检索结果-内蒙古大学图书馆

5th International Conference on Electrical Engineering and Control Technologies, CEECT 2023

作者： Xia, Yuanyang Li, Xiaocong Liu, Yuan Zhang, Lei Guangxi University Guangxi Key Laboratory of Power System Optimization and Energy Technology Nanning China Nanning University Intelligent Manufacturing College Nanning China Yalong River Hydropower Development Co. Ltd Marketing Department Chengdu China College of Electronic Information Engineering Anhui Water Conservancy Technical College Hefei China

ISBN: (纸本)9798350342253

When resonant grounding occurs, the fault components of the line are complex, and components with different properties cancel out or compensate each other, weakening the fault characteristics and easily making it difficult to select the grounding fault line. Considering the reality of line measurement channels, this paper utilizes an underdetermined blind source separation algorithm to separate the steady-state component, transient component, and noise of faults from the measurement signal. Using the high-order moments of each component of the zero-sequence current of the line as the criterion, accurate line selection of single-phase grounding faults can be achieved. Compared with Prony, HHT, and FFT methods, the method proposed in this paper has certain advantages. The simulation and on-site experimental results show that the accuracy of the method in line selection is all correct, and it has certain anti-interference ability. © 2023 IEEE.

关键词： Blind source separation

来源：评论

学校读者我要写书评

暂无评论

CB-YOLOv5 Algorithm for Small Target Detection in Aerial Images 4

CB-YOLOv5 Algorithm for Small Target Detection in Aerial Ima...

引用

4th International Conference for Emerging technology, INCET 2023

作者： Li, Yingjie Wang, Yitian Zhao, Huaici Shenyang University of Chemical Technology College of Information Engineering Shenyang110142 China Chinese Academy of Sciences Key Laboratory of Opto-Electronic Information Processing Shenyang110016 China Chinese Academy of Sciences Shenyang Institute of Automation Shenyang110016 China Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang110169 China

ISBN: (纸本)9798350335750

Aerial images are often plagued by background interference, and small targets with indistinct features, leading to low accuracy, high false detection rates, and high miss detection rates. To address these challenges, a small target detection algorithm based on YOLOv5, Coordinate-attention and Bidirectional-feature-pyramid-network YOLOv5 (CB-YOLOv5), is proposed in this paper. Considering the small number of pixels occupied by small targets and their indistinct features, a fourth target detection layer is added by concatenating the feature map from quadruple down-sampling during feature extraction with the feature map output from 8-fold up-sampling during feature fusion. Additionally, a coordinate attention mechanism is introduced during the feature extraction stage to improve small target localization and enhance detection accuracy. Finally, the original Path Aggregation Networks (PANet) structure is replaced with a weighted Bidirectional Feature Pyramid Network (BiFPN) structure during the feature fusion stage to improve the network's ability to fuse feature maps of different scales. The simulation results demonstrate that the CB-YOLOv5 improves mAP50 by 9.4%, mAP75 by 9.7%, and mAP50:95 by 7.8% compared to the original YOLOv5s model. Thus, the effectiveness of the CB-YOLOv5 algorithm for detecting small targets in aerial images is validated. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Gate oxide degradation of SiC IGBT induced by non-constant thermal-electrical coupled stresses

Gate oxide degradation of SiC IGBT induced by non-constant t...

引用

2023 International Exhibition and Conference for Power electronics, intelligent Motion, Renewable Energy and Energy Management, PCIM Asia 2023

作者： Luo, Rongde Yang, Shaodong Luo, Xia Niu, Hao Kuang, Xianjun Xu, Xiaowei Dong, Huafeng Dai, Zongbei Wu, Fugen State Key Laboratory of Precision Electronic Manufacturing Technology and Equipment Guangdong University of Technology Guangzhou510006 China School of Materials and Energy Guangdong University of Technology Guangzhou510006 China No.5 Electronics Research Institute of the Ministry of Industry and Information Technology Guangzhou511370 China Three Gorges Intelligent Industrial Control Technology Company Wuhan430070 China School of Physics and Optoelectronic Engineering Guangdong University of Technology Guangzhou510006 China

