检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Signal, control and Communication, SCC 2023

作者： Assadi, Khaoula Slimane, Jihane Ben Salhi, Salah University of Tunis El Manar National Engineering School of Tunis LR11ES20 Analysis Design and Control of Systems Laboratory Tunis1002 Tunisia Northern Border University Faculty of Computing and InformationTechnology Department of Computer Sciences Rafha91911 Saudi Arabia

ISBN: (纸本)9798350326390

The electrical power transmission lines play a crucial role in maintaining a continuous electricity supply. However, the exposed environment of these lines increases the risks of faults occurrence, necessitating prompt detection, and classification, to eliminate them within a specified time. In light of this, the present study introduces a methodology for the detection and classification of faults in a three-phase transmission line system employing the Extreme Learning Machine (ELM). A 220 kV, 300 km three-phase transmission line system was simulated in MATLAB/Simulink software, where the current and voltage signals were generated under different fault conditions including fault types, fault inception time, and fault resistance. The fundamental components of these signals were used as inputs in the ELM model. Different shunt fault types, including line-to-ground, line-to-line, double-line-to-ground, triple-line, and triple-line-to-ground were applied for fault detection and classification framework. Furthermore, the optimum number of hidden neurons in the ELM model was investigated in this study. In terms of the Mean Squared Error (MSE) and correlation coefficient, four ELM variants based on Sine, Sigmoid, Radial Basis, and Triangular Basis transfer functions were assessed for each module. The outcome of these metrics indicates that the ELM with the sigmoid model demonstrated superior performance compared to the other ELM models. Based on statistical metrics MSE, Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE), and also the computational time, the efficiency of ELM-Sigmoid and state-of-the-art methods of Multi-Layer Perceptron Neural Network (MLPNN) and Radial Basis Function Neural Network (RBFNN) were compared and analyzed during training and testing phases. The results obtained revealed that the ELM-Sigmoid model outperforms the other models in the detection and classification of shunt faults with significant accuracy and fast computational speed. ©

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

The automated Temperature Measuring System Based on Single-Dimensional Distributed Sensor

The Automated Temperature Measuring System Based on Single-D...

引用

2022 International Conference on Industrial engineering, Applications and Manufacturing, ICIEAM 2022

作者： Akhmetov, E.A. Belashova, E.S. Gashigullin, D.A. Kazan State Power Engineering University Division of Industrial Heat Power and Heating Systems Kazan Russia Kazan National Research Technical University Named after A. N. Tupolev - Kai Department of Computer Systems Kazan Russia Kazan National Research Technical University Named after A. N. Tupolev - Kai Department of Automated Design Systems Kazan Russia

ISBN: (纸本)9781665483698

The automated temperature measuring system based on a single-dimensional distributed sensor was created. The principle of an automated temperature measurement system based on a single-dimensional distributed sensor is innovative, as well as in demand from the point of view of reducing the cost of production. The developed system based on a single-dimensional distributed sensor can be used, for example, both in the field of robotics and in the field of flowmetry (when using it as a thermal anemometer). The proposed system includes a single-dimensional distributed sensor (SDDS) connected to a personal computer (PC) to obtain data about the measured environment using software (for example, LabVIEW). The system provides the measurement of the ambient temperature. Sensors based on the p-n junction are used. The system is operated using the software. There is a function to store temperature data. © 2022 IEEE.

关键词： Temperature measurement

来源：评论

学校读者我要写书评

暂无评论

Study of the Shock Loads Effect on the Operation of Multi-Motor Electric Drives of a Rolling Mill with a Second-order Elastic Coupling 5

Study of the Shock Loads Effect on the Operation of Multi-Mo...

