检索结果-内蒙古大学图书馆

2021 China automation Congress, CAC 2021

作者： Lan, Peng Wang, Lele Pu, Zhiqiang Qian, Dianwei Yi, Jianqiang Control and Computer Engineering North China Electric Power University Beijing102200 China Institute of Automation Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9781665426473

This paper considers a multi-target coverage problem where agents aim to efficiently cover multiple targets while maintaining connectivity. An improved harmony search algorithm is proposed. In particular, the harmony generation part of the harmony search algorithm is designed to generate all the harmony memory and new harmony vectors, so that all decisions are made at the beginning to ensure connectivity. Moreover, we propose a new strategy to dynamically adjust pitch adjusting rate (PAR) and bandwidth (BW). In the initial stage of the algorithm, small PAR and large BW value not only increase the diversity of understanding vectors, but also improve the global search ability of the algorithm. In the later stage of algorithm optimization, we use large PAR and small BW value, so as to improve the local search ability of the algorithm and make the solution vector converge[2]. Numerical simulation is performed to verify the effectiveness of the algorithm. We find that the performance of the proposed algorithm in this paper is close to the traditional greedy algorithm which has no connectivity restrictions. © 2021 IEEE

关键词： connectivity maintenance coverage harmony search

来源：评论

学校读者我要写书评

暂无评论

FedEFM: Federated Endovascular Foundation Model with Unseen Data

arXiv

引用

arXiv 2025年

作者： Do, Tuong Vu, Nghia Jianu, Tudor Huang, Baoru Vu, Minh Su, Jionglong Tjiputra, Erman Tran, Quang D. Chiu, Te-Chuan Nguyen, Anh Deparment of Computer Science University of Liverpool United Kingdom AIOZ Ltd. Singapore Automation & Control Institute TU Wien Austria Xi’an Jiaotong-Liverpool University China National Tsing Hua University Taiwan

In endovascular surgery, the precise identification of catheters and guidewires in X-ray images is essential for reducing intervention risks. However, accurately segmenting catheter and guidewire structures is challenging due to the limited availability of labeled data. Foundation models offer a promising solution by enabling the collection of similar-domain data to train models whose weights can be fine-tuned for downstream tasks. Nonetheless, large-scale data collection for training is constrained by the necessity of maintaining patient privacy. This paper proposes a new method to train a foundation model in a decentralized federated learning setting for endovascular intervention. To ensure the feasibility of the training, we tackle the unseen data issue using differentiable Earth Mover’s Distance within a knowledge distillation framework. Once trained, our foundation model’s weights provide valuable initialization for downstream tasks, thereby enhancing task-specific performance. Intensive experiments show that our approach achieves new state-of-the-art results, contributing to advancements in endovascular intervention and robotic-assisted endovascular surgery, while addressing the critical issue of data sharing in the medical domain. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Learning-Based Adaptive Compliance Method for Symmetric Bi-Manual Manipulation

SSRN

引用

SSRN 2024年

作者： Cao, Yuxue Zhao, Wenbo Wang, Shengjie Zheng, Xiang Ma, Wenke Zhao, Jiawei Zhang, Tao Beijing Institute of Control Engineering China Department of Automation Tsinghua University China Institute for Interdisciplinary Information Sciences Tsinghua University China Department of Computer Science City University of Hong Kong Hong Kong Qian Xuesen Laboratory of Space Technology China Department of Automatic Control Xi’an Research Institute of Hi-tech China

Symmetric bi-manual manipulation is an essential skill in on-orbit operations due to its potent load capacity. Previous works have applied compliant control to maintain the stability of manipulations. However, traditional methods have viewed motion planning and compliant control as two separate modules, which can lead to conflicts with the simultaneous change of the desired trajectory and impedance parameters in the presence of external forces and disturbances. Additionally, the joint usage of these two modules requires experts to manually adjust parameters. To achieve high efficiency while enhancing adaptability, we propose a novel Learning-based Adaptive Compliance algorithm (LAC) that improves the efficiency and robustness of symmetric bi-manual manipulation. Specifically, the algorithm framework integrates desired trajectory generation and impedance-parameter adjustment under a unified framework to mitigate contradictions and improve efficiency. Second, we introduce a centralized Actor-Critic framework with LSTM networks preprocessing the force states, enhancing the synchronization of bi-manual manipulation. When evaluated in dual-arm cooperative handling and peg-in-hole assembly experiments, our method outperforms baseline algorithms in terms of optimality and robustness. © 2024, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Repetitive T-S Fuzzy Model-Based Iterative Learning control Law Design 63

Repetitive T-S Fuzzy Model-Based Iterative Learning Control ...

