检索结果-内蒙古大学图书馆

第42届中国控制会议

作者： Linxiao Qin Tao Sun Shuo Zhang Xi-Ming Sun School of Control Science and Engineering Dalian University of Technology Department of Automation Tsinghua University

For many real-world scenarios,time series prediction needs to be performed on irregularly sampled *** ordinary differential equations have successfully introduced neural dynamical system(NDS) methods into such ***,these models suffer from a large computational cost,and cannot effectively utilize the temporal information in mini-batches,due to mismatched timestamps of *** this work,a unified architecture for NDS is developed,with two novel implementations on discrete input sequences(named TDINDS) and continuous sequences(named TCINDS).The reuse of network modules effectively reduces the scale of parameters and time consumption,while maintaining *** addition,a tensorized timeline alignment method is proposed,which preserves the temporal information of each training sample via reversible mappings,improving prediction performance and reducing time complexity by at least one order of *** are conducted on the Goo gleStock dataset,where we evaluate model accuracy and computational cost by predicting irregular future *** model robustness is tested using incomplete *** results demonstrate the superior performance of TDINDS and TCINDS,with mean square error reduced by 44% and 50% *** evaluation shows that tensorized timeline alignment is also a key factor to enhance irregular time series prediction ability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Measurement-Based control for Minimizing Energy Functions in Quantum Systems

引用

IFAC-PapersOnLine 2023年第2期56卷 5171-5178页

作者： Henrik Glavind Clausen Salahuddin Abdul Rahman Özkan Karabacak Rafal Wisniewski Section for Automation and Control Department of Electronic Systems Aalborg University Aalborg Denmark Department of Mechatronics Engineering Kadir Has University Istanbul Turkey

In variational quantum algorithms (VQAs), the most common objective is to find the minimum energy eigenstate of a given energy Hamiltonian. In this paper, we consider the general problem of finding a sufficient control Hamiltonian structure that, under a given feedback control law, ensures convergence to the minimum energy eigenstate of a given energy function. By including quantum non-demolition (QND) measurements in the loop, convergence to a pure state can be ensured from an arbitrary mixed initial state. Based on existing results on strict control Lyapunov functions, we formulate a semidefinite optimization problem, whose solution defines a non-unique control Hamiltonian, which is sufficient to ensure almost sure convergence to the minimum energy eigenstate under the given feedback law and the action of QND measurements. A numerical example is provided to showcase the proposed methodology.

关键词： Lyapunov control quantum non-demolition measurements semidefinite programming variational quantum algorithms

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Correlation between Student Learning Behaviors and Academic Performance in Blended Learning Environments

Analyzing the Correlation between Student Learning Behaviors...

引用

Chinese automation Congress (CAC)

作者： Ying Zhang Kang Chen Zhezhuang Xu Ye Lin Qingbo Zeng Department of Fujian Province Key Laboratory of Industrial Automation Control Technology and Information Processing Education College of Electrical Engineering and Automation Fuzhou University Fuzhou China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Blended learning integrates online and face-to-face (FTF) teaching methods to offer students in higher education a flexible and customized educational experience. Despite its significant advantages in promoting academic achievement and increasing student participation, blended learning presents challenges for educators due to difficulties in collecting and analyzing learning behavior data. Existing research mainly focuses on single learning modes, and data collection methods primarily rely on interviews and questionnaires, which can be subjective. To address these challenges, this study developed a mobile software called EasyClass, integrated with an online Small Private Online Course(SPOC) platform, to automatically record student behaviors in a blended learning environment. Obtaining data from an undergraduate blended learning course, statistical methods are used to analyze the correlation between student behaviors and final grades, as well as to identify factors affecting grades. The results of multivariate linear regression models confirmed the feasibility and effectiveness of blended instruction. This study provides a new approach to identifying and disseminating effective data collection strategies in blended learning, enabling educators and educational institutions to better understand and assess student behaviors, and to further explore their impact on final academic achievement.

关键词： Correlation automation Statistical analysis Education Linear regression Process control Data collection Software Hybrid learning Interviews

来源：评论

学校读者我要写书评

暂无评论

Online Learning Enabled Hierarchical Distributionally Robust Model Predictive control of Green-Hydrogen Microgrids under Uncertainties 5

Online Learning Enabled Hierarchical Distributionally Robust...

