检索结果-内蒙古大学图书馆

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Rokocakau, Samuela Tresca, Giulia Mohammadzadeh, Behrouz Zanchetta, Pericle Cirrincione, Giansalvo Cirrincione, Maurizio University of Pavia Department of Electrical Computer and Biomedical Engineering Pavia Italy University of Picardie Jules Verne Laboratory of Novel Technologies Amiens France University of the South Pacific School of Information Technology Engineering Mathematics and Physics Suva Fiji Belfort90010 Cedex France

ISBN: (纸本)9798350376067

In this work, a novel Hybrid 1-D Convolutional Transformer Neural Network is utilized for diagnosing faults in a Cascaded H-Bridge PMSM drive system. This innovative method exhibits high precision in open-circuit switch fault detection and localization for multi-class classification. The neural network model is used to assess the overall health status, locate faulty modules, faulty phase leg localization and identify individual switch faults in two different Cascaded H-Bridge topologies: one H-Bridge per phase (Topology I) and three H-Bridges per phase (Topology II) PMSM drive systems. The study showcases the prediction accuracy, reliability, and robustness of the neural network models for both topologies. In Topology I, the model achieved accuracy rates above 99% in its fault detection and localization tasks, with an average prediction time of around 1ms per sample for all considered diagnostic scenarios. Despite Topology II being more complex. the model had prediction accuracy rates exceeding 98% and an average prediction time between 1.5ms and 9ms per sample for all its considered diagnostic scenarios. Both drive system topologies resulted in minimal memory usage of approximately 2MB and 2.1MB, respectively. © 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

Fault Diagnosis using 1-D Convolutional Transformer Hybrid Neural Network for Cascaded H-Bridge Converters

Fault Diagnosis using 1-D Convolutional Transformer Hybrid N...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

ISBN: (纸本)9798350376067

In this work, the 1-D Convolutional Transformer Hybrid Neural Network is compared to other deep learning and non-neural techniques for Open Switch Fault Detection and Localization in a Cascaded H-Bridge Converter. The novel approach outperforms others in multiclass classification switch fault detection and localization. Two H-Bridge topologies are analyzed, with the hybrid neural network achieving high prediction accuracy in both. Key metrics like prediction accuracy, speed and memory size highlight the architecture's advantages. The models detect overall system health, locate faulty phase modules and identify single switch faults, reaching accuracy rates of up to 99% and 98% for Topologies I and II, respectively. The model size is approximately 2MB for both topologies, with average prediction times of 1ms for Topology I. Topology II's 2-class scenario for overall health status has an average prediction time of 9ms, while other scenarios take 1.5ms. The advancement of AI-based technologies can help improve the reliability and robustness of inverter systems by understanding and implementing strategies discussed in this paper. © 2024 IEEE.

关键词： cascaded H-bridge convolution fault detection fault diagnostics localization multi-head attention non-neural PMSM drive power converter transformer neural network

来源：评论

学校读者我要写书评

暂无评论

A Wireless Power Transfer Antenna and Active Rectifier System Compatible with Qi and AirFuel Standards

A Wireless Power Transfer Antenna and Active Rectifier Syste...

引用

International Symposium on Power Electronics, electrical Drives, Automation and Motion, SPEEDAM

作者： Elisabetta Moisello Alberto Cattani Piero Malcovati Edoardo Bonizzoni Department of Electrical Computer and Biomedical Engineering University of Pavia Italy STMicroelectronics Cornaredo Italy

ISBN: (数字)9798350387599

ISBN: (纸本)9798350387605

This paper proposes a dual-standard antenna configuration and active rectifier circuit for wireless power transfer (WPT), compatible with both AirFuel and Qi requirements. The proposed antenna configuration performance, considering the measured characteristics of available coils on the market, was evaluated by means of Cadence Virtuoso simulations and compared to the state-of-the-art, verifying its advantages. The proposed active rectifier circuit was designed in a 90-nm BCD process and enables reconfigurability depending on the operating frequency. A complete WPT system model, including a power transmitter (TX) and the proposed dual-standard antenna and active rectifier (AR) system, was simulated in Cadence Virtuoso for a wide range of conditions, deriving the efficiency breakdown of the overall system. In this way, a detailed performance evaluation of the proposed antenna configuration and active rectifier circuit was provided.

关键词： Antenna measurements Coils Electric breakdown Atmospheric modeling Transmitting antennas Rectifiers Wireless power transfer

来源：评论

学校读者我要写书评

暂无评论

Comparing Beta Regression and Quantile Regression Forests for Probabilistic Photovoltaic Energy Forecasting ⁎

引用

IFAC-PapersOnLine 2025年第1期59卷 325-330页

作者： Marco Capelletti Valentina Fogli Edoardo Santilli Matteo Gardini Riccardo Vignali Giuseppe De Nicolao Department of Electrical Computer and Biomedical Engineering University of Pavia Italy Global Quants & Risk Modeling Eni Plenitude S.p.A.

