检索结果-内蒙古大学图书馆

Analysis of Iron Loss Characteristics of PM-Assisted and Fluid-Shaped Synchronous Reluctance Machines for Micro EVs

Transactions of the Korean Institute of electrical Engineers 2025年第3期74卷 425-431页

作者： Choi, Jaesung Choi, Gilsu Dept. of Electrical and Computer Engineering Inha University Korea Republic of

This paper examines the iron loss characteristics of a permanent magnet-assisted synchronous reluctance machine (PMa-SynRM) and a fluid-shape synchronous reluctance machine (FS-SynRM) for micro EV applications, emphasizing the impact of DC bias fields and minor loops on iron loss estimation. Iron losses are comparatively evaluated using three methods: the Steinmetz method with constant coefficients, the loss separation method with varying coefficients and FFT, and the hysteresis-based model that accounts for minor loops and DC bias fields. The results show that iron losses per unit stack length are higher in the PMa-SynRM, where the effects of DC bias fields and minor loops are more pronounced. Moreover, the Steinmetz and loss separation methods, which neglect these effects, overestimate motor efficiency by up to 1.5% and 0.3%, respectively. This study highlights the importance of incorporating DC bias and minor loops in iron loss and efficiency calculations for micro EV traction machines. © The Korean Institute of electrical Engineers.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Optimization of Torque and Torque Ripple in Double V-Type IPMSM Using a Random Forest-Based Modified PSO-GA Hybrid Method

引用

Transactions of the Korean Institute of electrical Engineers 2025年第2期74卷 266-272页

作者： Kwon, Yong-Jun Choi, Dae-Sun Wang, Chang-Hyeon Oh, Ho-Jin Yoon, Han-Joon Jung, Sang-Yong Dept. of Electrical and Computer Engineering SungkyunKwan University Korea Republic of

Interior Permanent Magnet Synchronous Machines (IPMSMs) are widely used not only as drive motors for Electric Vehicles (EVs) but also in various industrial fields due to their high efficiency and high power output characteristics. However, because of the embedded magnets, IPMSMs exhibit significant torque ripple during operation, necessitating the use of optimization algorithms to address this issue. For IPMSMs, which have a large number of design variables, the feasible design space is defined by multiple constraints, increasing the complexity of the design optimization process. Therefore, this paper proposes a Random Forest-based Modified PSO-GA hybrid method to perform optimization in the presence of multiple constraints and applies it to the torque and torque ripple improvement design of a Double V-Type IPMSM. ©The Korean Institute of electrical Engineers.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

A Study on Rotor Shape for Reducing Low-Order Radial Force in Interior Permanent Magnet Synchronous Motors for Air Compressor

引用

Transactions of the Korean Institute of electrical Engineers 2025年第1期74卷 56-63页

作者： Cheo, Daeseon Kim, Nam-Ho Cho, Jae-Hoon Kwon, Yong-Jun Jung, Sang-Yong Dept. of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

In this paper, a rotor design to reduce low order raidal force and electromagnetic vibration in interier permanent magnet synchronous motor (IPMSM) for an air compressor is proposed. First, according to the analysis results of radial force and no-load air-gap flux density of V-type 1-layer and 2-layer models, 2-layer model is selected as the initial model since it exhibits lower low radial force than 1-layer model. Additionally, the no-load air-gap flux density of the 2-layer model is further analyzed, confirming that the low order radial forces affected by 20th order harmonic and the fundamental component of no-load air-gap flux density have a 180° phase difference, canceling each other out. Moreover, the sensitivity anlysis of rotor notches reveals that the 3-Notch model effectively increases magnitude of 20th order harmonic. Based on the aformentionted analysis, as a result, by applying notches to the 2-layer model rotor, the low order radial force and electromagnetic vibration are reduced. Copyright © The Korean Institute of electrical Engineers.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Development of a Reinforcement Learning-Based Control Education Platform Using Python and LW-RCP

引用

Transactions of the Korean Institute of electrical Engineers 2025年第1期74卷 118-126页

作者： Lee, Jongbeom Lee, Taegun Ju, Doyoon Sam Lee, Young Dept. of Electrical and Computer Engineering Inha University Incheon Korea Republic of

