检索结果-南通市图书馆

Optimized Mask-RCNN model for particle chain segmentation based on improved online ferrograph sensor

Friction 2024年第6期12卷 1194-1213页

作者： Shuo WANG Miao WAN Tonghai WU Zichen BAI Kunpeng WANG key laboratory of Education Ministry for Modern Design and rotor-Bearing System Xi’an Jiaotong UniversityXi’an 710049China

Ferrograph-based wear debris analysis(WDA)provides significant information for wear fault analysis of mechanical *** decades of offline application,this conventional technology is being driven by the online ferrograph sensor for real-time wear state ***,online ferrography has been greatly limited by the low imaging quality and segmentation accuracy of particle chains when analyzing degraded lubricant oils in practical *** address this issue,an integrated optimization method is developed that focuses on two aspects:the structural re-design of the online ferrograph sensor and the intelligent segmentation of particle *** enhancing the imaging quality of wear particles,the magnetic pole of the online ferrograph sensor is optimized to enable the imaging system directly observe wear particles without penetrating ***,a light source simulation model is established based on the light intensity distribution theory,and the LED installation parameters are determined for particle illumination uniformity in the online ferrograph *** this basis,a Mask-RCNN-based segmentation model of particle chains is constructed by specifically establishing the region of interest(ROI)generation layer and the ROI align layer for the irregular particle *** these measures,a new online ferrograph sensor is designed to enhance the image acquisition and information extraction of wear *** verification,the developed sensor is tested to collect particle images from different degraded oils,and the images are further handled with the Mask-RCNN-based model for particle feature *** results reveal that the optimized online ferrography can capture clear particle images even in highly-degraded lubricant oils,and the illumination uniformity reaches 90%in its imaging *** importantly,the statistical accuracy of wear particles has been improved from 67.2%to 94.1%.

关键词： wear particle analysis online ferrography particle image acquisition particle chain segmentation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Dynamic Vision-Based Machinery Fault Diagnosis With Cross-Modality Feature Alignment

引用

IEEE/CAA Journal of Automatica Sinica 2024年第10期11卷 2068-2081页

作者： Xiang Li Shupeng Yu Yaguo Lei Naipeng Li Bin Yang key laboratory of Education Ministry for Modern Design and rotor-Bearing System Xi’an Jiaotong UniversityXi’an 710049China IEEE

Intelligent machinery fault diagnosis methods have been popularly and successfully developed in the past decades,and the vibration acceleration data collected by contact accelerometers have been widely *** many industrial scenarios,contactless sensors are more *** event camera is an emerging bio-inspired technology for vision sensing,which asynchronously records per-pixel brightness change polarity with high temporal resolution and low *** offers a promising tool for contactless machine vibration sensing and fault ***,the dynamic vision-based methods suffer from variations of practical factors such as camera position,machine operating condition,***,as a new sensing technology,the labeled dynamic vision data are limited,which generally cannot cover a wide range of machine fault *** at these challenges,a novel dynamic vision-based machinery fault diagnosis method is proposed in this *** is motivated to explore the abundant vibration acceleration data for enhancing the dynamic vision-based model performance.A crossmodality feature alignment method is thus proposed with deep adversarial neural networks to achieve fault diagnosis knowledge *** event erasing method is further proposed for improving model robustness against *** proposed method can effectively identify unseen fault mode with dynamic vision *** on two rotating machine monitoring datasets are carried out for validations,and the results suggest the proposed method is promising for generalized contactless machinery fault diagnosis.

关键词： Condition monitoring domain generalization eventbased camera fault diagnosis machine vision

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Comparison-embedded evidence-CNN model for fuzzy assessment of wear severity using multi-dimensional surface images

引用

Friction 2024年第6期12卷 1098-1118页

作者： Tao SHAO Shuo WANG Qinghua WANG Tonghai WU Zhifu HUANG key laboratory of Education Ministry for Modern Design and rotor-Bearing System Xi’an Jiaotong UniversityXi’an 710049China State key laboratory for Mechanical Behavior of Materials Xi’an Jiaotong UniversityXi’an 710049China

Wear topography is a significant indicator of tribological behavior for the inspection of machine health *** intelligent in-suit wear assessment method for random topography is here ***-dimension(3D)topography is employed to address the uncertainties in wear ***,3D topography reconstruction from a worn surface is accomplished with photometric stereo vision(PSV).Then,the wear features are identified by a contrastive learning-based extraction network(WSFE-Net)including the relative and temporal prior knowledge of wear ***,the typical wear degrees including mild,moderate,and severe are evaluated by a wear severity assessment network(WSA-Net)for the probability and its associated uncertainty based on subjective *** integrating the evidence information from 2D and 3D-damage surfaces with Dempster–Shafer(D–S)evidence,the uncertainty of severity assessment results is further *** proposed model could constrain the uncertainty below 0.066 in the wear degree evaluation of a continuous wear experiment,which reflects the high credibility of the evaluation result.

