检索结果-内蒙古大学图书馆

SPIE 12th International Symposium on Multispectral Image processing and Pattern Recognition, MIPPR 2023

作者： Huang, Shixiang Chi, Longyun Fu, Wenxing Tian, Jinwen National Key Laboratory of Multispectral Information Intelligent Processing Technology Huazhong University of Science and Technology Wuhan China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (数字)9781510674943

ISBN: (纸本)9781510674936

As a crucial auxiliary technique in inertial navigation, scene matching has been widely applied in aircraft navigation and guidance. To enhance the adaptability and efficiency of scene matching algorithms in complex environments, existing approaches have gradually shifted towards heterogeneous scene matching, such as optical/ infrared scene matching based on deep learning features, with a focus on point features. However, due to the complex and diverse nonlinear distortions between optical and infrared images, the matching accuracy often fails to meet the practical requirements of navigation and positioning. In view of this problem, an EPM-Net algorithm based on edge features is proposed to improve matching performance by extracting more stable and discriminative edge point descriptors. Experimental results on infrared datasets demonstrate that this method achieves an average matching accuracy improvement of more than four times compared to traditional and existing deep learning methods. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Motor Fault Diagnosis Under Complex Working Conditions Based on Signal Fusion and CA-CNN

Motor Fault Diagnosis Under Complex Working Conditions Based...

引用

2024 China Automation Congress, CAC 2024

作者： Cai, Mingxuan Liu, Qi Liu, Yuxiang Yang, Bo Department of Automation Shanghai Jiao Tong University shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

ISBN: (纸本)9798350368604

Accurate fault diagnosis plays a key role in the safe and efficient operation of electrical motors. Aiming at multi-class motor fault diagnosis under complex working conditions, a signal fusion-based fault diagnosis framework is proposed. Measurement parameters from different sensors are first transformed by wavelet denoising and fast Fourier transform (FFT). Then, multiple parameters spectrum and working condition information are integrated and converted into high-dimension matrices. Finally, a channel-attention-based convolution neural network (CA-CNN) is proposed to extract fault patterns from a reconstructed matrix and output diagnosis results. Experiment results on both simulated and experimental datasets verify the effectiveness of the proposed method. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Pricing Strategy for Smart Grid Based on PSO and Distributed Iterative Algorithm

A Pricing Strategy for Smart Grid Based on PSO and Distribut...

引用

International Conference on Communications, Signal processing, and systems, CSPS 2023

作者： Wang, Xiaocheng Ma, Haogang Yin, Yuan Li, Zelong Tianjin Key Laboratory of Wireless Mobile Communications and Power Transmission College of Electronic and Communication Engineering Tianjin Normal University Tianjin300387 China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai China

ISBN: (纸本)9789819975556

This paper proposes a pricing strategy for the Market by using a Stackelberg game-based bi-level programming model. In the model, the wholesale price and the retail price is optimized by the Market to increase its profit. In the model, the Energy Provider (EP) optimize optimizes the adjustment coefficient to increase the trading probability with the Utility Company (UC). Besides, the Market can sell the power to the UC directly. Then, the UCs determine their retail price by non-cooperative game to increase their profit. The simulation results reveal that the Market determines the optimal price to maximize profits. On the other hand, the proposed price strategy of EP can increase the trading probability, which promotes more UCs to trade with EP, thus increasing its benefit. Finally, UCs get a bash equilibrium through the non-cooperative game. The research proves that the proposed strategy is a win–win strategy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning with Hierarchical Graph Structure for Flexible Job Shop Scheduling

Reinforcement Learning with Hierarchical Graph Structure for...