This paper proposes a reinforcement learning-based control education platform utilizing Python and light-weight rapid control prototyping (LW-RCP). The platform employs the Sim-to-Real technique, in which neural networks are trained in a Python-based simulation environment and applied to real systems. The trained networks are converted into a format compatible with Matlab/Simulink. The lab-built LW-RCP is used to implement a real-time controller under the Simulink environment by incorporating the converted networks. The proposed platform allows students to easily apply reinforcement learning theory to real systems, contributing to the integration of reinforcement learning control into control curriculum. The effectiveness of the proposed platform is demonstrated by implementing a reinforcement learning controller for the pendubot system. The implemented controller performs the swing-up and transition control and exhibits strong disturbance rejection and recovery properties. © 2025 Korean Institute of electrical Engineers. All rights reserved.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Hybrid CNN-ViT architecture to exploit spatio-temporal feature for fire recognition trained through transfer learning

引用

Multimedia Tools and Applications 2025年第8期84卷 4703-4732页

作者： Shahid, Mohammad Wang, Hong-Cyuan Chen, Yung-Yao Hua, Kai-Lung Dept. of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei Taiwan Dept. of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei Taiwan

Fires are becoming one of the major natural hazards that threaten the ecology, economy, human life and even more worldwide. Therefore, early fire detection systems are crucial to prevent fires from spreading out of control and causing destruction. Based on vision sensors, many fire detection techniques have evolved with the recent surge of curiosity in deep learning, which exploits the spatial features of individual images. However, fire can take different forms, scales, and combustion materials can produce different colors, making accurate fire detection from an image challenging. Small fires captured from long-distance cameras lack salient features, further complicating detection. This paper proposes a hybrid structure that uses attention-enhanced convolutional neural networks and vision transformers (CNN-ViT) to detect fire. The proposed CNN-ViT first pays spatial attention to every frame and then aggregates temporal contextual information from neighboring frames to improve detection performance. Due to the limited availability of training fire datasets, the study employs deep transfer learning for feature extraction using pre-trained CNN. We used various metrics to examine the efficacy of the proposed approach. The results showed that the CNN-ViT method outperformed previous models based on spatial-temporal characteristics by achieving a relative improvement in accuracy and F1 score. The satisfactory results on images contaminated with different intensities of noise confirm the robustness of the approach. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

SINR-Delay Constrained Node Localization in RIS-Assisted Time-Varying IoT Networks Using ML Frameworks

引用

IEEE Transactions on Network and Service Management 2025年第2期22卷 1544-1557页

作者： Bhardwaj, Vikash Kumar Mundada, Gagan Sahoo, Omm Prakash Shukla, Mahendra K. Pandey, Om Jee Varanasi Dept. of Electronics Engineering 221005 India University of California San Diego Computer Science and Engineering Dept United States Varanasi Dept. of Electrical Engineering 221005 India ABV-IIITM Gwalior Dept. of Information Technology India

Node localization in time-varying Internet of Things (IoT) networks is an essential problem due to increased delay and poor Signal-to-Interference plus Noise Ratio (SINR) at the Base Station (BS). To improve the received signal strength at the BS, Reconfigurable Intelligent Surface (RIS) has recently been used between transmitter and receiver. Additionally, novel phase prediction methods and optimal weight assignment frameworks have been proposed over RIS and BSs, respectively. Nevertheless, these methods suffer from poor performance due to their heuristic approach, resulting in more time consumption and poor SINR. Motivated by the aforementioned challenges, we propose a novel node localization method over a RIS-assisted time-varying IoT network using Machine Learning (ML) frameworks in this work. Firstly, the method computes the optimal phase configuration over the RIS corresponding to each element using coeff2phaseNN, which has been trained on channel coefficients among the transmitter, receiver, and RIS. Subsequently, the weight of the individual antenna element at the BS is optimized using the proposed VectorSync model. The results confirm that the coeff2phaseNN method demonstrates a reduction of 89.79% in total MSE loss compared to the Artificial Neural Network-RIS (ANN-RIS) method. Additionally, it demonstrates a 71.04% reduction in the absolute RIS phase prediction deviation from the optimal phase compared to the ANN-RIS method. Moreover, the proposed VectorSync method attains a 79.28% and 92.29% reduction in time required for optimal weight assignment compared to the Bartlett and Capon methods, respectively. Finally, the Localization Error(LR) using the proposed method is compared to conventional methods in a time-varying experimental scenario and found to be the minimum, i.e., 6.156%. © 2004-2012 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

IEEE Vehicular Technology Society Bylaws Changes [Society News]

引用

IEEE VEHICULAR TECHNOLOGY MAGAZINE 2025年第1期20卷 111-112页

作者： Rubinstein, Tom Dept. of Electrical & Computer Engineering Auburn University Auburn AL USA

Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Object Detection Through a Learning-Based Joint-Initiative Supervised Autonomy (JISA) Framework

Improved Object Detection Through a Learning-Based Joint-Ini...

