检索结果-内蒙古大学图书馆

4th International Conference on Artificial Intelligence and Big Data, ICAIBD 2021

作者： Cui, Zihao Kong, Xiangwei Hao, Peifeng Software College Northeastern University Shenyang China School of Mechanical Engineering Automation Liaoning Province Key Laboratory of Multidisciplinary Design Optimization of Complex Equipment Northeastern University Key Laboratory of Vibration and Control of Aero-Propulsion System Ministry of Education Shenyang China

ISBN: (纸本)9780738131702

This paper proposes a new Siamese network model for fault diagnosis with limited training samples. We introduce residual blocks to the Siamese network model for few-shot learning. By using the same or different types of sample pairs to learn, our model further improves the accuracy of the Siamese network in bearing fault diagnosis under different workloads and noisy environments. Experiments on the CWRU and MFPT data set showed that the proposed model outperforms the convolutional Siamese network in bearing fault diagnosis. The accuracy of our model has achieved more than 93% accuracy with 90 training samples on the CWRU and MFPT data set. All our models and experiments are available from https://***/WunaiDczh/Few_data_Learing. © 2021 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

PID Parameter Optimization of Secondary Cooling Water Distribution Model for Continuous Casting Based on Improved Artificial Bee Colony Algorithm 4

PID Parameter Optimization of Secondary Cooling Water Distri...

引用

4th International Conference on Artificial Intelligence and Big Data, ICAIBD 2021

作者： Wang, Yibing Kong, Xiangwei Hao, Peifeng Software College Northeastern University Shenyang China School of Mechanical Engineering Automation Liaoning Province Key Laboratory of Multidisciplinary Design Optimization of Complex Equipment Northeastern University Key Laboratory of Vibration and Control of Aero-Propulsion System Ministry of Education Shenyang China

ISBN: (纸本)9780738131702

Dynamic control of secondary cooling in continuous casting is the key technology to improve the quality and efficiency of the slab. In order to improve the quality and efficiency of the slab, a new control strategy of secondary cooling water distribution based on an improved artificial bee colony algorithm is proposed. Based on the traditional artificial bee colony algorithm, adding the learning factor to the optimal individual learning factor and random individual of the current population and integrating the output overshoot mechanism into the objective function is effective to avoid the great overshoot phenomenon caused by the abruptly change of casting speed and the large fluctuation of casting surface temperature. The transfer function was constructed based on the coupling relationship between the distribution of secondary cooling water and slab surface temperature. The Simulink simulation model was established, which was compared with the PSO-DSWPI Method and conventional PID controller. The results showed that the improved artificial bee colony algorithm has a more minor error, higher control accuracy and more smooth step response, which provided a new method for realizing more accurate control of secondary cooling dynamic water distribution and had practical significance for improving slab quality. © 2021 IEEE.

关键词： Cooling water

来源：评论

学校读者我要写书评

暂无评论

Vision-based Autonomous Landing of UAV on Dynamic Apron

Vision-based Autonomous Landing of UAV on Dynamic Apron

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Pengyu Yue Jing Xin Zhijie Mao Yongchang Lu Youmin Zhang Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an P.R.China Department of Mechanical Industrial & Aerospace Engineering Concordia University Montreal QC Canada

Aiming at the landing problem of Unmanned Aerial Vehicle (UAV) without landmarks and global coordinates, this paper proposes an efficient vision-based UAV autonomous landing solution. Firstly, image information is obtained from the bottom visual sensor of the UAV, and the YOLOV5 object detection method is employed to determine the initial position of the dynamic apron. Subsequently, an improved dynamic apron tracking method based on Spatio-Temporal Transformer is designed. This method updates an initial template through target detection algorithm and utilizes multi-source perceptual data for confidence evaluation and dynamic template updates. It outputs the distribution estimation of the predicted bounding box corner coordinates, and achieves the high reliability continuous positional smoothing estimation and dynamic apron loss re-detection based on UAV vision. Finally, the UAV calculates the horizontal control quantity based on the horizontal relative position between the UAV and the apron obtained. The vertical control quantity is calculated based on the vertical relative position between the UAV and the apron. The vertical relative position is estimated using laser ranging and visual odometry techniques. Based on the results of horizontal tracking control and vertical regulation, velocity commands for the UAV in all three directions are generated, enabling the UAV to achieve autonomous landing on the dynamic apron. This paper achieves precise landing for dynamic apron in real-world environments. The experimental results demonstrate that this method avoids the limitations of labeled data and global information on autonomous landing of UAV. Even under GPS-denied conditions, the UAV can generate control commands based on visual data and achieve autonomous landing for randomly moving apron.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application of PID parameters optimization based on GWO in mould level system

Application of PID parameters optimization based on GWO in m...