引用

5th IEEE International Conference on Modern Electrical and Energy System, MEES 2023

作者： Tytiuk, Valerii Kalinin, Alexey Druzhinin, Valeriy Kuznetsov, Vitalii Chornyi, Oleksii Busher, Victor Kryvyi Rih National University Department of Electromechanics Kryvyi Rih Ukraine Abylkas Saginov Karaganda Technical University Npjsc Department of Informative Computer Systems Karaganda Kazakhstan Karaganda Industrial University Npjsc Department of Power Engineering Temirtau Kazakhstan Ukrainian State University of Science and Technologies Department of the Electrical Engineering Dnipro Ukraine National University Institute of Electromechanics Energy Saving and Automatic Control Systems Kremenchuk Mykhailo Ostrogradskyi Kremenchuk Ukraine National University "odessa Maritime Academy" Dept. of Electrical Engineering and Electronics Odessa Ukraine

ISBN: (纸本)9798350359787

This paper presents a study for optimizing a hot rolling mill. The paper is devoted to the study of ways to reduce the effect of shock loads of synchronous electric drives of the roughing mill group on the relative lengthening of the metal strip in the inter-stand gap of the rolling stands of the finishing mill group. The elasticity of the metal strip in the inter-stand gap of the rolling mill has a significant impact on the movement of intercoupled multi-motor electric drives of the finishing mill group. Another crucial route of exposure that influences the motion of the electric drives within the finishing mill group involves the electromagnetic connection between the drives in the roughing and finishing mill groups. The impact of the electromagnetically connected circuits is evident through the effect of shock loads from synchronous electric drives on the angular velocity of the direct current electric drives within the finishing mill group. The characteristics of the electromagnetic communication circuit are established by the power grid arrangement and equipment specifications. To assess the quality of work of electric drives of the finishing mill group, it is proposed to use the relative lengthening of the metal strip in the inter-stand gap, which is an important indirect indicator of the quality of rolling. The mathematical model of a hot rolling mill that takes into account both the elasticity of the metal strip that connects the DC electric drives of the finishing group, and the electromagnetic coupling circuit that takes into account the impact loads of synchronous electric drives of the roughing group on the example of the mill 1700 of ArcelorMittal Temirtau JSC was proposed in this paper. Using the mathematical model developed in Simulink software using the methods of planning the experiment, regression models were obtained to establish the dependence of the parameters of overexcitation of a synchronous motor on the magnitude of the voltage sag in the no

关键词： Electric loads

来源：评论

学校读者我要写书评

暂无评论

Bleeding Simulation with Physical Visco-Elasticity and its Application to Virtual Surgery

SSRN

引用

SSRN 2023年

作者： Sun, Pengyu Liu, Peter Xiaoping School of Mechanical Electronic and Control Engineering Beijing Jiaotong University Beijing100044 China Department of Systems and Computer Engineering Carleton University OttawaON Canada

Background and objectives: Being composed of blood cells and plasma, the blood flow has different rheological properties from common fluids. However, current bleeding simulations mostly focus on the morphology of blood, but ignore the special rheological properties of blood flow. In this paper, we consider the effect of the aggregation behavior of red blood cells on the blood flow process, in order to improve the visual fidelity of bleeding ***: In particular, the elastic force caused by viscoelastic fluid elasticity is incorporated into the standard N-S momentum equation, and an improved momentum equation which characterizes the rheological characteristics of viscoelastic blood is constructed. The obtained new momentum equation is solved by using the smooth particle hydrodynamic (SPH) *** and Conclusions: The effect of introducing elastic force on the motion of particles is analyzed from the microscopic particle perspective by designing a two-dimensional particle system. Simulation results show that the presented method improves the simulation realism of the diffusion process of viscoelastic blood, and in the meantime, eliminates the discontinuous boundary due to blood gushing out of the wound. Additionally, the presented method is able to simulate the viscoelastic rheological properties of bleeding without significant distortion even when the number of bleeding particles is small. © 2023, The Authors. All rights reserved.

关键词： Navier Stokes equations

来源：评论

学校读者我要写书评

暂无评论

control of Nonlinear systems Under Multiple Time-Varying Output Constraints: A Single Funnel Approach

Control of Nonlinear Systems Under Multiple Time-Varying Out...