引用

2025 International Conference on Control, Automation, and Instrumentation, IC2AI 2025

作者： Tarabay, Andrea Daher, Naseem American University of Beirut Dept. of Electrical and Computer Engineering Beirut Lebanon American University of Beirut Dept. of Electrical and Computer Engineering Dept. of Mechanical Engineering Beirut Lebanon

ISBN: (纸本)9798331529604

Object detection is faced with accuracy and robustness limitations due to unstructured environments with objects of different sizes and occlusions. Despite advancements in object detection models, these models have not reached a point to possess a comparable level of perception to humans, thus limiting their ability to effectively address challenges in diverse environments. Hence, adopting a human-in-the-loop approach in autonomous systems can handle complex perception scenarios. To tackle these issues, the Joint-Initiative Supervised Autonomy (JISA) framework is used to allow a human supervisor to intervene once the agent is uncertain of its predictions based on its self-confidence (SC) metric, or when the human deems the prediction incorrect based on his/her situation awareness (SA). However, the existing JISA framework formally defines the levels of autonomy between the human and the agent, but does not provide a means for learning from human interventions. In this paper, we present an enhanced version of JISA in object detection applications by implementing a learning scheme that is inspired by the Interactive Corrections and Reinforcement for an Epistemic and Aleatoric uncertainty-aware Teaching (ICREATe) algorithm. To address these challenges, we evaluate the results of the proposed framework and demonstrate that the model effectively learns and improves its performance through human feedback. © 2025 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Quantum-Enhanced Machine Learning for Precision Breast Cancer Diagnosis 17

Quantum-Enhanced Machine Learning for Precision Breast Cance...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Banerjee, Agniva Indian Institute of Science Education and Research Bhopal Dept. Electrical Engineering and Computer Science Bhopal India

ISBN: (纸本)9798331531195

Cancer is the leading cause of premature mortality. Globally, the prevalence of cancer is on the rise, and early-stage diagnosis is crucial for cancer recovery and survival. However, the presence of circulating tumor cells (CTCs) and heterogeneity within the tumor makes it hard to track how cancer changes over time and how resistance to treatment develops. Unfortunately, the cancer diagnosis precision remains inadequate, endangering precious human lives and necessitating costly procedures for accurate treatment. Machine learning (ML) has proven capable of discovering meaningful information and making predictions, particularly with large datasets. Moreover, quantum computers (QCs) inherently possess superposition and parallel computation, features not found in classical computing. Researchers have demonstrated that quantum neural networks (QNNs) achieve a significantly better effective dimension than classical NNs. In this context, this study investigates the application of classical and quantum machine learning (QML) algorithms to classify breast cancer images. Region-based segmentation is used to identify regions of interest and image processing algorithms are performed on segmented breast cancer images to extract meaningful features (e.g., perimeter, area, compactness). An user interface (UI) based software is created to swiftly distinguish benign and malignant instances during image analysis. Although QNNs perform poorly than the classical NNs, there is still a long way to go in developing feature maps and techniques for better performance. In contrast, the classical NNs have gone a long way with well-established algorithms and packages available to us. This research shows that with further development, QML has the potential to enhance cancer diagnosis accuracy and speed, ultimately improving early detection and treatment outcomes. © 2025 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

nCTX: A Neural Network-Powered Lossless Compressive Transmission using Shared Information

引用

IEEE Transactions on Mobile Computing 2025年第6期24卷 5386-5399页

作者： Nam, Wooseung Lee, Sungyong Lee, Joohyun Lee, Kyunghan Dept. of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of School of Electrical Engineering Hanyang University Ansan15588 Korea Republic of

In this work, we explore the possibility of a new delivery method for lossless data, namely compressive transmission. It aims at minimizing the transmission data volume at runtime by exploiting the tailored information shared between the sender and the receiver. There are two approaches to leverage shared information for compression: 1) using a DNN-based codec as a proxy for shared information and 2) applying redundancy elimination using deduplication. However, these approaches have not been studied in dept. to utilize the trade-off between the compression rate and the amount of shared information. Compared to these approaches, compressive transmission is unique as it fully leverages the abundance of information available on both sides, which is chosen and placed purposely. To bring the concept to reality, we propose nCTX, a neural network-powered Compressive Transmission System that adaptively exploits a generative model and matching blocks. nCTX extracts the optimal semantic data from the input data, exploiting shared information to closely imitate the original and compensate it with the offset (i.e., difference). Extensive evaluations in mobile platforms confirm that nCTX reduces the transmission volume significantly by 25.8% and 23.3% compared to FLIF and RC, the state-of-the-art image codecs, respectively, in comparable or shorter computation times. ©2002-2012 IEEE.

关键词： Spatio-temporal data

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：