检索结果-内蒙古大学图书馆

IEEE International Conference on Image Processing

作者： Jun Chen Yiwei Wang Haiyan Zhang School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

The key to face recognition lies in how to improve the model’s ability to extract facial features. To this end, numerous loss functions based on different metrics have been proposed to increase the margin of feature distinction between different classes. Methods based on Cosine distance significantly enhance face recognition performance by focusing on angular constraints between samples and classes, demonstrating their superiority over those based on Euclidean distance. However, a significant oversight in these methods is the neglect of feature magnitude’s importance in representing facial features. To address this gap, our study introduces the NormIntegrated Softmax loss (NIface loss), a novel loss function that amalgamates feature norms with angular information. This integration offers a comprehensive perspective for feature classification, augmenting the compactness of intra-class features. Extensive evaluations on large-scale public datasets have demonstrated the efficacy of NIface loss in enhancing recognition accuracy and stability.

关键词： Measurement Technological innovation Image recognition Accuracy Face recognition Focusing Euclidean distance

来源：评论

学校读者我要写书评

暂无评论

Simulation and Experiment of Planar Magnetic Sensor

Simulation and Experiment of Planar Magnetic Sensor

引用

China Instrument and control Society (ACCIS), Academic Conference of

作者： Jiaqi Lu Fang Jin Kaifeng Dong Junlei Song Wenqin Mo Yajuan Hui Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Automation China University of Geosciences Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China

ISBN: (数字)9798350350326

ISBN: (纸本)9798350350333

In this paper, aiming at the planar magnetic sensor, the model of the planar magnetic sensor probe is constructed from the principle of magnetic line orbit transfer. The planar magnetic sensor probe is simulated and analyzed by COMSOL Multiphysics software. The influence of the horizontal width, height, length, and relative permeability parameters of the magnetic line orbit transfer structure on the orbit transfer coefficient of the magnetic line orbit transfer structure is studied. The simulation results analyze the influence of the structural parameters of the magnetic line transfer on the transfer coefficient, and the optimal parameter conditions are obtained. In order to verify the simulation results, an experimental test platform was built to test the planar magnetic sensor, and the magnetic line of force rail structure with the best experimental effect was obtained. The magnetic line of the force rail structure selects soft magnetic material with relative permeability greater than 5000, the horizontal width is 3mm, the height is 14mm, and the length of the magnetic line of the force rail structure in the experiment is determined to be 5mm according to the actual demand and the production process. Finally, the conversion efficiency of the planar magnetic sensor to the Z-axis magnetic field can reach 39.9 %. This study provides a research idea for promoting the planar design of magnetic sensors.

关键词： Rails Magnetic flux leakage Magnetic field measurement Magnetic sensors Simulation Force Orbits Permeability Soft magnetic materials Magnetic fields

来源：评论

学校读者我要写书评

暂无评论

Few-shot Pose-free View Synthesis with 3D Gaussian Splatting

Few-shot Pose-free View Synthesis with 3D Gaussian Splatting

引用

Chinese Automation Congress (CAC)

作者： Yuan Huang Chi Xu Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education School of Automation China University of Geosciences Wuhan China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Recent advancements in Novel View Synthesis using neural radiance fields and 3D Gaussian splatting have demon-strated promising results. However, these methods conventionally rely on accurate initial poses and point clouds from the model of structure from motion, which poses challenges in sparse input views. To addressing these drawbacks, we introduces an novel method for view synthesis based on 3D Gaussian splatting. Our approach operates on sparse input views without the prerequisite of pose priors, achieving reconstruction and real-time rendering of novel perspectives. For the deficiency of camera poses and point cloud, we employ an end- to-end deep learning model to recover the 3D structure from a few of 2D images to initialize the 3D Gaussian point cloud. In addressing the issue with few-shot, we utilize the differentiable rasterization module to render depth map and apply regulation on it. Additionally, we incorporate supervision between input views by interpolating to generate novel perspectives during training. Experimental results demonstrate that our proposed method significantly enhances the capabilities of 3D Gaussian splatting for novel view synthesis in sparse views and without the necessity of camera pose priors.

关键词： Point cloud compression Training Solid modeling Three-dimensional displays Structure from motion Cameras Rendering (computer graphics) Regulation Real-time systems Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Design of Load Frequency controller for Power System Based on Equivalent Input Disturbance Method

Design of Load Frequency Controller for Power System Based o...