ISBN: (纸本)9783800761326

The SiC/SiO2interface property has become a non-negligible reliability risk for SiC power electronic devices. The degradation mechanism of the SiC/SiO2interface of SiC IGBTs under non-constant thermal-electrical coupled stresses was investigated in this study, based on variation analysis of sensitive static characteristics. Under positive bias (Group 2: +70 V, Group 3: +50 V) at 150 °C for 675 h, VGE(TH)increased slightly. Then a mild rebound happened to Groups 2 and 3 after 15 days of recovery (Stage 2: under 25 °C / 50 %RH). Afterwards, a significant decrease of VGE(TH)within 48 h under negative bias (Group 2: -70 V, Group 3: -50 V), probably due to the holes captured by traps rapidly at or near the SiC/SiO2interface. The harsher stresses led to more serious VGE(TH)drift as expected. While no significant VGE(TH) fluctuations were observed after HTSS tests (at 150°C). Besides, the IGESand V(BR)CESdid not change significantly, which indicates there is no permanent damage. © VDE VERLAG GMBH - Berlin - Offenbach.

关键词： Silicon carbide

来源：评论

学校读者我要写书评

暂无评论

Fruit target detection method based on faster R-CNN

引用

International Journal of Wireless and Mobile Computing 2021年第3期21卷 207-213页

作者： Yin, Guanghui Xie, Yuanmin Yun, Juntong Ning, Lichuan Liu, Ying Wuhan University of Science and Technology Hubei Wuhan China Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Hubei Wuhan China Hubei Provincial Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Hubei Wuhan China Research Centre for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Hubei Wuhan China

With the rapid development of agricultural modernisation, fruit picking is becoming more and more automatic. The detection of fruit target by machine vision technology is the key to realise fruit automatic picking. In recent years, with the development of deep learning technology, target detection algorithm based on deep learning has gradually become a hot research topic, and the detection accuracy has been greatly improved. However, the shape and size of fruits in natural environment are different, and the light intensity changes at any time, which affects the detection accuracy to a certain extent. In this paper, aiming at the problem of fruit detection and location in natural environment, based on Fast R-CNN target detection model, a fruit detection and location method combining image processing and deep learning is proposed. The experimental results show that the combination of image processing and deep learning can achieve high detection accuracy and speed. Copyright © 2021 Inderscience Enterprises Ltd.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

robot multimodal anomaly diagnosis by learning time-lagged complex dynamics

Robot multimodal anomaly diagnosis by learning time-lagged c...

引用

2021 IEEE International Conference on Real-Time Computing and robotics, RCAR 2021

作者： Yang, Lin Yan, Wu Xu, Zhihao Wu, Hongmin Guangdong Provincial Key Laboratory of Electronic Information Products Reliability Technology Guangzhou China Institute of Intelligent Manufacturing Guangdong Academy of Sciences Guangzhou China

ISBN: (纸本)9781665436786

robots are prone to making anomalies when performing manipulation tasks in unstructured environments, it is often desirable that robots can detect, diagnose them, and then effectively provides prior experiences for rapidly adapting the robot anomalous behaviors. The traditional methods on anomaly diagnosis are to focus on univariate time series and ignore the modality correlation and time-dependent, which can't be applied in a Human-robot collaborative (HRC) system that is integrated with multiple sensors for improving autonomy and safety. The variability and temporal consistency of multimodal sensory data exacerbate anomaly diagnosis still an open problem in robotics. Here we propose a novel method of multimodal anomaly diagnosis by learning the time-lagged dynamics of anomalies detected during an HRC task. Specifically, a time-lagged variational auto-encoder model (tlVAE) is first proposed to compress complex multivariate dynamics into simpler manifolds, and the manifolds are used to fitting a dynamic time warping-based K-nearest neighbors model for anomaly diagnosis in a multi-classes classification scheme. A real-robot anomaly dataset is presented to evaluate the significance and effectiveness in extracting underlying time-dependent patterns, results indicate that the efficiency and precision of diagnosis can be improved by introducing a sparse representation of the multivariate sample. Meanwhile, we compare the accuracy of anomaly diagnosis with several commonly used sparse representation methods, including Principal Component Analysis (PCA), Time-lagged Independent Component Analysis (TICA), Autoencoder (AE) as well as Variational Autoencoder (VAE). The resulting anomaly diagnosis accuracy of 97.6% across 7 kinds of anomalies, which outperformed all the baselines. © 2021 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Towards More Accurate Tiny Object Tracking: Benchmark and Algorithm