引用

IEEE Conference on Decision and control

作者： Farhad Mehdifar Lars Lindemann Charalampos P. Bechlioulis Dimos V. Dimarogonas Division of Decision and Control Systems KTH Royal Institute of Technology Stockholm Sweden Thomas Lord Department of Computer Science University of Southern California Los Angeles CA USA Department of Electrical and Computer Engineering Division of Systems and Control University of Patras Patra Greece

This paper proposes a novel control framework for handling (potentially coupled) multiple time-varying output constraints for uncertain nonlinear systems. First, it is shown that the satisfaction of multiple output constraints boils down to ensuring the positiveness of a scalar variable (the signed distance from the time-varying output-constrained set's boundary). Next, a single funnel constraint is designed properly, whose satisfaction ensures convergence to and invariance of the time-varying output-constrained set. Then a robust and low-complexity funnel-based feedback controller is designed em-ploying the prescribed performance control method. Finally, a simulation example clarifies and verifies the proposed approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Non-euclidean monotone operator theory and applications

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 14872-14904页

作者： Alexander Davydov Saber Jafarpour Anton V. Proskurnikov Francesco Bullo Center for Control Dynamical Systems and Computation University of California Santa Barbara Santa Barbara CA Department of Electrical Computer and Energy Engineering University of Colorado Boulder Boulder CO Department of Electronics and Telecommunications Politecnico di Torino Turin Italy

While monotone operator theory is often studied on Hilbert spaces, many interesting problems in machine learning and optimization arise naturally in finite-dimensional vector spaces endowed with non-Euclidean norms, such as diagonally-weighted ℓ1 or ℓ1 norms. This paper provides a natural generalization of monotone operator theory to finitedimensional non-Euclidean spaces. The key tools are weak pairings and logarithmic norms. We show that the resolvent and reected resolvent operators of non-Euclidean monotone mappings exhibit similar properties to their counterparts in Hilbert spaces. Furthermore, classical iterative methods and splitting methods for finding zeros of monotone operators are shown to converge in the non-Euclidean case. We apply our theory to equilibrium computation and Lipschitz constant estimation of recurrent neural networks, obtaining novel iterations and tighter upper bounds via forward-backward splitting.

关键词： non-Euclidean norms monotone operator theory fixed point equations nonexpansive maps

来源：评论

学校读者我要写书评

暂无评论

State Derivative Normalization for Continuous-Time Deep Neural Networks

arXiv

引用

arXiv 2024年

作者： Weigand, Jonas Beintema, Gerben I. Ulmen, Jonas Görges, Daniel Tóth, Roland Schoukens, Maarten Ruskowski, Martin Chair of Machine Tools and Control Systems RPTU Kaiserslautern The German Research Center for Artificial Intelligence Kaiserslautern Germany Group The Department of Electrical Engineering Eindhoven University of Technology Netherlands The Systems and Control Laboratory The Institute for Computer Science and Control Budapest Hungary Institute for Electromobility RPTU Kaiserslautern Germany

The importance of proper data normalization for deep neural networks is well known. However, in continuous-time state-space model estimation, it has been observed that improper normalization of either the hidden state or hidden state derivative of the model estimate, or even of the time interval can lead to numerical and optimization challenges with deep learning based methods. This results in a reduced model quality. In this contribution, we show that these three normalization tasks are inherently coupled. Due to the existence of this coupling, we propose a solution to all three normalization challenges by introducing a normalization constant at the state derivative level. We show that the appropriate choice of the normalization constant is related to the dynamics of the to-be-identified system and we derive multiple methods of obtaining an effective normalization constant. We compare and discuss all the normalization strategies on a benchmark problem based on experimental data from a cascaded tanks system and compare our results with other methods of the identification literature. © 2024, CC BY-SA.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Adversarial Attacks Against Uncertainty Quantification

arXiv

引用

arXiv 2023年

作者： Ledda, Emanuele Angioni, Daniele Piras, Giorgio Fumera, Giorgio Biggio, Battista Roli, Fabio Department of Computer Control and Management Engineering Sapienza University of Rome Italy Department of Electric and Electronic Engineering University of Cagliari Italy Department of Informatics Bioengineering Robotics and Systems Engineering University of Genova Italy

