检索结果-内蒙古大学图书馆

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Wright, Robert Fajri, Poria Fu, Xingang Asrari, Arash University of Nevada Reno Department of Electrical and Biomedical Engineering Reno United States Purdue University Northwest Department of Electrical and Computer Engineering Hammond United States

ISBN: (纸本)9798350376067

Rotating machines, such as Induction Motors (IMs), play critical functions for industrial equipment, owing to their reliability and robustness. However, costly downtime occurs when these motors sustain faults, such as damaged bearings. Condition-Based Monitoring (CBM) methods and early fault detection are paramount in safeguarding machinery from unexpected damage and downtime. With the rapid development of artificial intelligence, Machine Learning (ML) techniques have emerged at the forefront of monitoring the health of IMs. This paper contributes a study comparing single and double-channel phase current approaches towards Convolutional Neural Networks (CNN) employing Short-Time Fourier Transform (STFT) based spectrograms. Motor current signals can be readily and non-invasively collected from the motor compared to other signals. Regarding classification accuracy, the double-channel method is an effective approach for bearing fault classification using motor phase current signals. © 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

Design of a Standalone Hybrid Renewable Energy System - A Hospital in Lafayette, Indiana, USA 5

Design of a Standalone Hybrid Renewable Energy System - A Ho...

引用

5th IEEE International Conference on Communication, Computing and Industry 6.0, C2I6 2024

作者： Thapa, Samir Asrari, Arash Naderi, Ehsan Fajri, Poria Purdue University Northwest Department of Electrical and Computer Engineering HammondIN United States Arkansas State University College of Engineering and Computer Science Department of Electrical Engineering JonesboroAR United States University of Nevada Department of Electrical and Biomedical Engineering RenoNV United States

ISBN: (纸本)9798350379884

This paper presents the design of a standalone hybrid renewable energy system (HRES) for a hospital in Lafayette, Indiana, USA, to enhance energy reliability and reduce costs. The proposed system integrates photovoltaic (PV) panels, wind turbines, batteries, and a backup diesel generator. Using Hybrid Optimization Model for Electric Renewables (HOMER) software, the system is optimized for cost-effectiveness and sustainability, while electrical Transient Analyzer Program (ETAP) software is employed to ensure a safe operation under varying conditions. Results verify that the developed HRES meets the hospital's energy needs, significantly reduces operational costs, and minimizes carbon emissions, offering a sustainable model for healthcare facilities. © 2024 IEEE.

关键词： Windmill

来源：评论

学校读者我要写书评

暂无评论

Induction Motor Fault Diagnosis Using Shifting Window Data Augmentation of Current Signals

Induction Motor Fault Diagnosis Using Shifting Window Data A...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

ISBN: (纸本)9798350376067

Deep learning models have been shown to be capable of enhancing Condition-Based Monitoring (CBM) methods for rotating machinery, such as Induction Motors (IMs). However, the performance of these models heavily depends on the training set's size as well as how the signals are presented to the model. Once a model is trained on segmented signals over a fixed period, its accuracy can decline when the system is tested on randomly sampled signals. Meanwhile, models trained using data augmentation techniques can be generalized better to unforeseen conditions. This paper introduces a method to augment the phase current signals during training using a shifting window technique. Regarding classification accuracy, this method is demonstrated as a practical approach for generalizing the model and is shown to perform better than the current techniques. © 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

An experimental and numerical approach for optimization of internal and external corrugations with various geometries in cylindrical thin-walled concertina energy absorbers under quasi-static axial load

引用

Mechanics of Advanced Materials and Structures 2024年第25期31卷 6628-6642页

作者： Rahpeima, Reza Nateghi Boroujeni, Iman Nia, Ali Alavi Graduate institute of biomedical electronics and bioinformatics College of Electrical Engineering and Computer Science National Taiwan University Taipei Taiwan Department of Mechanical Engineering Tarbiat Modares University Tehran Iran Department of Mechanical Engineering Bu-Ali Sina University Hamedan Iran

Thin-walled tubes have been extensively used as energy absorbers in many engineering structures that are under dynamic or quasi-static loads. In this article, the effect of corrugation and its geometry on the collapse characteristics of aluminum concertina tubes under quasi-static axial load is investigated both experimentally and numerically. The numerical simulations were performed with the use of LS-Dyna commercial software. Then, several chosen samples were tested experimentally to verify the results of the simulation. Forty different samples with four different corrugation geometries including singly isosceles triangular corrugation, continual isosceles triangular corrugation, continual scalene triangular corrugation, and continual semi-circular corrugation, and each with 10 different size dimensions were simulated. Among all of these simulations, six of them, each with two replicates were subjected to experimental tests. Experimental examples are aluminum cylindrical thin-walled tubes with the same thickness, height, and diameter that corrugations with different geometries are applied to them by the use of the cold rolling method. Finally, to describe the findings in more theoretical terms, a comparison between our obtained results and earlier theoretical investigations is made. The results show a significant influence of corrugations application on the improvement of the collapse characteristics of the cylindrical tubes so that the collapse style of intact tubes can be controlled by applying corrugations. The results show that by increasing the amplitude and number of corrugations, the absorbed energy, and the initial maximum force decrease. It is also found that among the different corrugation geometries, the corrugations with singly isosceles triangular geometry have the highest energy absorption as well as the lowest initial maximum force. © 2023 Taylor & Francis Group, LLC.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Application of TQWT based filter-bank for sleep apnea screening using ECG signals