引用

2021 International Conference on Internet, Education and Information Technology, IEIT 2021

作者： Sitong, Liu Xiangwei, Kong Peifeng, Hao Hezhan, Gao Software College Northeastern University Shenyang China School of Mechanical Engineering Automation Northeastern University Key Laboratory of Vibration and Control of Aero-Propulsion System Ministry of Education Liaoning Province Key Laboratory of Multidisciplinary Design Optimization of Complex Equipment Shenyang China

ISBN: (纸本)9781665425636

Mold level stability is a very important factor in the continuous casting process. To effectively control the liquid level at the set value, solve the problems of disturbance, nonlinearity, and time-varying in the system, as well as modeling difficulties caused by uncertain factors, and aiming at the shortcomings of conventional PID control, the gray wolf algorithm is introduced the gray wolf optimization algorithm is used to self-tune the PID parameters, and the objective function is constructed based on the adjustment time and steady-state error of the mold liquid level system. Finally, the simulation and experimental results show that the algorithm optimization proposed in this paper is compared with the particle swarm algorithm, and the step response of the system is smoother. Gray Wolf optimized PID control has a fast response speed, with an adjustment time of 3.87s, which is lower than 13.46s for conventional PID control and 5.58s for the PSO algorithm. It can significantly improve the control accuracy and other performance indicators of the system. It provides a reference for improving the level control of the continuous casting mold. © 2021 IEEE.

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

Blendnet: Metric-Based Method for Few-Shot Image Classification

SSRN

引用

SSRN 2022年

作者： Yang, Jiming Da, Feipeng Southeast University School of Automation Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China

Image classification task often requires a massive amount of data. Learning to adapt when little data is available could be difficult. In this work, a framework named BlendNet is proposed for few-shot learning. Unlike conventional metric-based methods, a classifier blending features from different levels is proposed to assist the framework to obtain better accuracy and generalization performance. To alleviate the variance of the network for classifying the same class of objects, an data augmentation method is exploited to obtain the image representation robustly. Extensive experiments are conducted to validate our method under the meta-learning paradigm using few-shot classification datasets. The experiments demonstrate that our proposed framework provides competitive results on both Omniglot and mini -ImageNet benchmarks. Our code is available at https: // *** / tyolm / BlendNet . © 2022, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Adaptive control of Discrete-time Nonlinear systems Using ITF-ORVFL

引用

IEEE/CAA Journal of Automatica Sinica 2022年第3期9卷 556-563页

作者： Xiaofei Zhang Hongbin Ma Wenchao Zuo Man Luo School of Automation Beijing Institute of TechnologyBeijing 100081 School of Vehicle and Mobility Tsinghua UniversityBeijing 100084China School of Automation Beijing Institute of Technologyand also with the State Key Laboratory of Intelligent Control and Decision of Complex Systems(Beijing Institute of Technology)Beijing 100081China School of Automation Beijing Institute of TechnologyBeijing 100081and he is with Beijing Institute of Electronic System EngineeringBeijing 100854China School of Automation Beijing Institute of TechnologyBeijing 100081and she is with Ant GroupBeijing 310013China

Random vector functional ink(RVFL)networks belong to a class of single hidden layer neural networks in which some parameters are randomly *** network structure in which contains the direct links between inputs and outputs is unique,and stability analysis and real-time performance are two difficulties of the control systems based on neural *** this paper,combining the advantages of RVFL and the ideas of online sequential extreme learning machine(OS-ELM)and initial-training-free online extreme learning machine(ITFOELM),a novel online learning algorithm which is named as initial-training-free online random vector functional link algo rithm(ITF-ORVFL)is investigated for training *** link vector of RVFL network can be analytically determined based on sequentially arriving data by ITF-ORVFL with a high learning speed,and the stability for nonlinear systems based on this learning algorithm is *** experiment results indicate that the proposed ITF-ORVFL is effective in coping with nonparametric uncertainty.

关键词： Adaptive control initial-training-free online learning algorithm random vector functional link networks

来源：评论

学校读者我要写书评

暂无评论

Identify Influential Nodes in complex Networks: A K-Orders Entropy-Based Method

SSRN

引用

SSRN 2023年

作者： Wu, Yali Dong, Ang Ren, Yuanguang Jiang, Qiaoyong Department of Information and Control Engineering Xi’an University of Technology Xi’an710048 China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an University of Technology Xi’an710048 China The School of Computer Science and Engineering Xi’an University of Technology Xi’an710048 China

Identifying influential nodes is a recognized challenge for the tremendous number of nodes in complex networks. Most of proposed methods detect the influential nodes based on their degree or topological location, which only consider the local or global information of the network causing inaccuracy. In this paper, we propose a k-orders entropy-based method to identify influential nodes. The influence of node is determined by its entropy with local and global information. The entropy reflecting local information is measured by the different order neighbors' information of nodes while the entropy reflecting global information by the betweenness centrality. The experiments conducted on real-world networks demonstrate the proposed method is more accurate than other methods. © 2023, The Authors. All rights reserved.

