检索结果-内蒙古大学图书馆

SSRN 2022年

作者： Liu, Shuang Meng, Qingfu Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Hebei066004 China Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Mr Hebei066004 China

Aiming at the vibration behavior of the main driving system of rolling mill when the lubrication condition changes, the Hopf bifurcation phenomenon of the system under unsteady lubrication condition is analyzed, and an improved hybrid control strategy is proposed to suppress the vibration of rolling mill. Firstly, according to the variation law of lubrication conditions in rolling process, the dynamic rolling moment of the main drive system under unsteady lubrication was given, and the torsional vibration mechanical model of the main drive system was established, and the Hopf bifurcation behavior of the system under boundary lubrication was analyzed. It is found that when the subcritical Hopf bifurcation occurs in the system, the main transmission system of the linker will experience sudden and destructive instability oscillations. Therefore, this paper proposes an improved hybrid control strategy to control the Hopf bifurcation behavior of the system. The traditional hybrid control strategy uses a single control parameter to control both parameter disturbance and state feedback. Here, two control parameters are used to control parameter disturbance and state feedback respectively. In the state feedback part, nonlinear feedback is used to replace the traditional linear feedback. After the control is added, the critical value of Hopf bifurcation can be changed and the stability region of the system can be increased by adjusting the control parameters of the disturbance part of the parameters. Here, direct Normal form calculation method is introduced to calculate the Hopf bifurcation specification of the system. By adjusting the control parameters of the state feedback part by the canonical coefficient, the system can be changed from subcritical bifurcation to supercritical bifurcation, the phase trajectory of the system can be changed from unstable limit cycle to stable limit cycle, and the amplitude of limit cycle can be controlled. The effectiveness of the proposed

关键词： Lubrication

来源：评论

学校读者我要写书评

暂无评论

Multi-dimension and multi-modal rolling mill vibration prediction model based on multi-level network fusion

引用

Journal of Central South University 2024年第9期31卷 3329-3348页

作者： CHEN Shu-zong LIU Yun-xiao WANG Yun-long QIAN Cheng HUA Chang-chun SUN Jie School of Electrical Engineering Yanshan UniversityQinhuangdao 066004China Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan UniversityQinhuangdao 066004China Shougang Jingtang United Iron&Steel Co. Ltd.Tangshan 063200China State Key Laboratory of Rolling and Automation Northeastern UniversityShenyang 110819China

Mill vibration is a common problem in rolling production,which directly affects the thickness accuracy of the strip and may even lead to strip fracture accidents in serious *** existing vibration prediction models do not consider the features contained in the data,resulting in limited improvement of model *** address these challenges,this paper proposes a multi-dimensional multi-modal cold rolling vibration time series prediction model(MDMMVPM)based on the deep fusion of multi-level *** the model,the long-term and short-term modal features of multi-dimensional data are considered,and the appropriate prediction algorithms are selected for different data *** on the established prediction model,the effects of tension and rolling force on mill vibration are *** the 5th stand of a cold mill in a steel mill as the research object,the innovative model is applied to predict the mill vibration for the first *** experimental results show that the correlation coefficient(R^(2))of the model proposed in this paper is 92.5%,and the root-mean-square error(RMSE)is 0.0011,which significantly improves the modeling accuracy compared with the existing *** proposed model is also suitable for the hot rolling process,which provides a new method for the prediction of strip rolling vibration.

关键词： rolling mill vibration multi-dimension data multi-modal data convolutional neural network time series prediction

来源：评论

学校读者我要写书评

暂无评论

Coupling effect of micro-textured tools and cooling conditions on the turning performance of aluminum alloy 6061

