from ... This study proposes an optimized ensemble learning framework for energy-efficiency assessment in low-voltage distribution networks by integrating multiple data sources.The framework integrates heterogeneous data from smart meters,SCADA systems,meteorological stations,and network topology databases,employing advanced feature engineering to extract 89 essential predictors from 147 initial features.Three gradient boosting algorithms-Random Forest,XGBoost,and LightGBM-are combined through an elastic net stacking strategy with Bayesian hyperparameter optimization.The stacking ensemble achieved superior performance with an MAE of 118.4 kWh,an RMSE of 164.2 kWh,an MAPE of 3.98%,and an R2of 0.952,representing 16.8%improvement over individual models.SHAP analysis provided model interpretability,identifying temperature,historical consumption,and temporal features as the primary drivers of efficiency.The framework demonstrated robust performance under data quality degradation and successfully generalized across diverse network configurations.Field implementation yielded an 8.3%reduction in distribution losses(95%CI:7.2%-9.4%,p<0.0001),34%decrease in transformer failure rates(95%CI:28%-40%,p=0.003),and 12%-15%operational cost reduction.The framework's ability to provide accurate predictions from 15 min to 24 h ahead while maintaining computational efficiency enables proactive distribution network management,supporting the transition toward efficient and sustainable power systems. 展开更多
关键词 Ensemble learning energy efficiency assessment low-voltage distribution networks multi-source data integration SHAP analysis
暂未订购 下载PDF
Construction of an Early Warning Model for Sepsis Complicating Severe Acute Pancreatitis Based on Multi-source Physiological Signal Fusion 认领 引用
17
作者 HU Jin-jin DENG Xing +1 位作者 LU Zhi-ping QUE Gan-bo 《Chinese Journal of Biomedical Engineering(English Edition)》 CAS 2026年第1期16-25,共10页
Objective:To construct an early warning model for sepsis complicating severe acute pancreatitis based on multi-source physiological signal fusion,improve the efficiency of early sepsis identification,and provide objec... Objective:To construct an early warning model for sepsis complicating severe acute pancreatitis based on multi-source physiological signal fusion,improve the efficiency of early sepsis identification,and provide objective decision-making evidence for clinical early intervention.Methods:A total of 66 patients diagnosed with severe acute pancreatitis admitted from February 2019 to February2024 were enrolled and divided into sepsis and non-sepsis groups.Multi-dimensional data were collected,including dynamic physiological signals(electrocardiography,respiration,blood pressure)and routine laboratory biomarkers(procalcitonin,white blood cell count).All signals underwent targeted preprocessing,and multi-domain features were extracted from time,frequency,and nonlinear dimensions.Weighted feature fusion and principal component analysis(PCA)were performed for dimensionality reduction,and 24 core principal components were finally retained.A hybrid deep learning model integrating convolutional neural network(CNN)and long shortterm memory(LSTM)was established.The overall dataset was randomly divided into a training set and a validation set at a ratio of 7∶3.Model performance was quantitatively evaluated using accuracy,sensitivity,specificity,and the area under the receiver operating characteristic curve(AUC),and was further compared with conventional single infection biomarkers.Results:Feature weight analysis demonstrated that procalcitonin,respiratory rate variability,and standard deviation of mean arterial pressure were the dominant core warning features.In the validation cohort,the proposed model achieved an accuracy of 85.0%,a sensitivity of 83.3%,a specificity of86.7%,and an AUC of 0.903(95%CI:0.786-0.969),which was significantly superior to traditional biomarkers including procalcitonin and white blood cell count(P<0.001).The model provided early sepsis warnings at an average time of(18.56±6.13)h before clinical confirmation,and 72.0%of patients acquired a clinical intervention window of no less than 12 h.Conclusion:The multi-source physiological signal fusion model integrates dynamic physiological time-series signals and static laboratory indicators to effectively capture subtle and complex early physiological perturbations during sepsis progression.It exhibits superior performance in both warning accuracy and timeliness compared with conventional detection methods,which serves as a reliable quantitative tool for early identification of sepsis in patients with severe acute pancreatitis. 展开更多
关键词 multi-source physiological signal fusion severe acute pancreatitis sepsis early warning model machine learning
Research on Rapid Update and Accuracy Improvement of DOM Based on Multi-source Aerial Data Fusion 认领 引用
18
作者 GAN Yuting 《外文科技期刊数据库（文摘版）自然科学》 2026年第1期042-045,共4页
