检索结果-南通市图书馆

Journal of Dynamics, Monitoring and Diagnostics 2022年第1期1卷 2-8页

作者： Wenting Wang Yaguo Lei Tao Yan Naipeng Li asoke knandi Key Laboratory of Education Ministry for Modern Design&Rotor-Bearing System Xi’an Jiaotong UniversityXi’anChina Department of Electronic and Electrical Engineering Brunel University LondonUxbridgeUK School of Mechanical Engineering Xi’an Jiaotong UniversityXi’anChina

Recently,deep learning(DL)has been widely used in the field of remaining useful life(RUL)*** various DL technologies,recurrent neural network(RNN)and its variant,e.g.,long short-term memory(LSTM)network,have gained extensive attention for their ability to capture temporal *** existing RNN-based methods have demonstrated their RUL prediction effectiveness,they still suffer from the following two limitations:1)it is difficult for the RNN to directly extract degradation features from original monitoring data and 2)most RNN-based prognostics methods are unable to quantify RUL *** address the aforementioned limitations,this paper proposes a new prognostics method named residual convolution LSTM(RC-LSTM)*** the RC-LSTM,a new ResNet-based convolution LSTM(Res-ConvLSTM)layer is stacked with a convolution LSTM(ConvLSTM)layer to extract degradation representations from monitoring ***,under the assumption that the RUL follows a normal distribution,an appropriate output layer is constructed to quantify the uncertainty of prediction ***,the effectiveness and superiority of the RC-LSTM are verified using monitoring data from accelerated bearing degradation tests.

关键词： Deep learning residual convolution LSTM network remaining useful life prediction uncertainty quantification

Label Recovery and Trajectory Designable Network for Transfer Fault Diagnosis of Machines With Incorrect Annotation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 932-945页

作者： Bin Yang Yaguo Lei Xiang Li Naipeng Li asoke K.Nandi the Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System the School of Mechanical EngineeringXi’an Jiaotong UniveristyXi’an 710049 the Hunan Provincial Key Labortory of Health Maintenance for Mechanical Equipment Hunan Univeristy of Science and TechnologyXiangtan 411201China the Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System Xi’an Jiaotong UniveristyXi’an 710049China the Department of Electronic and Electrical Engineering Brunel University LondonUxbridge UB83PHUK

The success of deep transfer learning in fault diagnosis is attributed to the collection of high-quality labeled data from the source ***,in engineering scenarios,achieving such high-quality label annotation is difficult and *** incorrect label annotation produces two negative effects:1)the complex decision boundary of diagnosis models lowers the generalization performance on the target domain,and2)the distribution of target domain samples becomes misaligned with the false-labeled *** overcome these negative effects,this article proposes a solution called the label recovery and trajectory designable network(LRTDN).LRTDN consists of three ***,a residual network with dual classifiers is to learn features from cross-domain ***,an annotation check module is constructed to generate a label anomaly indicator that could modify the abnormal labels of false-labeled samples in the source *** the training of relabeled samples,the complexity of diagnosis model is reduced via semi-supervised ***,the adaptation trajectories are designed for sample distributions across *** ensures that the target domain samples are only adapted with the pure-labeled *** LRTDN is verified by two case studies,in which the diagnosis knowledge of bearings is transferred across different working conditions as well as different yet related *** results show that LRTDN offers a high diagnosis accuracy even in the presence of incorrect annotation.

关键词： Deep transfer learning domain adaptation incorrect label annotation intelligent fault diagnosis rotating machines

Uncertainty-Aware Deep Learning: A Promising Tool for Trustworthy Fault Diagnosis

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第6期11卷 1317-1330页

作者： Jiaxin Ren Jingcheng Wen Zhibin Zhao Ruqiang Yan Xuefeng Chen asoke K.Nandi School of Mechanical Engineering Xi’an Jiaotong UniversityXi’an 710049China Department of Electronic and Electrical Engineering Brunel University LondonKingston LaneUxbridgeUB83PHUK IEEE