引用

Advances in Manufacturing 2023年第4期11卷 663-681页

作者： Guo-Liang Liu Jin-Tao Zheng Chuan-Zhen Huang Shu-Feng Sun Xin-Fu Liu Long-Jie Dai De-Xiang Wang Xiang-Yu Wang Key Lab of Industrial Fluid Energy Conservation and Pollution Control Ministry of EducationKey Lab of Industrial Fluid Energy Conservation and Pollution ControlMinistry of EducationSchool of Mechanical and Automotive EngineeringQingdao University of TechnologyQingdao266520ShandongPeople’s Republic of China State Key Laboratory of High Performance Complex Manufacturing Central South UniversityChangsha410083People’s Republic of China Key Laboratory of High-Efficiency and Clean Mechanical Manufacture(Ministry of Education) School of Mechanical EngineeringShandong UniversityJinan250061People’s Republic of China School of Mechanical Engineering Yanshan UniversityQinhuangdao066004HebeiPeople’s Republic of China Qingdao Choho Ind Co Ltd Qingdao266705ShandongPeople’s Republic of China School of Mechanical Engineering University of JinanJinan250022People’s Republic of China

Micro-texturing has been widely proven to be an effective technology for achieving sustainable ***,the performance of micro-textured tools under different cooling conditions,especially their coupling effect on machined surface integrity,was scarcely *** this paper,the non-textured,linear micro-grooved,and curvilinear micro-grooved inserts were used to turn aluminum alloy 6061 under dry,emulsion,and liquid nitrogen cryogenic cooling *** coupling effects of different micro-textures and cooling conditions on cutting force,cutting temperature,and machined surface integrity,including the surface roughness,work hardening,and residual stress,were revealed and discussed in *** indicated that the micro-grooved tools,especially the curvilinear micro-grooved tools,not only reduced the cutting force and cutting temperature,but also improved the machined surface *** addition,the micro-grooved tools can cooperate with the emulsion or liquid nitrogen to reduce the cutting force,cutting temperature,and improve the machined surface integrity generally,although the combination of emulsion cooling condition and micro-grooved tools generated negative coupling effects on cutting forces and surface work ***,the combination of curvilinear micro-grooved cutting tools and cryogenic cooling condition resulted in the lowest cutting force and cutting temperature,which generated the surface with low roughness,weak work hardening,and compressive residual stress.

关键词： Micro-grooved cutting tool Cooling condition Cutting force Cutting temperature Surface integrity

来源：评论

学校读者我要写书评

暂无评论

Dynamic Multi-Objective Optimization Algorithm for Classification of Decision Variables Based on Objective Monotonicity

SSRN

引用

SSRN 2023年

作者： Wei, Lixin Yang, Qingshuai Guo, Zeyin Institute of Electrical Engineering Yanshan University Hebei Qinhuangdao066004 China Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Hebei Qinhuangdao066004 China

Dynamic multi-objective optimization problems (DMOPs) are prevalent in daily life, and the aim of dealing with DMOPs is to track the moving Pareto Front(PF) and find a series of Pareto Sets (PS) at different moments. Strategies based on decision variable classification improve the performance of multi-objective evolutionary algorithms. However, it has been a challenge to ensure fast and accurate classification. In this study, a decision variable classification method based on objective monotonicity(CDMO) is proposed to reduce the negative effects of inaccurate classification. In addition, a multi-step convergence prediction method and a diversity maintenance strategy are proposed to improve the algorithm performance. The effectiveness of the CDMO algorithm is verified by comparing it with three state-of-the-art DMOEAs on 16 benchmark test problems. The experimental results show that the CDMO algorithm is able to obtain high-quality populations with good convergence and distributivity in a dynamic environment. © 2023, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Federated Learning With Meta-Layers Training for Privacy-Preserving in Vehicular Consumer Electronics

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Shen, Xiaoyang Li, Haibin Li, Yaqian Zhang, Wenming Alenazi, Mohammed J.F. Agarwal, Kadambri Yanshan University College of Electrical Engineering Hebei Qinhuangdao066000 China Key Laboratory of Industrial Computer Control Engineering of Hebei Province Hebei Qinhuangdao066000 China King Saud University College of Computer and Information Sciences Department of Computer Engineering Riyadh11451 Saudi Arabia ABES Engineering College Department of Computer Science and Engineering Ghaziabad201009 India