As a core geospatial data product, Digital Orthophoto Map (DOM) plays a key role in many fields such as urban planning, disaster assessment, engineering surveying and mapping, and topographic mapping. With the increas... As a core geospatial data product, Digital Orthophoto Map (DOM) plays a key role in many fields such as urban planning, disaster assessment, engineering surveying and mapping, and topographic mapping. With the increasing requirements of various industries for the timeliness and accuracy of DOM, the traditional single-data-source update method can hardly meet the actual needs. Aiming at this problem, this paper deeply studies the rapid update and accuracy improvement methods of DOM driven by multi-source aerial data fusion. The research shows that multi-source aerial data fusion technology can effectively improve the efficiency and accuracy of DOM update, providing reliable support for the efficient application of geospatial data. 展开更多
关键词 multi-source aerial data data fusion Digital Orthophoto Map (DOM) rapid update accuracy optimization
暂未订购 下载PDF
Fracturing mechanism of pre-damaged granite induced by multi-source dynamic disturbances in tunnels 认领 引用 被引量：2
19
作者 Biao Wang Benguo He +1 位作者 Xiating Feng Hongpu Li 《International Journal of Mining Science and Technology》 SCIE EI CAS CSCD 2025年第9期1439-1459,共21页
To elucidate the fracturing mechanism of deep hard rock under complex disturbance environments,this study investigates the dynamic failure behavior of pre-damaged granite subjected to multi-source dynamic disturbances... To elucidate the fracturing mechanism of deep hard rock under complex disturbance environments,this study investigates the dynamic failure behavior of pre-damaged granite subjected to multi-source dynamic disturbances.Blasting vibration monitoring was conducted in a deep-buried drill-and-blast tunnel to characterize in-situ dynamic loading conditions.Subsequently,true triaxial compression tests incorporating multi-source disturbances were performed using a self-developed wide-low-frequency true triaxial system to simulate disturbance accumulation and damage evolution in granite.The results demonstrate that combined dynamic disturbances and unloading damage significantly accelerate strength degradation and trigger shear-slip failure along preferentially oriented blast-induced fractures,with strength reductions up to 16.7%.Layered failure was observed on the free surface of pre-damaged granite under biaxial loading,indicating a disturbance-induced fracture localization mechanism.Time-stress-fracture-energy coupling fields were constructed to reveal the spatiotemporal characteristics of fracture evolution.Critical precursor frequency bands(105-150,185-225,and 300-325 kHz)were identified,which serve as diagnostic signatures of impending failure.A dynamic instability mechanism driven by multi-source disturbance superposition and pre-damage evolution was established.Furthermore,a grouting-based wave-absorption control strategy was proposed to mitigate deep dynamic disasters by attenuating disturbance amplitude and reducing excitation frequency. 展开更多
关键词 Multi-source dynamic disturbances Blasting vibration Deep-buried tunnel Acoustic emission Time-delayed rockburst
暂未订购 下载PDF
Monitoring track irregularities using multi-source on-board measurement data 认领 引用 被引量：1
20
作者 Qinglin Xie Fei Peng +4 位作者 Gongquan Tao Yu Ren Fangbo Liu Jizhong Yang Zefeng Wen 《Railway Engineering Science》 EI 2025年第4期746-765,共20页
Accurate monitoring of track irregularities is very helpful to improving the vehicle operation quality and to formulating appropriate track maintenance strategies.Existing methods have the problem that they rely on co... Accurate monitoring of track irregularities is very helpful to improving the vehicle operation quality and to formulating appropriate track maintenance strategies.Existing methods have the problem that they rely on complex signal processing algorithms and lack multi-source data analysis.Driven by multi-source measurement data,including the axle box,the bogie frame and the carbody accelerations,this paper proposes a track irregularities monitoring network(TIMNet)based on deep learning methods.TIMNet uses the feature extraction capability of convolutional neural networks and the sequence map-ping capability of the long short-term memory model to explore the mapping relationship between vehicle accelerations and track irregularities.The particle swarm optimization algorithm is used to optimize the network parameters,so that both the vertical and lateral track irregularities can be accurately identified in the time and spatial domains.The effectiveness and superiority of the proposed TIMNet is analyzed under different simulation conditions using a vehicle dynamics model.Field tests are conducted to prove the availability of the proposed TIMNet in quantitatively monitoring vertical and lateral track irregularities.Furthermore,comparative tests show that the TIMNet has a better fitting degree and timeliness in monitoring track irregularities(vertical R2 of 0.91,lateral R2 of 0.84 and time cost of 10 ms),compared to other classical regression.The test also proves that the TIMNet has a better anti-interference ability than other regression models. 展开更多
关键词 Track irregularities Vehicle accelerations On-board monitoring Multi-source data Deep learning
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 12 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