检索结果-内蒙古大学图书馆

14th Mediterranean Conference on Power Generation Transmission, Distribution and Energy Conversion, MEDPOWER 2024

作者： Kawathas, Theodoros E. Konstantopoulos, George C. Department of Electrical and Computer Engineering University of Patras Rion26504 Greece

ISBN: (纸本)9781837242689

In this paper, a novel distributed integral control algorithm is proposed that enhances the resilience of power systems consisting of inverter-interfaced Distributed Energy Resources (DERs). Utilising the structure of the bounded integral controller, the proposed solution achieves frequency restoration, voltage regulation and accurate active and reactive power sharing among the inverters, while inherently satisfying a given apparent power constraint for each inverter via its unique dynamic structure. The boundedness property of the controller is analytically proven using invariance set theory. Furthermore, in the case where one or more inverters reach their apparent power limit as a result of a disturbance (e.g. change in load demand, cyber-attack etc.), the non-compromised inverters restore the grid frequency to its nominal value and continue to share the active and reactive power among them, while the compromised units are automatically excluded from the power sharing procedure, hence enhancing the system resilience. The effectiveness of the proposed controller in achieving the desired control tasks, even in presence of cyber attacks, is validated using a 4-node microgrid with 4 inverter-interfaced DERs created in the Typhoon HIL real time digital simulator. © The Institution of engineering & technology 2024.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Short- and Medium-Term electrical Load Forecasting in Bangladesh Using Machine Learning Approaches

Short- and Medium-Term Electrical Load Forecasting in Bangla...

引用

2024 International Conference on Advances in Computing, Communication, electrical, and Smart Systems, iCACCESS 2024

作者： Cheragee, Sheikh Hasib Pall, Shuvo Chandra Kanchan, Muntasir Hasan Islam, Md. Samiul Tarek, Muhammad Masud Joy, Shoriful Huq Rahman, Md Toufiqur Bangladesh University of Engineering and Technology Electrical and Electronic Engineering Dhaka Bangladesh State University of Bangladesh Computer Science and Engineering Dhaka Bangladesh University of Rajshahi Electrical and Electronic Engineering Rajshahi Bangladesh

ISBN: (纸本)9798350350289

Planning and managing a power grid relies heavily on accurate predictions of future load. Operational choices involving resource utilization, infrastructural management, implementation schedule planning, investment plans, and maximizing power use while minimizing waste due to under or over-generation all rely on load prediction. In this study, it is utilized three different machine learning algorithms for medium- and short-term load forecasting, namely K-Nearest Neighbors (KNN) based Regression, Random Forest (RF) based regression, and Decision Tree (DT) Regression, to see how well these methods work on half-hourly historical electricity load data from the Bangladesh Power system (BPS) network, which can be found on the Power Grid Company of Bangladesh (PGCB) website and was downloaded between January 2021 and December 2022. To determine the most appropriate method for load forecasting of BPS, a comparison is made between the three approaches concerning the accuracy, mean absolute percentage error (MAPE), root means squared error (RMSE), and mean squared error (MSE). According to the findings, the RF model is superior to the others in making short- and medium-term forecasts due to its greater accuracy, minimal MSE, RMSE, and MAPE. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

The Cybernetic Artificial Intelligence (CAI): Α new scientific field for modelling and controlling Complex Dynamical Systems 22

The Cybernetic Artificial Intelligence (CAI): Α new scienti...

引用

22nd IFAC Conference on technology, Culture and International Stability, TECIS 2024

作者： Groumpos, Peter P. Department of Electrical and Computer Engineering University of Patras Greece26550 Greece

Artificial Intelligence (AI) has been considered a revolutionary and world-changing science, although it is still a young field and has a long way to go before it can be established as a viable theory. Every day, new knowledge is created at an unthinkable speed, and the Big Data Driven World is already upon us. AI has developed a wide range of theories and software tools that have shown remarkable success in addressing difficult and challenging societal problems. However, the field also faces many challenges and drawbacks that have led some people to view AI with skepticism. One of the main challenges facing AI is the difference between correlation and causation, which plays an important role in AI studies. Additionally, although the term Cybernetics should be a part of AI, it was ignored for many years in AI studies. To address these issues, the Cybernetic Artificial Intelligence (CAI) field has been proposed and analyzed here for the first time. The Fuzzy Cognitive Map approach is used for creating new knowledge. An algorithm for developing the CAI approach is proposed. The only hope for the survival of the planet lies in the quick development of Cybernetic Artificial Intelligence (CAI). The importance of differentiating between professional/personal ethics and eternal values is highlighted, and their importance in future AI applications is emphasized for solving challenging societal problems. Ultimately, the future of AI heavily depends on accepting certain ethical values and the acceptance of the CAI as a viable new scientific field. © 2024 The Authors. This is an open access article under the CC BY-NC-ND license.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis Between H∞ and Sliding Mode Controllers on Automatic Voltage Regulator System 2

A Comparative Analysis Between H∞ and Sliding Mode Controll...

