检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 2253-2263页

作者： Deng, Guizhou Fu, Huiqiao Wang, Xinpeng Liu, Canghai Tang, Kaiqiang Chen, Chunlin Southwest University of Science and Technology Mechanical Engineering School of Manufacturing Science and Engineering Mianyang621000 China Nanjing University School of Management and Engineering Nanjing210093 China Nanjing University Department of Control and Systems Engineering School of Management and Engineering Nanjing210093 China

Rapid adaptation to the environment is the long-term task of reinforcement learning. However, reinforcement learning faces great challenges in dynamic environments, especially with continuous state-action spaces. In this article, we propose a systematic incremental reinforcement learning method via performance evaluation and policy perturbation (IRL-PEPP) to improve the adaptability of reinforcement learning algorithms in dynamic environments with continuous state-action spaces, which mainly includes three parts, i.e., performance evaluation, policy perturbation, and importance weighting. First, in performance evaluation, we apply the learned optimal policy to sample a few episodes in the original environment and use these samples to evaluate the policy applicability in the new environment. Then, in policy perturbation, the policy is perturbed according to the policy applicability to balance the tradeoff between exploration and exploitation in the new environment. Finally, importance weighting is applied to weight the information to speed up the adjustment process of the policy. Experimental results demonstrate the feasibility and efficiency of the proposed IRL-PEPP method for continuous control tasks in comparison with the existing state-of-the-art methods. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Image Semantic Segmentation Used in Automatics 17

Image Semantic Segmentation Used in Automatics

引用

17th International Conference on engineering of Modern Electric systems, EMES 2023

作者： Spoiala, Viorica University of Oradea Control Systems Engineering and Management Department Oradea Romania

ISBN: (纸本)9798350310634

This paper presents the importance of segmentation methods used in the object analysis in computer vision and image proccessing field, in the automated processes. Image segmentation is a crucial stage of image processing in the context of industrial automation. The detection of objects is one of the main purposes of image segmentation, and in order to do this, it is necessary to perform the segmentation and extraction of the image's significant elements in advance. Putting pixels into semantic classifications is the foundation of semantic segmentation, this being a deep learning method. In order to apply segmentation in computer vision of automated processes the first step could be to label the objects and then to train a neural network to apply this labels to all the similar objects detected in similar images. In this paper some images were segmented by using labels and deep learning methods. After the theoretical aspects are presented, then some examples are made in Matlab environment. © 2023 IEEE.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Energy-Saving Distributed Flexible Job Shop Scheduling Optimization with Dual Resource Constraints Based on Integrated Q-Learning Multi-Objective Grey Wolf Optimizer

引用

Computer Modeling in engineering & Sciences 2024年第8期140卷 1459-1483页

作者： Hongliang Zhang Yi Chen Yuteng Zhang Gongjie Xu School of Management Science and Engineering Anhui University of TechnologyMa’anshan243032China Laboratory of Multidisciplinary Management and Control of Complex Systems of Anhui Higher Education Institutes Anhui University of TechnologyMa’anshan243032China Department of Industrial Engineering School of Mechanical EngineeringNorthwestern Polytechnical UniversityXi’an710072China

The distributed flexible job shop scheduling problem(DFJSP)has attracted great attention with the growth of the global manufacturing *** DFJSP research only considers machine constraints and ignores worker *** one critical factor of production,effective utilization of worker resources can increase ***,energy consumption is a growing concern due to the increasingly serious environmental ***,the distributed flexible job shop scheduling problem with dual resource constraints(DFJSP-DRC)for minimizing makespan and total energy consumption is studied in this *** solve the problem,we present a multi-objective mathematical model for DFJSP-DRC and propose a Q-learning-based multi-objective grey wolf optimizer(Q-MOGWO).In Q-MOGWO,high-quality initial solutions are generated by a hybrid initialization strategy,and an improved active decoding strategy is designed to obtain the scheduling *** further enhance the local search capability and expand the solution space,two wolf predation strategies and three critical factory neighborhood structures based on Q-learning are *** strategies and structures enable Q-MOGWO to explore the solution space more efficiently and thus find better Pareto *** effectiveness of Q-MOGWO in addressing DFJSP-DRC is verified through comparison with four algorithms using 45 *** results reveal that Q-MOGWO outperforms comparison algorithms in terms of solution quality.

