检索结果-内蒙古大学图书馆

Graph convolutional network soft sensor for process quality prediction

Journal of Process control 2023年第1期123卷 12-25页

作者： Jia, Mingwei Xu, Danya Yang, Tao Liu, Yi Yao, Yuan Institute of Process Equipment and Control Engineering Zhejiang University of Technology Hangzhou310023 China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China Department of Chemical Engineering National Tsing Hua University Hsinchu30013 Taiwan

The nonlinear time-varying characteristics of the process industry can be modeled using numerous data-driven soft sensor methods. However, the intrinsic relationships among the variables, especially the localized spatial–temporal correlations that shed light on model behavior, have received little attention. In this study, a soft sensor based on a graph convolutional network is constructed by introducing the concept of graph to process modeling. The focus is on obtaining localized spatial–temporal correlations that aid in comprehending the intricate interactions among the variables included in the soft sensor. The model is trained by considering the regularization terms and it learns distinctive localized spatial–temporal correlations in an end-to-end manner. Furthermore, long-term dependence is established via temporal convolution. Thus, both the localized spatial–temporal correlations and time-series properties are captured. The feasibility of the proposed soft sensor is illustrated using two fermentation processes. The localized spatial–temporal correlations of this case study are visualized, and they demonstrate that the soft sensor is not a black-box model;instead, it is consistent with process knowledge. © 2023 Elsevier Ltd

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

PSMFNet:Lightweight Partial Separation and Multiscale Fusion Network for Image Super-Resolution

引用

Computers, Materials & Continua 2024年第10期81卷 1491-1509页

作者： Shuai Cao Jianan Liang Yongjun Cao Jinglun Huang Zhishu Yang Institute of Intelligent Manufacturing GDASGuangdong Key Laboratory of Modern Control TechnologyGuangzhou510030China School of Mechanical&Automotive Engineering South China University of TechnologyGuangzhou511442China Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming650500China School of Faculty of Intelligent Manufacturing Wuyi UniversityJiangmen529020China

The employment of deep convolutional neural networks has recently contributed to significant progress in single image super-resolution(SISR)***,the high computational demands of most SR techniques hinder their applicability to edge devices,despite their satisfactory reconstruction *** methods commonly use standard convolutions,which increase the convolutional operation cost of the *** this paper,a lightweight Partial Separation and Multiscale Fusion Network(PSMFNet)is proposed to alleviate this ***,this paper introduces partial convolution(PConv),which reduces the redundant convolution operations throughout the model by separating some of the features of an image while retaining features useful for image ***,it is worth noting that the existing methods have not fully utilized the rich feature information,leading to information loss,which reduces the ability to learn feature *** by self-attention,this paper develops a multiscale feature fusion block(MFFB),which can better utilize the non-local features of an *** can learn long-range dependencies from the spatial dimension and extract features from the channel dimension,thereby obtaining more comprehensive and rich feature *** the role of the MFFB is to capture rich global features,this paper further introduces an efficient inverted residual block(EIRB)to supplement the local feature extraction ability of PSMFNet.A comprehensive analysis of the experimental results shows that PSMFNet maintains a better performance with fewer parameters than the state-of-the-art models.

关键词： Deep learning single image super-resolution lightweight network multiscale fusion

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient Path Finding and Moving Stability-Focused Trajectory Planning for Mobile Robots

Towards Efficient Path Finding and Moving Stability-Focused ...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Hou, Muyang Lei, Zhenya Hu, Haidong Wang, Zhong Wang, Yong Xie, Le Wang, Hesheng Shanghai Jiao Tong University Department of Automation Shanghai200240 China School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China Beijing Institute of Control Engineering Beijing100190 China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Department of Automation Shanghai200240 China

ISBN: (纸本)9781665481090

Nowadays, mobile robots play an important role in a variety of service scenarios. They need to plan and track trajectories to accomplish tasks such as delivery or guided tours. In such tasks, there are two remaining challenges: on one hand, the time and memory consumption of present path planners are still significant;on the other hand, service robots, which have a higher center of gravity, demand greater moving stability than that of current trajectory planners provide. To address these two challenges. Firstly, we propose a safety boundary first A∗ which fully utilizes environmental obstacle information to create a safety boundary and searches in it to quickly find an initial path. Secondly, we formulate the trajectory optimization problem as a nonlinear optimization problem, where the smoothness, safety, feasibility, and moving stability of the robot are taken into account. Furthermore, to constrain the robot's lateral acceleration, we design a time allocation algorithm based on non-uniform B-spline, enhancing the quality of the resulting trajectory. Simulations and real-world experiments demonstrate that our algorithms significantly improve path search efficiency, enhance moving stability, reduce the difficulty of tracking, and improve the quality of task completion. © 2024 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Latent-Enhanced Variational Adversarial Active Learning Assisted Soft Sensor

引用

IEEE Sensors Journal 2023年第14期23卷 15762-15772页

作者： Dai, Yun Yang, Chao Liu, Yi Yao, Yuan Zhejiang University of Technology Institute of Process Equipment and Control Engineering Hangzhou310023 China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China National Tsing Hua University Department of Chemical Engineering Hsinchu300044 Taiwan

