IEEJ Transactions on Electrical and Electronic Engineering最新文献

筛选
英文 中文
Study on VFTO Suppression in 220 kV GIS Based on a Dynamic Synchronous Parallel Resistor Model 基于动态同步并联电阻器模型的220kv GIS中VFTO抑制研究
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-11-03 Epub Date: 2026-04-08 DOI: 10.1002/tee.70303
Fusen Han, Shuheng Dan
{"title":"Study on VFTO Suppression in 220 kV GIS Based on a Dynamic Synchronous Parallel Resistor Model","authors":"Fusen Han,&nbsp;Shuheng Dan","doi":"10.1002/tee.70303","DOIUrl":"https://doi.org/10.1002/tee.70303","url":null,"abstract":"<p>Very fast transient overvoltages (VFTO) in GIS during disconnector operation are strongly influenced by repeated breakdown and arc reignition. Conventional parallel-resistor models usually apply time-controlled switching and may not coincide with the actual arc state, leading to biased suppression assessment. This paper proposes a dynamically synchronized parallel-resistor model implemented in ATP-EMTP via the MODELS module, where the resistor is inserted and withdrawn in real time according to the instantaneous arc condition. A segmented arc model covering pre-breakdown, steady arcing, and extinction is established using a hyperbolic function, a constant low resistance, and a simplified Mayr model, together with breakdown and extinction criteria, enabling full-process reproduction of stepwise VFTO waveforms. Simulation on a 220 kV GIS substation verifies that the proposed scheme effectively reduces VFTO amplitude, wavefront steepness, and oscillatory components, while mitigating restrike development and trapped charge. By sweeping the parallel resistor from 100 to 800 Ω, the recommended range is 300–400 Ω; at 400 Ω, VFTO amplitude and breakdown steepness at the load side are reduced by 29.36% and 64.49%, respectively. A normalized impedance-scale index <i>R</i>/<i>Z</i><sub>tr</sub> is further introduced (<i>Z</i><sub>tr</sub> ≈ 70 Ω), yielding a recommended range of 4.3–5.7 for the studied system. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 12","pages":"1828-1838"},"PeriodicalIF":1.0,"publicationDate":"2026-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149311693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Understanding the High-Load Characteristics of Lithium-ion Batteries Using a Combination of Three- and Two-Electrode Measurements 利用三电极和双电极测量的组合来理解锂离子电池的高负载特性
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-11-03 Epub Date: 2026-04-08 DOI: 10.1002/tee.70304
Akihiko Kono, Kohei Yakushiji, Yoji Fujita, Hiroaki Urushibata
{"title":"Understanding the High-Load Characteristics of Lithium-ion Batteries Using a Combination of Three- and Two-Electrode Measurements","authors":"Akihiko Kono,&nbsp;Kohei Yakushiji,&nbsp;Yoji Fujita,&nbsp;Hiroaki Urushibata","doi":"10.1002/tee.70304","DOIUrl":"https://doi.org/10.1002/tee.70304","url":null,"abstract":"<p>To enhance control strategies for lithium-ion batteries (LIBs) in vehicle applications, it is crucial to accurately understand their output behavior under high loads. However, conventional two-electrode cells lack a reference electrode, making individually monitoring of positive and negative electrode potentials difficult and thereby limiting the analysis of overpotential and ohmic loss. In this study, LiCoO<sub>2</sub> and graphite were used as electrode materials and their single-electrode characteristics and full-cell performance were evaluated using a three-electrode cell and a two-electrode cell, respectively, under high-load conditions up to 10C discharge and with electrolyte salt concentrations of 500, 1000, and 2000 mol/m<sup>3</sup>. Increasing the salt concentration improved the capacity of the LiCoO<sub>2</sub> but reduced that of the graphite. The full-cell capacity was notably low at 500 mol/m<sup>3</sup> but similar between 1000 and 2000 mol/m<sup>3</sup>. The single-electrode analysis results showed that the full-cell capacities were dominated by LiCoO<sub>2</sub> at 500 and 1000 mol/m<sup>3</sup> and by graphite at 2000 mol/m<sup>3</sup>. These results indicate a latent reversal phenomenon not observable from full-cell data alone. Electrochemical impedance and direct-current resistance measurements, along with the reaction rate equation, enabled a theoretical interpretation of these behaviors. These findings highlight that high-load LIB dynamics can only be fully understood through single-electrode analysis. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 12","pages":"1877-1887"},"PeriodicalIF":1.0,"publicationDate":"2026-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149311692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Control-Oriented Neural Network for Systems with Nonlinear Elements 非线性单元系统的面向控制的神经网络
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-11-03 Epub Date: 2026-04-07 DOI: 10.1002/tee.70306
Yuji Wakasa, Ryuichiro Takemura, Shosuke Sudo, Shuji Matsuo, Ryosuke Adachi