关键词： Distributed flexible job shop scheduling problem dual resource constraints energy-saving scheduling multi-objective grey wolf optimizer Q-learning

来源：评论

学校读者我要写书评

暂无评论

Point Cloud Classification Using Content-Based Transformer via Clustering in Feature Space

引用

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 231-239页

作者： Yahui Liu Bin Tian Yisheng Lv Lingxi Li Fei-Yue Wang the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 the School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100190 IEEE the Transportation and Autonomous Systems Institute(TASI)and the Department of Electrical and Computer Engineering Purdue School of Engineering and TechnologyIndiana University-Purdue University Indianapolis(IUPUI)Indianapolis 46202 USA

Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space(content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectN N. Source code of this paper is available at https://***/yahuiliu99/PointC onT.

关键词： Content-based Transformer deep learning feature aggregator local attention point cloud classification

来源：评论

学校读者我要写书评

暂无评论

Social Radars: Finding Targets in Cyberspace for Cybersecurity

引用

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 279-282页

作者： Lili Fan Changxian Zeng Yutong Wang Jiaqi Ma Fei-Yue Wang School of Information and Electronics Beijing Institute of TechnologyBeijing 100081China School of Science Dalian Minzu UniversityDalian 116600China State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Department of Civil and Environmental Engineering University of CaliforniaLos AngelesCA 90024 USA IEEE State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190 Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China

INSPIRED by the insight from American political scientist Lasswell, who summarized the environmental role in societal surveillance [1], Schramm coined the term “social radar” [2] as it resembles the activities of radar in collecting and processing information, playing a crucial role in helping humans perceive changes in the internal and external environment and promptly adjusting adaptive behaviors.

关键词： prompt summarized insight

来源：评论

学校读者我要写书评

暂无评论

Improving Power Response of Single-controllable VSG-Based Active Distribution Network

引用

CSEE Journal of Power and Energy systems 2025年第1期11卷 102-114页

作者： Shah Fahad Arman Goudarzi Pierluigi Siano Ji Xiang Department of Electrical and Computer Engineering Missouri University of Science and TechnologyUSA University of Victoria Canada Department of Management&Innovation Systems University of SalernoItaly Department of Electrical and Electronic Engineering Science University of JohannesburgJohannesburg2006South Africa National Laboratory of Industrial Control Technology College of Electrical EngineeringZhejiang UniversityHangzhou310058China

controlling an active distribution network(ADN)from a single PCC has been advantageous for improving the performance of coordinated Intermittent RESs(IRESs).Recent studies have proposed a constant PQ regulation approach at the PCC of ADNs using coordination of non-MPPT based ***,due to the intermittent nature of DGs coupled with PCC through uni-directional broadcast communication,the PCC becomes vulnerable to transient *** address this challenge,this study first presents a detailed mathematical model of an ADN from the perspective of PCC regulation to realize rigidness of PCC against ***,an H_(∞)controller is formulated and employed to achieve optimal performance against disturbances,consequently,ensuring the least oscillations during transients at ***,an eigenvalue analysis is presented to analyze convergence speed limitations of the newly derived system ***,simulation results show the proposed method offers superior performance as compared to the state-of-the-art methods.

关键词： Cooperative control of DGs hierarchical control system high penetration of intermittent RESs H_(∞)control optimal control in power systems single-controllable active distribution networks

来源：评论

学校读者我要写书评

暂无评论

System for Determining the Shape of the Wavefront of a Nonsinusoidal Periodic Acoustic Wave 17

System for Determining the Shape of the Wavefront of a Nonsi...

引用

17th International Conference on engineering of Modern Electric systems, EMES 2023

作者： Codoban, Adrian Coroiu, Laura Gergely, Eugen Sarosi, Jozsef University of Oradea Department Control Systems Engineering and Management Oradea Romania University of Szeged Department of Mechatronics and Automation Szeged Hungary