引用

5th IEEE International Electrical and Energy Conference, CIEEC 2022

作者： Ning, Chao Li, Longyan Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai China

ISBN: (数字)9781665411042

ISBN: (纸本)9781665411042

This paper proposes a novel online-learning enabled hierarchical operation framework for a green-hydrogen microgrid (MG) with a high penetration of renewable energy (RE) and hybrid energy storage. The operation framework features a bi-level multi-timescale structure which integrates a day-ahead optimal scheduling with online learning distributionally robust model predictive control (OL-DRMPC). Day-ahead scheduling optimization is employed at the high level to provide MG energy dispatch references, while the OL-DRMPC is carried out in the low level for reference-tracking under uncertainties incurred by RE and load forecast errors. To confront the imperfect knowledge of forecast-error distributions, distributionally robust conditional value-at-risk constraints are imposed on MG system states, namely the storage of battery and hydrogen, for a family of distributions called ambiguity set. By exploiting a Dirichlet process mixture model, a streaming-data-driven ambiguity set for uncertain parameters is devised over the runtime of controller and flexibly captures multimodal structure and fine-grained moment information of each mixture component. Enabled by online learning, the proposed strategy enjoys the merit of offering a reliable and intelligent MG operation. Case studies are used to demonstrate its effectiveness and superiority. © 2022 IEEE.

关键词： Energy storage

来源：评论

学校读者我要写书评

暂无评论

A novel feature enhancement module for small object detection

A novel feature enhancement module for small object detectio...

引用

2022 IEEE International Conference on Industrial Technology, ICIT 2022

作者： Wang, Ruogu Li, Ning Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai China

ISBN: (纸本)9781728119489

Generic object detection has made great progress in recent years, yet small object detection is still facing a serious problem of missed detection. The problem is caused by two reasons: low resolution in small targets and feature loss during deep convolution downsampling. Some previous studies used feature pyramid structures and multi-scale training predictions to alleviate this problem, but still cannot efficiently utilise the feature information of small targets. In this paper, firstly we propose a novel and effective feature enhancement module to extract more features;secondly, a filter size design method is presented to extract features of matching objects and incorporate context information;finally, an adaptive fusion method is used to process outputs of our module and improve model robustness. We select YOLOv3 as base model and carry out several experiments on a special Small Object Dataset and the results show that our work can achieve an increase of about seven percentage points (35.73%) compared to 28.78% on baseline. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Model Predictive control Based on Amplitude Decaying Aggregation Strategy for Hydrogen Gas Turbine

Model Predictive Control Based on Amplitude Decaying Aggrega...

引用

2022 Chinese automation Congress, CAC 2022

作者： Ma, Aoyun Li, Dewei Xi, Yugeng Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Key Laboratory of System Control and Information Processing Department of Automation Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781665465335

The hydrogen gas turbine can be the key technology for carbon-neutral in the future. The flexibility of gas turbine under various operation conditions is an important issue. A state-space model of hydrogen gas turbine with different hydrogen volume ratio mixed fuel is constructed based on Rowen model, and a full-dimensional state observer is designed to obtain the states of state-space model. The model predictive control method based on amplitude decaying aggregation strategy is presented to stabilize the rotational speed of hydrogen gas turbine under various constraints, which are to ensure the safety of operation. The number of variables contained in the optimization problem to be solved online is reduced by aggregation strategy. The simulation results confirmed that the presented method works well, and the effects of the hydrogen volume ratio for the performance of hydrogen gas turbine are discussed. © 2022 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Integrated Power and Hydrogen Trading in Multimicrogrid Coupled with Offsite Hydrogen Refueling Stations 6

Integrated Power and Hydrogen Trading in Multimicrogrid Coup...

引用

6th IEEE Conference on Energy Internet and Energy System Integration, EI2 2022

作者： Li, Longyan Ning, Chao Department of Automation Shanghai Jiao Tong University 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)9798350347159

This paper proposes a novel two-level electricity and hydrogen market framework for multi-microgrids (MMGs) coupled with offsite hydrogen refueling stations (HRSs), aiming to strengthen the synergy between electricity and hydrogen. The local hydrogen market among the MMG and HRSs is modeled by multi-leader multi-follower Stackelberg game theory, in which microgrids play the role of leaders to adjust hydrogen prices while HRSs participate as followers to determine their hydrogen purchase scheme. Moreover, to deal with economic and technical issues of the MMG in a holistic manner, Nash bargaining theory is used to model the electricity transaction among microgrids. A distributed algorithm is developed to solve such games, thus reducing the cost of information communication and the risk of privacy exposure. The case study demonstrates that this market mechanism guarantees benefits for all parties and boosts the independence of MMGs by reducing transactions with the main grid. © 2022 IEEE.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Improved Double Deep Q Network Algorithm Based on Average Q-Value Estimation and Reward Redistribution for Robot Path Planning