This work focuses on the analysis of probabilistic power curve models that link the energy production of a photovoltaic system with the irradiance forecasts of the weather provider. It is shown that the essential information is provided by global horizontal irradiance (GHI) forecasts, which can be used to obtain simple and meaningful probabilistic models using non-parametric (quantile Regression forests) and parametric (Beta regression) methods. The second step is the analysis of the monthly performance of power curve models, to understand whether their performance can improve by taking monthly variability into account.

关键词： Renewable energy forecasting Estimation learning Statistical data analysis Solar power forecasting Generalized linear models Quantile regression forest

来源：评论

学校读者我要写书评

暂无评论

Day-ahead Optimal Scheduling of Microgrids Participating in Multiple Energy Markets

Day-ahead Optimal Scheduling of Microgrids Participating in ...

引用

2024 IEEE PES Innovative Smart Grid Technologies Europe Conference, ISGT EUROPE 2024

作者： Kivi, Mohsen M. Achnib, Asma Damm, Gilney Bosisio, Alessandro Shirvani, Rouzbeh Institut de Recherche Estp 28 Avenue du Président Wilson CachanF-94230 France University of Pavia Department of Electrical Computer and Biomedical Engineering Pavia Italy Paris93162 France

ISBN: (纸本)9789531842976

Local flexibility markets (LFMs) have emerged as a promising solution for integrating Distributed Energy Resources into the distribution network, helping to address challenges such as grid stability and congestion. However, the optimal strategies for Microgrids (MG) and aggregators to effectively participate in these markets remain largely unexplored. This paper presents a multi-objective optimization approach for the day-ahead scheduling of MG in LFMs and day-ahead (DA) energy markets. By developing a detailed MG model with various distributed energy resources and storage systems, the study aims to minimize operational costs while maximizing market participation and revenue. A comparative case study highlights the economic benefits of dual-market participation over a single DA market strategy. © 2024 IEEE.

关键词： Distributed energy

来源：评论

学校读者我要写书评

暂无评论

Advanced IoT-Based Wireless Sensors for Remote Geotechnical Monitoring and Structural Diagnostics

引用

IFAC-PapersOnLine 2024年第9期58卷 193-198页

作者： Martin Pies Jan Velicka Radovan Hajovsky Department of Cybernetics and Biomedical Engineering Faculty of Electrical Engineering and Computer Science VSB-Technical University of Ostrava 17.listopadu 15 Ostrava Czech Republic

This paper presents an innovative design and implementation of a wireless sensor module using low-power Internet of Things (IoT) technologies for applications in geotechnical engineering and structural diagnostics, with a main focus on monitoring rock formations below the water surface in areas without access to electrical power. Designed for continuous monitoring of linear displacements and other critical parameters in structural engineering, geotechnical engineering and engineering diagnostics, this sensor module is particularly useful in remote locations. Utilizing wireless data transmission and advanced IoT technologies such as LoRa, IQRF and NB-IoT, this system allows for flexible coverage options and efficient remote management. The system allows users to remotely change measurement parameters, the period of messaging and set thresholds for alarm activation. The study highlights the importance of innovative IoT solutions to improve accuracy and efficiency in monitoring geotechnical and civil engineering structures, especially in challenging sub-surface environments, opening new opportunities for predictive maintenance and risk management in these specific applications.

关键词： Multi sensor systems Networks of sensors actuators Measurement instrumentation IoT Sensor Networks Geotechnical Monitoring Wireless Data Transmission Underwater Rock Formations Remote Energy-independent Systems

来源：评论

学校读者我要写书评

暂无评论

MedDock: A 3D-Printed Smart Pill Dispenser with Sensitive Textile Sensor for Adherence Monitoring

MedDock: A 3D-Printed Smart Pill Dispenser with Sensitive Te...

引用

International Workshop on Wearable and Implantable Body Sensor Networks (BSN)

作者： Mehmet Seckin Shehjar Sadhu Md Abdullah Al Rumon Madison Gravel Heather DiFazio Nicholas Johnson Kaci Perry Dhaval Solanki Kunal Mankodiya Department of Electrical Computer and Biomedical Engineering University of Rhode Island Kingston RI USA

ISBN: (数字)9798331530143

ISBN: (纸本)9798331530150

One-fifth of adults in United States take at least five daily prescription medications. Maintaining a consistent medication schedule is particularly challenging for individuals with neurodegenerative disorders due to declines in cognitive and motor skills. For example, individuals with Parkinson's disease experience impaired fine motor skills and tremors, which can lead to difficulty in handling small pills or opening standard medication bottles. Additionally, the complexity of medication regimens in these patients further complicates timely and accurate medication intake management. Using a medication dispenser can help patients maintain independence in management thereby reducing caregiver burden. In this work, we introduce MedDock, a medication management system featuring a 3D-printed smart cap and a textile-based force-resistive sensor designed to automatically dispense medication at pre-set times without the users need to open the bottle cap. The MedDock device is equipped with an ESP8266 Wi-Fi Microcontroller Unit and servo motors that control the pill dispensing mechanism at regular intervals. The textile sensor is used to detect pill drop (i.e., when the pill is dispensed) and pill pick up (i.e., when the pill is taken by the user). To test the feasibility of our system we conducted an in-home experiment (N=8 healthy participants; 4 female, 4 male; 54–85 years old). The system was deployed for 3 days to the participant's home. To analyze the feasibility, we evaluated the time elapsed between pill drop and pill intake which was found to be on average of 15.97 (±7.53) seconds. We present the design, comprehensive benchtop testing, and results from an in-home deployment study, demonstrating the feasibility and effectiveness of MedDock in supporting and monitoring medication adherence.

