检索结果-内蒙古大学图书馆

Estimation of Equivalent Thermal Conductivity for Electric machine Windings Using Conformal Mapping Method

IEEE Transactions on Transportation Electrification 2025年第3期11卷 7662-7672页

作者： Tang, Zhaopeng Wang, Yunchong Yu, Feng-Yuan Shi, Dan Shen, Jian-Xin Zhejiang University Zhejiang Provincial Key Laboratory of Electrical Machine Systems College of Electrical Engineering Hangzhou310027 China

It is important to predict the temperature distribution in the windings of electric machines, where the thermal model of an equivalent homogeneous material is used to simulate the winding conductors as well as the insulation and impregnation between the conductors. This article presents an analytical method for better estimating the equivalent thermal conductivity of the windings. According to the periodicity and symmetry of the heat flux field in the windings, the windings are segmented into square units, while the equivalent thermal conductivity of the whole windings is replaced with those of square units. Conformal mapping and equivalent transformation are used to reduce the complexity of solving the equivalent thermal conductivity of each square unit. Comparative study shows that the proposed analytical model is more accurate than the commonly used models. The partial stator temperature simulation was done to further verify that the proposed analytical model can be well applied to the actual windings. Experiments were conducted by fabricating and testing various winding samples, and a comparison between the finite volume method (FVM) thermal simulation and experimental tests verifies the accuracy of the proposed model. © 2015 IEEE.

关键词： Conformal mapping

来源：评论

学校读者我要写书评

暂无评论

Using Physiological Signals for Pain Assessment: An Evaluation of Deep Learning Models 30

Using Physiological Signals for Pain Assessment: An Evaluati...

引用

30th International Conference on Mechatronics and machine Vision in Practice, M2VIP 2024

作者： Zheng, Jianan Lin, Yingzi Northeastern University Intelligent Human-Machine Systems Laboratory Boston United States

ISBN: (纸本)9798350391916

Pain assessment is of major significance in clinical environments. The current gold standard is self-reporting of pain based on the patient's subjective willingness. However, pain assessment based on physiological signals is developing rapidly due to the objectivity and real-time nature of physiological signals. This study aims to systematically compare the performance of convolutional neural networks (CNN) combined with long short-term memory networks (LSTM), bidirectional long short-term memory networks (BiLSTM), transformers, and gated recurrent units (GRU) models in pain classification tasks. We assessed these hybrid models' performance experimentally using a variety of metrics, such as accuracy, precision, recall, F1 score, training time, and inference time. The experimental results show that the CNN+Transformer model best performs in most evaluation metrics with an accuracy of 0.795, while the CNN+GRU model performs the worst with an accuracy of only 0.559. In addition, we also analyze the computational efficiency of each model in terms of training and inference time. Overall, this paper provides important direction for future research and real-world applications by thoroughly evaluating the effectiveness of various deep learning models in pain classification tasks. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Exploring the Relationship Between Imitated and Associated Mechanism on Performance of Visual Imagery Brain-Computer Interface 46

Exploring the Relationship Between Imitated and Associated M...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Tai, Pengrui Yang, Jingcheng Qi, Shaowen Li, Guanglin Fu, Yunfa Li, Yongcheng Kunming University of Science and Technology Kunming China Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems SIAT-CAS China Cas Key Laboratory of Human-Machine Intelligence-Systems SIAT-CAS China

ISBN: (纸本)9798350371499

Visual Imagery (VI) can be defined as the manipulation of visual information derived from memory rather than perception. Currently, the brain responses underlying imitation and associative VI are not clear. In this study, we explore the differences from imitation to associative VI on the brain responses based on EEG signals. In this study, eight participants were instructed to observe visual cues from three predefined images or characters (tree, computer, or sphere), and then imagine the same cues. The results indicate that there is a significant difference in power intensity among electrode channels in the occipital lobe, posterior parietal lobe, and temporal lobe during the imagination phase between imitative tasks and associative tasks, as revealed by t-tests (p © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Priority-Dependent Notifications for Smart Glasses Based on Peripheral Visual Cues

引用

i-com 2022年第2期21卷 239-252页

作者： Faulhaber, Anja K. Hoppe, Moritz Schmidt, Ludger Human-Machine Systems Engineering Group University of Kassel Kassel Germany

Smart glasses are increasingly commercialized and may replace or at least complement smartphones someday. Common smartphone features, such as notifications, should then also be available for smart glasses. However, notifications are of disruptive character given that even unimportant notifications frequently interrupt users performing a primary task. This often leads to distractions and performance degradation. Thus, we propose a concept for displaying notifications in the peripheral field of view of smart glasses and with different visualizations depending on the priority of the notification. We developed three icon-based notifications representing increasing priority: A transparent green icon continuously becoming more opaque (low priority), a yellow icon moving up and down (medium priority), and a red and yellow flashing icon (high priority). To evaluate the concept, we conducted a study with 24 participants who performed a primary task and should react to notifications at the same time using the Nreal Light smart glasses. The results showed that reaction times for the low-priority notification were significantly higher and it was ranked as the least distracting. The medium- A nd high-priority notifications did not show a clear difference in noticeability, distraction, or workload. We discuss implications of our results for the perception and visualization of notifications in the peripheral field of view of smart glasses and, more generally, for augmented reality applications. © 2022 Walter de Gruyter GmbH, Berlin/Boston.