As the acquisition of variables that measure quality is typically challenging, labeled samples for building a model for soft sensors are often inadequate. Additionally, owing to the installation of redundant sensors, high-dimensional process data with strong correlations are acquired. Therefore, in this study, a sample selection strategy for active learning (AL), referred to as latent-enhanced variational adversarial AL (LVAAL), is developed to enhance quality prediction performance with limited labeled data. The LVAAL method uses a minimax game to explore the latent representation of the original data. Specifically, a latent-enhanced variational autoencoder (LEVAE) is used to deceive the adversarial network into predicting all samples, both labeled and unlabeled, as labeled. However, the adversarial network attempts to indicate the difference between latent representations. Subsequently, Gaussian process regression (GPR) is adopted as a base model for LVAAL. With the proposed LVAAL selection strategy, informative unlabeled samples are incrementally selected, thereby enhancing the prediction performance. The application results for a numerical case and an industrial example demonstrate the advantages of LVAAL compared with existing AL strategies. © 2001-2012 IEEE.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

A Unified Planning Model for Microgrids Considering Typical Scenarios and Operational Simulations 3

A Unified Planning Model for Microgrids Considering Typical ...

引用

3rd Asia Power and Electrical Technology Conference, APET 2024

作者： Su, Mengmeng Peng, Jun Zhang, Yong Li, Min Li, Zhenwei Ban, Mingfei North China Branch of State GRID Corporation of China Beijing China School of Electrical Engineering and Automation Harbin Institute of Technology Harbin China College of Computer and Control Engineering Northeast Forestry University Harbin China

ISBN: (纸本)9798350367690

The structure of microgrids and the models considered have a significant impact on the planning and operational outcomes of micro grids. Additionally, micro grids encompass various models of primary equipment, including wind, solar, diesel, and storage, while the demand-side response mechanisms are continually being refined. This necessitates the construction of diverse load types, thereby increasing the complexity of micro grid planning and highlighting the need for further research into microgrid planning models. This paper presents various typical mathematical models for microgrids, employs spectral clustering algorithms to obtain representative scenarios, and constructs a unified planning model for microgrids. Furthermore, it elucidates the model adjustment methods under different planning objectives and conducts case analyses of microgrid planning issues. © 2024 IEEE.

关键词： Microgrids

来源：评论

学校读者我要写书评

暂无评论

AggFollower: Aggressiveness Informed Car-Following Modeling

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-15页

作者： Chen, Xianda Yuan, Xinyi Zhu, Meixin Zheng, Xinhu Shen, Shaojie Wang, Xuesong Wang, Yinhai Wang, Fei-Yue Guangzhou China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong SAR China School of Transportation Engineering Tongji University Shanghai China Department of Civil and Environmental Engineering University of Washington Seattle WA USA State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

Car-following is the most common driving scenario where a following vehicle follows a lead vehicle in the same lane. One crucial factor of car-following behavior is driving style which affects speed and gap selection, acceleration pattern, and fuel consumption. However, existing car-following research used limited categories of driving style through pre-defined patterns and failed to encode driving style into data-driven car-following models. To address these limitations, we propose the Aggressiveness Informed Car-Following (AICF) modeling approach, which embeds driving style as a dynamic input feature in data-driven car-following models. In detail, We design driving aggressiveness tokens using four physical quantities (jerk, acceleration, relative speed, and relative spacing) to capture the heterogeneity of driving aggressiveness. These tokens were then embedded into a physics-informed Long Short-Term Memory (LSTM) based car-following model for trajectory prediction. To evaluate the effectiveness of our approach, we conducted extensive experiments based on 12,540 car-following events extracted from the HighD dataset and 24,093 events from the Lyft dataset. Compared to models devoid of considerations for driving aggressiveness levels, AICF exhibits superior efficacy in mitigating the Mean Square Error (MSE) of spacing and collision rate. To the best of our knowledge, this is the first work to directly incorporate real-time driving aggressiveness tokens as input features into data-driven car-following models, enabling a more comprehensive understanding of aggressiveness in car-following behavior. IEEE

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Robust Divergence Learning for Missing-Modality Segmentation

Robust Divergence Learning for Missing-Modality Segmentation

引用

2024 China automation Congress, CAC 2024

作者： Cheng, Runze Sun, Zhongao Zhang, Ye Li, Chun MSU-BIT-SMBU Joint Research Center of Applied Mathematics Shenzhen MSU-BIT University Shenzhen518172 China Institute of Control Theory and Control Engineering School of Automation Beijing Institute of Technology Beijing100081 China School of Mathematics and Statistics Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9798350368604

