检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and automation (ICRA)

作者： Mingrui Liu Xinyang Tang Yeqiang Qian Jiming Chen Liang Li College of Control Science and Engineering Zhejiang University Hangzhou P. R. China Department of Automation Shanghai Jiao Tong University Shanghai P. R. China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Precise and long-term stable localization is essential in parking lots for tasks like autonomous driving or autonomous valet parking, etc. Existing methods rely on a fixed and memory-inefficient map, which lacks robust data association approaches. And it is not suitable for precise localization or long-term map maintenance. In this paper, we propose a novel mapping, localization, and map update system based on ground semantic features, utilizing low-cost cameras. We present a precise and lightweight parameterization method to establish improved data association and achieve accurate localization at centimeter-level. Furthermore, we propose a novel map update approach by implementing high-quality data association for parameterized semantic features, allowing continuous map update and refinement during re-localization, while maintaining centimeter-level accuracy. We validate the performance of the proposed method in real-world experiments and compare it against state-of-the-art algorithms. The proposed method achieves an average accuracy improvement of 5cm during the registration process. The generated maps consume only a compact size of 450 KB/km and remain adaptable to evolving environments through continuous update.

关键词： Location awareness Accuracy Scalability Semantics Cameras Robustness Maintenance

来源：评论

学校读者我要写书评

暂无评论

Batch constrained multi-objective Bayesian optimization using the example of ultrasonic wire bonding

Batch constrained multi-objective Bayesian optimization usin...

引用

IEEE/ASME (AIM) International Conference on Advanced Intelligent Mechatronics

作者： Fabian Reiling Christian Henke Matthias Hunstig Stefan Gröger Ansgar Trächtler department Scientific Automation Fraunhofer Institute for Mechatronic Systems Design Paderborn Germany Deputy Head of Research at Hesse GmbH Paderborn Germany Head of Chair of Control Engineering and Mechatronics Paderborn Germany

ISBN: (数字)9798350355369

ISBN: (纸本)9798350355376

Setting optimum process parameters for complex manufacturing processes such as ultrasonic wire bonding is already challenging for one target variable. Due to numerous influencing physical factors, such processes often lack the necessary detailed physical models. Due to the lack of these models, such processes cannot be adjusted to an optimum using classic optimization methods. In manufacturing processes in particular, the process must be optimized with regard to several objectives such as process time or quality. A popular method for optimizing such processes without models is multi-objective Bayesian optimization. For this purpose, surrogate models in the form of Gaussian processes are used in combination with a multi-objective acquisition function. In real processes, parallel function evaluation offers advantages in terms of trial efficiency and scalability. In this paper, we present a new algorithm for batch-constrained Bayesian multi-objective optimization. With this algorithm, an arbitrary number of function evaluations per iteration can be specified, whereby a more efficient determination of the Pareto front approximation can be achieved in real applications. For this purpose, the Expected Hypervolume Improvement is extended by a term to consider a quality criterion. Using the ultrasonic wire bonding process as an example, we experimentally prove that the proposed framework is able to approximate the Pareto front of the system with only a few function evaluations. For this purpose, the process capability index should be maximized and the process time minimized.

关键词： Manufacturing processes Mechatronics Scalability Optimization methods Predictive models Approximation algorithms Acoustics

来源：评论

学校读者我要写书评

暂无评论

Detection and Description of Local Features of a Thermal Image

Detection and Description of Local Features of a Thermal Ima...

引用

International Conference on Industrial engineering, Applications and Manufacturing (ICIEAM)

作者： I. I. Naumov R. R. Ibadov A. G. Gazaryan Faculty of Automation Mechatronics and Control Don State Technical University Rostov-on-Don Russia Department of Electrical Engineering and Electronics Don State Technical University Rostov-on-Don Russia Institute of Advanced Mechanical Engineering “Rostselmash” Don State Technical University Rostov-on-Don Russia

ISBN: (数字)9798331512194

ISBN: (纸本)9798331512200

Thermal images present challenges for traditional computer vision methods due to the lack of clear textures and low contrast. In this paper, we present a hybrid architecture based on a Siamese triplet network and transformers, which provides an accuracy improvement of 42 % over classical methods SIFT, SURF and 28% over state-of-the-art CNN approaches SuperPoint, D2-Net. Key innovations include a thermal-adaptive descriptor, dynamic triplet loss, and a fusion module that integrates spatial and thermal features. Evaluations on industry-standard KAIST, FLIR, Thermal Urban datasets demonstrate excellent performance, with the method detecting 91 % of keypoints in daytime scenes and remaining robust in adverse conditions such as fog, rain, and low visibility. Moreover, the algorithm runs at 45 fps on embedded systems, making it suitable for real-time applications. The algorithm has potential applications in autonomous driving, surveillance, and medical diagnostics.

关键词： Technological innovation Accuracy Heuristic algorithms Surveillance Thermal engineering Computer architecture Transformers Feature extraction Convolutional neural networks Thermal stability

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of the Modified Flux-Coupling-Type SFCL in VSC-HVDC System

Performance Analysis of the Modified Flux-Coupling-Type SFCL...