Towards More Accurate Tiny Object Tracking: Benchmark and Al...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Jizhe Yu Yu Liu Hongkui Wei Kaiping Xu DUT School of Software Technology & DUT-RU International School of Information Science and Engineering Dalian University of Technology Dalian China State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System Engineering Beijing China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Despite the significant progress in tiny object tracking algorithms based on convolutional neural networks, the performance falls short of the ideal level due to dataset challenges like limited scale, limited match backdrop, low match popularity, and low-resolution(720p) images. The lack of specialized large-scale tiny object tracking datasets leads data-hungry tracking algorithms to rely on small and saturated datasets from TrackNet. This paper propels the development of tiny object tracking and contributes the first large-scale dataset, Badminton100K, for tiny ball tracking. We provide over 100K annotations covering over 200 videos from 12 professional match events. Our dataset covers high-resolution(1080p) match videos in broad and diverse contexts. Moreover, considering the fast-moving tiny balls in videos often leads to challenges such as blur, afterimage, overlap, and disappearance. As another contribution, we also propose a novel Multi-stage and Multi-scale Fusion Network (MMFNet), which can extract local high-resolution details in the shallow stages and capture global semantic information in the deep stages, addressing these challenging tasks through multiple stages multi-scale feature fusion, enabling accurate identification and localization of tiny balls. Extensive experiments show that our method achieves unprecedented state-of-the-art tracking performance on Badminton100K. The dataset and the algorithm code are available at https://***/Gi-gigi/MMFNet.

关键词： Location awareness Accuracy Image resolution Semantics Transfer learning Propulsion Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Research on Hybrid Flow-shop Scheduling Based on INSGA-II Algorithm 4

Research on Hybrid Flow-shop Scheduling Based on INSGA-II Al...

引用

4th International Conference on robotics, intelligent Control and Artificial Intelligence, RICAI 2022

作者： Chen, Haopeng Fang, Zaojun Zhong, Caiming Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo Zhejiang China Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo Zhejiang China Zhejiang Key Laboratory of Robot and Intelligent Manufacturing Equipment Technology Ningbo Zhejiang China College of Science and Technology Ningbo University Ningbo Zhejiang China

ISBN: (纸本)9781450398343

Aiming at the hybrid flow shop scheduling problem (HFSP), a multi-objective optimization scheduling model is established with the objectives of minimizing makespan, energy consumption and total load, and an improved non-dominated sorting genetic algorithm-II (INSGA-II) is proposed to solve the problem. Combining the problem characteristics of task sequencing and equipment selection in the production process of hybrid flow shop, a double-layer coding rule combining the job sequence code (JSC) and machine allocation code (MAC) is adopted. Different crossover and mutation operators are used for JSC and MAC respectively to improve the global search capability of the algorithm. Aiming at the poor local search capability of NSGA-II, neighborhood search is introduced to improve the quality of population. Finally, the optimal parameters combination of the algorithm is determined by orthogonal experiment, and the feasibility and effectiveness of INSGA-II for solving the multi-objective scheduling problem in hybrid flow shop are verified by simulation experiments. © 2022 ACM.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

General Elastic Computing Acceleration Method for Semantic Segmentation 23

General Elastic Computing Acceleration Method for Semantic S...