Recently,intelligent fault diagnosis based on deep learning has been extensively investigated,exhibiting state-of-the-art ***,the deep learning model is often not truly trusted by users due to the lack of interpretability of“black box”,which limits its deployment in safety-critical applications.A trusted fault diagnosis system requires that the faults can be accurately diagnosed in most cases,and the human in the deci-sion-making loop can be found to deal with the abnormal situa-tion when the models *** this paper,we explore a simplified method for quantifying both aleatoric and epistemic uncertainty in deterministic networks,called *** SAEU,Multivariate Gaussian distribution is employed in the deep architecture to compensate for the shortcomings of complexity and applicability of Bayesian neural *** on the SAEU,we propose a unified uncertainty-aware deep learning framework(UU-DLF)to realize the grand vision of trustworthy fault ***,our UU-DLF effectively embodies the idea of“humans in the loop”,which not only allows for manual intervention in abnor-mal situations of diagnostic models,but also makes correspond-ing improvements on existing models based on traceability ***,two experiments conducted on the gearbox and aero-engine bevel gears are used to demonstrate the effectiveness of UU-DLF and explore the effective reasons behind.

关键词： Out-of-distribution detection traceability analysis trustworthy fault diagnosis uncertainty quantification.

Research on Indoor Positioning Technology of WSN based on T-RL Partition Path Model

在线全文

学校读者我要写书评

暂无评论

Journal of Communications and Information Networks 2024年第3期9卷 219-232页

作者： Wei Wang Xinlin Wang Yutong Liu Yulin Ren Maozhen Li asoke K.Nandi School of Information and Communication Engineering North University of ChinaTaiyuan 030051China Department of Electronic and Computer Engineering Brunel University LondonUxbridge UB83PHUK

To address the issues of unstable received signal strength indicator(RSSI)and low indoor positioning accuracy caused by walls and obstacles,the propagation conditions of the wireless communication system are categorized into two distinct environments:line-of-sight(LOS)and non-line-of-sight(NLOS).In the LOS environment,the traditional logarithmic path loss model is *** the NLOS environment,the impact of walls on signal transmission is considered,leading to the development of a multi-wall path loss model based on the T-RL method,with improvements made to the key parameter,the Fresnel coefficient *** breakpoint value d=2.3 m in the partitioned model is determined,and the positional coordinates of the unknown nodes are calculated using the trilateration *** results indicate that the T-RL based multi-wall model improves localization accuracy by 47%in NLOS environments compared to the traditional logarithmic path loss *** average localization error using the T-RL partitioned path loss model is 0.7021 m,representing a 55.9%improvement over the logarithmic path loss model and a 16.8%enhancement over the T-RL attenuation multi-wall model,thereby providing better environmental adaptability.

关键词： WSN indoor positioning loss model reflection transmission RSSI

Connected Components-based Colour Image Representations of Vibrations for a Two-stage Fault Diagnosis of Roller Bearings Using Convolutional Neural Networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Mechanical Engineering 2021年第3期34卷 73-93页

作者： Hosameldin O.A.Ahmed asoke K Nandi Department of Electronic and Electrical Engineering Brunel University LondonUxbridge UB83PHUK School of Mechanical Engineering Xi’an Jiaotong UniversityXi’anChina

Roller bearing failure is one of the most common faults in rotating *** techniques for bearing fault diagnosis based on faults feature extraction have been *** feature extraction from fault signals requires expert prior information and human ***,deep learning algorithms have been applied extensively in the condition monitoring of rotating machines to learn features automatically from the input *** its robust performance in image recognition,the convolutional neural network(CNN)architecture has been widely used to learn automatically discriminative features from vibration images and classify health *** paper proposes and evaluates a two-stage method RGBVI-CNN for roller bearings fault *** first stage in the proposed method is to generate the RGB vibration images(RGBVIs)from the input vibration *** begin this process,first,the 1-D vibration signals were converted to 2-D grayscale vibration *** the conversion was completed,the regions of interest(ROI)were found in the converted 2-D grayscale vibration ***,to produce vibration images with more discriminative characteristics,an algorithm was applied to the 2-D grayscale vibration images to produce connected components-based RGB vibration images(RGBVIs)with sets of colours and texture *** the second stage,with these RGBVIs a CNN-based architecture was employed to learn automatically features from the RGBVIs and to classify bearing health *** cases of fault classification of rolling element bearings are used to validate the proposed *** results of this investigation demonstrate that RGBVI-CNN can generate advantageous health condition features from bearing vibration signals and classify the health conditions under different working loads with high ***,several classification models trained using RGBVI-CNN offered high performance in the testing results of the overall classification accura