引用

2nd International Conference on Power, electrical, Electronics and Industrial Applications, PEEIACON 2024

作者： Dev, Soumik Ahmed, Anis Khulna University of Engineering & Technology Department of Electrical and Electronic Engineering Khulna9203 Bangladesh

ISBN: (纸本)9798331517984

This study addresses the design of two robust controller types for automatic voltage regulators (AVRs): H∞ and sliding mode controllers (SMC). Two AVR transfer function models were studied- the third-order model and the second-order approximate model. The AVR's performance criteria included rise time, settling time, overshoot percentage, and ITAE (Integral Time Absolute Error). A tan hyperbolic function was used to lessen the chattering effect in SMC. In terms of parametric uncertainties, SMC was found more robust than the H-infinity controller. The effect of injecting disturbance in the system was also studied. The entire design and simulation was done through the MATLAB Simulink software. © 2024 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

A Web Application Based Mental Health & Illness Diagnosis with Machine Learning Approach and NLP Based Chat System 5

A Web Application Based Mental Health & Illness Diagnosis wi...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Etika, Rawshan Tabbasum Progga, Tasnuva Tasnim Khan, Mohammad Monirujjaman North South University Department of Electrical and Computer Engineering Dhaka Bangladesh

ISBN: (纸本)9798331530013

This research aims to transform mental health care by addressing critical gaps in existing systems and making support universally accessible free of cost. A centralized platform with a dynamic website has been developed, integrating advanced technologies for mental health illness early detection and an empathetic chatbot that responds personalized to users' emotional needs such as identifying issues and showing guidance, ensuring timely interventions The platform is designed to support individuals facing mental health challenges who may lack access to traditional therapy due to financial or other constraints, combining early detection models for mental health disorders with a compassionate chatbot that offers guidance and emotional support.. The outcome achieves high reliability and effectiveness, with detection models reaching prominent accuracy rates: 97% for depression detection (AdaBoost), 92% for suicidal tendencies (Stochastic Gradient method), and 89% for stress (Naive Bayes). NLTK is used to process the chats through a series of steps like tokenization and following entity classifiers for a better understanding of the chats and to give efficient responses to users' queries. This research Integrates vital mental health resources into a free, accessible platform, addressing a substantial gap in mental health care today. Additionally, the platform offers a curated list of certified mental health professionals and care homes for those seeking professional support when it's needed. © 2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Realtime Person Identification via Gait Analysis Using IMU Sensors on Edge Devices

Realtime Person Identification via Gait Analysis Using IMU S...

引用

2024 International Conference on Neuromorphic Systems, ICONS 2024

作者： Venkatachalam, Shanmuga Nair, Harideep Vellaisamy, Prabhu Zhou, Yongqi Youssfi, Ziad Shen, John Paul Carnegie Mellon University Department of Electrical & Computer Engineering United States

ISBN: (纸本)9798350368659

All individuals have a unique gait signature, or walking style, that can serve as their biometric identifier. While recent research has shown that deep neural networks can perform effective gait recognition, these studies often prioritize classification accuracy with little regard to model complexity and hardware efficiency. In this paper, an efficient four-layered convolutional neural network (CNN) model is proposed for real-time gait-based person identification targeting edge devices such as wearables, microcontrollers, and neuromorphic chips. This model is trained on a public gait dataset augmented with custom collected data, totaling to 24 classes. Despite its relatively small size (236 KB), the model achieves a high accuracy of 96.7%. It delivers fast inference time of 70 ms requiring only 5 KB of RAM and consumes just 125 mW power during continuous inference on an Arduino Nano 33 BLE Sense. Model efficacy is further demonstrated by converting proposed CNN to a spiking neural network (SNN) and running realtime inference on BrainChip's neuromorphic platform, Akida SoC, within 72 mW power. © 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

Pedestrian wind flow prediction using spatial-frequency generative adversarial network

引用

Building Simulation 2024年第2期17卷 319-334页

作者： Pengyue Wang Maozu Guo Yingeng Cao Shimeng Hao Xiaoping Zhou Lingling Zhao School of Architecture and Urban Planning Beijing University of Civil Engineering and ArchitectureBeijing100044China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing100044China School of Electrical and Information Engineering Beijing University of Civil Engineering and ArchitectureBeijing100044China School of Computer Science and Technology Harbin Institute of TechnologyHarbin150001China

