检索结果-内蒙古大学图书馆

43rd Chinese control Conference, CCC 2024

作者： Zhang, Xinyao Cao, Junzhe Dalian University of Technology Control Science and Engineering Dalian116024 China Dalian University of Technology Key Lab. of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian116024 China

ISBN: (纸本)9789887581581

Airfoil flow field is of great significance to the design optimization of aircraft shape. Convolutional Neural Networks (CNNs) have been applied in flow field prediction studies, which greatly reduce the cost of computation time in traditional Computational Fluid Dynamics (CFD) methods. However, such CNN-based approaches normally bring extra errors due to the procedure of interpolating irregular grid data into Cartesian grids, which may lead to underperforming prediction accuracy. In this paper, an improved PointNet++ point cloud deep learning method was proposed for the airfoil flow field prediction. The unstructured grid vertices in the CFD domain were treated as point cloud as well as the input of neural network, and only the original information of the data was adopted to avoid interpolation. Neighborhood relationship features were defined and spliced with neighborhood point features, and the features were integrated by simultaneously solving for the maximum, minimum, sum, and average values to extract the local or global features of the system to enhance the performance of deep network for extracting the information. Finally, the proposed network was trained and tested by using 549 sets of flow field data formed by 61 airfoils under 9 angle-of-attack conditions, and further predicted for an additional 32 datasets with different airfoils and conditions. The simulation results show that the method proposed in this study gets lower prediction errors in terms of pressure, Mach number, x-direction velocity, and y-direction velocity than the two other current point cloud deep networks, PointNet and PointNet++. At the same time, the computation speed of this method is about 14 times faster than the traditional CFD method. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Computational fluid dynamics

来源：评论

学校读者我要写书评

暂无评论

Serrated chip characteristics and formation mechanism in high-speed machining of selective laser melted Ti6Al4V alloys

引用

Science China(Technological Sciences) 2023年第5期66卷 1435-1450页

作者： LIU DeJian WANG YouQiang NI ChenBing ZHU LiDa ZHENG ZhongPeng 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

Serrated chips,consisting of extremely uneven plastic deformation,are a prominent feature of high-speed machining of difficultto-machine *** paper focuses on the evolution of chip form,chip morphology features(chip free surface,tool-chip contact surface,and chip edge),and chip segment parameters in subsequent high-speed(vc=50 and 150 m min-1)machining of selective laser melted(SLMed)Ti6Al4V alloys,which are significantly different from conventional Ti6Al4V alloy in microstructure,mechanical properties and *** effect of laser beam scanning schemes(0°,67.5°,and 90°),machined surfaces(top and front),and cutting speeds on serrated chip characteristics of SLMed Ti6Al4Valloys was *** on the Johnson-Cook constitutive model of SLMed Ti6Al4Valloys,an orthogonal cutting model was developed to better understand the effect of physical-mechanical properties on the shear localization,which dominates the formation mechanism of serrated chips in post-machining of SLMed Ti6Al4V *** results showed that the critical cutting speed(CCS)for chip serration of SLMed Ti6Al4V alloy is lower than that for serrated chips of conventional Ti6Al4V alloy,and the serrated profile of SLMed Ti6Al4V chips was more regular and ***,due to anisotropic microstructure and mechanical properties of SLMed Ti6Al4Valloys,the serration degree of chips produced on the top surfaces of SLMed Ti6Al4Valloys is more prominent than that of chips generated on the front *** addition,because of the poor deformation coordination and high plastic flow stresses of needle-like martensiteα′,the plastic flow and grain distortion in the adiabatic shear band(ASB)of SLMed Ti6Al4V chips are significantly smaller than those in the ASB of conventional Ti6Al4V with equiaxed grains.

关键词： serrated chips selective laser melted Ti6Al4V alloys high-speed machining chip characteristics anisotropic properties

来源：评论

学校读者我要写书评

暂无评论

On non-von Neumann flexible neuromorphic vision sensors

引用

npj Flexible Electronics 2024年第1期8卷 638-663页

作者： Hao Wang Bin Sun Shuzhi Sam Ge Jie Su Ming Liang Jin Institute for Future Shandong Key Laboratory of Industrial Control TechnologySchool of AutomationQingdao UniversityQingdao 266071China College of Electronic and Information Engineering Qingdao UniversityQingdao 266071China Department of Electrical and Computer Engineering and Institute for Functional Intelligent MaterialsNational University of SingaporeSingapore 117583Singapore