Machine-learning models can be fooled by adversarial examples, i.e., carefully-crafted input perturbations that force models to output wrong predictions. While uncertainty quantification has been recently proposed to detect adversarial inputs, under the assumption that such attacks exhibit a higher prediction uncertainty than pristine data, it has been shown that adaptive attacks specifically aimed at reducing also the uncertainty estimate can easily bypass this defense mechanism. In this work, we focus on a different adversarial scenario in which the attacker is still interested in manipulating the uncertainty estimate, but regardless of the correctness of the prediction;in particular, the goal is to undermine the use of machine-learning models when their outputs are consumed by a downstream module or by a human operator. Following such direction, we: (i) design a threat model for attacks targeting uncertainty quantification;(ii) devise different attack strategies on conceptually different UQ techniques spanning for both classification and semantic segmentation problems;(iii) conduct a first complete and extensive analysis to compare the differences between some of the most employed UQ approaches under attack. Our extensive experimental analysis shows that our attacks are more effective in manipulating uncertainty quantification measures than attacks aimed to also induce misclassifications. © 2023, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Adversarial Attacks Against Uncertainty Quantification

Adversarial Attacks Against Uncertainty Quantification

引用

International Conference on computer Vision Workshops (ICCV Workshops)

作者： Emanuele Ledda Daniele Angioni Giorgio Piras Giorgio Fumera Battista Biggio Fabio Roli Department of Computer Control and Management Engineering Sapienza University of Rome Italy Department of Informatics Bioengineering Robotics and Systems Engineering University of Genova Italy Department of Electric and Electronic Engineering University of Cagliari Italy

Machine-learning models can be fooled by adversarial examples, i.e., carefully-crafted input perturbations that force models to output wrong predictions. While uncertainty quantification has been recently proposed to detect adversarial inputs, under the assumption that such attacks exhibit a higher prediction uncertainty than pristine data, it has been shown that adaptive attacks specifically aimed at reducing also the uncertainty estimate can easily bypass this defense mechanism. In this work, we focus on a different adversarial scenario in which the attacker is still interested in manipulating the uncertainty estimate, but regardless of the correctness of the prediction; in particular, the goal is to undermine the use of machine-learning models when their outputs are consumed by a downstream module or by a human operator. Following such direction, we: (i) design a threat model for attacks targeting uncertainty quantification; (ii) devise different attack strategies on conceptually different UQ techniques spanning for both classification and semantic segmentation problems; (iii) conduct a first complete and extensive analysis to compare the differences between some of the most employed UQ approaches under attack. Our extensive experimental analysis shows that our attacks are more effective in manipulating uncertainty quantification measures than attacks aimed to also induce misclassifications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decentralised Iterative Learning control for High Performance Collaborative Tracking Problem with Output Constraints

Decentralised Iterative Learning Control for High Performanc...

引用

UKACC International Conference on control (control)

作者： Bin Chen Bing Chu Department of Automatic Control and Systems Engineering University of Sheffield Sheffield U.K. School of Electronics and Computer Science University of Southampton Southampton U.K.

ISBN: (数字)9798350374261

ISBN: (纸本)9798350374278

High performance collaborative tracking problem, requiring a group of independent subsystems to generate a global output that can precisely track the desired reference in a repetitive manner, has found lots of applications in practice. However, for such an important control task, existing iterative learning control (ILC) methods have not considered the constraint on each subsystem's output, which leads to potential risk within the control process. This paper proposes a novel optimisation based ILC method to address the high performance collaborative tracking problem with output constraints. The proposed ILC framework can guarantee not only each subsystem's output constraint is always satisfied during the control process, but also the monotonic convergence of a well-defined performance index to a possibly minimum value. To avoid huge computational complexity for large scale systems, we further apply the idea of the alternative direction method of multipliers (ADMM) to implement the proposed ILC frame-work in a decentralised manner, which allows the resulting decentralised methods to be applied to large scale and changing systems. Moreover, the decentralised ILC method proposed in this paper is suitable for non-minimum phase, heterogeneous and/or homogeneous systems, which is appealing in practice. Convergence properties of the proposed ILC algorithms are analysed rigorously, and numerical examples are given to demonstrate the algorithms' effectiveness.

关键词： Collaboration Process control Performance analysis Large-scale systems Task analysis Computational complexity Optimization

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：