Multimodal Magnetic Resonance Imaging (MRI) provides essential complementary information for analyzing brain tumor subregions. While methods using four common MRI modalities for automatic segmentation have shown success, they often face challenges with missing modalities due to image quality issues, inconsistent protocols, allergic reactions, or cost factors. Thus, developing a segmentation paradigm that handles missing modalities is clinically valuable. A novel single-modality parallel processing network framework based on Hölder divergence and mutual information is introduced. Each modality is independently input into a shared network backbone for parallel processing, preserving unique information. Additionally, a dynamic sharing framework is introduced that adjusts network parameters based on modality availability. A Hölder divergence and mutual information-based loss functions are used for evaluating discrepancies between predictions and labels. Extensive testing on the BraTS 2018 and BraTS 2020 datasets demonstrates that our method outperforms existing techniques in handling missing modalities and validates each component’s effectiveness. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Parameter Estimation and Tracking control of MIMO Linear Systems Without Prior Knowledge of control Signs and Parameter Bounds

引用

IEEE Transactions on Automatic control 2024年第6期70卷 3695-3710页

作者： Xu, Yuchun Zhang, Yanjun Zhang, Ji-Feng Chinese Academy of Sciences Key Laboratory of Systems and Control Institute of Systems Science Academy of Mathematics and Systems Science Beijing100190 China Beijing Institute of Technology School of Automation Beijing100081 China Beijing Institute of Technology State Key Lab of Automation Intelligent Unmanned Systems Beijing100081 China University of Chinese Academy of Sciences School of Mathematics Sciences Beijing100149 China Zhongyuan University of Technology School of Automation and Electrical Engineering Zhengzhou450007 China Chinese Academy of Sciences Academy of Mathematics and Systems Science Beijing100190 China

Dealing with the uncertain high-frequency gain matrix, denoted as Kp, is a fundamental problem in multivariable adaptive control systems. In this paper, we propose a new solution for parameter estimation and adaptive control for a general class of multi-input multi-output discrete-time linear time-invariant systems. The proposed scheme does not require any prior knowledge of the sign or bound information of Kp, and thus, significantly relaxes the design conditions in traditional multivariable adaptive control systems. Compared with the commonly used Nussbaum gain or multi-model techniques for addressing the unknown signs of Kp, the proposed scheme does not rely on any additional design conditions or any switching mechanism, while still ensuring closed-loop stability and asymptotic output tracking. Specifically, an output feedback adaptive control law is developed based on a matrix decomposition technique, which leads to derivation of a modified estimation error model. Subsequently, a gradient-based parameter update law is formulated only relying on the non-zero condition of the leading principle minors of Kp. Through designing gain functions and stable filters, the controller is always non-singular and does not involve any causal contradiction problem. Simulation study showcases the design process and demonstrates the effectiveness of the proposed scheme. © 1963-2012 IEEE.

关键词： MIMO systems

来源：评论

学校读者我要写书评

暂无评论

Power-Hardware-in-the-Loop Motor Emulator under Four-Quadrant Operation Condition 10

Power-Hardware-in-the-Loop Motor Emulator under Four-Quadran...

引用

10th IEEE International Power Electronics and Motion control Conference, IPEMC 2024 ECCE Asia

作者： Zhang, Gengchen Guo, Hong Xu, Jinquan Wang, Gaoxiang Zhang, Li Jin, Wenbo Zhao, Xiaopeng Liu, Ying Beihang University School of Automation Science and Electrical Engineering Bejing China Southwest China Research Institute of Electronic Equipment Chengdu China Xian Flight Automatic Control Research Institute Xi'an China National Key Laboratory of Science and Technology on Aircraft Control Xi'an China

ISBN: (纸本)9798350351330

In order to solve the problems of long cycle and the difficulty of test, this paper proposes a method of power-in-the-loop motor simulator. Firstly, the topology of the motor simulator is proposed, composed of an interface filtering unit, a motor simulation unit and an energy management unit. Secondly, a discretization method for permanent magnet synchronous motor(PMSM) is designed for DSP control. Thirdly, this paper proposes a method combining quasi-proportional resonance control(QPR) and direct current control to ensure the control accuracy. Finally, the motor simulator is verified by experiments. © 2024 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Target Assignment in the Multi-UAV Combat Based on Distributed Compensation Auction Algorithm with Fixed-Time Consensus Protocol 7th

Target Assignment in the Multi-UAV Combat Based on Distri...

引用

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Chen, Yiyang Hua, Yongzhao Yu, Jianglong Dong, Xiwang Institute of Artificial Intelligence Beihang University Beijing100191 China School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control Laboratory Beihang University Beijing100191 China

ISBN: (纸本)9789819733231

This paper mainly focuses on the target assignment problems in the unmanned aerial vehicle (UAV) swarm combat. Firstly, the idea of the multi-UAV swarm combat is shown and the constraints and the benefit matrix of the target assignment task are modeled. Secondly, a fixed-time consensus protocol is utilized to estimate the state of all the other agents and its convergence is proved by Lyapunov method. Then, a distributed compensation auction algorithm is proposed. Finally, the proposed distributed compensation auction algorithm is simulated and the results demonstrate the successful completion of the assignment task with only neighboring information. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Lyapunov methods

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：