引用

Iranian Conference on Electrical engineering (ICEE)

作者： Mohammad Khakroei Ashkan Mirzaei Rajeooni Mahdi Rahimi Pirbasti Hossein Heydari MAPNA Electric & Control Engineering & Manufacturing Company (MECO) Alborz Iran Department of Engineering and R&D MAPNA Generator Engineering and Manufacturing Company (PARS) Alborz Iran Department of Electrical Engineering (Center of Excellence for Power System Automation and Operation) Iran University of Science and Technology (IUST) Tehran Iran

Although Voltage Source Converters based on HVDC (VSC-HVDC) systems have several advantages, they are vulnerable to DC fault currents. Concerning the inherent characteristics of high-temperature superconducting (HTS) material, using HTS in the fault current limiter could be a solution to limit the current in VSC-HVDC. The present paper seeks to provide an elaborately better solution to the problem mentioned above of the fault currents than what has previously been proposed. The object of this research is a modified flux coupling type superconductor fault current limiter (MFC-SFCL) to attenuate the fault current in VSC-HVDC network. The principle mechanism and operation of the SFCL and VSC-HVDC systems are modeled in detail, involving interplay or synergy between electrical and thermal properties. The simulation results demonstrate that the purposed MFC-SFCL has the proper function to mitigate the fault current.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Wavelet Transformation for Recognizing Various Defects in Diagnosis of Power Transformers

Wavelet Transformation for Recognizing Various Defects in Di...

引用

International Russian automation Conference (RusAutoCon)

作者： Andrey A. Kuznetsov Maria A. Volchanina Anton V. Gorlov Department “Theoretical electrical engineering” Omsk State Transport University (OSTU) Omsk Russian Federation Department “Automation and control systems” Omsk State Transport University (OSTU) Omsk Russian Federation “Theoretical electrical engineering” Omsk State Transport University (OSTU) Omsk Russian Federation

ISBN: (数字)9798350349818

ISBN: (纸本)9798350349825

The article discusses the use of discrete wavelet transform in diagnosing power oil-filled transformers using automated acoustic monitoring tools. The article is based on the results of experiments using a simulator with an expanded set of defects. Comparison of acoustic signals on a power transformer with signals from a defect simulator made it possible to formulate a criterion for the presence of an insulation defect. An experimental test of the proposed criterion was carried out on signals of various powers and using electrodes of various shapes. The paper presents expressions that implement the criterion for recognizing the type and degree of development of an insulation defect in power transformers. Examples of processing acoustic signals using wavelet transformation in the MatLab program are given. For each type of signals considered, numerical values of the defect recognition criterion are given. At the end of the article, conclusions and prospects for further development of the proposed approach are formulated.

关键词： Substations Shape Process control Oil insulation Acoustics Discharges (electric) Discrete wavelet transforms Monitoring Power transformer insulation Matlab

来源：评论

学校读者我要写书评

暂无评论

Signature Verification and Forgery Recognition System Using KNN, Backpropagation and CNN 3

Signature Verification and Forgery Recognition System Using ...

引用

3rd IEEE International Virtual Conference on Innovations in Power and Advanced Computing Technologies, i-PACT 2021

作者： Desai, Tejaswini Samanta, Ritusree Sarkar, Siddharth Sharmila, A. School of Electrical Engineering Vellore Institute of Technology Vellore India School of Electronics Engineering Vellore Institute of Technology Vellore India Vellore Institute of Technology Department of Control and Automation Vellore India

ISBN: (纸本)9781665426916

Signature verification is behavioral biometric and is most widely used among other types of biometric recognition system like fingerprint, voice, iris etc. There are many biometric verification systems like finger print scanning, face recognition, iris scanning, and voice recognition etc. But cost of deploying for some systems is extremely high and some of the systems are not portable. In-order to find a middle ground between efficiency, effectiveness in mass quantity and portability, we take a deeper look into signature verification system which can be deployed to produce fruitful results. In this project there is development of various algorithms to verify the signature and to analyze if it is genuine or not. It involves implementation of KNN, CNN and Backpropagation. © 2021 IEEE.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Group Decision and Cooperative Planning Based on Preference and Fuzzy Measure 1

引用

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

作者： Ma, Xiwen Xie, Wei Yang, Jingsong Zhang, Weidong Lu, Jinhui School of Oceanography Shanghai Jiao Tong University Shanghai China State Key Laboratory of Satellite Ocean Environment Dynamics Second Institute of Oceanography Ministry of Natural Resources Hangzhou China Department of Automation Shanghai Jiao Tong University Shanghai China Zhuhai China School of Information and Communication Engineering Hainan University Hainan Haikou China National Engineering Research Center of Ship and Shipping Control System Shanghai China Crossocean of Suzhou technology No. 218 East Oingdao Road Suzhou China