关键词： complex networks

来源：评论

学校读者我要写书评

暂无评论

Multiplexed model predictive attitude control for nadir-pointing satellite using only magnetorquers

引用

control engineering Practice 2025年 162卷

作者： Yang, Sen Ling, Keck Voon Wang, Zhenhua Li, Huiping School of Astronautic Harbin Institute of Technology Harbin150001 China School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Harbin150001 China School of Marine Science and Technology Northwestern Polytechnical University Xi'an710072 China

Due to the low failure risk of magnetorquers, the control strategy based on magnetic actuators can significantly enhance the reliability of the satellite attitude control system. In light of this advantage, this paper conducts research on model predictive control (MPC) algorithm for nadir-pointing satellites equipped only with magnetorquers. Firstly, to facilitate controller design, the linear time-varying (LTV) model for nadir-pointing satellites is derived by linearizing the nonlinear equations around the operating point. Then, leveraging this linearized representation, an LTV multiplexed MPC (MMPC) method with exponential weighting is proposed. The MMPC scheme allows for faster sampling rates and quicker responses to disturbances, thereby enhancing the overall performance of the satellite attitude control system while retaining the benefits of MPC. Finally, compared with a state-of-the-art SMPC method, the proposed method is particularly advantageous in situations where computational resources are limited, specifically for satellites that rely only on onboard computing capabilities. © 2025

关键词： Nonlinear equations

来源：评论

学校读者我要写书评

暂无评论

Second harmonic generation of laser beams in transverse mode locking states

引用

Advanced Photonics 2022年第2期4卷 68-77页

作者： Zilong Zhang Yuan Gao Xiangjia Li Xin Wang Suyi Zhao Qiang Liu Changming Zhao Beijing Institute of Technology School of Optics and PhotonicsBeijingChina Ministry of Education Key Laboratory of Photoelectronic Imaging Technology and SystemBeijingChina Ministry of Industry and Information Technology Key Laboratory of Photonics Information TechnologyBeijingChina Arizona State University School for Engineering of MatterTransport and EnergyDepartment of Aerospace and Mechanical EngineeringTempeArizonaUnited States Ministry of Education Key Laboratory of Photonic Control Technology(Tsinghua University)BeijingChina Tsinghua University Department of Precision InstrumentState Key Laboratory of Precision Measurement Technology and InstrumentsBeijingChina

Nonlinear frequency conversion of structured beams has been of great interest *** present an intracavity second harmonic generation(SHG)of laser beams in transverse mode locking(TML)states with a specially designed sandwich such as a microchip *** intracavity nonlinear frequency conversion process of a laser beam in a TML state to its second harmonic is theoretically and experimentally investigated,considering different relative phase and weight parameters between the basic modes in the TML *** between the far-field SHG beam patterns of fundamental frequency transverse modes in coherently locked and incoherently superposed states demonstrates that the SHG of TML beams can carry more *** rarely observed far-field SHG beam patterns are obtained,and they are consistent with the theoretical analysis and numerical *** the obtained SHG beams,the characteristics of the structured fundamental frequency beams can also be conversely investigated or *** work may have important applications in optical 3D printing,optical trapping of particles,and free-space optical communication areas.

关键词： transverse mode locking optical vortex lattice structured beams second harmonic generation

来源：评论

学校读者我要写书评

暂无评论

Cooperative Resource Allocation for NOMA-MEC Multi-Cell Network

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Cai, Yujin Zhang, Zaichen Huang, Yongming Yu, Wenwu Nie, Xiaokai Liu, Hongzhe Southeast University School of Mathematics Jiangsu Nanjing211189 China Southeast University National Mobile Communications Research Laboratory Nanjing211189 China Purple Mountain Laboratories Nanjing211111 China Southeast University School of Automation Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Southeast University Shenzhen Research Institute Shenzhen518057 China

Integrating non-orthogonal multiple access (NOMA) and mobile edge computing (MEC) enables IoT nodes to offload their complicated tasks to MEC servers. Most of the existing resource allocation schemes in NOMA-MEC networks are based on the centralized optimization framework, which may increase the communicational and computational burden on the central unit. In this paper, the NOMA-MEC multi-cell network without the central unit is considered. To minimize the task completion time and offloading cost, a joint optimization problem including sub-channel allocation, transmit power, offloaded proportions, computing frequencies of IoT nodes and MEC servers, and price of MEC resources is investigated. In order to tackle the formulated mixed integer nonlinear programming problem, a two-stage low-complexity distributed algorithm based on the cooperation of all base stations (BSs) is proposed. Specifically, in Stage 1, a distributed heuristic sub-channel allocation algorithm is designed based on the sub-channel gains. In Stage 2, with the obtained sub-channel allocation result, a cooperative distributed continuous variable optimization algorithm is devised based on the distributed optimization and alternating optimization methods. Numerical results demonstrate the convergence of the proposed two-stage algorithm for three interference cases. Besides, the impacts of system parameters and schemes on the network performance are analyzed. More importantly, the resource allocation time can be significantly shortened by employing the cooperation of BSs compared with the centralized algorithm © 1967-2012 IEEE.

关键词： Nonlinear programming

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：