引用

Computers, Materials & Continua 2024年第11期81卷 2769-2790页

作者： Yameng Yin Lieping Zhang Xiaoxu Shi Yilin Wang Jiansheng Peng Jianchu Zou Key Laboratory of Advanced Manufacturing and Automation Technology Guilin University of TechnologyEducation Department of Guangxi Zhuang Autonomous RegionGuilin541006China Guangxi Key Laboratory of Special Engineering Equipment and Control Guilin University of Aerospace TechnologyGuilin541004China Guilin Mingfu Robot Technology Company Limited Guilin541199China Key Laboratory of AI and Information Processing Education Department of Guangxi Zhuang Autonomous RegionHechi UniversityYizhou546300China

By integrating deep neural networks with reinforcement learning,the Double Deep Q Network(DDQN)algorithm overcomes the limitations of Q-learning in handling continuous spaces and is widely applied in the path planning of mobile ***,the traditional DDQN algorithm suffers from sparse rewards and inefficient utilization of high-quality *** those problems,an improved DDQN algorithm based on average Q-value estimation and reward redistribution was ***,to enhance the precision of the target Q-value,the average of multiple previously learned Q-values from the target Q network is used to replace the single Q-value from the current target Q ***,a reward redistribution mechanism is designed to overcome the sparse reward problem by adjusting the final reward of each action using the round reward from trajectory ***,a reward-prioritized experience selection method is introduced,which ranks experience samples according to reward values to ensure frequent utilization of high-quality ***,simulation experiments are conducted to verify the effectiveness of the proposed algorithm in fixed-position scenario and random *** experimental results show that compared to the traditional DDQN algorithm,the proposed algorithm achieves shorter average running time,higher average return and fewer average *** performance of the proposed algorithm is improved by 11.43%in the fixed scenario and 8.33%in random *** not only plans economic and safe paths but also significantly improves efficiency and generalization in path planning,making it suitable for widespread application in autonomous navigation and industrial automation.

关键词： Double Deep Q Network path planning average Q-value estimation reward redistribution mechanism reward-prioritized experience selection method

来源：评论

学校读者我要写书评

暂无评论

An Expansion-based Document Ranking Framework Incorporated with Core Concern Capturing 5

An Expansion-based Document Ranking Framework Incorporated w...

引用

5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022

作者： Qi, Yinqiao Xin, Jinghao Li, Ning Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai China

ISBN: (数字)9781665498388

ISBN: (纸本)9781665498388

Entity-based ranking is a popular research area in document ranking as knowledge graphs can introduce additional evidence for ranking systems. In most entity-based ranking framework, the original query is transformed into a set of entities and candidate documents are ranked according to their relevance to the entity set. However, mistakes can easily occur during the transformation process, which introduce noise to the ranking system. This paper represents an expansion-based ranking framework, which expand the original query with high-quality candidate entities to mitigate the impact of transformation mistakes and enrich the semantics of the query in the meanwhile. Compared with existing query expansion methods, our expansion method is lightweight as it reduces much computational burden and requests little extra information. However, the core concerns of the users might be covered up after query expansion. To alleviate this dilemma, a core concern capturing method is pro-posed, wherein the attention weight of each inter-entity relation is measured to capture the core entity pairs in the expanded query. Experiments on the S2-CS dataset demonstrate the effectiveness of our lightweight query expansion method and the superiority of our core concern capturing method. Compared with a classical retrieval model, our method provides 11% improvements in terms of NDCG@15. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Development and control of Underwater Gliding Robots:A Review

引用

IEEE/CAA Journal of Automatica Sinica 2022年第9期9卷 1543-1560页

作者： Jian Wang Zhengxing Wu Huijie Dong Min Tan Junzhi Yu the State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 the School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China the State Key Laboratory for Turbulence and Complex System Department of Mechanics and Engineering ScienceBIC-ESATCollege of EngineeringPeking UniversityBeijing 100871China

As one of the most effective vehicles for ocean development and exploration,underwater gliding robots(UGRs)have the unique characteristics of low energy consumption and strong ***,by borrowing the motion principles of current underwater robots,a variety of novel UGRs have emerged with improving their maneuverability,concealment,and environmental friendliness,which significantly broadens the ocean *** this paper,we provide a comprehensive review of underwater gliding robots,including prototype design and their key *** the perspective of motion characteristics,we categorize the underwater gliding robots in terms of traditional underwater gliders(UGs),hybrid-driven UGs,bio-inspired UGs,thermal UGs,and ***,their buoyancy driven system,dynamic and energy model,and motion control are concluded with detailed ***,we have discussed the current critical issues and future *** review offers valuable insight into the development of next-generation underwater robots well-suited for various oceanic applications,and aims to gain more attention of researchers and engineers to this growing field.

关键词： Buoyancy driven motion control oceanic applications system development underwater gliding robots

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：