检索结果-内蒙古大学图书馆

Specificity-preserving RGB-D saliency detection

Computational Visual Media 2023年第2期9卷 297-317页

作者： Tao Zhou Deng-Ping Fan Geng Chen Yi Zhou Huazhu Fu School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China Key Laboratory of System Control and Information Processing Ministry of EducationShanghaiChina Computer Vision Lab ETH Z¨urichZ¨urichSwitzerland School of Computer Science and Engineering Northwestern Polytechnical UniversityXi’anChina School of Computer Science and Engineering Southeast UniversityNanjingChina Inception Institute of Artificial Intelligence Abu DhabiUnited Arab Emirates

Salient object detection(SOD)in RGB and depth images has attracted increasing research *** RGB-D SOD models usually adopt fusion strategies to learn a shared representation from RGB and depth modalities,while few methods explicitly consider how to preserve modality-specific *** this study,we propose a novel framework,the specificity-preserving network(SPNet),which improves SOD performance by exploring both the shared information and modality-specific ***,we use two modality-specific networks and a shared learning network to generate individual and shared saliency prediction *** effectively fuse cross-modal features in the shared learning network,we propose a cross-enhanced integration module(CIM)and propagate the fused feature to the next layer to integrate cross-level ***,to capture rich complementary multi-modal information to boost SOD performance,we use a multi-modal feature aggregation(MFA)module to integrate the modalityspecific features from each individual decoder into the shared *** using skip connections between encoder and decoder layers,hierarchical features can be fully *** experiments demonstrate that our SPNet outperforms cutting-edge approaches on six popular RGB-D SOD and three camouflaged object detection *** project is publicly available at https://***/taozh2017/SPNet.

关键词： salient object detection(SOD) RGB-D cross-enhanced integration module(CIM) multi-modal feature aggregation(MFA)

来源：评论

学校读者我要写书评

暂无评论

Effect of Extrusion Temperature on the Mechanical Properties and Corrosion Behavior of LZ91 Alloys

引用

Acta Metallurgica Sinica(English Letters) 2023年第11期36卷 1822-1832页

作者： Xuejian Wang Huaqiang Xiao Keqiang Su Bo Lin Tongmin Wang Enyu Guo School of Mechanical Engineering Guizhou UniversityGuiyang550000China Key Laboratory of Solidification Control and Digital Preparation Technology(Liaoning Province) School of Materials Science and EngineeringDalian University of TechnologyDalian116024China Ningbo Institute of Dalian University of Technology Ningbo315000China

Microstructural observations,tensile tests,potentiodynamic polarization measurements,and corrosion morphology examinations are conducted to investigate the effect of extrusion temperature on the mechanical properties and corrosion behavior of LZ91 *** results show that the tensile strength of the LZ91 alloy is increased by 86 MPa after extrusion at 25℃.Meanwhile,the corrosion resistance is improved by about 2.7 times,and the maximum corrosion depth is decreased by 60μ*** increase in the tensile strength can be mainly attributed to theα-Mg precipitate strengthening inβ-*** improvement of the corrosion resistance is due to the fact that the nano-sized MgLiZn and refinedα-Mg precipitates inβ-Li weaken the effect of the cathodic phase on micro-galvanic corrosion,thereby decreasing the cathodic current density and local corrosion ***,when the extrusion temperature is increased to 300°C,the corrosion rate is significantly accelerated due to the increase of the micro-galvanic corrosion caused byα-Mg precipitate coarsening at high temperatures.

关键词： Mg-Li alloy Extrusion temperature Mechanical properties Corrosion behavior

来源：评论

学校读者我要写书评

暂无评论

Swarm-Based Dynamic Coverage of Multi-ASV Systems in the Presence of Measurement Noises

引用

IEEE Transactions on Vehicular Technology 2025年第5期74卷 7237-7250页

作者： Liu, Lu Jiao, Shijian Han, Bing Li, Tieshan Peng, Zhouhua Dalian Maritime University School of Marine Electrical Engineering Dalian116026 China Dalian Key Laboratory of Swarm Control and Electrical Technology for Intelligent Ships Dalian116026 China State Key Laboratory of Maritime Technology and Safety Dalian116026 China Shanghai Ship and Shipping Research Institute National Engineering Research Center of Ship & Shipping Control System Shanghai200135 China University of Electronic Science and Technology of China School of Automation Engineering Chengdu611731 China

