检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Shi, Runwu Yen, Benjamin Nakadai, Kazuhiro Dept. of Systems & Control Engineering Tokyo Institute of Technology Tokyo Japan

This paper aims to achieve single-channel target speech extraction (TSE) in enclosures by solely utilizing distance information. This is the first work that utilizes only distance cues without using speaker physiological information for single-channel TSE. Inspired by recent single-channel Distance-based separation and extraction methods, we introduce a novel model that efficiently fuses distance information with time-frequency (TF) bins for TSE. Experimental results in both single-room and multi-room scenarios demonstrate the feasibility and effectiveness of our approach. This method can also be employed to estimate the distances of different speakers in mixed speech. Online demos are available at https://***/distance-demo-page/. Copyright © 2024, The Authors. All rights reserved.

关键词： Source separation

来源：评论

学校读者我要写书评

暂无评论

Challenges and Solutions for Practical Implementation of Process Bus Based Substation Protection and Automation System

Challenges and Solutions for Practical Implementation of Pro...

引用

2023 IEEE Asia Meeting on Environment and Electrical engineering, EEE-AM 2023

作者： Soetomo, Kevin Hamamatsu, Koichi Thuan, Dinh Huu Linh, Nguyen Manh Quang, Lai Vu Okai, Makoto Power Grid System Solutions Toshiba Energy Systems & Solutions Corporation Engineering Dept. Kawasaki Japan Technical Department Ho Chi Minh City Viet Nam Ltd. Engineering Dept. Hanoi Viet Nam Ltd. Sales & Engineering Division Hanoi Viet Nam Toshiba Energy Systems & Solutions Corporation Protection and Control Dept. Fuchu Japan

ISBN: (纸本)9798350381061

The protection and control system in substations has undergone significant evolution since the era of hardwired systems. In recent years, the increasing trend of digital transformation (DX) across various fields, including protection and automation systems, has led to the promotion of IEC 61850 process bus-based digital substations. However, recent analysis and evaluation have revealed numerous challenges in various aspects, such as technical issues, system performance, test methods, maintenance, and economic considerations. Moreover, many of these challenges lie outside the scope of international standards like IEC 61850 and IEC 61869. As a result, the worldwide implementation of digital substations has been hindered. This paper aims to describe the issues encountered during the implementation of process bus technology and propose solutions that focus on optimizing system configuration based on our experience in implementing digital substation projects and developing MU and IED. Addressing these issues is crucial to fully unlocking the potential of digital substations. One of the most promising advantages is the availability of digital data collected from substation equipment. By utilizing this data, overall power system operational efficiency can be enhanced, and equipment management can be optimized. Predictive maintenance can be implemented, enabling the early detection of potential equipment failures, minimizing unplanned outages, and reducing the need for emergency repairs, which contribute to unnecessary carbon emissions and equipment downtime. Ultimately, digital substations empower end-users to reduce greenhouse gas emissions, improve energy efficiency, and seamlessly integrate power systems, thereby supporting the carbon-neutral initiative and facilitating the transition towards a sustainable energy future. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Forecasting Breakdowns of Electric Motors of a Sugar Factory Using Machine Learning Methods 4

Forecasting Breakdowns of Electric Motors of a Sugar Factory...

引用

4th IEEE KhPI Week on advanced Technology, KhPI Week 2023

作者： Zaiets, Nataliia Vlasenko, Lidiia Lutska, Nataliia Zhyltsov, Andrii Dept. of Automation and Robotic Systems National University of Life and Environmental Sciences of Ukraine Kyiv Ukraine Dept. of Software Engineering and Cyber Security State University of Trade and Economics Kyiv Ukraine Dept. of Automation and Computer Technologies of Control Systems National University of Food Technologies Kyiv Ukraine Dept. of Electromagnetic Systems The Institute of Electrodynamics The National Academy of Sciences of Ukraine Kyiv Ukraine