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 893-904页

作者： Nishad, Anurag Pachori, Ram Bilas Acharya, U. Rajendra Discipline of Electrical Engineering Indian Institute of Technology Indore Indore453552 India Department of Electronics and Computer Engineering Ngee Ann Polytechnic Singapore599489 Singapore Department of Biomedical Engineering School of Science and Technology SIM University Singapore599491 Singapore Department of Biomedical Engineering Faculty of Engineering University of Malaya Kuala Lumpur50603 Malaysia

The sleep apnea is a disease in which there is the absence of airflow during respiration for at least 10 s. It may occur several times during the night sleep. This disease can lead to many types of cardiovascular diseases. To detect this disease, signals obtained from many channels of polysomnography are to be observed visually by physicians for the long duration. This procedure is expensive, time-consuming, and subjective. Hence, it is required to build an automated system to detect the sleep apnea with few channels. This paper uses single-lead electrocardiogram (ECG) signal to detect apneic and non-apneic events. The proposed method uses tunable-Q wavelet transform (TQWT) based filter-bank instead of TQWT to decompose the segment of ECG signal into several constant bandwidth sub-band signals. Then centered correntropies are computed from the various sub-band signals. The obtained features are then fed to the various classifiers to select the optimum performing classifier. In this work, we have obtained the highest classification accuracy, specificity, and sensitivity of 92.78%, 93.91%, and 90.95% respectively using random forest classifier. Hence, our developed prototype is ready for validation with the huge database and clinical usage. © Springer-Verlag GmbH Germany, part of Springer Nature 2018.

关键词： Filter banks

来源：评论

学校读者我要写书评

暂无评论

A Remedial Action Scheme Against False Data Injection Cyberattacks Targeting ULTC Transformers in Smart Distribution Systems

A Remedial Action Scheme Against False Data Injection Cybera...

引用

2024 IEEE IAS Industrial and Commercial Power System Asia, I and CPS Asia 2024

作者： Naderi, Ehsan Asrari, Arash Fajri, Poria College of Engineering and Computer Science Arkansas State University Department of Electrical Engineering JonesboroAR United States Purdue University Northwest Department of Electrical and Computer Engineering HammondIN United States University of Nevada Electrical and Biomedical Engineering Department RenoNV United States

ISBN: (纸本)9798350352290

This paper proposes an on-line remedial action scheme (OLRAS) in order to mitigate the voltage violations caused by false data injection attacks (FDIAs) targeting under load tap changing (ULTC) transformers in smart distribution systems. The FDIA framework contains two different phases. In the attack phase, distribution system operator (DSO), being in attacker's shoe, considers cyberattack scenarios through compromising the results of volt-var optimization problem in a radial distribution grid modified with distributed energy resources (DERs) such as photovoltaic (PV) units and wind turbines (WTs). The outcome of the attack phase will be the compromised voltage profile of the distribution grid showing different rates of voltage violations. In the reaction phase, the DSO rapidly identifies a customized distribution feeder reconfiguration (CDFR) in order to update the flows of active and reactive power throughout the targeted distribution system and recover the voltage profile. The objective functions of the proposed CDFR are defined to minimize the impacts of such cyberattacks targeting ULTCs within distribution grids. This will empower DSOs to react to severe cyberattacks, bypassing the detection stage, and address the voltage violations in a timely manner. The effectiveness of the proposed OLRAS is validated on an IEEE test system. © 2024 IEEE.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

Development of Novel-Epoxy-Based Transformer Bushing Insulator for High Breakdown Voltage (BDV) 3

Development of Novel-Epoxy-Based Transformer Bushing Insulat...

引用

3rd International Conference on Emerging Trends in electrical, Control, and Telecommunication engineering, ETECTE 2024

作者： Siddique, Abubakar Akram, Laraib Aslam, Waseem Mishal, Areeba Shahid, Muhammad Usama Ahmed, Haseeb Department of Electrical and Biomedical Engineering Khwaja Fareed University of Engineering and Information Technology Rahim Yar Khan Pakistan Department of Electrical Electronics & Computer Engineering University of Sargodha Sargodha Pakistan