This paper is concerned with the dynamic coverage of multiple autonomous surface vehicles (ASVs) in the presence of static and dynamic obstacles, limited communication distance, and measurement noises. A modular control method including planning, guidance, and control is proposed. At the planning level, a swarm-based dynamic coverage strategy is developed to achieve the coverage of a given domain. Both the collision avoidance and connectivity preservation issues are solved by using artificial potential fields. At the kinematic level, novel adaptive line-of-sight guidance laws are presented based on cascade extended state observers (CESOs), such that accurate guidance signals are given by compensating for time-varying sideslip angle and suppressing measurement noises. At the kinetic level, two CESOs are developed to estimate the internal model uncertainties and external environmental disturbance, and antidisturbance kinetic control laws are designed subsequently. The proposed CESOs overcome the noises sensitivity problem of classical observers, and thus facilitate the practical implementation under measurement noises. The input-to-state stability of the closed-loop system is confirmed by the Lyapunov theory and cascade stability theory. Simulation and hardware-in-the-loop experiment results are provided to demonstrate the effectiveness of the proposed swarm-based dynamic coverage method. © 1967-2012 IEEE.

关键词： Velocity measurement

来源：评论

学校读者我要写书评

暂无评论

Bearing Fault Diagnosis for Variable Operating Conditions Based on Deep Learning and Mutual Attention Feature Fusion

Bearing Fault Diagnosis for Variable Operating Conditions Ba...

引用

第43届中国控制会议

作者： YongQi Li Hao Xia School of Control Science and Control Engineering Dalian University of Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Rolling bearings are critical components of rotating mechanical equipment and a major source of industrial equipment ***,bearing fault diagnosis is of significant importance for ensuring the safe and reliable operation of *** recent years,fault diagnosis based on deep learning and feature fusion has been extensively ***,most existing fault diagnosis methods based on feature fusion perform independent feature extraction,failing to deeply explore fault characteristic *** limitation results in suboptimal diagnostic performance under external high-frequency noise and variable load and speed *** address these issues,this paper proposes an adaptive denoising algorithm based on the combination of Ensemble Empirical Mode Decomposition and Continuous Wavelet Transform(EEMD-CWT).Furthermore,the paper employs time-frequency scale transformation and mutual attention mechanism for feature ***,a hybrid fault diagnosis neural network,Deep Residual Spiking Network with Bidirectional Long Short-Term Memory and Attention(DRSNATTENTION-BILSTM),was *** proposed methodology is validated through testing on a rolling bearing dataset and compared with experiments using typical *** results confirm the effectiveness and superiority of the proposed model,offering valuable insights for research in rolling bearing fault diagnosis.

关键词： Fault Diagnosis EEMD-CWT Feature Fusion

来源：评论

学校读者我要写书评

暂无评论

Dual-polarized and real-time reconfigurable metasurface absorber with infrared-coded remote-control system

引用

Nano Research 2022年第8期15卷 7498-7505页

作者： Jiangyong Liu Yuping Duan Tuo Zhang Lingxi Huang Huifang Pang Key Laboratory of Solidification Control and Digital Preparation Technology(Liaoning Province) School of Materials Science and EngineeringDalian University of TechnologyDalian 116085China

The reconfigurable metasurfaces which can regulate the microwave absorption performance at the sub wavelength scale provide a possibility to construct intelligent stealth ***,the existing reconfigurable-metasurface-based absorbers seriously limit the medium and long-distance regulation in practical application due to the complex circuit path and regulation ***,an infrared-coded dual-polarized metasurface absorber(IDMA)with remote-control mode was proposed,which realized the realtime dynamic regulation of the intensity and frequency range of absorption peaks by combining the infrared-coding remotecontrol technology with the active metasurface *** proposed remote-control system can switch the 8-bit binary coding sequences stored in the microcontroller unit(MCU)by an infrared transceiver,so as to regulate the state of active devices under X-and Y-polarizations,*** experimental results showed that the reflection/absorption responses can be regulated by switching different binary codes,and the reflection loss(RL)can be tuned below−7.5 dB(absorptivity over 82%)in wide range of 6.20–18 ***,the corresponding equivalent circuit model was established and the distributions of surface current and electric field were analyzed to elucidate the dynamic reconfigurable mechanism of the metasurface *** proposed IDMA,which combines intelligent electronic technology with active metasurface absorber,creatively realizes the remote control of active metasurface absorber and opens up a new way for the stealth technology of smart absorber in the future.

