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 lab.led 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

Adaptive Graph Convolution Neural Differential Equation for Spatio-Temporal Time Series Prediction

引用

IEEE Transactions on Knowledge and Data Engineering 2025年第6期37卷 3193-3204页

作者： Han, Min Wang, Qipeng Dalian University of Technology Key Lab. of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Liaoning Dalian116024 China Dalian University of Technology Prof. Technol. Innov. Center of Distributed Control for Industrial Equipment of Liaoning Province Liaoning Dalian116024 China Dalian University of Technology Faculty of Electronic Information and Electrical Engineering Liaoning Dalian116024 China

Multivariate time series prediction has aroused widely research interests during decades. However, the spatial heterogeneity and temporal evolution characteristics bring much challenges for high-dimensional time series prediction. In this paper, a novel adaptive graph convolution module is introduced to automatically learn the spatial correlation of multivariate time series and a Koopman-based neural differential equation is proposed to simulate the nonlinear system state evolution. In detail, the correlation between multivariate time series is revealed by the consine similarity of node embedding to infer the potential relationship between nodes and the spatio-temporal feature fusion module is utilized. The LSTM-based network is adopted as Koopman operator to reveal the latent states of spatio-temporal time series and the reversible assumption is imposed on the Koopman operator. Furthermore, the Euler-trapezoidal integration are utilized to simulate the temporal dynamics and multiple-step prediction is carried out in the latent space from the perspective of dynamical differential equation. The proposed model could explicitly discover the spatial correlation by adaptive graph convolution and reveal the temporal dynamics by neural differential equation, which make the modeling more interpretable. Simulation results show the effectiveness on spatio-temporal dynamic discovery and prediction performance. © 1989-2012 IEEE.

关键词： Time series analysis

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

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

Compliance while resisting: a shear-thickening fluid controller for physical human-robot interaction

arXiv

引用

arXiv 2025年

作者： Chen, Lu Chen, Lipeng Chen, Xiangchi Lu, Haojian Zheng, Yu Wu, Jun Wang, Yue Zhang, Zhengyou Xiong, Rong State Key Laboratory of Industrial Control Technology Zhejiang University Zhejiang Hangzhou China Tencent Robotics X Lab Shenzhen China

Physical human-robot interaction (pHRI) is widely needed in many fields, such as industrial manipulation, home services, and medical rehabilitation, and puts higher demands on the safety of robots. Due to the uncertainty of the working environment, the pHRI may receive unexpected impact interference, which affects the safety and smoothness of the task execution. The commonly used linear admittance control (L-AC) can cope well with high-frequency small-amplitude noise, but for medium-frequency high-intensity impact, the effect is not as good. Inspired by the solid-liquid phase change nature of shear-thickening fluid, we propose a Shear-thickening Fluid control (SFC) that can achieve both an easy human-robot collab.ration and resistance to impact interference. The SFC’s stability, passivity, and phase trajectory are analyzed in detail, the frequency and time domain properties are quantified, and parameter constraints in discrete control and coupled stability conditions are provided. We conducted simulations to compare the frequency and time domain characteristics of L-AC, nonlinear admittance controller (N-AC), and SFC, and validated their dynamic properties. In real-world experiments, we compared the performance of L-AC, N-AC, and SFC in both fixed and mobile manipulators. L-AC exhibits weak resistance to impact. N-AC can resist moderate impacts but not high-intensity ones, and may exhibit self-excited oscillations. In contrast, SFC demonstrated superior impact resistance and maintained stable collab.ration, enhancing comfort in cooperative water delivery tasks. Additionally, a case study was conducted in a factory setting, further affirming the SFC’s capability in facilitating human-robot collab.rative manipulation and underscoring its potential in industrial applications. Copyright © 2025, The Authors. All rights reserved.

关键词： industrial robots

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

VTAO-BiManip: Masked Visual-Tactile-Action Pre-training with Object Understanding for Bimanual Dexterous Manipulation

arXiv

引用

arXiv 2025年

作者： Sun, Zhengnan Shi, Zhaotai Chen, Jiayin Liu, Qingtao Cui, Yu Ye, Qi Chen, Jiming College of Control Science and Engineering Zhejiang University Hangzhou310027 China State Key Laboratory of Industrial Control Technology Zhejiang University China Key Key Lab of CS&AUS of Zhejiang Province China

Bimanual dexterous manipulation remains significant challenges in robotics due to the high DoFs of each hand and their coordination. Existing single-hand manipulation techniques often leverage human demonstrations to guide RL methods but fail to generalize to complex bimanual tasks involving multiple sub-skills. In this paper, we introduce VTAOBiManip, a novel framework that combines visual-tactile-action pretraining with object understanding to facilitate curriculum RL to enable human-like bimanual manipulation. We improve prior learning by incorporating hand motion data, providing more effective guidance for dual-hand coordination than binary tactile feedback. Our pretraining model predicts future actions as well as object pose and size using masked multimodal inputs, facilitating cross-modal regularization. To address the multiskill learning challenge, we introduce a two-stage curriculum RL approach to stabilize training. We evaluate our method on a bottle-cap unscrewing task, demonstrating its effectiveness in both simulated and real-world environments. Our approach achieves a success rate that surpasses existing visual-tactile pretraining methods by over 20%. Copyright © 2025, The Authors. All rights reserved.