The structure andmechanismof thehuman visual system contain rich treasures,and surprising effects can be achieved by simulating the human visual *** this article,starting from the human visual system,we compare and discuss the discrepancies between the human visual system and traditional machine vision *** the wide variety and large volume of visual information,the use of nonvon Neumann structured,flexible neuromorphic vision sensors can effectively compensate for the limitations of traditional machine vision systems based on the von Neumann ***,this article addresses the emulation of retinal functionality and provides an overview of the principles and circuit implementation methods of non-von Neumann computing ***,in terms of mimicking the retinal surface structure,this article introduces the fabrication approach for flexible sensor ***,this article analyzes the challenges currently faced by non-von Neumann flexible neuromorphic vision sensors and offers a perspective on their future development.

关键词： Neumann system starting

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

Design of recognition algorithm for multiclass digital display instrument based on convolution neural network

引用

Biomimetic Intelligence & Robotics 2023年第3期3卷 67-74页

作者： Xuanzhang Wen Yuxia Wang Qiuguo Zhu Jun Wu Rong Xiong Anhuan Xie Polytechnic Institute Zhejiang UniversityHangzhou 310015China College of Control Science and Engineering Zhejiang UniversityHangzhou 310027China State Key Laboratory of Industrial Control and Technology Zhejiang UniversityHangzhou 310027China Zhejiang Lab Hangzhou 311121China

Digital display instrument identification is a crucial approach for automating the collection of digital display *** this study,we propose a digital display area detection CTPNpro algorithm to address the problem of recognizing multiclass digital display *** developed a multiclass digital display instrument recognition algorithm by combining the character recognition network constructed using a convolutional neural network and bidirectional variable-length long short-term memory(LSTM).First,the digital display region detection CTPNpro network framework was designed based on the CTPN network architecture by introducing feature fusion and residual ***,the digital display instrument identification network was constructed based on a convolutional neural network using twoway LSTM and Connectionist temporal classification(CTC)of indefinite ***,an automatic calibration system for digital display instruments was built,and a multiclass digital display instrument dataset was constructed by sampling in the *** compared the performance of the CTPNpro algorithm with other methods using this dataset to validate the effectiveness and robustness of the proposed algorithm.

关键词： Multiclass display instrument Digital display area detection Character recognition Convolutional neural network Characteristics of the fusion

来源：评论

学校读者我要写书评

暂无评论

Distributed Resilient Frequency control Based on Estimation of Sensor and Actuator Attacks in AC Microgrids 48

Distributed Resilient Frequency Control Based on Estimation ...

引用

48th Annual Conference of the IEEE industrial Electronics Society, IECON 2022

作者： Ma, Kai Dong, Yufei Zhao, Peng Yang, Jie Yanshan University Key Lab of Industrial Computer Control Engineering of Hebei Province Qinhuangdao China Yanshan University School of Electrical Engineering Qinhuangdao China

ISBN: (数字)9781665480253

ISBN: (纸本)9781665480253

The consensus based distributed frequency control strategy makes all measurements and control units in microgrids vulnerable to false data injection (FDI) attacks. This paper presents an observer-based resilient frequency control for estimating and compensating for FDI attacks on sensors and actuators in AC microgrids. Firstly, attacks of sensors and actuators are estimated online simultaneously by observers. Then a distributed H∞ output feedback protocol is used to ensure that the frequency consensus tracking is achieved with cooperative uniform ultimate boundedness. The control strategy is completely distributed and does not require any quantitative information about attacks. Furthermore, there is no limit to the number and location of attacked units. Several case studies are provided to verify the effectiveness of the proposed resilient frequency control strategy. © 2022 IEEE.

关键词： Frequency estimation

来源：评论

学校读者我要写书评

暂无评论

Specificity-preserving RGB-D saliency detection

引用

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

Scheduling Optimization of Coal Washing Process Based on Two-Stage Fuzzy Heuristic Algorithm 13

Scheduling Optimization of Coal Washing Process Based on Two...