关键词： microwave absorption active metasurface reflection/absorption infrared-coded remote-control real-time dynamic control

来源：评论

学校读者我要写书评

暂无评论

PICRUSt2 functionally predicts organic compounds degradation and sulfate reduction pathways in an acidogenic bioreactor

引用

Frontiers of Environmental science & engineering 2022年第4期16卷 81-93页

作者： Jun Li Aimin Li Yan Li Minhui Cai Gan Luo Yaping Wu Yechao Tian Liqun Xing Quanxing Zhang State Key Laboratory of Pollution Control and Resources Reuse School of the EnvironmentNanjing UniversityNanjing 210023China Jiangsu Key Laboratory of Chemical Pollution Control and Resources Reuse School of Environmental and Biological EngineeringNanjing University of Science and TechnologyNanjing 210094China

For comprehensive insights into the influences of sulfate on performance,microbial community and metabolic pathways in the acidification phase of a two-phase anaerobic system,a laboratory-scale acidogenic bioreactor was continuously operated to treat wastewater with elevated sulfate concentrations from 2000 to 14000 mg/*** results showed that the acidogenic bioreactor could achieve sulfate reduction efficiency of greater than 70%for influent sulfate content less than 12000 mg/*** sulfate induced the accumulation of volatile fatty acids(VPAs),especially propionate and butyrate,which was the primary negative effects to system performance under the high-sulfate ***-throughput sequencing coupled with PICRUSt2 uncovered that the accumulation of VFAs was triggered by the decreasing of genes encoding short-chain acyl-CoA dehydrogenase(EC:1.3.8.1),regulating the transformation of propanoyl-CoA to propenoyl-CoA and butanoyl-CoA to crotonyl-CoA of propionate and butyrate oxidation pathways,which made these two process hardly ***,genes encoding(EC:1.3.8.1)were mainly carried by order *** was the most abundant sulfate-reducing bacteria and identified as the primary host of dissimilatory sulfate reduction ftinctional *** analysis indicated the dissimilatory sulfate reduction process predominated under a low sulfate environment,but was not favored under the circumstance of *** the increase of sulfate,the assimilatory sulfate reduction process finally overwhelmed dissimilatory as the dominant sulfate reduction pathway in acidogenic bioreactor.

关键词： Acidogenic phase reactor High-sulfate wastewater Sulfate reduction Acidogenic fermentation PICRUSt2

来源：评论

学校读者我要写书评

暂无评论

A hybrid genetic algorithm for the electric vehicle routing problem with time windows

引用

control Theory and Technology 2022年第2期20卷 279-286页

作者： Qixing Liu Peng Xu Yuhu Wu Tielong Shen School of Control Science and Engineering Dalian University of TechnologyDalian 116024China Department of Mechanical Engineering Sophia UniversityTokyo 102-8554Japan

Driven by the new legislation on greenhouse gas emissions,carriers began to use electric vehicles(EVs)for logistics *** paper addresses an electric vehicle routing problem with time windows(EVRPTW).The electricity consumption of EVs is expressed by the battery state-of-charge(SoC).To make it more realistic,we take into account the terrain grades of roads,which affect the travel process of *** our work,the battery SoC dynamics of EVs are used to describe this *** aim to minimize the total electricity consumption while serving a set of *** tackle this problem,we formulate the problem as a mixed integer programming ***,we develop a hybrid genetic algorithm(GA)that combines the 2-opt algorithm with *** simulation results,by the comparison of the simulated annealing(SA)algorithm and GA,the proposed approach indicates that it can provide better solutions in a short time.