引用

63rd IEEE Conference on Decision and control, CDC 2024

作者： Maniarski, Robert Paszke, Wojciech Tao, Hongfeng Rogers, Eric Institute of Automation Electronic and Electrical Engineering University of Zielona Góra ul. Szafrana 2 Zielona Góra65-246 Poland Jiangnan University Key Laboratory of Advanced Process Control for Light Industry of Ministry of Education Wuxi214000 China University of Southampton School of Electronics and Computer Science SouthamptonSO17 1BJ United Kingdom

ISBN: (纸本)9798350316339

This paper develops an iterative learning control law for a class of nonlinear systems. The approach used to represent the nonlinear system dynamics is a Takagi-Sugeno fuzzy repetitive process that considers the two directions of information propagation. Then, the control action investigated is a state feedback control law combined with a PD-type feed-forward learning control law. Consequently, linear matrix inequality techniques can be used for control design. Furthermore, this approach allows the design of control action to satisfy the requirements on both the error convergence and the transient dynamics. Finally, an example demonstrates the properties of the new design. © 2024 IEEE.

关键词： State feedback

来源：评论

学校读者我要写书评

暂无评论

A novel internal crack detection method for photovoltaic (PV) panels based on the air-coupled ultrasonic

引用

Sensors and Actuators A: Physical 2025年 392卷

作者： Sun, Tianyi Bai, Tianyang Cao, Shengxian Fan, Siyuan Zhang, Yanhui School of Automation Engineering Northeast Electric Power University Jilin132012 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China School of Control and Computer Engineering North China Electric Power University Beijing102206 China

Accurately assessing the potential risk of cracks in photovoltaic (PV) panels is crucial for improving the system's energy conversion efficiency and safety. This paper develops a novel internal crack detection device for PV panels based on air-coupled ultrasonics and establishes a dedicated model for PV panel crack detection. Considering the anisotropy of silicon, the Rayleigh–Lamb equation is first used to obtain the dispersion curve of Lamb waves. The continuous wavelet transform (CWT) is then applied to analyze the A0 mode Lamb wave echo signals within a single cycle to distinguish between cracked and non-cracked regions. Further, the original signal is enhanced using singular value decomposition (SVD) to strengthen the signal features, and a direct relationship model between the signal echo and the crack length is proposed. Finally, the model's validity is verified by measuring actual crack data from PV panels. The results show that the optimal frequency of Lamb waves for crack detection in PV panels is 200 kHz, with an attenuation coefficient of 6.4 dB/mm and incidence and exit angles of 11°. Compared to electroluminescence (EL) and inductive thermal imaging methods, the proposed approach achieves higher accuracy, reaching 84.26%. © 2025

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Economic Aspects of a Resource Sharing Manufacturing Network under Turbulences 18

Economic Aspects of a Resource Sharing Manufacturing Network...

引用

18th European Conference on Management Leadership and Governance, ECMLG 2022

作者： Szaller, Ádám Fries, Christian Nick, Gábor Kádár, Botond Fraunhofer Institute for Manufacturing Engineering and Automation IPA Stuttgart Germany University of Stuttgart Institute of Industrial Manufacturing and Management IFF Germany Institute for Computer Science and Control Budapest Hungary Department of Manufacturing Science and Engineering Budapest University of Technology and Economics Budapest Hungary EPIC InnoLabs Nonprofit Ltd. Budapest Hungary

ISBN: (纸本)9781914587573

Nowadays, manufacturing companies face more difficulties than ever. Unrest in global supply chains triggered by fluctuating customer demand, raw material shortages and crises (Covid pandemic, global warming, wars) complicate the utilization of production resources necessary for economic success. Also, the rapidly changing environment causes existing production plans to be adapted, which results in order changes, causing additional costs for manufacturers. One solution to cope with these problems is cooperation and sharing resources: requesting capacity from partners when having shortages and offering them temporarily in case of excess capacity. In this paper, a platform-based resource sharing mechanism is investigated from the economic perspective. In the mechanism, requests and offers are matched by a central platform applying a complex matching logic. The platform provides valid alternatives based on the incoming ordersthat the requesting company can choose from. Companies are rating each other's performance after each interaction based on delivery accuracy;choosing between resource offers is made based on the cumulated rating about the offeror and the price of the offer. Within this paper, the aim is to investigate the resource sharing mechanism from the economic point of view based on an approach to the responsiveness of a supply chain structure to turbulence, to support decision-makers trying to cope with unexpected changes. For this purpose, here the mechanism is briefly introduced, and basic concepts about turbulences in supply chains are also presented. Cost types related to resource sharing manufacturing companies are distinguished, and the model is validated with agent-based simulation. A simulation experiment is performed to investigate the use-case of outsourced jobs having different price levels. Based on the experiment, it can be concluded that there is a price level limit in such a resource sharing federation, under which it is worth it to collaborate