引用

New Energy and Energy Storage System control Summit Forum (NEESSC)

作者： Jianrong Zhang Hang Xu Hongzhang Wang Chuanke Zhang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China

ISBN: (数字)9798350389012

ISBN: (纸本)9798350389029

In the power system, due to the instability of the external environment, safe and stable operation cannot always be guaranteed, as it frequently encounters varying degrees of external disturbances. In order to mitigate the effects of these disturbances on the system, the power system can operate safely and stably, In this paper, a power system load frequency control (LFC) based on Equivalent Input Disturbance (EID) method is proposed from the perspective of active disturbance suppression. Firstly, the disturbances present in the environment are unified as external disturbances, and then a single area the electric power system model with external disturbance was constructed. Then, a controller algorithm based on EID was designed using EID equivalent processing method and linear matrix inequality method to address the issue of external interference in the power system. Finally, a numerical example is used to validate the effectiveness and accuracy of the controller by simulating with two aspects, fixed perturbation and random perturbation, respectively.

关键词： Perturbation methods Process control Interference Power system stability control systems Linear matrix inequalities Numerical models Frequency control Load modeling Energy storage

来源：评论

学校读者我要写书评

暂无评论

Time-attenuating Twin Delayed DDPG Reinforcement Learning for Trajectory Tracking control of Quadrotors

arXiv

引用

arXiv 2023年

作者： Deng, Boyuan Sun, Jian Li, Zhuo Wang, Gang School of Automation Beijing Institute of Technology Beijing100081 China Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology Beijing100081 China

Continuous trajectory tracking control of quadrotors is complicated when considering noise from the environment. Due to the difficulty in modeling the environmental dynamics, tracking methodologies based on conventional control theory, such as model predictive control, have limitations on tracking accuracy and response time. We propose a Time-attenuating Twin Delayed DDPG, a model-free algorithm that is robust to noise, to better handle the trajectory tracking task. A deep reinforcement learning framework is constructed, where a time decay strategy is designed to avoid trapping into local optima. The experimental results show that the tracking error is significantly small, and the operation time is one-tenth of that of a traditional algorithm. The OpenAI Mujoco tool is used to verify the proposed algorithm, and the simulation results show that, the proposed method can significantly improve the training efficiency and effectively improve the accuracy and convergence stability. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

GCN-Transformer Autoencoder with Knowledge Distillation for Unsupervised Video Anomaly Detection

引用

Journal of Advanced Computational Intelligence and intelligent Informatics 2025年第3期29卷 659-667页

作者： Yan, Mingchao Xiong, Yonghua She, Jinhua School of Automation China University of Geosciences No.388 Lumo Road Hongshan District Hubei Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems No.388 Lumo Road Hongshan District Hubei Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education No.388 Lumo Road Hongshan District Hubei Wuhan430074 China School of Engineering Tokyo University of Technology 1404-1 Katakura Hachioji Tokyo192-0982 Japan

Video anomaly detection is crucial in intelligent surveillance, yet the scarcity and diversity of abnormal events pose significant challenges for supervised methods. This paper presents an unsupervised framework that integrates graph attention networks (GATs) and Transformer architectures, combining masked autoencoders (MAEs) with self-distillation training. GATs are utilized to model spatial and inter-frame relationships, while Transformers capture long-range temporal dependencies, overcoming the limitations of traditional MAE and self-distillation approaches. The model employs a two-stage training process: first, a lightweight MAE combined with a GAT-Transformer fusion constructs a knowledge distillation module;second, the student autoencoder is optimized by integrating a graph convolutional autoencoder and a classification head to identify synthetic anomalies. We evaluate the proposed method on three representative datasets—ShanghaiTech Campus, UBnormal, and UCSD Ped2—and achieve promising results. © Fuji Technology Press Ltd.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

H∞ state estimation for delayed neural networks via variable-augmented-based free-weighting matrices method

引用

Journal of the Franklin Institute 2025年第7期362卷

作者： Chang, Xu-Kang He, Yong School of Automation China University of Geosciences Wuhan430074 China Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

The issue of H∞ state estimation for neural networks with time-varying delays is investigated in this study. Firstly, an augmented Lyapunov-Krasovskii functional (LKF) with two delay-product-type terms is constructed to enhance the consideration of system state, delay, and delay derivative information. Furthermore, for taking into account more effective information, the LKF is augmented with both single and double integral variables. Accordingly, the LKF derivative becomes a higher-order term that exhibits nonlinear characteristics of the time delay. To solve the nonlinear problem, a variable-augmented-based free-weighting-matrices (VAFWMs) approach is employed to transform the nonlinear term into a linear form and provides more freedom in obtaining less-conservative results. Consequently, two improved H∞ state estimation criteria are derived. Lastly, a numerical example is provided to demonstrate the merits and effectiveness of the presented methods. Meanwhile, to prove the practical viability of the presented methods, this study extends the methods to a real-world quadruple-tank process system. © 2025 The Franklin Institute