引用

2023 International Annual Conference on Complex systems and Intelligent Science, CSIS-IAC 2023

作者： Zhang, Linli Li, Dewei Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Dept. of Automation Shanghai China

ISBN: (纸本)9798350309003

The flexible job shop scheduling problem (FJSP) is a NP-hard combinatorial optimization challenge, having extensive real-world industrial applications. For a given instance of FJSP, a scheduling solution need to be devised, which entails determining the appropriate machine for each operation and establishing the sequence in which operations are processed on a given machine, all while adhering to certain constraints. However, many of the methods are lacking in flexibility, unable to cope effectively with multi-relational operations and machine selection scenarios. This can make the representation of state and action challenging in practice, leading to a significant increase in decision complexity. This paper considers these issues by a hierarchical graph structure with a model that synergistically integrates two modules: the environment and the decision module. The environment module is characterized by a hierarchical graph neural network which defines the multi-relational FJSP instance where all machine and operation data are stored. The decision module incorporates the Actor-Critic networks, designed to train reasoning strategies and enhance decision performance, based on the states and rewards provided at each step by the environment module. The objective is to derive optimal scheduling strategies through interactions between the decision agent and the environment, targeting the minimum resources consumed or makespan. Numerical simulations validate the efficacy of the proposed approach, showing its potential to yield superior results and thereby enhance performance. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

V2X Communication Assisted Hierarchical Path Planning for Connected and Automated Vehicles

V2X Communication Assisted Hierarchical Path Planning for Co...

引用

2023 China Automation Congress, CAC 2023

作者： Li, Jiahang Chen, Cailian Gao, Fengkun Yang, Bo Guan, Xinping Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Department of Automation Shanghai200240 China

ISBN: (纸本)9798350303759

Connected and Automated Vehicles (CAVs) have attracted increasing attention in intelligent transportation systems. An effective path planning enables the efficient operation of CAVs so that they can coordinate traffic flow and avoid accidents. This paper presents a framework of V2X communication assisted hierarchical path planning system for CAVs that aims to improve computational efficiency and safety performance. The proposed framework consists of two stages: pre-planning and online-planning. The pre-planning stage leverages the computing and storage capabilities of Roadside Units (RSUs) to generate and filter candidate trajectories for different driving scenarios. The online-planning stage adjusts the pre-planned trajectory based on the vehicle's driving risk index, which considers the distance and relative speed to the surrounding vehicles. The performance of effectiveness, safety, and timeliness of the proposed framework is evaluated and demonstrated by a simulation study in different scenarios. Compared with conventional methods, the proposed method improves the computational efficiency by 23% and reduces the collision rate by 13 %. © 2023 IEEE.

关键词： Vehicle to Everything

来源：评论

学校读者我要写书评

暂无评论

Digital Twin Based Sintering Proportioning: Improved Whale Optimization Method

Digital Twin Based Sintering Proportioning: Improved Whale O...

引用

2023 China Automation Congress, CAC 2023

作者： Liu, Wei Ding, Xuda Bai, Xuehan Chen, Cailian Guan, Xingping Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Department of Automation Shanghai200240 China

ISBN: (纸本)9798350303759

Sintering proportion optimization plays a crucial role in determining the final product quality of sintered iron ore. However, the traditional approach of separating the optimization processes between the procurement and technical departments often fails to achieve the global optimum. In this paper, We propose a joint optimization approach for sintering proportioning based on digital twin (DT) technology. To tackle the complex constraints of this joint optimization problem, we develop a multiple improved whale optimization algorithm (MIWOA) that overcomes the issue of getting trapped in local optima. The proposed MIWOA incorporates three strategies, including a nonlinear convergence factor, Levy flight, and Gaussian mutation. Besides, the numerical simulations are conducted in order to analyze the influence of the convergence factors. Finally, various related approaches for sintering proportioning optimization are tested, and DT-based MIWOA achieved the best performance. © 2023 IEEE.

关键词： Sintering

来源：评论

学校读者我要写书评

暂无评论

Global practical stabilization of the double integrator system with an imperfect sensor and subject to a bounded disturbance

引用

control Theory and Technology 2024年第3期22卷 468-478页

作者： Zhiyuan Zhu Yuanlong Li Zongli Lin Department of Automation Shanghai Jiao Tong Universityand Key Laboratory of System Control and Information Processing of Ministry of EducationShanghai 200240China Charles L.Brown Department of Electrical and Computer Engineering University of VirginiaP.0.Box 400743CharlottesvilleVA 22904-4743USA

This paper is concerned with global practical stabilization of the double integrator system with an imperfect sensor and subject to an additive bounded output *** imperfect sensor nonlinearity possesses the nonlinear characteristics of saturation and dead *** of the presence of output dead zone and the additive disturbance,the states cannot be expected to driven into an arbitrarily small neighborhood of the *** solve the global practical stabilization problem,we proposes a low gain-based linear dynamic output feedback law,under which the first state enters and remains in a bounded set whose size is depended on the bound of disturbance and the range of dead zone and the second state enters and remains in a pre-specified arbitrarily small set,both in finite *** results illustrate the effectiveness of our proposed control method.

