检索结果-内蒙古大学图书馆

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 285-295页

作者： Liu, Chen Shi, Zhenyu He, Shibo Tang, Shunpu Yang, Qianqian The State Key Lab. of Industrial Control Technology Zhejiang University Hangzhou310027 China

Detecting defects on railway tracks is critical for the operation of high-speed trains. Despite a plethora of machine vision-based methods designed to tackle this problem, the majority adopt a supervised setting and demand considerable labeled training data, inclusive of defective samples, which is expensive and impractical. In this paper, we propose an Invertible Reconstruction neural Network (IRNet) for semi-supervised rail surface defect detection, where only normal images are accessible during training. Firstly, we devise an information-preserving feature encoder comprising several invertible blocks. This structure safeguards subtle visual patterns distinguishing normal and defective images from being obscured by background information, guaranteed by its mathematical reversibility property. Second, to overcome the overgeneralization issue of conventional autoencoders caused by imperfectly crafted decoders, we propose a novel decoder-free reconstruction workflow based on the invertible feature encoder. Specifically, we force one portion of extracted features to approach a predefined constant tensor during the training stage by minimizing their mean squared error. Next, we feed the remained features and the predefined constant tensor backward into the encoder to reconstruct the original images. During the testing phase, we formulate an anomaly score that consolidates the reconstruction error and mean squared error to spot defects. Extensive experiments are conducted on 4 real-world datasets. Our method consistently outperforms state-of-the-art techniques, demonstrating an average increase of 8.5% on the F1 score. © 2023 IEEE. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

A novel rotor dynamic balancing method based on blade tip clearance measurement without the once per revolution sensor

引用

Chinese Journal of Aeronautics 2025年第2期38卷 445-458页

作者： Weibo LI Weimin WANG Shuai ZHANG Jiale WANG Yulong LIN Tianqing LI Key Lab of Engine Health Monitoring-Control and Networking of Ministry of Education Beijing University of Chemical TechnologyBeijing 100029China State Key Laboratory of High-end Compressor and System Technology Beijing University of Chemical TechnologyBeijing 100029China

The existence of the aeroengine casing,limited monitoring points,and multi-fault characteristics make obtaining the rotor’s vibration transmission characteristics challenging,resulting in difficulties accurately identifying the rotor *** paper utilizes a high-frequency composite sensor to monitor the engine’s blade tip clearance(BTC)and extracts unbalanced information from BTC signals for rotor dynamic balancing,while avoiding the need for the once per revolution(OPR)***,the vibration characteristics of the rotor-blade system under multi-fault conditions are ***,based on BTC measurement,a none OPR method and an unbalance identification method are proposed,in which the radial vibration of the blade tip in the BTC signals at different speeds is extracted and operated in the time domain to obtain the rotor unbalanced vibration,the signal is reconstructed,and cross-correlation analysis is used to accurately identify the magnitude and phase of the unbalanced ***,a rotor test bench is utilized for experimental *** results reveal that the dynamic balancing method based on the BTC signal can more precisely identify the rotor unbalance than the traditional rotor dynamic balancing *** application of this technique will effectively improve engine health management and fault prediction.

关键词： Aeroengine Rotor unbalance Composite sensor None once per revolution Blade tip clearance Dynamic balancing

来源：评论

学校读者我要写书评

暂无评论

RoG-SAM: A Language-Driven Framework for Instance-Level Robotic Grasping Detection

引用

IEEE Transactions on Multimedia 2025年 27卷 3057-3068页

作者： Mei, Yunpeng Sun, Jian Peng, Zhihong Deng, Fang Wang, Gang Chen, Jie Beijing Institute of Technology State Key Lab of Autonomous Intelligent Unmanned Systems Beijing100081 China Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China Tongji University Department of Control Science and Engineering Shanghai201804 China

Robotic grasping is a crucial topic in robotics and computer vision, with broad applications in industrial production and intelligent manufacturing. Although some methods have begun addressing instance-level grasping, most remain limited to predefined instances and categories, lacking flexibility for open-vocabulary grasp prediction based on user-specified instructions. To address this, we propose RoG-SAM, a language-driven, instance-level grasp detection framework built on Segment Anything Model (SAM). RoG-SAM utilizes open-vocabulary prompts for object localization and grasp pose prediction, adapting SAM through transfer learning with encoder adapters and multi-head decoders to extend its segmentation capabilities to grasp pose estimation. Experimental results show that RoG-SAM achieves competitive performance on single-object datasets (Cornell and Jacquard) and cluttered datasets (GraspNet-1Billion and OCID), with instance-level accuracies of 91.2% and 90.1%, respectively, while using only 28.3% of SAM's trainable parameters. The effectiveness of RoG-SAM was also validated in real-world environments. A demonstration video is available at https://***/playlist?list=PL7et4nGJAImLGytsJbglGbXl1hacA2dy. © 1999-2012 IEEE.