关键词： Turbulence

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation for Machine Translation via Dependency Subtree Swapping

arXiv

引用

arXiv 2023年

作者： Nagy, Attila Lakatos, Dorina Petra Barta, Botond Nanys, Patrick Ács, Judit Department of Automation and Applied Informatics Budapest University of Technology and Economics Hungary Institute for Computer Science and Control Eötvös Loránd Research Network Hungary

We present a generic framework for data augmentation via dependency subtree swapping that is applicable to machine translation. We extract corresponding subtrees from the dependency parse trees of the source and target sentences and swap these across bisentences to create augmented samples. We perform thorough filtering based on graph-based similarities of the dependency trees and additional heuristics to ensure that extracted subtrees correspond to the same meaning. We conduct resource-constrained experiments on 4 language pairs in both directions using the IWSLT text translation datasets and the Hunglish2 corpus. The results demonstrate consistent improvements in BLEU score over our baseline models in 3 out of 4 language pairs. Our code is available on GitHub1 © 2023, CC BY.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Integral Reinforcement Learning-Based Angular Acceleration Autopilot for High Dynamic Flight Vehicles

SSRN

引用

SSRN 2023年

作者： Liu, Yingxin Hu, Yuhui Shen, Kai Qiu, Jiatai Neusypin, Konstantin A. School of Automation Beijing Institute of Technology Beijing100081 China Faculty of Computer Science and Control Systems Bauman Moscow State Technical University Moscow105005 Russia

In the synthesis of acceleration autopilot for high dynamic flight vehicle (HDFV), the full perception of system states, such as the angle of attack, is usually unavailable. Autopilots with feedback of angular acceleration (AFAA) have become more perspective for HDFV with stringent requirements on response speed and high maneuverability, compared with autopilot with feedback of angular rate (AFAR). Although classical optimal control methodology has validated its great vitality during the synthesis of autopilots both in theory and practice while this approach requires complete knowledge of the system dynamics. Reinforcement learning (RL) method has now proved to be an effective technique for adaptive optimal control of partially unknown nonlinear systems. In this paper, a novel data-driven integral RL algorithm with feedback of angular acceleration was proposed for the synthesis of HDFV’s autopilot. And numerical simulation was carried out to validate the effectiveness of proposed online integral RL-based angular acceleration autopilot for HDFVs. Besides, the tracking performance under different wave commands, the robustness against parameter uncertainties and the noise attenuation capacity between classical optimal tracking approach and proposed integral RL method were analyzed for AFAR and AFAA, respectively. Simulation results showed, angular acceleration autopilot with proposed integral RL algorithm possessed better tracking performance against various disturbances. © 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

Impact of Customer Order Change Dimensions on Order Management

Impact of Customer Order Change Dimensions on Order Manageme...

引用

2022 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2022

作者： Fries, Christian Szaller, Adam Bauernhansl, Thomas Schuh, Gunther Fraunhofer Institute for Manufacturing Engineering and Automation Ipa Stuttgart70569 Germany University of Stuttgart Institute of Industrial Manufacturing and Management Iff Stuttgart70569 Germany Institute for Computer Science and Control Budapest1111 Hungary Bme Department of Manufacturing Science and Engineering Budapest1111 Hungary of Rwth Aachen University Aachen Germany

ISBN: (数字)9781665486873

ISBN: (纸本)9781665486873

Today, manufacturing companies are surrounded by constantly changing external influences. These entail the risk of inefficiencies in the operational process, especially when existing plans have to be adapted. A common trigger of such modifications are customer order changes. They cause unplanned costs, which endanger the profitability of the company. However, the estimation of these additional costs is complex and therefore missing in today's operation. This paper therefore defines customer order change types and determines their effects based on the Aachener PPS-Model. The individual processing areas of a customer order are described and mathematically formulated. Agent-based simulation is used to evaluate the critical change dimensions. Simulation experiments showed that the additional costs generated due to customer order changes decrease if the average relative date and quantity change are reduced. If both change scopes are reduced equally, in the case of reducing quantity, the additional costs are a slightly higher than in the case of reducing date change. © 2022 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

HunSum-1: an Abstractive Summarization Dataset for Hungarian

arXiv

引用

arXiv 2023年

作者： Barta, Botond Lakatos, Dorina Nagy, Attila Nyist, Milán Konor Ács, Judit Department of Automation and Applied Informatics Budapest University of Technology and Economics Hungary Institute for Computer Science and Control Eötvös Loránd Research Network Hungary

We introduce HunSum-1: a dataset for Hungarian abstractive summarization, consisting of 1.14M news articles. The dataset is built by collecting, cleaning and deduplicating data from 9 major Hungarian news sites through CommonCrawl. Using this dataset, we build abstractive summarizer models based on huBERT and mT5. We demonstrate the value of the created dataset by performing a quantitative and qualitative analysis on the models' results. The HunSum-1 dataset, all models used in our experiments and our code are available open source. © 2023, CC BY.

关键词： Open systems

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：