ISBN: (数字)9789819733323

ISBN: (纸本)9789819733316

To pursue interest balance and improve collaboration efficiency, this paper proposes a multi-agent cooperation method integrating decision-making and planning. Based on preference and fuzzy measures, this method can balance individual and group benefits under fuzzy uncertain environment. The equilibrium solution of a multi-agent multi-objective game, namely group decision-making (GDM) solution, can be obtained by the Gaussian oscillation particle swarm optimization (GOPSO) algorithm, which overcomes the dilemma of a multi-objective group game and improves the computational efficiency. Considering the smoothness and continuity of the trajectory, a heuristic motion planning (MP) generation model that satisfies the kinematic constraints and minimizes differential thrust is proposed, which improves the cooperation efficiency. To verify the performance of this proposed method, simulation results are presented and some comparative statements are given. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Investigating the dynamic memory effect of human drivers via ON-LSTM

引用

Science China(Information Sciences) 2020年第9期63卷 83-93页

作者： Shengzhe DAI Zhiheng LI Li LI Dongpu CAO Xingyuan DAI Yilun LIN Department of Automation Tsinghua University Shenzhen International Graduate School Tsinghua University Department of Mechanical and Mechatronics Engineering University of Waterloo State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

It is a widely accepted view that considering the memory effects of historical information(driving operations) is beneficial for vehicle trajectory prediction models to improve prediction accuracy. However,many commonly used models(e.g., long short-term memory, LSTM) can only implicitly simulate memory effects, but lack effective mechanisms to capture memory effects from sequence data and estimate their effective time range(ETR). This shortage makes it hard to dynamically configure the most suitable length of used historical information according to the current driving behavior, which harms the good understanding of vehicle motion. To address this problem, we propose a modified trajectory prediction model based on ordered neuron LSTM(ON-LSTM). We demonstrate the feasibility of ETR estimation based on ON-LSTM and propose an ETR estimation method. We estimate the ETR of driving fluctuations and lane change operations on the NGSIM I-80 dataset. The experiment results prove that the proposed method can well capture the memory effects during trajectory prediction. Moreover, the estimated ETR values are in agreement with our intuitions.

关键词： driving behavior memory effect trajectory prediction historical information ON-LSTM

来源：评论

学校读者我要写书评

暂无评论

Multimodal Emotion Recognition Based on Multi-Scale Facial Features and Cross-Modal Attention

Multimodal Emotion Recognition Based on Multi-Scale Facial F...

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： Chengao Bao Luefeng Chen Min Li Min Wu Witold Pedrycz Kaoru Hirota School of Automation China University of Geosciences Wuhan China the Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Automation and the Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education China University of Geosciences Wuhan China Department of Electrical and Computer Engineering University of Alberta Edmonton Canada Tokyo Institute of Technology Yokohama Japan Tokyo Institute of Technology Tokyo Japan

ISBN: (数字)9798331521950

ISBN: (纸本)9798331521967

A multi-modal emotion recognition method based on facial multi-scale features and cross-modal attention (MS-FCA) network is proposed. The MSFCA model improves the traditional single-branch ViT network into a two-branch ViT architecture by using classification tokens in each branch to interact with picture embeddings in the other branch, which facilitates effective interactions between different scales of information. Subsequently, audio features are extracted using ResNet18 network. The cross-modal attention mechanism is used to obtain the weight matrices between different modal features, making full use of inter-modal correlation and effectively fusing visual and audio features for more accurate emotion recognition. Two datasets are used for the experiments: eNTERFACE'05 and REDVESS dataset. The experimental results show that the accuracy of the proposed method on the eNTERFACE'05 and REDVESS datasets is 85.42% and 83.84% respectively, which proves the effectiveness of the proposed method.

关键词： Emotion recognition Visualization Accuracy Service robots Semantics Human-robot interaction Speech recognition Feature extraction Data mining Facial features

来源：评论

学校读者我要写书评

暂无评论

CPT-based Active Power Filter with Repetitive controller and Capacitor Voltage Feedforward under Non-Ideal Grid

CPT-based Active Power Filter with Repetitive Controller and...

引用

IEEE ANDESCON

作者： José de Arimatéia O. Filho Paulo Fernando Silva Luis De Oro Arenas Tiago Davi Curi Busarello Helmo Kelis Morales Paredes Institute of Science and Technology of Sorocaba São Paulo State University (Unesp) Sorocaba Brazil Department of Control Automation and Computing Engineering Federal University of Santa Catarina (UFSC) Blumenau Brazil

ISBN: (数字)9798350355284

ISBN: (纸本)9798350355291

This paper proposes the design of a repetitive controller along with capacitor voltage feedforward applied to an LCL filter active power filter (APF). The repetitive controller can operate in systems with disturbances exhibiting high harmonic content and the feedforward action can reshape the output impedance of the APF. The conservative power theory (CPT) is proposed to obtain reference signals for the purpose of total mitigation of unwanted currents. The proposed technique ensures that only the active current flows through the electrical grid, while maintaining the stability of the APF-grid system through passivity theory. Finally, the proposed control strategy is validated using the Matlab/Simulink® software under several conditions of grid imbalances and harmonic distortions.

关键词： Power filters Stability criteria Capacitors Power system stability Active filters Filtering theory Impedance Voltage control Feedforward systems Power harmonic filters

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：