关键词： Glass

来源：评论

学校读者我要写书评

暂无评论

Analysis and Design of a Three-Coil Coplanar Couper WPT System with Automatic Seamless CC to CV for Charging Battery 11th

Analysis and Design of a Three-Coil Coplanar Couper WPT Syst...

引用

11th Frontier Academic Forum of Electrical engineering, FAFEE 2024

作者： Feng, Qunqun Li, Xi Song, Ke Chen, Bin Luo, Bin School of Information Engineering Nanchang University Nanchang330036 China Key Laboratory of Intelligent Systems and Human-Machine Interaction Jiangxi China

ISBN: (纸本)9789819788118

Load-independence constant current (CC) and constant voltage (CV) charging are the two stages of the battery charging. To simplify the complexity of the control strategy during the switching process from the CC mode to the CV mode of the wireless charging system, a low-profile three-coil inductive power transfer (IPT) system based on a switchable hybrid structure is proposed, where all coils are placed coplanar to save space and low-profile ferrite plates are strategically placed on and beneath the junctions of adjacent coils to enhance primary couplings and suppress cross couplings. Two switches are set on the primary side to reconfigure the resonant circuit to choose CC mode or CV mode, while increasing the compactness of the receiver side. The current in the primary coil remains essentially unchanged, when the load is open-circuited, short-circuited, or removed, indicating a higher level of safety in the system. Throughout the charging process, zero phase angle (ZPA) and zero voltage switching (ZVS) are maintained. Thus, a higher power transmission efficiency (PTE) is obtained. An experimental platform is built to verify the theory. The experimental and theoretical results are in good agreement, and the maximum PTE was measured as 96.73%. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Resonant circuits

来源：评论

学校读者我要写书评

暂无评论

Enhancing Autonomous Vehicle Safety Based on Operational Design Domain Definition, Monitoring, and Functional Degradation: A Case Study on Lane Keeping System

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-15页

作者： Jiang, Zhengmin Pan, Wenbo Liu, Jia Han, Yunjie Pan, Zhongmin Li, Huiyun Pan, Yi Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems China

Autonomous vehicles encounter safety challenges in dynamic and unpredictable environments at present. To address this issue, this paper introduces a series of safety mechanisms related to the Operational Design Domain (ODD) for defining, monitoring, and implementing functional degradation strategies of lane-keeping systems. Initially, causal inference and vehicle dynamics stability theory are employed to establish the ODD space. Subsequently, a counterfactual-based lane detection monitor is developed, utilizing structural equations to instantiate causal relationships between lane detection accuracy and perception-related ODD elements. Simultaneously, a lateral control monitoring method is introduced through the fitting of stable boundary parameters. Functional degradation maneuvers are triggered upon any warning from ODD monitoring. To strengthen the quantitative analysis of the safety benefits of the presented mechanisms, a Kriging-based Subset Simulation (KSS) algorithm is proposed. This algorithm requires only 11.96% to 13.02% of the computing resources compared to standard subset simulation technology. Experimental results demonstrate the potential of our ODD definition, monitoring, and functional degradation strategy approach in significantly reducing lane departure rates from 1.01×10-3 to 6.82×10-6. Overall, our research introduces an innovative, interpretable, and scalable analytical framework for the safety enhancement of autonomous vehicles. IEEE

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Exploring contextual priors for real-world image super-resolution

引用

Computational Visual Media 2025年第1期11卷 159-177页

作者： Shixiang Wu Chao Dong Yu Qiao Guangdong–Hong Kong–Macao Joint Laboratory of Human–Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China University of Chinese Academy of Sciences Beijing 100049China Shanghai AI Laboratory ShanghaiChina.

Real-world blind image super-resolution is a challenging problem due to the absence of target high resolution images for *** by the recent success of the single image generation based method SinGAN,we tackle this challenging problem with a refined model SR-SinGAN,which can learn to perform single real image ***,we empirically find that downsampled LR input with an appropriate size can improve the robustness of the generation ***,we introduce a global contextual prior to provide semantic *** helps to remove distorted pixels and improve the output ***,we design an image gradient based local contextual prior to guide detail *** can alleviate generated artifacts in smooth areas while preserving rich details in densely textured regions(e.g.,hair,grass).To evaluate the effectiveness of these contextual priors,we conducted extensive experiments on both artificial and real *** show that these priors can stabilize training and preserve output fidelity,improving the generated image *** furthermore find that these single image generation based methods work better for images with repeated textures compared to general images.