Vehicular consumer electronics, such as autonomous vehicles (AVs), need collecting large amounts of private user information, which face the risk of privacy leakage. To protect the privacy of consumers, researchers have proposed to apply federated learning (FL) to privacy-preserving vehicular consumer electronics, that is, leveraging FL for collaborative training of a decision model without exchanging the sensitive information generated by AVs. However, FL generally needs to exchange the gradients of client models periodically with the central server, which can be attacked by adversaries to infer user information. Thereby, it may still face the risk of privacy leakage. To solve that challenge, we put forward a novel FL framework, called FL with Meta-Layers Training (FL-MLT). Instead of exchanging the gradients of the client models, it exchanges, meta-layers with the central servers. Since meta-layers are only a slice of the client models, exchanging them helps protect privacy. On the other hand, they contain meta-knowledge to help the FL training process. In the experiments, we conduct extensive visual classification simulation to evaluate FL-MLT, and the experimental results demonstrate the superior performance of FL-MLT. © 1975-2011 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

An Improved Hybrid Aquila Optimizer and Pigeon-Inspired Optimization Algorithm with Its Application in PID Parameter Optimization

An Improved Hybrid Aquila Optimizer and Pigeon-Inspired Opti...

引用

International Symposium on computer Science and Intelligent controls (ISCSIC)

作者： Dongning Chen Xinwei Du Haowen Wang Qinggui Xian Jianhao Sha Chengyu Yao School of Mechanical Engineering Yanshan University Qinhuangdao China Hebei Key Laboratory of Industrial Computer Control Engineering Yanshan University Qinhuangdao China

ISBN: (数字)9798350380286

ISBN: (纸本)9798350380293

To improve the optimization performance of the standard Aquila Optimizer (AO), an Improved Hybrid Aquila Optimizer and Pigeon-Inspired Optimization (IHAOPIO) algorithm based on stochastic balancing factor and Dimension-by-dimension Centroid Opposition-Based Learning (DCOBL) strategy is proposed. Wilcoxon test is introduced to statistically analyze the data of six classical benchmark functions. Compared with several other optimization algorithms, the proposed IHAOPIO algorithm has better optimization capability in accuracy. The improved algorithm is used to the PID parameter optimization of one electro-hydraulic position servo system and achieves good control effect.

关键词： computer science Accuracy Benchmark testing Servomotors Optimization Standards Intelligent control

来源：评论

学校读者我要写书评

暂无评论

MPC-Based Trajectory Tracking control Strategy Incorporating Autonomous Lane-Changing Mechanism for Intelligent Vehicles

MPC-Based Trajectory Tracking Control Strategy Incorporating...

引用

Conference on Vehicle control and Intelligence (CVCI)

作者： Dongxue Zhang Huiwen Liu Xiaohong Jiao Ting Zhang Hebei Key Laboratory of Industrial Computer Control Engineering Yanshan University Qinhuangdao Hebei Province China School of Vehicle and Mobility Tsinghua University Beijing China

ISBN: (数字)9798331504892

ISBN: (纸本)9798331504908

Navigating the intricate traffic environment, lane-changing has emerged as a frequent and essential driving maneu-ver for intelligent vehicles. However, it is challenging to guarantee the safety of the intelligent vehicle and the trajectory tracking accuracy against the external environment during lane-changing. Considering these challenges to overcome, the model predictive control (MPC)-based trajectory tracking strategy incorporating an autonomous lane-changing mechanism is proposed in this paper. The autonomous lane-changing mechanism considering lane-changing intention is proposed to ensure that the intelligent vehicle generates safe lane-changing decisions and trajectories. Subsequently, the MPC strategy that considers the physical char-acteristics of the intelligent vehicle is proposed to guarantee the accuracy and smoothness of trajectory tracking. The validation of its effectiveness and advantages is established on the PreScan and MATlab/Simulink co-simulation platforms.

关键词： Accuracy Intelligent vehicles Trajectory tracking Navigation Vehicle safety Trajectory MATlab Predictive control

来源：评论

学校读者我要写书评

暂无评论

Decision Variable Classification-Based Evolutionary Algorithm for Dynamic Multi-Objective Optimization