关键词： Electric vehicles Vehicle routing Battery SoC Hybrid genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

A Enhanced Feature Extraction for 3D Object Detection 25

A Enhanced Feature Extraction for 3D Object Detection

引用

25th IEEE China Conference on System Simulation Technology and its Application, CCSSTA 2024

作者： Meng, Qingao Tong, Jigang Yang, Sen Xie, Tian Jin, Xin Tianjin University of Technology The School of Electrical Engineering and Automation Tianjin China Avic Xi'an Flight Automatic Control Research Institute National Key Laboratory of Science and Technology on Aircraft Control Xi'an China

ISBN: (纸本)9798350366600

3D object detection is crucial for autopilot and augmented reality applications. However, accurate feature extraction is the key to achieve high-precision detection, but traditional methods face the challenges of information loss and computational inefficiency. To address this, we propose an enhanced feature extraction method. We first divide the 3D space into voxel grids of varying scales. Then, using 3D sparse convolution, we extract features which are compressed along the Z axis to form BEV (Bird's Eye View) feature images. An efficient multi-scale attention mechanism is then employed to enhance these BEV features. The refined feature map is subsequently located and classified through a CT-stacking module and RPN (Region Proposal Network). Voxel features from the proposal and 3D backbone are passed through a voxel RoI pool to directly extract RoI features from the 3D features for further refinement. Finally, a cascaded attention network refines the proposal and strengthens confidence prediction. Experiments on test set validate our method effectiveness, showing improved accuracy over traditional voxel methods. Overall, this enhanced feature extraction technique offers a promising solution for 3D target detection, particularly in scenarios demanding high real-time performance and precision. © 2024 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Zero-Sequence Current Analysis Approach for Rotating Machinery Fault Diagnosis of Induction Motor Drivetrain Based on Sparse Learning

引用

IEEE Transactions on Power Electronics 2025年第7期40卷 9800-9810页

作者： Liu, Zhao-Hua Long, Jun-Jie Wei, Hua-Liang Liu, Kan Zhang, Ying-Jie Li, Xiao-Hua Hunan University of Science and Technology School of Information and Electrical Engineering Xiangtan411201 China The University of Sheffield School of Electrical and Electronic Engineering Department of Automatic Control and Systems Engineering SheffieldS1 3JD United Kingdom Hunan University College of Mechanical and Vehicle Engineering Changsha410082 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China

Fault diagnosis of rotating machinery driven by induction motors has received increasing attention. Current diagnostic methods, which can be performed on existing inverters or current transformers of three-phase induction machines, have become a more economical and reliable alternative to vibration diagnostic methods. Existing references mainly focus on the stator current analysis of single-phase, but most single-phase current analysis methods utilize only a fraction of the total information accessible in the three-phase system. Field experience shows that zero-sequence current (ZSC) has more distinctive fault characteristics compared to single-phase current, and therefore it is better to use in mechanical fault detection and diagnostic tasks. This article proposes a novel sparse learning-based method for ZSC analysis for induction rotating motor drive fault diagnosis. First, it elaborates and compares the effectiveness of ZSC in revealing fault characteristics compared with single-phase current by analyzing the fault diagnosis mechanism of ZSC. In addition, the method proposes a correlation entropy-enhanced sparse learning method for the problem of high-frequency noise and interference in the ZSC signals, so as to enhance the learning of the features of the noise-containing signals. The diagnostic efficacy of the proposed method has been verified through experiments on two real datasets. © 1986-2012 IEEE.

关键词： Induction motors

来源：评论

学校读者我要写书评

暂无评论

Multi-robot obstacle avoidance based on artificial potential field method

Multi-robot obstacle avoidance based on artificial potential...

引用

第43届中国控制会议

作者： Zeyu Liu Xuejun Pan Shiyi Guo School of Control Science and Control Engineering Dalian University of Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Aiming at the obstacle avoidance problem of multi-robot formation in random obstacle environment,this paper proposes an improved method based on artificial potential field method,which solves the problem of unreachable target and local minimum by improving the attraction and repulsion function and introducing simulated annealing *** on the formation structure of the leader-follower method,the dynamic formation transformation obstacle avoidance strategy is adopted to solve the problems of serious formation damage and poor flexibility in the formation *** enabling multirobots to quickly avoid obstacles and reducing the response time of restoring formation after obstacle avoidance,the ability of robot formation to maintain its own formation can be effectively *** improved algorithm is simulated and compared in *** experimental results show the effectiveness and feasibility of the method.

关键词： Mobile robot Artificial potential field method obstacle avoidance simulated annealing algorithm

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：