关键词： wear severity assessment contrastive learning subjective logic Dempster-Shafer(D-S)evidence theory

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Dynamic Vision Enabled Contactless Cross-Domain Machine Fault Diagnosis With Neuromorphic Computing

引用

IEEE/CAA Journal of Automatica Sinica 2024年第3期11卷 788-790页

作者： Xinrui Chen Xiang Li Shupeng Yu Yaguo Lei Naipeng Li Bin Yang the key laboratory of Education Ministry for Modern Design and rotor-Bearing System Xi’an Jiaotong UniversityXi’an 710049China

Dear Editor,This letter presents a novel dynamic vision enabled contactless cross-domain fault diagnosis method with neuromorphic *** event-based camera is adopted to capture the machine vibration states in the perspe... 详细信息

关键词： fault less diagnosis

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Investigation of control effects of end-wall selfadaptive jet on three-dimensional corner separation of a highly loaded compressor cascade

引用

Chinese Journal of Aeronautics 2024年第6期37卷 109-126页

作者： Hejian WANG Bo LIU Xiaochen MAO Botao ZHANG Zonghao YANG School of Power and Energy Northwestern Polytechnical UniversityXi’an 710129China The National key laboratory of Science and Technology on aerodynamic Design and Research Xi’an 710129China Taihang laboratory Chengdu 610000China

To overcome the limitations posed by three-dimensional corner separation,this paper proposes a novel flow control technology known as passive End-Wall(EW)self-adaptive *** single EW slotted schemes(EWS1 and EWS2),alongside a combined(COM)scheme featuring double EW slots,were *** results reveal that the EW slot,driven by pressure differentials between the pressure and suction sides,can generate an adaptive jet with escalating velocity as the operational load *** high-speed jet effectively re-excites the local low-energy fluid,thereby mitigating the corner ***,the EWS1 slot,positioned near the blade leading edge,exhibits relatively low jet velocities at negative incidence angles,causing jet separation and exacerbating the corner ***,the EWS2 slot is close to the blade trailing edge,resulting in massive low-energy fluid accumulating and separating before the slot outlet at positive incidence *** contrast,the COM scheme emerges as the most effective solution for comprehensive corner separation *** can significantly reduce the total pressure loss and improve the static pressure coefficient for the ORI blade at 0°-4° incidence angles,while causing minimal negative impact on the aerodynamic performance at negative incidence ***,the corner stall is delayed,and the available incidence angle range is broadened from -10°--2°to -10°-4°.This holds substantial promise for advancing the aerodynamic performance,operational stability,and load capacity of future highly loaded compressors.

关键词： Three-dimensional corner separation End-wall adaptive jet Total pressure loss Highly loaded compressor cascade Compressors

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

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

引用

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

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Reconstruction of particle distribution for tomographic particle image velocimetry based on unsupervised learning method

引用

Particuology 2024年第10期93卷 349-363页

作者： Duanyu Zhang Haoqin Huang Wu Zhou Mingjun Feng Dapeng Zhang Limin Gao School of Energy and Power Engineering University of Shanghai for Science and TechnologyShanghai200093China Shanghai key laboratory of Multiphase Flow and Heat Transfer for Power Engineering University of Shanghai for Science and TechnologyShanghai200093China National key laboratory of aerodynamic Design and Research Northwestern Polytechnical UniversityXi'an710072China

The development of deep learning has inspired some new methods to solve the 3D reconstruction problem for Tomographic Particle Image Velocimetry (Tomo-PIV). However, the supervised learning method requires a large number of data with ground truth as training information, which is very difficult to gather from experiments. Although synthetic datasets can be used as alternatives, they are still not exactly the same with the real-world experimental data. In this paper, an Unsupervised Reconstruction Technique based on U-net (UnRTU) is proposed to reconstruct volume particle distribution explicitly. Instead of using ground truth data, a projection function is used as an unsupervised loss function for network training to reconstruct particle distribution. The UnRTU was compared with some traditional algebraic reconstruction algorithms and supervised learning method using synthetic data under different particle density and noise level. The results indicate that UnRTU outperforms these traditional approaches in both reconstruction quality and noise robustness, and is comparable to the supervised learning methods AI-PR. For experimental tests, particles dispersed in cured epoxy resin are moved by an electric rail with a certain speed to obtain the ground truth data of particle velocity. Compared with other algorithms, the reconstructed particle distribution by UnRTU has the best reconstruction fidelity. And the accuracy of the 3D velocity field estimated by UnRTU is 12.9% higher than that from the traditional MLOS-MART algorithm. It demonstrates significant potential and advantages for UnRTU in 3D reconstruction of particle distribution. Finally, UnRTU was successfully applied to the high-speed planar cascade airflow field, demonstrating its applicability for measuring complex fluid flow fields at higher particle density.