ISBN: (纸本)9798350395532

The paper demonstrates the process of developing mathematical models for identifying breakdowns of electric motors using machine learning methods. The authors have developed three mathematical models for identifying breakdowns of electric drives with a power of 55 kW, 1500 rpm on the example of sugar production: model for quadratic discriminant analysis;binary classification decision tree;feedforward neural network model. The best structures and parameters of the models were determined by machine learning methods. The performance of the models on the training and test sets was more than 96% by F-score. It was proposed to use all three models independently for diagnosing breakdowns of electric drives, while the decision maker makes the final decision on the replacement or repair of electrical equipment. This approach is justified and effective because of the diversity of models. The developed models, except for assessing the state of the engine, can also be used for simulation modelling, forecasting, and serve as information support for process operators in organizing equipment maintenance. The availability of real-time information about the state of equipment in production will allow timely repair or replacement of equipment, thereby reducing the risks of stopping production and increasing the resource efficiency of technological processes. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A Review on Improvement in Detection of Cyberattacks Using Artificial Intelligence for the Grid Applications 11

A Review on Improvement in Detection of Cyberattacks Using A...

引用

11th IEEE Open Conference of Electrical, Electronic and Information Sciences, eStream 2024

作者： Vilkelyte, Zivile Wojciechowski, Jerzy Bojarczak, Piotr Fallah, Saad El Kharbach, Jaouad Jamil, Mohammed Ouazzani Vanagas, Jonas Vilnius TECH Dept. Electrical Engineering Vilnius Lithuania Casimir Pulaski University of Radom Dept. Control Systems and Electronics Radom Poland Fez Morocco Université Sidi Mohamed Ben Abdellah Faculté des Sciences Dhar El Mahraz Laboratoire de Physique de Solide Fez Morocco Vilnius TECH Vilnius Dept. Electrical Engineering Lithuania

ISBN: (纸本)9798350352412

The integration of artificial intelligence and machine learning technologies into critical infrastructures, such as smart grids, has raised significant concerns regarding cybersecurity. This paper explores the dual role of artificial intelligence and machine learning in both enhancing and challenging cybersecurity within smart grid systems. By analysing the current stateof-the-art research and technology, the utilisation of artificial intelligence and machine learning to fortify cybersecurity defences while addressing potential vulnerabilities. The the emergence of cyber threats targeting Internet-of-Things-based smart grids is highlighted and solutions to mitigate these risks are proposed. Through a comprehensive review of literature, the efficacy of artificial intelligence driven cybersecurity measures in detecting and preventing cyberattacks are evaluated. Additionally, challenges associated with implementing these solutions in smart grid environments, such as data complexity and computational requirements are taken into account. The findings underscore the critical importance of ongoing research and innovation to ensure the resilience of smart grid cybersecurity. © 2024 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Design and performance analysis of tetrafurcated optical fiber displacement sensors for enhanced range and linearity 11

Design and performance analysis of tetrafurcated optical fib...

引用

Photonic Instrumentation engineering XI 2024

作者： Zubia, Gorka Zubia, Joseba Durana, Gaizka Aldabaldetreku, Gotzon Amorebieta, Josu Dept. of Automatic Control and Systems Engineering University of the Basque Country Plaza Ingeniero Torres Quevedo 1 Bilbao48013 Spain Dept. of Communications Engineering University of the Basque Country Plaza Ingeniero Torres Quevedo 1 Bilbao48013 Spain Dept. of Applied Mathematics University of the Basque Country Plaza Ingeniero Torres Quevedo 1 Bilbao48013 Spain

ISBN: (纸本)9781510670464

Optical fiber displacement sensors (OFDS) offer several advantages over conventional sensors due to their compact size and immunity to electromagnetic interference. These are particularly useful for applications in confined spaces, including aeronautical turbines. The critical component of OFDS is the fiber bundle, whose response depends on the arrangement, radius, and number of fibers. We developed a straightforward yet effective method for designing OFDSs based on sensor specifications: working point, range, and sensitivity. This allows to determine the bundle geometry directly from the specified requirements. Among the explored designs, the tetrafurcated bundle stands out, composed by a transmitting fiber at the center, surrounded by three collections of receiving fibers. This paper demonstrates that tetrafurcated OFDS designs significantly enhance both the range and linearity. Additionally, they effectively reduce the dead zone of the sensors, enabling precise measurements even at very short distances. The design has been manufactured and experimentally validated. Simulation and measurements are in good agreement with an MSE of 0.26%. Our findings highlight the practicality and reliability of tetrafurcated OFDS designs, opening new possibilities for advanced displacement sensing applications. © 2024 SPIE.