SSRN

引用

SSRN 2023年

There are many dynamic multi-objective optimization problems (DMOPs) in real life, and such problems require the algorithms to converge quickly to a new Pareto Front and maintain the diversity of solution sets after the environment changes. To achieve these objectives, a dynamic multi-objective evolutionary algorithm (DEA) based on decision variable classification is proposed in this paper. First, the decision variables are classified into two categories using the decision variable clustering method: convergence-related variables and diversity-related variables. Then, the convergence optimization strategy and the diversity optimization strategy are used to optimize these two categories of decision variables, so that the algorithm can obtain excellent convergence and good diversity while fast tracking the Pareto front. In addition, a method for calculating the degree of environmental change, which uses the information after environmental change, is proposed to improve the algorithm’s ability to respond to environmental change. The proposed algorithm is compared with three state-of-the-art dynamic multi-objective optimization evolutionary algorithms on 16 benchmark problems. The experimental results show that the algorithm can effectively solve dynamic multi-objective optimization problems. © 2023, The Authors. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

A switching-based backstepping sliding mode control for space manipulator in presence of gravity variation

引用

High Technology Letters 2021年第4期27卷 454-462页

作者： Liu Fucai Zhao Wenna Meng Lingcong Liu Shuo Key Laboratory of Industrial Computer Control Engineering of Hebei Province Yanshan UniversityQinhuangdao 066004P.R.China Engineering Department University of SheffieldSheffieldUK

A novel switching-based backstepping sliding mode control(SBSMC) scheme is devised for the space manipulator exposed to different *** a view to distinct differences in dynamics properties when the operating conclition of space manipulator changer,the space manipulator can be thought of as a system composed of two subsystems,the ground subsystem and the space *** different types of backstepping sliding mode(BSM) controllers are designed,one is suited for the ground subsystem and the other is for the space *** switching between two subsystems can be implemented automatically when the switching mechanism is triggered,and the controllers for their subsystems experience synchronous *** this way,the space manipulator always has good behaviors in trajectory ***,multi-Lyapunov functions are introduced to prove the stability of this switching *** to simulation results,the method constructed in this research has better performance in control precision and adaptability compared with proportional-derivative(PD) control.

关键词： space manipulator microgravity switching system multi-Lyapunov functions backstepping sliding mode control(BSMC)

来源：评论

学校读者我要写书评

暂无评论

EAVFormer: an end-to-end audio and visual emotion recognition network based on transformers

引用

Multimedia Systems 2025年第3期31卷 1-22页

作者： Liu, Haoran Sun, Zijian Li, Haibin Li, Yaqian Zhang, Wenming Song, Tao School of Information Science and Engineering Yanshan University Qinhuangdao066004 China The Key Laboratory for Special Fiber and Fiber Sensor of Hebei Province Yanshan University Qinhuangdao066004 China Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao066004 China Shenzhen Research Institute of Yanshan University Shenzhen518057 China Key Lab of Measurement Technology & Instrumentation of Hebei Province School of Electrical Engineering Yanshan University Qinhuangdao066004 China

Audio-visual emotion recognition, integrating information from various sources, enhances the comprehensive understanding and analysis of human emotions. However, existing methods in this field primarily focus on feature fusion, often overlooking the equally crucial stage of feature extraction. Typically, these methods employ pre-trained models to extract features during the initial phase, complicating modality-specific feature extraction and increasing system complexity and coordination challenges, which hinder effective audio-visual feature fusion. To address these issues, we propose an end-to-end audio-visual emotion recognition model, EAVFormer. For the audio modality, we input raw audio signals along with a mix of mel spectrograms and Mel Frequency Cepstral Coefficients (MFCCs), employing a hierarchical transformer technique that facilitates both shallow local and deep global feature extraction to fully harness complementary acoustic information, significantly enhancing the acoustic modality’s contribution. For the visual modality, we input raw video frames and employ a hierarchical transformer feature extraction method that integrates three-dimensional convolution and spatio-temporal self-attention mechanisms to address spatial and temporal redundancies and dependencies, thereby enhancing the expression of dynamic visual information. In the modal fusion stage, we construct dual-modality representations and encode inter-modal information while preserving modality-specific and meaningful intra-modal features. Testing on three popular datasets RAVDESS, CREMA-D, and CMU-MOSEI demonstrates that EAVFormer surpasses existing state-of-the-art methods in audio-visual emotion recognition accuracy, achieving rates of 95.17%, 86.13%, and 78.22%, respectively. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Image coding

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：