关键词： Bearing fault diagnosis Image representation of vibrations Deep learning Convolutional neural networks

Aggregate dust model to study the polarization properties of comet C/1996 B2 Hyakutake

在线全文

学校读者我要写书评

暂无评论

Research in Astronomy and Astrophysics 2010年第4期10卷 355-362页

作者： Himadri Sekhar Das Abinash Suklabaidya Saonli Datta Majumder asoke Kumar Sen Department of Physics Assam University

The observed linear polarization data of comet Hyakutake are studied at wavelengths λ=0.365 μm,λ=0.485 μm and 0.684μm through simulations using Ballistic Particle-Cluster Aggregate and Ballistic Cluster-Cluster Aggregate aggregates of 128 spherical *** first found that the size parameter of the monomer,x ～ 1.56-1.70,turned out to be the most suitable which provides the best fits to the observed dust scattering properties at three wavelengths：λ=0.365 μm,0.485μm and 0.684μ***,the effective radius of the aggregate （r） lies in the range 0.45 μm ≤ r ≤ 0.49 μm at λ=0.365 μm;0.60 μm ≤ r ≤ 0.66 μm at λ=0.485 μm and 0.88 μm ≤ r ≤ 0.94 μm at λ=0.684 μ*** using superposition T-MATRIX code and the power-law size distribution,n（r）～ r-3,the best-fitting values of complex refractive indices are calculated for the observed polarization data at the above three *** best-fitting complex refractive indices （n,k） are found to be （1.745,0.095） at λ=0.365 μm,（1.743,0.100） at λ=0.485 μm and （1.695,0.100） at λ=0.684 μ*** refractive indices derived from the present analysis correspond to a mixture of both silicates and organics,which are in good agreement with the in situ measurement of comets by different spacecraft.

关键词： comets:general - dust extinction - scattering - polarization

Optical spectroscopy and photometry of main-belt asteroids with a high orbital inclination

在线全文

学校读者我要写书评

暂无评论

Research in Astronomy and Astrophysics 2017年第2期17卷 43-50页

作者： Aya Iwai Yoichi Itoh Tsuyoshi Terai Ranjan Gupta asoke Sen Jun Takahashi National Institute of Advanced Industrial Science and Technology Ibaraki 305-8563Japan Nishi-Harima Astronomical Observatory Center for AstronomyUniversity of HyogoISIyogo 679-5313Japan National Astronomical Observatory of Japan HiloHawaii 96720USA Inter-University Centre for Astronomy and Astrophysics GaneshkhindPune 411 007India Department of Physics Assam UniversitySilchar 788 001India

We carried out low-resolution optical spectroscopy of 51 main-belt asteroids, most of which have highly-inclined orbits. They are selected from D-type candidates in the SDSS-MOC 4 catalog. Using the University of Hawaii 2.2 m telescope and the Inter-University Centre for Astronomy and Astrophysics 2 m telescope in India, we determined the spectral types of 38 asteroids. Among them, eight asteroids were classified as D-type asteroids. Fractions of D-type asteroids are 3.0 ± 1.1% for low orbital inclination main-belt asteroids and 7.3 ± 2.0% for high orbital inclination main-belt asteroids. The results of our study indicate that some D-type asteroids were formed within the ecliptic region between the main belt and Jupiter, and were then perturbed by Jupiter.

关键词： minor planets, asteroids general -- techniques spectroscopic

Scale‐wise interaction fusion and knowledge distillation network for aerial scene recognition

在线全文

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2023年第4期8卷 1178-1190页

作者： Hailong Ning Tao Lei Mengyuan An Hao Sun Zhanxuan Hu asoke K.Nandi School of Computer Science and Technology Xi'an University of Posts and TelecommunicationsShaanxi Key Laboratory of Network Data Analysis and Intelligent ProcessingXi'anChina Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'anChina School of Electronic Information and Artificial Intelligence Shaanxi University of Science and TechnologyXi'anChina School of Computer Central China Normal UniversityWuhanChina Department of Electronic and Electrical Engineering Brunel University LondonLondonUK Xi'an Jiaotong University Xi'anChina