ISBN: (纸本)9798331504861

In today’s trends, nanocomposites have garnered significant interest due to their potential to enhance dielectric properties and be used as insulators. Incorporating nanoparticles into the base epoxy makes achieving highly efficient dielectric materials feasible. However, the low electric field stress management capability and insufficient relative permittivity of typical epoxy provide a hindrance. Efforts have been made to overcome these limitations by adding nanosized fillers with high relative permittivity to the epoxy to enhance the dielectric properties. This research study focuses on the development of Novel-Epoxy-Based Transformer Bushing Insulator using nanomaterial Al2O3 and SiO2. The epoxy resin served as the base material, with nano-fillers added to improve its dielectric properties. The hardener was added to initiate the curing process and create a highly crosslinked structure. Surfactants were introduced to improve the interaction between the epoxy resin and nanoparticles. The nano-silica and nano-alumina particles were combined in different ratio configurations to create the nanocomposites by using the preparation method;Sol-Gel and Green Synthesis, which were subsequently tested for their dielectric properties. The proposed sample is the nanocomposite made by the green synthesis method and with the combination of 0.3 g + 0.3 g of the nanoparticle. Results show improved dielectric strength of the proposed nanocomposites compared to conventional porcelain materials. This paper presents an environment friendly approach for developing epoxy-based transformer bushing insulators, offering enhanced performance. ©2024 IEEE.

关键词： Permittivity

来源：评论

学校读者我要写书评

暂无评论

computer-free computational imaging: optical computing for seeing through random media

引用

Light(Science & Applications) 2022年第7期11卷 4-5页

作者： Yunzhe Li Lei Tian Department of Electrical and Computer Engineering Boston UniversityBostonMA02215USA Department of Biomedical Engineering Boston UniversityBostonMA02215USA

Diffractive Deep Neural Network enables computer-free,all-optical“computational imaging”for seeing through unknown random diffusers at the speed of light.

关键词： random free enable

来源：评论

学校读者我要写书评

暂无评论

Deep Semantic Segmentation of Echocardiographic Images using Vision Transformers

Deep Semantic Segmentation of Echocardiographic Images using...

引用

2023 IEEE International Ultrasonics Symposium, IUS 2023

作者： Bosco, Edoardo Casula, Filippo Cotogni, Marco Cusano, Claudio Matrone, Giulia University of Pavia Department of Electrical Computer and Biomedical Engineering Pavia Italy

ISBN: (纸本)9798350346459

Deep learning (DL) methods have revolutionized image segmentation by providing tools to automatically identify structures within images, with high levels of accuracy. In particular, Convolutional Neural Networks (CNN), such as the U-Net and its variants, have achieved remarkable results in many segmentation tasks. Only recently, Vision Transformer (ViT)-based models have emerged and in some cases demonstrated to outperform CNNs in semantic segmentation tasks. However, transformers typically require larger amounts of data for training as compared to CNNs. This can result in a significant drawback given the time-consuming nature of collecting and annotating data, especially in a clinical setting. In particular, only a few studies involved the application of ViT networks for ultrasound image *** this study, we propose one of the earliest applications of ViT-based architectures for segmenting the left heart chambers in 2D echocardiographic images. Indeed, the identification of cardiac structures, like e.g. heart chambers, can be used to derive relevant quantitative parameters, such as atrial and ventricular volumes, the ejection fraction, *** trained and tested several ViT models using the publicly available CAMUS dataset, composed by cardiac image sequences from 500 patients, with the corresponding mask labels of the left ventricle and left atrium. ViT networks performances were then compared to an implementation of the U-Net. We demonstrate how, on this type of data, recent ViT variants can reach and even outperform CNNs, despite the limited data availability. © 2023 IEEE.

关键词： Echocardiography

来源：评论

学校读者我要写书评

暂无评论

Lecture Hall Monitoring System using Access Control Mechanism at the University of Ghana 9

Lecture Hall Monitoring System using Access Control Mechanis...

引用

9th IEEE International Conference on Adaptive Science and Technology, ICAST 2024

作者： Adjaye, Aboagye Isaac Abdul-Kadir, Napari Kelly, Norman Michael, Amui Longdon, Sowah Nii Percy, Okae Alidu, Abubakari Kan-Dapaah, Kwabena University of Ghana Department of Computer Engineering Ghana Academic City University College Department of Electrical and Electronic Engineering Ghana University of Ghana Department of Biomedical Engineering Ghana

ISBN: (纸本)9798350385403

In an era where technology is evolving rapidly, there is a need to efficiently secure access control systems within educational institutions and office environments. Access control systems are crucial in ensuring the security and legal access to physical and digital resources. In this research, a system was designed and implemented to monitor the lecture hall and office environment within the School of engineering Sciences, University of Ghana. The system integrated multiple layers of access controls, including biometric fingerprint recognition, Radio Frequency Identification (RFID) card authentication, and personal identification number (PIN). A database was generated to identify people who use the facilities. This provided a robust and user-friendly hybrid system. The system leverages modern database technologies to record and manage access, enabling real-time monitoring of lecture halls and office spaces. Moreover, it offers a user-friendly interface for administrators, lecturers, lab attendants, and other users. The database generated could also be used to check class attendance. The results demonstrate significant improvements in security, attendance tracking, and overall access management efficiency in the School of engineering Sciences. © 2024 IEEE.

关键词： Radio frequency identification (RFID)

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：