关键词： Optical fibers

来源：评论

学校读者我要写书评

暂无评论

Funnel Neural Network Model Predictive control for a 4 DoF Robot Manipulator

Funnel Neural Network Model Predictive Control for a 4 DoF R...

引用

2024 Advances in Science and engineering Technology International Conferences, ASET 2024

作者： Stihi, Sana Aouaichia, Abdelhadi Gad, Omar Fareh, Raouf Khadraoui, Sofiane Bettayeb, Maamar Kara, Kamel University of Sharjah Dept. of Electrical Engineering Sharjah United Arab Emirates Laboratory of Electrical Systems and Remote Control Blida 1 University Algeria Dceies King Abdulaziz University Saudi Arabia

ISBN: (纸本)9798350344134

This paper introduces the design of a Prescribed Performance Neural Network Model Predictive control (PPNNMPC) tailored for a 4 Degrees of Freedom (DoF) robot manipulator in trajectory tracking applications. The design of the proposed controller is formulated using Model Predictive control (MPC) methodology, which has the advantage of predicting the system's future behavior to achieve optimal robot control. Then, the prescribed performance function is incorporated into the control law by integrating the transformed error in the optimization process. The Prescribed Performance Function (PPF) maintains the tracking error within predefined limits, enhancing the system's transient response. Furthermore, integrating Neural Networks (NN) and prescribed performance functions into the control law design mitigates the common computational time drawback associated with MPC. Simulation results emphasize the superior efficiency of the suggested controller in contrast to the traditional model predictive control, demonstrating reduced overshoot, small settling time, improved computational efficiency, and accurate tracking of desired set-points. © 2024 IEEE.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Sallen-Key Dual Channel Low-Pass Filter with Tunable Cutoff Frequency

Sallen-Key Dual Channel Low-Pass Filter with Tunable Cutoff ...

引用

2022 IEEE International Multi-Conference on engineering, Computer and Information Sciences, SIBIRCON 2022

作者： Denisenko, Darya Yu. Prokopenko, Nikolay N. Butyrlagin, Nikolay V. Dept. of Information Systems and Radio Engineering DTSU Rostov-on-Don Russia Dept. of Automatic Control Systems SFU Rostov-on-Don Russia Dept. of Information Systems and Radio Engineering DTSU Institute for Design Problems in Microelectronics of RAS Zelenograd Rostov-on-Don Russia

ISBN: (纸本)9781665464802

A two-channel Sallen-Key low-pass filter on three non-inverting amplifiers is studied, which has the property of unrelated digital set of the upper cut-off frequency at constant index of the transmission coefficient in the bandwidth range. The restructuring of the upper cutoff frequency and the attenuation of the pole is carried out by modify the resistors' resistance of one in the upper channel of the low-pass filter. It is shown that a non-inverting amplifier in the lower channel of the low-pass filter can have a small value of the systematic zero bias voltage component, what is important for the operation of the low-pass filter at the input of analog-to-digital converters. It has been established that due to the construction of a low-pass filter according to a two-channel architecture, the requirement for the magnitude of the output static voltage of the upper channel is removed. The base equations of the new low-pass filter scheme are given and the summary modeling in the Micro-Cap was pictured. © 2022 IEEE.

关键词： Cutoff frequency

来源：评论

学校读者我要写书评

暂无评论

Fractional Exponential Reaching Law Sliding Mode control for a Robot Manipulator Tracking Application 12

Fractional Exponential Reaching Law Sliding Mode Control for...