关键词： Tomographic particle image velocimetry 3D reconstruction Unsupervised learning Convolutional neural network

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Design strategy and relevant flow mechanisms of highly loaded 3D compressor tandem cascades

引用

Chinese Journal of Aeronautics 2024年第7期37卷 220-235页

作者： Xiaochen MAO Yunyu WANG Zhihua DING Hao CHENG Bo LIU School of Power and Energy Northwestern Polytechnical UniversityXi’an 710129China The National key laboratory of Science and Technology on aerodynamic Design and Research Xi’an 710129China Xi’an Thermal Power Research Institute Co.Ltd Xi’an 710072China

To investigate the design strategy of highly loaded tandem cascades at both the midspan and endwall,the overall performance and flow mechanisms of four typical tandem cascades based on the optimization were analyzed from multiple perspectives *** results show that the interference effects on the Front Blade(FB)and Rear Blade(RB)should not be overlooked during the design phase,and the design strategies at the midspan and endwall are completely *** the midspan,the optimization aims to increase the interference effects and the strength of the gap jet while maintaining the same load on the FB and ***,the endwall optimal airfoil exhibits weakening interference effects,advancement of the gap jet location,and load transfer from the FB to *** further analysis of flow characteristics,the midspan optimal airfoil is beneficial for inhibiting the low-energy fluid from interacting with the suction surface of RB under the design condition,but results in earlier occurrence of corner *** endwall optimal airfoil helps suppress the development of the secondary flow and delay the onset of corner ***,by combining the benefits of these two design approaches,additional forward sweep effects are achieved,further enhancing the performance of the tandem cascade.

关键词： Tandem cascade Interference effect Vortex structure Load split Compressor

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Tribological properties of low-temperature time-dependent pretreated graphite for mechanical seal pairs in high-speed turbopump

引用

Friction 2024年第2期12卷 305-318页

作者： Yangyang ZHAO Guoyuan ZHANG Junqian WANG He WANG Weigang ZHAO Qunfeng ZENG School of Mechano-Electronic Engineering Xidian UniversityXi’an 710071China Xi’an Aerospace Propulsion Institute Xi’an 710071China key laboratory of Education Ministry for Modern Design and rotor-Bearing System Xi’an Jiaotong UniversityXi’an 710049China

The friction coefficient and wear rate of pretreated graphite with liquid nitrogen were obtained by using a ball-on-disk tester,and the wear of GCr15–graphite seal pairs with the low-temperature time-dependent pretreatment was discussed by comparing the wear *** results show that liquid nitrogen pretreatment can affect the hardness and interlayer spacing of *** range of the friction coefficients of pretreated graphite changes from 0.17 to *** the increase of liquid nitrogen pretreatment time,the wear mechanism of graphite would change from dominated three-body wear to adhesion *** experimental results of the mechanical seal with liquid nitrogen pretreatment show that the wear rate of stator is less than 0.00165 mm^(3)·N^(−1)·m^(−1),and the graphite shows a good low-temperature compatibility.

关键词： graphite low-temperature pretreatment mechanical seal friction and wear

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Resonance mechanism of flapping wing based on fluid structure interaction simulation

引用

Chinese Journal of Aeronautics 2024年第5期37卷 243-262页

作者： Yueyang GUO Wenqing YANG Yuanbo DONG Dong XUE National key laboratory of Science and Technology on aerodynamic Design and Research School of AeronauticsNorthwestern Polytechnical UniversityXi'an 710072China Research&Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen 518063China Yangtze River Delta Research Institute of Northwestern Polytechnical University Taicang 215400China

Certain insect species have been observed to exploit the resonance mechanism of their *** order to achieve resonance and optimize aerodynamic performance,the conventional approach is to set the flapping frequency of flexible wings based on the Traditional Structural Modal(TSM)***,there exists controversy among researchers regarding the relationship between frequency and aerodynamic *** that the structural response of wings can be influenced by the surrounding air vibrations,an analysis known as Acoustic Structure Interaction Modal(ASIM)is introduced to calculate the resonant *** this study,Fluid Structure Interaction(FSI)simulations are employed to investigate the aerodynamic performance of flapping wings at modal frequencies derived from both TSM and ASIM *** performance is evaluated for various mass ratios and frequency ratios,and the findings indicate that the deformation and changes in vortex structure exhibit similarities at mass ratios that yield the highest aerodynamic ***,the flapping frequency associated with the maximum time-averaged vertical force coefficient at each mass ratio closely aligns with the ASIM frequency,as does the frequency corresponding to maximum ***,the ASIM analysis can provide an effective means for predicting the optimal flapping frequency for flexible ***,it enables the prediction that flexible wings with varying mass ratios will exhibit similar deformation and vortex structure *** paper offers a fresh perspective on the ongoing debate concerning the resonance mechanism of Flexible Flapping Wings(FFWs)and proposes an effective methodology for predicting their aerodynamic performance.

关键词： Flexible Flapping Wing(FFW) Acoustic Structure Interaction Modal(ASIM) Fluid Structure Interaction(FSI) Resonance mechanism aerodynamic performance

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：