关键词： Output saturation Disturbance rejection Output dead zone Low gain feedback-Linear output feedback Practical stabilization

来源：评论

学校读者我要写书评

暂无评论

Query Attack by Multi-Identity Surrogates

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第2期5卷 684-697页

作者： Chen, Sizhe Huang, Zhehao Tao, Qinghua Huang, Xiaolin Department of Automation and Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China MOE Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai200240 China ESAT-STADIUS Katholieke Universiteit Leuven Leuven3000 Belgium

Deep neural networks (DNNs) are acknowledged as vulnerable to adversarial attacks while the existing black-box attacks require extensive queries on the victim DNN to achieve high success rates. For query-efficiency, surrogate models of the victim are used to generate transferable adversarial examples (AEs) because of their gradient similarity (GS), i.e., surrogates' attack gradients are similar to the victim's ones. However, it is generally neglected to exploit their similarity on outputs, namely the prediction similarity (PS), to filter out inefficient queries by surrogates without querying the victim. To jointly utilize and also optimize surrogates' GS and PS, we develop QueryNet, a unified attack framework that can significantly reduce queries. QueryNet creatively attacks by multi-identity surrogates, i.e., crafts several AEs for one sample by different surrogates and also uses surrogates to decide on the most promising AE for the query. After that, the victim's query feedback is accumulated to optimize not only surrogates' parameters but also their architectures, enhancing both the GS and the PS. Although QueryNet has no access to pretrained surrogates' prior, it reduces queries by averagely about an order of magnitude compared to alternatives within an acceptable time, according to our comprehensive experiments: 11 victims (including two commercial models) on MNIST/CIFAR10/ImageNet, allowing only 8-b image queries, and no access to the victim's training data. The code is available at https://***/Sizhe-Chen/QueryNet. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Counter-swarm Splitting Strategy using Receding Horizon control Algorithm 41

A Counter-swarm Splitting Strategy using Receding Horizon Co...

引用

第41届中国控制会议

作者： Angwei Zhang Dewei Li Haibin Shao Lulu Pan Yaonan Guan the Department of Automation and the Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper proposes a model predictive control framework for the task of countering the swarm of autonomous *** on the Boids model,the neighbor selection mechanism and interaction model are further employed to characterize the formation of the target *** is assumed that individuals in the target swarm are equipped with a collision avoidance *** the perspective of the position and velocity of individuals in the target swarm,Lanchester's index and polarization index are employed to characterize the performance of the counter-swarm strategy,*** strategy of splitting the target swarm via attacking its geometric centroid is proposed and the model predictive control framework for the counter-swarm task is designed.A simulation is finally provided to illustrate the effectiveness of the proposed strategy.

关键词： counter swarm model predictive control autonomous systems Boids model collision avoidance

来源：评论

学校读者我要写书评

暂无评论

Time-varying Output Formation control Based on a Reduced-order Output-feedback Protocol 41

Time-varying Output Formation Control Based on a Reduced-ord...

引用

第41届中国控制会议

作者： Zhuo Chen Xianwei Li Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

This paper investigates time-varying output formation(TVOF) of homogeneous linear multi-agent systems based on a reduced-order output-feedback ***,a reduced-order output-feedback protocol using relative information of neighboring agents is *** this protocol,a necessary and sufficient condition for achieving TVOF is *** explicit expression of the time-varying formation reference function and a feasibility condition for TVOF are *** an algorithm is proposed for designing the protocol *** is shown that when the dynamics of each agent is stabilizable and detectable,the multi-agent system can achieve a desired TVOF under the protocol designed by the *** with existing results which only consider full-order protocols,the proposed protocol has a lower order and thus has lower implementation *** simulation is finally presented to demonstrate the effectiveness of the proposed protocol.

关键词： Time-varying output formation(TVOF) multi-agent systems output feedback reduced-order design

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：