Pedestrian wind flow is a critical factor in designing livable residential environments under growing complex urban *** pedestrian wind flow during the early design stages is essential but currently suffers from inefficiencies in numerical *** learning,particularly generative adversarial networks(GAN),has been increasingly adopted as an alternative method to provide efficient prediction of pedestrian wind ***,existing GAN-based wind flow prediction schemes have limitations due to the lack of considering the spatial and frequency characteristics of wind flow *** study proposes a novel approach termed SFGAN,which embeds spatial and frequency characteristics to enhance pedestrian wind flow *** the spatial domain,Gaussian blur is employed to decompose wind flow into components containing wind speed and distinguished flow edges,which are used as the embedded spatial *** information of wind flow is obtained through discrete wavelet transformation and used as the embedded frequency *** spatial and frequency characteristics of wind flow are jointly utilized to enforce consistency between the predicted wind flow and ground truth during the training phase,thereby leading to enhanced *** results demonstrate that SFGAN clearly improves wind flow prediction,reducing Wind_MAE,Wind_RMSE and the Fréchet Inception Distance(FID)score by 5.35%,6.52%and 12.30%,compared to the previous best method,*** also analyze the effectiveness of incorporating the spatial and frequency characteristics of wind flow in predicting pedestrian wind *** reduces errors in predicting wind flow at large error intervals and performs well in wake regions and regions surrounding *** enhanced predictions provide a better understanding of performance variability,bringing insights at the early design stage to improve pedestrian wind *** proposed spatial-frequen

关键词： pedestrian wind flow prediction generative adversarial network Gaussian kernel wavelet transform objective function

来源：评论

学校读者我要写书评

暂无评论

A novel online reinforcement learning-based linear quadratic regulator for three-level neutral-point clamped DC/AC inverter

Energy Conversion and Economics

引用

Energy Conversion and Economics 2024年第5期5卷 281-292页

作者： Qie, Tianhao Zhang, Xinan Xiang, Chaoqun Iu, Herbert Ho Ching Fernando, Tyrone Department of Electrical Electronic and Computer Engineering The University of Western Australia Perth Australia School of Traffic and Transportation Engineering Central South University Changsha China

This article proposes a novel online reinforcement learning-based linear quadratic regulator for the three-level neutral-point clamped DC/AC voltage source inverter. The proposed controller employs online updated fixed-weight recurrent neural network (NN) and policy iteration to dynamically adjust the optimal control gains based on real-time measurements without any knowledge of the system model or offline pre-training. Moreover, it produces a constant switching frequency with low current harmonics. Compared to the existing control methods, it provides superior control performance, guaranteed control stability, and simplified NN design. Experimental results are presented to verify the effectiveness of the proposed control method. © 2024 The Author(s). Energy Conversion and Economics published by John Wiley & Sons Ltd on behalf of The Institution of engineering and technology and the State Grid Economic & Technological Research Institute Co., Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Low-Cost Inertial Measurement Unit for Ship Motion Estimation

A Low-Cost Inertial Measurement Unit for Ship Motion Estimat...

引用

2024 Panhellenic Conference on Electronics and Telecommunications, PACET 2024

作者： Papafotis, Konstantinos Georgousis, Georgios Oustoglou, Costas Dimas, Christos Sotiriadis, Paul P. National Technical University of Athens Department of Electrical and Computer Engineering Greece

ISBN: (纸本)9798350318845

This paper presents the development of an Inertial Measurement Unit (IMU) tailored for maritime applications. Leveraging cost-effective MEMS sensors, the IMU integrates a 3-axis accelerometer and a 3-axis gyroscope. Utilizing a Kalman filter for roll, pitch, and yaw estimation, and an algorithm based on the Fast Fourier Transform (FFT) for heave, sway, and surge estimation, the proposed IMU enables comprehensive motion analysis for ships. The proposed system efficiently manages all required data processing, and does not relies on the ship's infrastructure highlighting the feasibility of utilizing low-cost MEMS sensors and embedded systems for accurate and reliable motion estimation in maritime environments. The accuracy of the proposed system is experimentally determined by using a high-accuracy IMU as reference. © 2024 IEEE.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

Gated Inference Network: Inference and Learning State-Space Models 38

Gated Inference Network: Inference and Learning State-Space ...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Hashempoor, Hamidreza Choi, Wan Seoul National University Department of Electrical and Computer Engineering Korea Republic of

This paper advances temporal reasoning within dynamically changing high-dimensional noisy observations, focusing on a latent space that characterizes the nonlinear dynamics of objects in their environment. We introduce the Gated Inference Network (GIN), an efficient approximate Bayesian inference algorithm for state space models (SSMs) with nonlinear state transitions and emissions. GIN disentangles two latent representations: one representing the object derived from a nonlinear mapping model, and another representing the latent state describing its dynamics. This disentanglement enables direct state estimation and missing data imputation as the world evolves. To infer the latent state, we utilize a deep extended Kalman filter (EKF) approach that integrates a novel compact RNN structure to compute both the Kalman Gain (KG) and smoothing gain (SG), completing the data flow. This design results in a computational cost per step that is linearly faster than EKF but introduces issues such as the exploding gradient problem. To mitigate the exploding gradients caused by the compact RNN structure in our model, we propose a specialized learning method that ensures stable training and inference. The model is then trained end-to-end on videos depicting a diverse range of simulated and real-world physical systems, and outperforms its counterparts -RNNs, autoregressive models, and variational approaches- in state estimation and missing data imputation tasks. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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：