引用

9th International Conference on Computing and Artificial Intelligence, ICCAI 2023

作者： Wei, Yiying Jiang, Yiyang Dai, Wei Yang, Zhijie Jiang, Ao School of Mechanical and Electronic Engineering Wuhan University of Technology Wuhan430070 China Intelligent Transportation Systems Research Center Wuhan University of Technology Wuhan430070 China School of Mechanical and Electronic Engineering Wuhan University of Technology China School of Mechanical Engineering Shanghai Jiao Tong University Shanghai200011 China The SAIC-GM-Wuling Automobile Co. Ltd. Liuzhou545000 China Hubei Digital Manufacturing Key Laboratory Wuhan430070 China

ISBN: (纸本)9781450399029

In the field of computer vision, deep convolution neural network plays an increasingly important role, and its accuracy in various tasks has gradually exceeded the traditional method. However, real-time is important in autonomous driving and mobile robot scenarios. Most processes need to be run locally and completed in a short time with sufficient precision. Semantic segmentation based on deep convolutional neural networks consumes huge computing resources, and the balance of accuracy and speed has been a difficult problem in industrial deployment. We propose a general elastic computing acceleration method for semantic segmentation, which makes full use of the correlation between the front and back frames of the input video. We use optical flow, fuzzy prediction and the combination of these two methods to accelerate the inference of semantic segmentation. Experiments show that our method greatly saves computing resources and retains high accuracy. On platforms with limited computing resources, it can well balance accuracy and speed. © 2023 Copyright held by the owner/author(s).

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Minimizing the Number of Leaders in Impulsive Multi-Agent Systems Under Switching Topologies

Minimizing the Number of Leaders in Impulsive Multi-Agent Sy...

引用

2023 China Automation Congress, CAC 2023

作者： Chen, Kaile Xue, Mengqi Huang, Jiahao Tang, Yang School of Information Science and Engineering East China University of Science and Technology Shanghai China College of Electronic and Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China The Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education East China University of Science and Technology Shanghai200237 China The Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Tongji University Shanghai201210 China

ISBN: (纸本)9798350303759

In this paper, the leader selection problem is studied for impulsive general linear multi-agent systems under switching topologies, which minimizes the number of leaders subject to the consensus tracking performance. First, a consensus criterion for the studied multi-agent systems is derived. Second, leader selection metrics are established via the submodular optimization technique according to the proposed criterion. Third, a leader selection scheme is presented, with a polynomial-time algorithm that returns candidate leader sets. Finally, the effectiveness of the developed leader selection scheme is verified by numerical examples. © 2023 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

3D Lane Detection from Front or Surround-View using Joint-Modeling & Matching

arXiv

引用

arXiv 2024年

作者： Zhou, Haibin Zhou, Huabing Chang, Jun Lu, Tao Ma, Jiayi The Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan430205 China The Computer Science School Wuhan University Wuhan430072 China The Electronic Information School Wuhan University Wuhan430072 China

3D lanes offer a more comprehensive understanding of the road surface geometry than 2D lanes, thereby providing crucial references for driving decisions and trajectory planning. While many efforts aim to improve prediction accuracy, we recognize that an efficient network can bring results closer to lane modeling. However, if the modeling data is imprecise, the results might not accurately capture the real-world scenario. Therefore, accurate lane modeling is essential to align prediction results closely with the environment. This study centers on efficient and accurate lane modeling, proposing a joint modeling approach that combines Bézier curves and interpolation methods. Furthermore, based on this lane modeling approach, we developed a Global2Local Lane Matching method with Bézier Control-Point and key-Point, which serve as a comprehensive solution that leverages hierarchical features with two mathematical models to ensure a precise match. We also introduce a novel 3D Spatial Encoder, representing an exploration of 3D surround-view lane detection research. The framework is suitable for front-view or surround-view 3D lane detection. By directly outputting the key points of lanes in 3D space, it overcomes the limitations of anchor-based methods, enabling accurate prediction of closed-loop or U-shaped lanes and effective adaptation to complex road conditions. This innovative method establishes a new benchmark in front-view 3D lane detection on the Openlane dataset and achieves competitive performance in surround-view 2D lane detection on the Argoverse2 dataset. Copyright © 2024, The Authors. All rights reserved.

关键词： Forecasting

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：