引用

13th IEEE Data Driven control and Learning Systems Conference, DDCLS 2024

作者： Zhou, Hui Wang, Zhiyuan Han, Zhongyang Wang, Linqing Zhao, Jun Wang, Wei Dalian University of Technology Key Lab. of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian116024 China School of Control Science and Engineering Dalian University of Technology Dalian116024 China

ISBN: (纸本)9798350361674

Coal washing and sorting plays a vital role for coal production. Reasonable scheduling of washing and sorting equipment, crushers and various coal silos in the coal washing and sorting process can effectively increase the total value of product coal and reduce the total energy consumption of equipment. In this paper, a multi-constrained nonlinear mixed integer programming model considering the start and stop of each equipment in the washing process is established to realize the specific regulation of the washing process. In order to overcome the problem such as local convergence when solving high-dimensional space problems, a two-stage fuzzy heuristic algorithm is proposed in this paper. In the first stage, a variety of population genetic algorithms based on fuzzy adaptive strategy control are designed for global search to establish an elite population bank to preserve high-quality individuals produced by various groups. In the second stage, an improved simulated annealing algorithm is used to perform a local search with a backtracking process on specific neighbors of individuals in the elite population bank, which can improve the stability of the algorithm and reduce the situation of falling into local convergence. Then the real data of a Chinese coal mining company was used for experiments, where the proposed algorithm is compared with other commonly used methods. The experimental results demonstrate that the proposed algorithm can increase the total coal value of the washed product by at least 1.7% compared to other algorithms, and the average total number of starts and stops of the equipment is reduced by about 7.3%, which are effectively beneficial for the related enterprise. © 2024 IEEE.

关键词： Coal mines

来源：评论

学校读者我要写书评

暂无评论

Optimal Resource Allocation Scheme for RIS-Assisted Vehicular Networks

Optimal Resource Allocation Scheme for RIS-Assisted Vehicula...

引用

第43届中国控制会议

作者： Wenxuan Chen Jiawei Su Zhixin Liu the School of Electrical Engineering Yanshan University Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Deploying reconfigurable intelligent surfaces(RIS)in vehicular networks can effectively improve the quality of wireless channel and increase network throughout,which is realized by optimizing the phase ***,the dynamic network environment and complex multi-user interference seriously affect network *** transmission powers blindly cannot solve the interference problem but also reduces the transmission efficiency of the RIS-based vehicular *** address the above challenges,this paper proposed a joint optimization scheme of transmission beamforming and phase *** on the block coordinate descent(BCD) theory,this paper decomposed the scheme into two sub-problems:transmission beamforming optimization and RIS phase shift optimization,and the joint optimization algorithm was *** results have demonstrated that the transmission rate has been improved with the assistance of RIS,with the multi-user interference effect being well-depressed.

关键词： Vehicular networks RIS Interference management Phase shift optimization

来源：评论

学校读者我要写书评

暂无评论

Integrative approach for predicting drug-target interactions via matrix factorization and broad learning systems

引用

Mathematical Biosciences and engineering 2024年第2期21卷 2608-2625页

作者： Xu, Wanying Yang, Xixin Guan, Yuanlin Cheng, Xiaoqing Wang, Yu College of Computer Science & Technology Qingdao University Qingdao266071 China School of Automation Qingdao University Qingdao266071 China Key Lab of Industrial Fluid Energy Conservation and Pollution Control Ministry of Education Qingdao University of Technology Qingdao266520 China School of Mechanical & Automotive Engineering Qingdao University of Technology Qingdao266520 China

In the drug discovery process, time and costs are the most typical problems resulting from the experimental screening of drug-target interactions (DTIs). To address these limitations, many computational methods have been developed to achieve more accurate predictions. However, identifying DTIs mostly rely on separate learning tasks with drug and target features that neglect interaction representation between drugs and target. In addition, the lack of these relationships may lead to a greatly impaired performance on the prediction of DTIs. Aiming at capturing comprehensive drug-target representations and simplifying the network structure, we propose an integrative approach with a convolution broad learning system for the DTI prediction (ConvBLS-DTI) to reduce the impact of the data sparsity and incompleteness. First, given the lack of known interactions for the drug and target, the weighted K-nearest known neighbors (WKNKN) method was used as a preprocessing strategy for unknown drug-target pairs. Second, a neighborhood regularized logistic matrix factorization (NRLMF) was applied to extract features of updated drug-target interaction information, which focused more on the known interaction pair parties. Then, a broad learning network incorporating a convolutional neural network was established to predict DTIs, which can make classification more effective using a different perspective. Finally, based on the four benchmark datasets in three scenarios, the ConvBLS-DTI’s overall performance out-performed some mainstream methods. The test results demonstrate that our model achieves improved prediction effect on the area under the receiver operating characteristic curve and the precision-recall curve. ©2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://***/licenses/by/4.0)

关键词： Learning systems

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：