Aerial scene recognition(ASR)has attracted great attention due to its increasingly essential *** of the ASR methods adopt the multi‐scale architecture because both global and local features play great roles in ***,the existing multi‐scale methods neglect the effective interactions among different scales and various spatial locations when fusing global and local features,leading to a limited ability to deal with challenges of large‐scale variation and complex background in aerial scene *** addition,existing methods may suffer from poor generalisations due to millions of to‐belearnt parameters and inconsistent predictions between global and local *** tackle these problems,this study proposes a scale‐wise interaction fusion and knowledge distillation(SIF‐KD)network for learning robust and discriminative features with scaleinvariance and background‐independent *** main highlights of this study include two *** the one hand,a global‐local features collaborative learning scheme is devised for extracting scale‐invariance features so as to tackle the large‐scale variation problem in aerial scene ***,a plug‐and‐play multi‐scale context attention fusion module is proposed for collaboratively fusing the context information between global and local *** the other hand,a scale‐wise knowledge distillation scheme is proposed to produce more consistent predictions by distilling the predictive distribution between different scales during *** experimental results show the proposed SIF‐KD network achieves the best overall accuracy with 99.68%,98.74%and 95.47%on the UCM,AID and NWPU‐RESISC45 datasets,respectively,compared with state of the arts.

关键词： deep learning image analysis image classification information fusion

Saddle Point Optimality Criteria of Interval Valued Non-Linear Programming Problem

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2021年第9期38卷 351-364页

作者： Md Sadikur Rahman Emad E.Mahmoud Ali Akbar Shaikh Abdel-Haleem Abdel-Aty asoke Kumar Bhunia Department of Mathematics The University of BurdwanBurdwan713104India Department of Mathematics and Statistics College of ScienceTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Physics College of SciencesUniversity of BishaP.O.Box 344Bisha61922Saudi Arabia Physics Department Faculty of ScienceAl-Azhar UniversityAssiut71524Egypt

The present paper aims to develop the Kuhn-Tucker and Fritz John criteria for saddle point optimality of interval-valued nonlinear programming *** achieve the study objective,we have proposed the definition of minimizer and maximizer of an interval-valued non-linear programming ***,we have introduced the interval-valued Fritz-John and Kuhn Tucker saddle point *** that,we have established both the necessary and sufficient optimality conditions of an interval-valued non-linear minimization ***,we have shown that both the saddle point conditions(Fritz-John and Kuhn-Tucker)are sufficient without any convexity *** with the convexity requirements,we have established that these saddle point optimality criteria are the necessary conditions for optimality of an interval-valued non-linear programming with real-valued ***,all the results are derived with the help of interval order ***,we illustrate all the results with the help of a numerical example.

关键词： Convexity of interval valued function extended Fritz-John theorem Interval order relation Karlin’s constraint saddle point optimality

Spectroscopic Survey of Hα Emission Line Stars Associated with Bright Rimmed Clouds

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Astronomy and Astrophysics 2019年第2期9卷 154-171页

作者： Kensuke Hosoya Yoichi Itoh Yumiko Oasa Ranjan Gupta asoke Kumar Sen Nishi-Harima Astronomical Observatory Center for AstronomyUniversity of HyogoKobeJapan Faculty of Education Saitama UniversitySaitamaJapan Inter University Center for Astronomy and Astrophysics(IUCAA) PuneIndia Department of Physics Assam UniversitySilcharIndia

The results of a spectroscopic survey of Hα emission line stars associated with fourteen bright rimmed clouds are presented. Slit-less optical spectroscopy was carried out with the Inter University Centre for Astronomy and Astrophysics (IUCAA) 2 m telescope and IUCAA Faint Object Spectrograph and Camera (IFOSC). Hα emission line was detected from 173 objects. Among them 85 objects have a strong Hα emission line with its equivalent width larger than 10 ?. Those are classical T Tauri stars. 52 objects have a weak Hα emission line with its equivalent width less than 10 ? and do not show intrinsic near-infrared excess. Those are weak-line T Tauri stars. On the other hand, 36 objects have a weak Hα emission line (?), although they show intrinsic near-infrared excess. Such objects are not common in low-mass star forming regions. Those are misfits of the general concept on formation process of a low-mass star, in which it evolves from a classical T Tauri star to a weak-line T Tauri star. Those might be weak-line T Tauri stars with a flared disk in which gas is heated by ultraviolet radiation from a nearby early-type star. Alternatively, we propose pre-transitional disk objects as their evolutional stage.

关键词： Star Formation Pre-Main Sequence Stars T Tauri Stars