关键词： unsupervised learning blind super-resolution image context image generation

来源：评论

学校读者我要写书评

暂无评论

Mission Profile-Based Lifetime Estimation and its System-Controlled Improvement Method of IGBT Modules for Electric Vehicle Converters

CPSS Transactions on Power Electronics and Applications

引用

CPSS Transactions on Power Electronics and Applications 2023年第3期8卷 246-256页

作者： Lu, Yiping Xiang, Enyao Zhu, Lin Gao, Hongyi Yang, Huan Zhao, Rongxiang College of Electrical Engineering Zhejiang University Zhejiang Provincial Key Laboratory of Electrical Machine Systems Hangzhou310058 China

The estimation of insulated gate bipolar transistor (IGBT) module lifetimes in electric vehicle (EV) converters is heavily influenced by long-term mission profiles (MPs), as their reliability is significantly affected by power fluctuations. This paper presents a lifetime estimation method for IGBT modules based on MPs, using a 115 kW electric drive system as a case study. First, considering the standard road spectrum for EVs, the mathematical model of an automotive motor, and its control strategy, the load conditions for the converters are calculated. Next, employing an electro-thermal coupling model of the power device, the power loss and junction temperature characteristics of the IGBT modules for EV converters under specific load conditions are analyzed. Sub-sequently, the consumed lifetime is determined using a physics-of-failure-based lifetime model and cumulative damage theory. Finally, the paper delves into the reliability-oriented control strategies of EV converters, which fully utilize the transmission ratio of the EV to enhance the IGBT module's lifetime. Test results demonstrate that, by employing the optimal transmission ratio, the lifetime can be extended by more than two times compared to the initial estimation value. © 2017 CPSS.

关键词： Electric vehicles

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Deep Learning Approach for Epileptic Seizure Detection in EEG signals

引用

IEEE Journal of Biomedical and Health Informatics 2023年 PP卷 1-12页

作者： Ahmad, Ijaz Wang, Xin Javeed, Danish Kumar, Prabhat Samuel, Oluwarotimi Williams Chen, Shixiong CAS Key Laboratory of Human-Machine Intelligence Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen Guangdong China

Early detection and proper treatment of epilepsy is essential and meaningful to those who suffer from this disease. The adoption of deep learning (DL) techniques for automated epileptic seizure detection using electroencephalography (EEG) signals has shown great potential in making the most appropriate and fast medical decisions. However, DL algorithms have high computational complexity and suffer low accuracy with imbalanced medical data in multi seizure-classification task. Motivated from the aforementioned challenges, we present a simple and effective hybrid DL approach for epileptic seizure detection in EEG signals. Specifically, first we use a K-means Synthetic minority oversampling technique (SMOTE) to balance the sampling data. Second, we integrate a 1D Convolutional Neural Network (CNN) with a Bidirectional Long Short-Term Memory (BiLSTM) network based on Truncated Backpropagation Through Time (TBPTT) to efficiently extract spatial and temporal sequence information while reducing computational complexity. Finally, the proposed DL architecture uses softmax and sigmoid classifiers at the classification layer to perform multi and binary seizure-classification tasks. In addition, the 10-fold cross-validation technique is performed to show the significance of the proposed DL approach. Experimental results using the publicly available UCI epileptic seizure recognition data set shows better performance in terms of precision, sensitivity, specificity, and F1-score over some baseline DL algorithms and recent state-of-the-art techniques. IEEE

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Single-Wavelength Laminar Optical Tomography for In Vivo Microvascular Three-Dimensional Imaging 46

Single-Wavelength Laminar Optical Tomography for In Vivo Mic...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Cui, Han Han, Dewei Liu, Wenquan Deng, Xinping Xin, Zhixuan Li, Guanglin Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Shenzhen China

ISBN: (纸本)9798350371499

Laminar Optical Tomography (LOT) is a promising non-invasive technique for three-dimensional imaging of complex biological structures, combining high resolution and deep penetration. In this study, a LOT system was assembled using a 520nm continuous-wave laser, exploiting the contrast mechanism provided by the unique optical absorption coefficient of hemoglobin at this wavelength for microvascular imaging. The system utilizes raster scanning to illuminate the target tissue's surface, capturing backscattered light intensity with a multi-channel Photomultiplier Tubes. The inverse problem of light propagation within the tissue is solved to reconstruct a three-dimensional image of microvasculature. Phantom and in-vivo rat ear results demonstrate the system's ability to image micro vessels with diameters of several hundred micrometers within the tissue. The implemented LOT system, known for its simplicity and cost-effectiveness, showcases its potential for applications in microvascular physiological and pathological research, as well as clinical diagnostics. © 2024 IEEE.

关键词： Clinical research

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：