关键词： Robot vision

来源：评论

学校读者我要写书评

暂无评论

UniFace++: Revisiting a Unified Framework for Face Reenactment and Swapping via 3D Priors

引用

International Journal of Computer Vision 2025年 1-17页

作者： Xu, Chao Qian, Yijie Zhu, Shaoting Sun, Baigui Zhao, Jian Liu, Yong Li, Xuelong State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China Walf 1069B Lab Sany Group Guangzhou China China Telecom Beijing China Northwestern Polytechnical University Xi’an China

Face reenactment and swapping share a similar pattern of identity and attribute manipulation. Our previous work UniFace has preliminarily explored establishing a unification between the two at the feature level, but it heavily relies on the accuracy of feature disentanglement, and GANs are also unstable during training. In this work, we delve into the intrinsic connections between the two from a more general training paradigm perspective, introducing a novel diffusion-based unified method UniFace++. Specifically, this work combines the advantages of each, i.e., stability of reconstruction training from reenactment, simplicity and effectiveness of the target-oriented processing from swapping, and redefining both as target-oriented reconstruction tasks. In this way, face reenactment avoids complex source feature deformation and face swapping mitigates the unstable seesaw-style optimization. The core of our approach is the rendered face obtained from reassembled 3D facial priors serving as the target pivot, which contains precise geometry and coarse identity textures. We further incorporate it with the proposed Texture-Geometry-aware Diffusion Model (TGDM) to perform texture transfer under the reconstruction supervision for high-fidelity face synthesis. Extensive quantitative and qualitative experiments demonstrate the superiority of our method for both tasks. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Synergistic mechanism of modified nZVI and Citrobacter reshaping sludge microbiome drives co-removal of HBCD and nutrients in municipal wastewater

引用

Environmental Chemistry and Ecotoxicology 2025年 7卷 872-881页

作者： Li, Tianyu He, Yuzhe Zhang, Weixian Peng, Xingxing School of Environmental Science and Engineering Sun Yat-sen University Guangdong Guangzhou510006 China Guangdong Provincial Key Laboratory of Environmental Pollution Control and Remediation Technology Guangzhou510275 China Tongji University College of Environmental Science & Engineering State Key Lab Pollut Control & Resource Reuse Shanghai Shanghai200092 China

Hexabromocyclododecane (HBCD), a persistent and toxic brominated flame retardant, poses severe ecological and health risks due to its bioaccumulation and endocrine-disrupting effects. Effective removal from wastewater is critical to mitigate risks. Coupling functional microbes with modified nanomaterials represents a robust approach for degrading such recalcitrant organohalides. Based on the research foundation of the functional bacterial strain Citrobacter sp. Y3 and a modified nano-zero-valent iron (nZVI) coupled system, we designed and constructed a novel anaerobic continuous stirred-tank reactor (CSTR) system for the treatment of municipal wastewater in this study. HBCD-contaminated wastewater and actual domestic sewage were fed into this CSTR system. During continuous monitoring of HBCD concentration changes over 360 h, we simultaneously tracked the removal efficiencies of nitrogen (N), phosphorus (P), and chemical oxygen demand (COD). The results demonstrated that the HBCD degradation rate reached 100 % within 72 h, while the removal of other nutrients met regulatory discharge requirements. The CSTR system significantly enriched diverse functional bacterial taxa harboring multiple functional genes, including organohalide-respiring bacteria (OHRB) (rdhA/B, PecA/B), iron-reducing bacteria (IRB) (cymA, fur), and nitrogen/phosphorus-removing bacteria (hzoB, haoA, norB and pstA/B/C). Dynamic interactions (synergistic cooperation and competition) among microbial communities drove the decomposition and transformation of pollutants. To our knowledge, this study provides the first demonstration of coupling functional bacteria with modified nanomaterials in activated sludge systems. © 2024

关键词： Health risks

来源：评论

学校读者我要写书评

暂无评论

Cutting force modeling in high-speed machining of selective laser melted Ti6Al4V alloys based on a modified constitutive model considering thermally activated effect