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

Adaptive-triggered H∞ sliding-mode optimal control for nonlinear input-limited systems

引用

Communications in Nonlinear Science and Numerical Simulation 2025年 149卷

作者： Zhang, Hongxu Wang, Honggui Department of Applied Mathematics Harbin University of Science and Technology Harbin150080 China Heilongjiang Provincial Key Laboratory of Optimization Control and Intelligent Analysis for Complex Systems Harbin University of Science and Technology Harbin150080 China

This paper concentrates on the H∞ sliding mode optimal control (SMOC) problem for nonlinear systems with mismatched interference and constrained input. Firstly, an adaptive-triggered strategy for the discontinuous control part is employed, which can suppress input interference and the separated matched disturbances. Also, the system trajectories are guaranteed to converge to the sliding manifold. Moreover, the adaptive-triggered strategy is optimized into self-triggered strategy with the aim to avoid the real-time measurement of triggered conditions, and the minimum time interval is obtained to prevent Zeno phenomenon. Subsequently, the optimal H∞ control problem of sliding motion turns into a two-person ZS game issue. To derive the solutions of event-trigger HJI equation, an adaptive dynamic programming (ADP) algorithm with critic-only structure is implemented to obtain the optimal control online. Furthermore, by utilizing the Lyapunov technique, the uniformly ultimately bounded (UUB) conditions about system state and the weight estimation error are obtained. At last, simulation outcomes are analyzed to validate the effectiveness of the control strategy. © 2025 Elsevier B.V.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Temperature Rising Model of Tubular Permanent Magnet Linear Synchronous Motor Based on Transfer Learning-Deep Neural Network

Temperature Rising Model of Tubular Permanent Magnet Linear ...

引用

第42届中国控制会议

作者： YiFei Wang Tao Wu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems System Integration and Industrial Robotics Laboratory

High temperature rise of permanent magnet linear synchronous motor can lead to irreversible demagnetization of the motor permanent magnet, which can negatively affect the motor performance. To address this problem, a thermal modeling analysis method based on Transfer learning-Deep neural network(TL-DNN) was proposed in this paper. Its specific implementation steps include(1) corresponding to different heat source inputs, the equivalent thermal circuit method and the finite element analysis was adopted based on the structure and main parameters of PMLSM including overall average temperature rise, coil temperature rise and permanent magnet temperature rise from the data sets of the motor;(2) TL-DNN was used to fit the functional relationship between the input source features and the output targets based on the characteristics of the sample data sets. In order to verify the accuracy of the prediction model with small sample data sets, this paper divided the proportion of the data set and compared the results with other classic nonparametric models(random forest, support vector machine, and deep neural network). The results show that the TL-DNN model outperforms other machine learning models and has better robustness and generalization ability when the training datasets are insufficient, and achieves an organic combination of physical field path model and data-driven model, which provides a feasible solution for PMLSM modeling in the case of small samples.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Weighting Factors Autotuning Strategy for Model Predictive Torque control of Permanent Magnet Synchronous Motor Based on Adaptive Multi-objective Black Hole Algorithm

A Weighting Factors Autotuning Strategy for Model Predictive...

引用

第42届中国控制会议

作者： Zixiang Zhou Tao Wu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems System Integration and Industrial Robotics Laboratory

The rational design of weighting factors in the cost function for finite control set model predictive torque control(FCS-MPTC) has been a matter of great interest in power electronics and electrical drives. In order to solve this problem, a weighting factors autotuning strategy for FCS-MPTC of permanent magnet synchronous motor(PMSM) based on the adaptive multi-objective black hole algorithm(AMOBH) is proposed. In this paper, the design process of the FCS-MPTC algorithm is first analyzed in detail. Then, an AMOBH algorithm that can take into account both population convergence and population diversity is introduced, and based on this algorithm, the design problem of the weighting factors is successfully transformed into a multiobjective optimization problem by means of reconstructing the cost function and designing the motor operation information collected in real time as the objective functions of the multi-objective optimization algorithm. Simulation results show that the proposed method can find a set of weighting factor combinations suitable for different working condition requirements, and these weighting factors can effectively improve the operation performance of the PMSM system.

关键词： Model Predictive Torque control Weighting Factors Multi-objective Optimization Algorithm Permanent Magnet Synchronous Motor

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：