引用

2024 12th International Conference on systems and control, ICSC 2024

作者： Stihi, Sana Aouaichia, Abdelhadi Gad, Omar Fareh, Raouf Khadraoui, Sofiane Bettayeb, Maamar University of Sharjah Sharjah United Arab Emirates University of Blida 1 Laboratory of Electrical Systems and Remote Control Algeria University of Sharjah Dept. of Electrical Engineering Sharjah United Arab Emirates

ISBN: (纸本)9798331531812

This paper proposes a control strategy for a robot manipulator with four Degrees Of Freedom (DOF) that takes advantage of sliding mode control theory, exponential reaching law, and fractional calculus. Tracking the joint space trajec-tories with precision is the goal of the proposed Fractional Exponential reaching law Sliding Mode control (FrExpSMC). Utilizing fractional calculus in the sliding surface enhances the robustness of the exponential reaching mode against external disturbances. The fractional calculus expression of the sliding surface ensures a finite time convergence of the controller and provides the controller with a fast response in the transient phase. The proposed control approach's efficiency and performances are demonstrated by simulation on a model of a 4-DOF robot manipulator and compared to the conventional sliding mode control. The stability of the closed-loop system is proved using Lyapunov theory. The results indicate that the recommended control outperforms the conventional sliding mode control in both tracking performance and robustness against step disturbances. © 2024 IEEE.

关键词： Robot applications

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Battery Management System for an Electric Vehicle Powered by Solar PV Array 59

An Intelligent Battery Management System for an Electric Veh...

引用

59th International Universities Power engineering Conference, UPEC 2024

作者： Challoob, Ali Falih Bin Rahmat, Nur Azzammudin Ramachandaramurthy, Vigna K. Saeed, Nagham Humaidi, Amjad Jaleel Institute of Power Engineering Universiti Tenaga Nasional Strategic Planning Centre Malaysia School of Computing and Engineering University of West London London United Kingdom University of Technology Control and Systems Eng. Dept. Baghdad Iraq

ISBN: (纸本)9798350379730

Implementing a Battery Management System (BMS) in Electric Vehicles (EVs) offers several benefits that enhance the efficiency, security, and durability of the vehicle's battery system. The BMS oversees and controls the performance of each cell in the battery pack, guaranteeing that they function within predetermined voltage and temperature thresholds to maintain safety. In this paper, an intelligent BMS for an EV model powered by a solar PV array was proposed using a fuzzy logic (FL) controller. The proposed method was applied to EVs consisting of four Lithium-ion batteries. The simulation results are achieved using MATLAB/Simulink software. The estimation of the state of charge (SOC) for each battery was used as input to the FL which controls the discharging/ charging mode for each battery via power semiconductor switches. Three different scenarios are used to verify the suggested method. A full control FL operation was obtained, and the batteries were protected successfully against overcharging and over-discharging. © 2024 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Practical Numerical Modeling Approach for a Design of a Two-Dimensional Linear Synchronous Actuator 14

Practical Numerical Modeling Approach for a Design of a Two-...

引用

14th International Symposium on Linear Drivers for Industry Applications, LDIA 2023

作者： Ito, Noriaki Koseki, Takafumi Ohnishi, Wataru Nakamura, Yuichiro Takahashi, Kenji Sekiguchi, Hiroyuki The University of Tokyo Dept. of Electrical Engineering and Information Systems Tokyo Japan Advanced Technology R&d Center Mitsubishi Electric Corporation Hyogo Japan

ISBN: (纸本)9798350329612

This paper proposes the design of a magnetically levitated planar motor, the configuration of a basic numerical method to embody the control concept, and the design procedure for an experimental test rig. This motor is stable in the levitating direction but unstable in the driving direction because it utilizes the repulsive force between the stator permanent magnets and the moving coils. One problem with magnetically levitated planar motors is the time-consuming nature of the three-dimensional finite element analysis. This analysis requires significant computational resources and can result in significant delays in the design process. To address this problem, a less time-consuming method using Gaussian process regression is presented. In addition, the proposed analysis is verified using a test rig equipped with several sensors. These sensors will provide measurements of static force characteristics and flux linkage to evaluate the performance and effectiveness of the motor under various operating conditions. © 2023 IEEE.

关键词： Finite element method

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：