引用

Science China(Technological Sciences) 2025年第3期68卷 138-155页

作者： Dejian LIU Chenbing NI Youqiang WANG Lida ZHU Zhongpeng ZHENG Wei LU Naixin ZHANG Xingbao HUANG School of Mechanical and Automotive Engineering Qingdao University of TechnologyQingdao266520China Key Lab of Industrial Fluid Energy Conservation and Pollution Control Ministry of EducationQingdao266520China School of Mechanical Engineering and Automation Northeastern UniversityShenyang110819China School of Mechanical Engineering Tsinghua UniversityBeijing100084China Shandong Zhongheng Jingxin Carbon Fiber Technology Development Co. LtdDezhou251100China State Key Laboratory of Bridge Safety and Resilience College of Civil EngineeringHunan UniversityChangsha410082China

The thermally activated effect can produce a vital influence on the mechanical property and cutting force of metal materials in the machining *** insight can be gained into the action criteria of the thermally activated effect on the cutting force,which provides a solid basis of the research of material performance and *** this study,a cutting force model of selective laser melted(SLMed)Ti6Al4V alloy is proposed by introducing the modified constitutive model with thermally activated effects and the analytical model of the deformation zone into the cutting force *** anisotropic properties of SLMed Ti6Al4V alloy under different scanning strategies(0°,67.5°,and 90°)are explored by combining with the cutting force model,constitutive model and analytical model of deformation zone(primary deformation and tool-chip contact area).The action of thermally activated effects on the cutting force,primary deformation and tool-chip contact zone is also researched in *** experiments and predictions of SLMed Ti6Al4V alloy under different scanning strategies have been implemented to reveal the effectiveness of this new *** comparison results indicate that the proposed milling force model can effectively predict milling force and reflect well on the anisotropy of SLMed Ti6Al4V *** addition,this proposed force model can well analyze the action mechanism of the thermally activated effect on the milling force of SLMed Ti6Al4V alloy,which is significantly essential for the machining mechanism research in terms of a microscopic perspective.

关键词： cutting force model modified constitutive model thermally activated effect SLMed Ti6Al4V alloy laser scanning strategies anisotropic properties

来源：评论

学校读者我要写书评

暂无评论

Accelerated activation of lattice oxygen for CO Oxidation: Promoting the role of oxygen vacancies

引用

APPLIED SURFACE SCIENCE 2025年 703卷

作者： Liu, Chang Wang, Qiao Gao, Fei Teng, Yifei Liaoning Tech Univ Coll Safety Sci & Engn Fuxin 123000 Peoples R China Liaoning Tech Univ Key Lab Mine Thermodynam Disasters & Control Minist Educ Fuxin 123000 Peoples R China Jilin Univ Coll Chem State Key Lab Inorgan Synth & Preparat Chem Changchun 130012 Peoples R China Chinalco Res Inst Sci & Technology Co Ltd Beijing 102209 Peoples R China

The role of surface oxygen sites in transition metal oxides has been a focal point in environmental and energy chemistry, particularly in catalytic oxidation reactions. Herein, the mobility and activation of lattice oxygen in MnCo2O4 were effectively modulated via in situ thermal treatment for CO oxidation. By weakening the metal--oxygen bond strength, active surface lattice oxygen was generated, which could be readily activated to participate in the catalytic oxidation of CO to CO2. The increased covalency of Co-O bonds not only improves the Co 3d-O 2p electronic structure but also generates active oxygen species on the surface, which are efficiently involved in the catalytic oxidation of CO to CO2, as demonstrated by soft XAS, XPS, and O2-TPD analyses. Our findings offer a reliable understanding of the dual activation process involving lattice and defect oxygen in heterogeneous catalytic oxidation reactions and provide a solid foundation for strategies aimed at enhancing catalytic oxidation activity.

关键词： Spinel oxides Electronic structure Surface oxygen sites Unsaturated coordination CO oxidation

来源：评论

学校读者我要写书评

暂无评论

CT-NeRF: Incremental Optimization of Neural Radiance Field and Camera Poses with Complex Trajectory

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Ran, Yunlong Li, Yanxu Ye, Qi Huo, Yuchi Cui, Zhaopeng Bai, Zechun Sun, Jiahao Chen, Jiming Zhejiang University College of Control Science and Engineering Hangzhou China Zhejiang University College of Control Science and Engineering State Key Laboratory of Industrial Control Technology China Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province China Zhejiang University State Key Lab of CAD and CG China