{"title":"Control-Oriented Neural Network for Systems with Nonlinear Elements","authors":"Yuji Wakasa,&nbsp;Ryuichiro Takemura,&nbsp;Shosuke Sudo,&nbsp;Shuji Matsuo,&nbsp;Ryosuke Adachi","doi":"10.1002/tee.70306","DOIUrl":"https://doi.org/10.1002/tee.70306","url":null,"abstract":"<p>This paper proposes a novel neural network (NN) architecture for the unified representation of typical nonlinear elements in control systems, including dead zones, input saturation, and hysteresis. The proposed architecture employs a compact structure composed of rectified linear units, enabling enhanced learning efficiency and reduced computational complexity in comparison with conventional general-purpose recurrent neural networks. It is further demonstrated that the inverse models corresponding to these nonlinear elements can be formulated in a closed-form expression without approximation, thereby facilitating precise nonlinear compensation even in data-driven control frameworks. The effectiveness of the proposed NN is confirmed through several numerical examples. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 12","pages":"1859-1865"},"PeriodicalIF":1.0,"publicationDate":"2026-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149311734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
DQN-Guided Subset-Induced OCSVM Kernel Approximation for Imbalanced Anomaly Detection 基于dqn引导的子集诱导OCSVM核近似的不平衡异常检测
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-11-03 Epub Date: 2026-04-06 DOI: 10.1002/tee.70296
Wenqian Yu, Jiaying Wu, Jinglu Hu
{"title":"DQN-Guided Subset-Induced OCSVM Kernel Approximation for Imbalanced Anomaly Detection","authors":"Wenqian Yu,&nbsp;Jiaying Wu,&nbsp;Jinglu Hu","doi":"10.1002/tee.70296","DOIUrl":"https://doi.org/10.1002/tee.70296","url":null,"abstract":"<p>Anomaly detection under limited normal data remains a fundamental challenge due to severe class imbalance and scarcity of anomalies. We propose a novel framework that reformulates support vector selection in One-Class SVM as a sequential decision-making problem. Based on the intuition of OCSVM, we treat support vectors as an <i>a priori</i> assumption for kernel approximation, rather than a posterior outcome of optimization. A Deep Q-Network (DQN) agent adaptively selects representative subsets guided by validation feedback, thereby inducing a task-aware low-rank kernel approximation, while ridge-regularized weight recovery ensures numerical stability. Extensive experiments on multiple tabular benchmarks covering diverse imbalanced anomaly detection scenarios show that the proposed method consistently outperforms traditional methods, deep learning models, and LLM-based baselines in both ranking and classification metrics, demonstrating particularly strong generalization to unseen data and across diverse datasets. © 2026 The Author(s). <i>IEEJ Transactions on Electrical and Electronic Engineering</i> published by Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 12","pages":"1922-1934"},"PeriodicalIF":1.0,"publicationDate":"2026-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/tee.70296","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149311728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Baseline Comparative Study of Supervised Machine Learning Algorithms for Japanese Email Spam Detection 日本垃圾邮件检测中监督机器学习算法的基线比较研究
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-11-03 Epub Date: 2026-08-06 DOI: 10.1002/tee.70394
Manabu Ishihara
{"title":"A Baseline Comparative Study of Supervised Machine Learning Algorithms for Japanese Email Spam Detection","authors":"Manabu Ishihara","doi":"10.1002/tee.70394","DOIUrl":"https://doi.org/10.1002/tee.70394","url":null,"abstract":"<p>This letter presents a baseline comparative study of six supervised machine learning algorithms—Linear Support Vector Machine, SVM with RBF kernel, Decision Tree, Random Forest, Naive Bayes, and Logistic Regression—for detecting spam in Japanese email. Feature vectors were constructed using MeCab-based morphological segmentation and Bag-of-Words representations. We systematically varied part-of-speech configurations, training data volume, and spam–ham ratios. Results indicate that noun-dominant features yield superior discrimination and that dataset scale and class balance strongly govern performance. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 12","pages":"1958-1960"},"PeriodicalIF":1.0,"publicationDate":"2026-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149311731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Trend Prediction Method for Rumor Coupling Propagation in Multilingual Environments 多语言环境下谣言耦合传播的趋势预测方法
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-11-03 Epub Date: 2026-06-11 DOI: 10.1002/tee.70293
Zhengbin Wang, Xiaoming Wang, Yaguang Lin