关键词： Schedules Medical services Reliability biomedical monitoring Servomotors Monitoring Wireless fidelity Standards Textiles Testing

来源：评论

学校读者我要写书评

暂无评论

Autoregressive Modeling of Time Series in Renewable Energy Systems

Autoregressive Modeling of Time Series in Renewable Energy S...

引用

IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)

作者： Kaan Icer Showrov Rahman Kaushallya Adhikari Department of Electrical Computer and Biomedical Engineering University of Rhode Island Kingston RI USA

ISBN: (数字)9798331540906

ISBN: (纸本)9798331540913

Autoregressive (AR) models have been increasingly used to forecast solar irradiance and estimate state-of-charge (SOC) in energy storage systems (ESSs). This work aims to apply AR models to real SOC and solar irradiance measurements. We determine the AR model coefficients using the modified covariance method while we estimate the model order using three standard metrics: final prediction error (FPE), Akaike information criterion (AIC), and criterion autoregressive transfer function (CAT). Additionally, we also evaluate the model order that minimizes the spectral Kullback-Leibler divergence between the data periodogram and the AR power spectral density estimates corresponding to the three metrics. We assess the model accuracy using root mean squared error (RMSE) and demonstrate that the lowest RMSE is generally achieved with higher model orders. The comparative analysis of the data collected under different weather conditions reveals that partly cloudy conditions are the most challenging.

关键词： Measurement Solar irradiance Clouds Time series analysis Estimation Transfer functions Predictive models Data models Standards Meteorology

来源：评论

学校读者我要写书评

暂无评论

(Invited) Air-Permeable MXene Electrode with Miura-ori Structure for Biosensing

(Invited) Air-Permeable MXene Electrode with Miura-ori Struc...

引用

243rd ECS Meeting

作者： Lin, Tzu-En Tsai, Chih-Ning Yang, Pei-Wen Huang, Chih-Ching Institute of Biomedical Engineering National Yang Ming Chiao Tung University Hsinchu300 Taiwan Department of Electrical and Computer Engineering College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu300 Taiwan Department of Bioscience and Biotechnology National Taiwan Ocean University Keelung202 Taiwan

ISBN: (纸本)9781607685395

In this work, we present an air-permeable MXene electrode capable of recording surface electromyographic (sEMG) signals on the skin surface based on the Miura-ori structure. MXene is a two-dimensional (2D) nanomaterial composed of transition metal carbides, nitrides, and carbonitrides developed in recent years. Taking advantage of the Miura-ori structure, MXene-based electrodes have high breathability as well as low and stable electrode-skin interfacial impedances, facilitating long-Term reliable electrophysiological monitoring. The electrolytic gel on conventional wet Ag/AgCl gel electrodes increases the impedance between the electrode and the skin as it gradually dries, inhibits sweat evaporation and affects signal acquisition. Therefore, we provide a fascinating electrode design that can be used to obtain high-quality sEMG signals for assessing body movements such as swallowing. © 2023 ECS-The Electrochemical Society.

关键词： Electrodes

来源：评论

学校读者我要写书评

暂无评论

Recommendation System for Relational Data Using Relational Hard C-Means

Recommendation System for Relational Data Using Relational H...

引用

International Conference on electrical engineering/Electronics, computer, Telecommunications and Information Technology, ECTI-CON

作者： Peerawich Phaknonkul Sansanee Auephanwiriyakul Nipon Theera-Umpon Computer Engineering Department Faculty of Engineering Chiang Mai University Chiang Mai Thailand Computer Engineering Department Faculty of Engineering Biomedical Engineering Institute Biomedical Engineering and Innovation Research Center Chiang Mai University Chiang Mai Thailand Electrical Engineering Department Faculty of Engineering Biomedical Engineering Institute Biomedical Engineering and Innovation Research Center Chiang Mai University Chiang Mai Thailand

ISBN: (数字)9798350381559

ISBN: (纸本)9798350381566

In several online services, automatic recommendation systems are needed to provide good experiences to users. There are four general recommendation types. One of them is the recommendation system based on the demographics information. Usually, the data used in the recommendation system has a relation among itself. Therefore, we introduced a demographics recommendation system using the relation Hard C-means (RHCM). In particular, the RHCM was applied to segment the data and create multi-prototypes. To make a recommendation, the k-NN was used. We tested our system on a bike sales transactions data set. We found that the average accuracy and Jaccard index for the 1st to 4th test data sets were 0.324 and 0.182, respectively.

关键词： Accuracy Telecommunications Indexes Information technology Recommender systems

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：