关键词： Bottles

来源：评论

学校读者我要写书评

暂无评论

Semi-Cervixseg: A Multi-Stage Training Strategy for Semi-Supervised Cervical Segmentation

Semi-Cervixseg: A Multi-Stage Training Strategy for Semi-Sup...

引用

IEEE International Symposium on Biomedical Imaging

作者： Juntao Jiang Yali Bi Chunlin Zhou Yong Liu Jiangning Zhang College of Control Science and Engineering Zhejiang University College of Computer and Information Science Southwest University State Key Laboratory of Industrial Control Technology Zhejiang University Youtu Lab Tencent

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Image segmentation plays a critical role in computer-aided diagnosis and treatment planning for cervical cancer. Obtaining a large number of lab.led images for supervised cervical segmentation is often lab.r-intensive and time-consuming. In this paper, we propose a multi-stage semi-supervised learning framework (Semi-CervixSeg) to address the cervical seg-mentation task in ultrasound images for Fetal Ultrasound Grand Challenge: Semi-Supervised Cervical Segmentation in ISBI 2025. Specifically, in the initial stage, we utilize unlab.led data through a multi-view random augmentation strategy, using consistency constraints and a contrastive learning method. Subsequently, a progressive multi-stage training strategy is adopted to generate and optimize pseudo-lab.ls, further improving segmentation results. Experimental re-sults demonstrate that the proposed method significantly im-proves segmentation performance compared with supervised methods. As a technical report for the challenge, this paper elab.rates on our methodology and experimental findings in detail. The code can be accessed at h t t p s: / / g i t hub. com/juntaoJianggavin/Semi-CervixSeg.

关键词： Training Image segmentation Ultrasonic imaging Codes Contrastive learning Semisupervised learning Writing Data models Planning Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

GRFR: Greedy rumor forwarding routing for wireless sensor/actor networks

引用

Information technology Journal 2008年第4期7卷 661-666页

作者： Chen, Jiming Fan, Jialu Cao, Xianghui Sun, Yousian State Key Lab. of Industrial Control Technology Institute of Industrial Process Control Zhejiang University Hangzhou 310027 China

In this research, a Greedy Rumor Forwarding Routing (GRFR) protocol is proposed for Wireless Sensor/Actor Networks (WSANs) based on geographic information, which improves rumor routing protocol. The study explores the performance of GRFR including both the network lifetime and communication delay at two different system architectures based on the software simulation platform SensorSimulator, which is a discrete event simulation framework for the networks built over OMNeT-l++. Furthermore, it is deeply investigated how the sensor nodes within one hop from the sink affect the network lifetime. © 2008 Asian Network for Scientific Information.

关键词： Discrete event simulation

来源：评论

学校读者我要写书评

暂无评论

A closed-loop particle swarm optimizer for multivariable process controller design

引用

Journal of Zhejiang University-Science A(Applied Physics & Engineering) 2008年第8期9卷 1050-1060页

作者： Kai HAN Jun ZHAO Zu-hua XU Ji-xin QIAN State Key Lab of Industrial Control Technology Institute of Industrial Process Control Zhejiang University Hangzhou 310027 China

Design of general multivariable process controllers is an attractive and practical alternative to optimizing design by evolutionary algorithms (EAs) since it can be formulated as an optimization problem. A closed-loop particle swarm optimization (CLPSO) algorithm is proposed by mapping PSO elements into the closed-loop system based on control theories. At each time step, a proportional integral (PI) controller is used to calculate an updated inertia weight for each particle in swarms from its last fitness. With this modification, limitations caused by a uniform inertia weight for the whole population are avoided, and the particles have enough diversity. After the effectiveness, efficiency and robustness are tested by benchmark functions, CLPSO is applied to design a multivariable proportional-integral-derivative (PID) controller for a solvent dehydration tower in a chemical plant and has improved its performances.

关键词： Multivariable process control Proportional-integral-derivative (PID) control Model predictive control (MPC) Particle swarm optimization (PSO) Closed-loop system

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：