{"title":"A Trend Prediction Method for Rumor Coupling Propagation in Multilingual Environments","authors":"Zhengbin Wang,&nbsp;Xiaoming Wang,&nbsp;Yaguang Lin","doi":"10.1002/tee.70293","DOIUrl":"https://doi.org/10.1002/tee.70293","url":null,"abstract":"<p>In view of the increasingly close integration trend of artificial intelligence and online social networks (OSNs), research on rumor propagation in multilingual environments (MEs) has become a key issue for maintaining the order of network information. First, this paper proposes a multilingual rumor coupling propagation model that describes the mechanisms of rumor coupling dissemination in OSNs by introducing a novel multilingual coupling state (MCS). Second, by constructing a Lyapunov function and applying the Routh–Hurwitz criterion, we theoretically establish the stability properties of the equilibria under different conditions. Finally, numerical simulations, including parameter sensitivity analysis and a real-world case study, demonstrate that the proposed S2LCR model with MCS can effectively describe rumor propagation mechanisms in MEs and accurately predict the spreading trend. The models and methods proposed herein can be applied to multilingual information governance scenarios such as social media, providing strong support and scientific basis for improving the controllability of information dissemination, optimizing public opinion guidance, and formulating emergency response strategies in such scenarios. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 12","pages":"1888-1902"},"PeriodicalIF":1.0,"publicationDate":"2026-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149311797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Compact Semantic-Aware Priors for Large-Margin Few-Shot Classification 面向大余量少样本分类的紧凑语义感知先验
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-11-03 Epub Date: 2026-04-29 DOI: 10.1002/tee.70302
Jiaying Wu, Jingyu Chen, Jia Luo, Jinglu Hu
{"title":"Compact Semantic-Aware Priors for Large-Margin Few-Shot Classification","authors":"Jiaying Wu,&nbsp;Jingyu Chen,&nbsp;Jia Luo,&nbsp;Jinglu Hu","doi":"10.1002/tee.70302","DOIUrl":"https://doi.org/10.1002/tee.70302","url":null,"abstract":"<p>Few-shot image classification seeks to recognize novel categories from only a handful of annotated examples, yet current Bayesian-style methods often depend on coarse priors extracted from base-class statistics that fail when support samples drift away from class centers. We introduce Compact Semantic-Aware Priors (CSAP)—a Bayesian framework that leverages lightweight, keyword-level semantics to build reliable and discriminative priors while explicitly enlarging inter-class margins. Instead of aligning visual features with high-dimensional sentence embeddings, CSAP distills a small set of salient word vectors generated directly from class labels, yielding a compact semantic space that robustly estimates cross-class similarity, selects the most informative base categories, and tightens posterior decision boundaries. Extensive experiments on two real-world benchmarks show that CSAP surpasses state-of-the-art counterparts by 1.96%–5.29% under both 1-shot and 5-shot settings, confirming the efficacy of compact semantic-aware priors for large-margin few-shot classification in the wild. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 12","pages":"1866-1876"},"PeriodicalIF":1.0,"publicationDate":"2026-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149312734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Development of a Handheld Hotspot Detecting Device Based on YOLOv5 Application on Thermal Images of Photovoltaic Panels 基于YOLOv5的手持式热点检测装置在光伏板热图像上的应用
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-10-04 Epub Date: 2026-09-02 DOI: 10.1002/tee.70421
Nguyen Phuoc Hoang Khang, Duong Minh Hai, Nguyen Chi Nhan
{"title":"Development of a Handheld Hotspot Detecting Device Based on YOLOv5 Application on Thermal Images of Photovoltaic Panels","authors":"Nguyen Phuoc Hoang Khang,&nbsp;Duong Minh Hai,&nbsp;Nguyen Chi Nhan","doi":"10.1002/tee.70421","DOIUrl":"https://doi.org/10.1002/tee.70421","url":null,"abstract":"<p>The booming of solar power systems has led to an increasing demand for monitoring and maintenance of solar panels. Hotspots on photovoltaic panels are a common dysfunction when operating solar power systems, reducing the generated power, system's efficiency, PV panel's lifespan and potentially causing serious hazard. Therefore, quick and accurate hotspots detection is important for maintenance, operation and safety. With the development of machine learning methods application in engineering, the combination of a machine learning model capable of detecting hotspots with thermal camera devices has high potential to improve the hotspot detection for better maintenance process. The main trend of research in the field is the application of UAV to collect thermal images of PV panels from aerial view to maximize monitoring area. However, UAV applications are facing many restrictions in several regions due to military capability, weather conditions and wide area requirements in operation. On the other hand, because of its complexity and flying control tasks, there is limited room for integration of machine learning models in UAV applications for real-time hotspot detection. Currently on the market, most existing devices and manufacturers still haven't applied AI achievements into products. This research is about the designing, developing and testing of a handheld hotspot detecting device with YOLOv5 application to process captured thermal images to detect hotspot area appeared. The development of the device included case designing, electronic designing, user interface designing and firmware development. The developed device using common components of Raspberry Pi 4, thermal camera with application of pre-trained YOLOv5 model with features of capturing and detecting hotspot areas on resulting thermal images and displaying result images on device's interface. Although the design is primitive with limited processing speed of 0.7 FPS when performing real time detections using YOLOv5 model, the device has capability of an Edge-AI device to apply in PV panels hotspot detection. Furthermore, the research also shows the requirements and difficulties in work-flow design when integrating machine learning models into practical applications and real time performance devices. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 11","pages":"1743-1750"},"PeriodicalIF":1.0,"publicationDate":"2026-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149099627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Design and Vibration Noise Analysis of Hybrid Magnetic Core for a Transformer 变压器混合磁芯设计及振动噪声分析
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-10-04 Epub Date: 2026-03-06 DOI: 10.1002/tee.70278
Chengcheng Liu, Weisong Li, Zhigang Zhao, Youhua Wang
{"title":"Design and Vibration Noise Analysis of Hybrid Magnetic Core for a Transformer","authors":"Chengcheng Liu,&nbsp;Weisong Li,&nbsp;Zhigang Zhao,&nbsp;Youhua Wang","doi":"10.1002/tee.70278","DOIUrl":"https://doi.org/10.1002/tee.70278","url":null,"abstract":"<p>Amorphous alloy is widely used in fabricating the core and shield part of transformers because of its low loss characteristic. However, it also suffers the disadvantages of low saturation flux density and great magnetostrictive effect. In this paper, a hybrid magnetic core structure is proposed to release above problems: specifically, oriented silicon steel (GOES) is utilized to design the inner core to improve the working flux density and reduce the vibration while the amorphous alloy is used to design the outer core to reduce the core loss. First, an equivalent magnetic circuit model of the hybrid magnetic core is established. The permeability of adopted two soft magnetic materials is iterated for obtaining accurate flux density distribution in each section of the hybrid magnetic core. In addition, the vibration and noise analysis model of the magnetic core is developed, and the calculated performance is verified by the measured results. Finally, the performance of a three-phase five-column transformer designed with the hybrid magnetic core is compared with the benchmark transformer with the amorphous alloy and GOES cores. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 11","pages":"1665-1674"},"PeriodicalIF":1.0,"publicationDate":"2026-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149099459","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Deep Transfer Convolutional Neural Network Framework for Microgrid Fault Detection 微电网故障检测的深度传递卷积神经网络框架
IF 1 4区 工程技术
IEEJ Transactions on Electrical and Electronic Engineering Pub Date : 2026-10-04 Epub Date: 2026-04-05 DOI: 10.1002/tee.70287
Zhaoqiang Su, Wei Jiang
{"title":"A Deep Transfer Convolutional Neural Network Framework for Microgrid Fault Detection","authors":"Zhaoqiang Su,&nbsp;Wei Jiang","doi":"10.1002/tee.70287","DOIUrl":"https://doi.org/10.1002/tee.70287","url":null,"abstract":"<p>Microgrid fault detection is challenged by diverse operating modes, nonlinear system dynamics, and limited availability of labeled fault data. Conventional threshold-based and model-based methods often exhibit reduced robustness under noise and multi-parameter fault conditions, while data-driven machine learning approaches typically require extensive training data. This paper proposes a Deep Transfer Convolutional Neural Network (DTCNN) framework for microgrid fault detection, leveraging a pretrained VGG-16 model to enhance feature extraction under limited data conditions. Voltage, current, and frequency signals are transformed into time–frequency spectrograms using the Short-Time Fourier Transform (STFT), enabling effective representation of transient and steady-state fault characteristics. Simulation results based on an industrial park microgrid demonstrate that the proposed DTCNN consistently outperforms conventional machine learning methods, including Support Vector Machines and Random Forests, in terms of accuracy, recall, and F1 score. Moreover, the proposed framework maintains stable detection performance across different operating modes and load conditions, indicating strong robustness and generalization capability. These results suggest that deep transfer learning provides an effective and practical solution for reliable microgrid fault detection. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.</p>","PeriodicalId":13435,"journal":{"name":"IEEJ Transactions on Electrical and Electronic Engineering","volume":"21 11","pages":"1656-1664"},"PeriodicalIF":1.0,"publicationDate":"2026-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149099575","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书