ISBN: (纸本)9798350310634

The shape of the wavefront is important for the most realistic reproduction of the acoustic wave. In acoustics, the wave front (or wave surface) is defined as the totality of points in the space of the propagating medium that have the same instantaneous elongation amplitude. In the ideal case, in a homogeneous and isotropic propagation medium without other disturbances, the wave has a spherical symmetry, i.e. the shape of the wavefront is circular and at large distances from the wave source, due to dispersion, the shape of the wavefront can be considered plan. In practice, however, due to the multiple component harmonics, reflections and possible summations of the primary acoustic wave, the elongation has a non-sinusoidal shape, and the wavefront may have an irregular random shape. Moreover, if the source of the wave or bodies from which it is reflected are in motion, the shape of the wavefront may even be variable in time. The paper presents a method for determining the shape of the wave front of a non-sinusoidal periodic plane acoustic wave, resulting from the addition of several harmonic components, reflected waves, etc. It uses an array of omnidirectional capacitive microphones arranged in line, at equal distances between them. At each of the microphones, the acoustic wave is captured out of phase depending on the position of the microphone in space and the shape of the wave front. These phase shifts placed next to each other give an image of the shape of the wavefront captured by the microphone system. The method presented in this paper reproduces sounds very realistically and can be used in Active Noise Cancel systems, in open spaces, with one or more mobile noise sources. One of the benefits is the increase in hearing comfort in noisy environments. Another is to record sounds with high fidelity. © 2023 IEEE.

关键词： Wavefronts

来源：评论

学校读者我要写书评

暂无评论

Innovation management Opportunities of Artificial Intelligence Social Enterprises in Romania 17

Innovation Management Opportunities of Artificial Intelligen...

引用

17th International Conference on engineering of Modern Electric systems, EMES 2023

作者： Pop, Marius Vlad Tont, Gabriela Sandor, Andrei Doctoral School of Engineering Sciences University of Oradea Oradea Romania University of Oradea Control Systems Engineering and Management Department Oradea Romania

ISBN: (纸本)9798350310634

This paper is focused on Ai Social Enterprise Opportunities in Romanian Ecosystem, on exploring the emerging grounds of Digital Innovation management. Clarity is needed in order to pursue goal-oriented initiatives, our research strategy is focused on maximizing the current strengths and adapting them to emerging needs in an AI opportunity perspective. © 2023 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Knowledge management System Evaluation Using Genetic Algorithm and Monte Carlo Method 17

Knowledge Management System Evaluation Using Genetic Algorit...

引用

17th International Conference on engineering of Modern Electric systems, EMES 2023

作者： Sandor, Andrei Tont, Gabriela Pop, Marius Vlad Doctoral School of Engineering Sciences University of Oradea Oradea Romania University of Oradea Control Systems Engineering and Management Department Oradea Romania

ISBN: (纸本)9798350310634

The performance and sustain ability of modern organizations heavily rely on knowledge. In order to be able to manage it, organizations use dedicated tools - knowledge management systems, which enhance knowledge-related processes. The use of this kind of systems can imply a high number of resources and therefore a comprehensive analysis on the performance of the system from the organizational requirements perspective is needed. This article proposes a performance evaluation method based on genetic algorithm and Monte Carlo simulation combining an optimization-based approach with a probabilistic perspective. The main advantage of this method is that it considers a set of very specific requirements or needs, making it a highly customizable tool. © 2023 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Circularity Reinforcement of Critical Raw Materials in Europe: A Case of Niobium

引用

Circular Economy and Sustainability 2024年第4期4卷 2449-2472页

作者： von Rennenberg, Theresa Yu, Yifei Fraccascia, Luca Yazan, Devrim Murat Department of Industrial Engineering and Business Information Systems University of Twente Drienerlolaan 5 Enschede 7522 NB Netherlands Department of Computer Control and Management Engineering Sapienza University of Rome Via Ariosto 25 Rome 00185 Italy

Critical Raw Materials attract increasing attention due to their depleting reserves and low recyclability. Niobium, one of the most rare and vital elements, is primarily found in Brazil. This research explores the potential impact of Circular Economy (CE) strategies on mitigating niobium's criticality within Europe. First, a niobium supply chain is designed and analysed by Enterprise Input–Output modelling. Second, the supply risk is calculated based on the criticality matrix proposed by the European Commission under three scenarios associated with resources, technologies, and policies. The results show that urban mining is a potential solution to reduce niobium’s criticality and mitigate its environmental impacts. A higher recycling input rate and/or a mix of recycling and substitution strategies is necessary to offset niobium’s criticality. Aligned with the CE action plan, the research offers a scientific foundation to strategically prevent the risk of niobium supply shortages. © The Author(s) 2024.

关键词： Circular economy Critical raw materials Enterprise input–output Niobium supply chain Scenario analysis

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：