Neural radiance field (NeRF) has achieved impressive results in high-quality 3D scene reconstruction. However, NeRF heavily relies on precise camera poses. While recent works like BARF have introduced camera pose optimization within NeRF, their applicability is limited to simple trajectory scenes. Existing methods struggle while tackling complex trajectories involving large rotations. To address this limitation, we propose CT-NeRF, an incremental reconstruction and optimization pipeline using only RGB images without pose and depth input. In this pipeline, we first propose a local-global bundle adjustment under a pose graph connecting neighboring frames to enforce the consistency between poses to escape the local minima caused by only pose consistency with the scene structure. Further, we instantiate the consistency between poses as a reprojection error constraint resulting from pixel-level correspondences between input image pairs. Through the incremental reconstruction, CT-NeRF enables the recovery of both camera poses and scene structure and is capable of handling scenes with complex trajectories. We evaluate the performance of CT-NeRF on two real-world datasets, NeRF-Buster and Free-Dataset, which feature complex trajectories. Results show CT-NeRF outperforms existing methods in novel view synthesis and pose estimation accuracy. © 1991-2012 IEEE.

关键词： 3D Reconstruction bundle adjustment NeRF novel view synthesis structure from motion

来源：评论

学校读者我要写书评

暂无评论

An Engineering Evaluation Methodology of Heterogeneous Network for Highway Infrastructure Monitoring Data Transmission Based on Graph Theory

An Engineering Evaluation Methodology of Heterogeneous Netwo...

引用

International Conference on Artificial Intelligence and Autonomous Transportation, AIAT 2024

作者： Li, Zhenhua Zhang, Yipeng Chen, Yi School of Electrical and Control Engineering North China University of Technology Beijing100144 China Research Institute of Highway Ministry of Transport Ministry of Transport Beijing100081 China State Key Lab of Intelligent Transportation System Ministry of Transport Beijing100081 China

ISBN: (纸本)9789819639564

A large-scale highway infrastructure monitoring system requires a complex and heterogeneous data transmission network to transmit different types and large amounts of sensor data. In order to meet the requirement of rapid modeling and performance evaluation of highway infrastructure monitoring data transmission networks in engineering construction projects, this paper proposes a graph modeling method for heterogeneous transmission networks of highway infrastructure monitoring data using relevant concepts and methods of graph theory. By combining network models with engineering implementation experience, an exploratory engineering evaluation method for evaluating network carrying capacity, end-to-end latency, and end-to-end reliability has been proposed. The above methods can be used to achieve rapid modeling of networks and rapid evaluation of key performance parameters. The evaluation conclusions can serve as the basis for optimizing and implementing the engineering design of highway infrastructure monitoring systems. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Network theory (graphs)

来源：评论

学校读者我要写书评

暂无评论

Dynamic Route Optimization for Multi-Vehicle Systems with Diverse Needs in Road Networks Based on Preference Games

引用

Computers, Materials and Continua 2025年第3期83卷 4167-4192页

作者： Wang, Jixiang Wei, Jing Chen, Siqi Yu, Haiyang Ren, Yilong School of Transportation Science and Engineering Beihang University Beijing100191 China School of Electrical and Control Engineering North China University of Technology Beijing100144 China Hangzhou Innovation Institute Beihang University Hangzhou310023 China The State Key Lab of Intelligent Transportation System Beijing100191 China

The real-time path optimization for heterogeneous vehicle fleets in large-scale road networks presents significant challenges due to conflicting traffic demands and imbalanced resource allocation. While existing vehicle-to-infrastructure coordination frameworks partially address congestion mitigation, they often neglect priority-aware optimization and exhibit algorithmic bias toward dominant vehicle classes—critical limitations in mixed-priority scenarios involving emergency vehicles. To bridge this gap, this study proposes a preference game-theoretic coordination framework with adaptive strategy transfer protocol, explicitly balancing system-wide efficiency (measured by network throughput) with priority vehicle rights protection (quantified via time-sensitive utility functions). The approach innovatively combines (1) a multi-vehicle dynamic routing model with quantifiable preference weights, and (2) a distributed Nash equilibrium solver updated using replicator sub-dynamic models. The framework was evaluated on an urban road network containing 25 intersections with mixed priority ratios (10%–30% of vehicles with priority access demand), and the framework showed consistent benefits on four benchmarks (Social routing algorithm, Shortest path algorithm, The comprehensive path optimisation model, The emergency vehicle timing collaborative evolution path optimization method) showed consistent benefits. Results show that across different traffic demand configurations, the proposed method reduces the average vehicle traveling time by at least 365 s, increases the road network throughput by 48.61%, and effectively balances the road loads. This approach successfully meets the diverse traffic demands of various vehicle types while optimizing road resource allocations. The proposed coordination paradigm advances theoretical foundations for fairness-aware traffic optimization while offering implementable strategies for next-generation cooperative vehicle-road systems, particul

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：