检索结果-内蒙古大学图书馆

Performance Analysis of Transfer-Learning Based Physics-Informed Neural Network for Effective Shape Variation Adaptation with Varying Hyper-parameters

引用

Transactions of the Korean Institute of Electrical Engineers 2023年第10期72卷 1149-1158页

作者： Han, Ji-Hoon Choi, Eui-Jin Hong, Sun-Ki Dept. of System and Control Engineering Hoseo University Korea Republic of Dept. of Information Control Engineering Hoseo University Korea Republic of

One of the most time-consuming parts of designing an electrical device is optimizing the geometry. Optimization involves fine-tuning dimensions such as slot widths and airgap lengths from a base geometry to meet user needs. FEA(Finite Element Analysis) is typically used to verify this performance. However, conventional FEA requires a separate analysis if the analysis geometry is varied even slightly. This causes a very long time consumption, and a transfer learning-based PINN(Physics-Informed Neural Network) is proposed to solve this problem. Since PINNs are at the basic level worldwide, their performance is analyzed according to hyper-parameters such as model parameters (e.g. weights or biases), preprocessing methods, activation functions, and the number of training data to increase their performance. Based on the analyzed hyper-parameters, the performance of the transfer learning-based PINN is verified under the condition of varying the airgap length of the E-I core. © 2023 Korean Institute of Electrical Engineers. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Home Care Assistance Solution based on a Software Multi-Agents system 24

Home Care Assistance Solution based on a Software Multi-Agen...

引用

24th International Conference on control systems and Computer Science, CSCS 2023

作者： Rasras, Mohammad Marin, Iuliana Radu, Serban University Politehnica of Bucharest Doctoral School of Automatic Control and Computers Bucharest Romania University Politehnica of Bucharest Dept. of Engineering in Foreign Languages Bucharest Romania University Politehnica of Bucharest Dept. of Computer Science Bucharest Romania

ISBN: (纸本)9798350313390

A smart home allows automated technology to control systems and appliances to assist daily life activities. In the current work, a prototype of a designed smart home health-aware system is presented. Three predefined ruled agents have been used to gather data, communicate between themselves, interpret the data based on several machine learning algorithms to predict abnormality for cardiac conditions. The paper also compares results obtained by running five machine learning algorithms. The agents function in accordance with predefined dataset describing residents ' age, gender, height, weight, systolic and diastolic blood pressure, cholesterol, and glucose levels, smoking and alcohol consumption habits, and lastly, physical activity. Our plan is to simplify ubiquitous health monitoring for smart home's residents. The proposed solution aims to monitor parametric measurements to alert health specialists in case of emergencies. © 2023 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

High-Speed Operational Amplifier with a Differentiating Circuit of Transient Correction

High-Speed Operational Amplifier with a Differentiating Circ...

引用

2024 Conference of Young Researchers in Electrical and Electronic engineering, ElCon 2024

作者： Titov, Alexey E. Alferova, Irina A. Kuznetsov, Dmitry V. Southern Federal University Dept. of Automatic Control Systems Rostov-on-Don Russia Don State Technical University Dept. of Scientific Research Rostov-on-Don Russia Don State Technical University Dept. of Cyber Security of Information Systems Rostov-on-Don Russia Don State Technical University Dept. of Information Systems and Radio Engineering Rostov-on-Don Russia

ISBN: (纸本)9798350360646

The relevance of the present research is related to the search for promising ideas for increasing the maximum slew rate of the output voltage (SRM) of new-generation operational amplifiers (OpAmps). Proposed circuit techniques that provide (with simultaneous use) an increase in SRM by more than 2 orders of magnitude. Such high-speed operational amplifiers are in demand today for application in drivers of high-speed ADCs (AD9208, AD9691, etc.), and as active elements in circuits of analog-to-discrete filters on switched capacitors. It is proposed to introduce (according to the developed rules) a nonlinear differentiating RC-circuit realized based on an additional differential stage and a differentiating capacitor of small capacitance into the classical OpAmps with one integrating correction capacitance. Such circuit "additives"practically do not change the low-signal dynamic and static parameters of the OpAmp, and at a large signal during the transient front, when the input stage enters the nonlinear mode, form a large current overcharge of the integrating correction capacitor. Consequently, the SRM of the OpAmp is significantly increased. © 2024 IEEE.

关键词： analog-to-digital converter analog-to-discrete filter maximum slew rate of output voltage nonlinear correction operational amplifier

来源：评论

学校读者我要写书评

暂无评论

Algorithms for Continuous Compression of Measurement Data Frames within the Spatial Approach

Algorithms for Continuous Compression of Measurement Data Fr...

引用

International Conference on control systems, Mathematical Modelling, Automation and Energy Efficiency (SUMMA)

作者： Ilya Bogachev Alexey Levenets En Un Chye Mark Sharapov Dept. of Automatic and System Engineering Pacific National University Khabarovsk Russia

Statement of the problem: for telemetry systems, among the variety of problems, we can distinguish a special class of problems related to the development of algorithms for continuous data processing. Their allocation into a separate class is due to the fact that within the framework of both the classical approach to compression and the spatial approach, this problem was considered strictly discretely, without taking into account deep correlations both in time between samples of the same source and between samples obtained in one point in time from different sources. Purpose of the study: development of effective adaptive and non-adaptive algorithms for continuous compression of measurement data frames. Results: algorithms for continuous compression of measurement data frames have been developed. A comparative analysis of the efficiency of their work and the work of a discrete compression algorithm based on the construction of prefix Huffman codes was carried out, which showed their significant superiority over this algorithm either in the compression ratio (adaptive algorithm) or in its speed (non-adaptive algorithm).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cascaded Predictive Speed control and Load Torque Rejection of PMSM

Cascaded Predictive Speed Control and Load Torque Rejection ...

引用

International Conference on system Theory, control, and Computing (ICSTCC)

作者： Madalin Costin Corneliu Lazar Dept. of Automatic Control and Applied Informatics "Gheorghe Asachi" Technical University of Iasi Iasi Romania Dept. of Automatic Control and Electrical Engineering "Dunarea de Jos" University of Galati Galati Romania

ISBN: (数字)9798350364293

ISBN: (纸本)9798350364309

In this paper, a new cascade control structure is proposed for model predictive control (MPC) of permanent magnet synchronous machine (PMSM). Based on the d-q model of the PMSM and the field-oriented control principle, the cascade structure consists of an inner loop for predictive control of d-q currents and an outer one for predictive control of speed and load torque rejection. To independently control the two currents in the inner loop, a decoupling algorithm was used, followed by MPC controllers that by their ability to manipulate the constraints in the design phase ensure efficient control considering the physical limitations of currents and voltages. Quadratic constraints of electrical signals are approximated by box constraints to reduce computational effort. For speed control and load torque rejection, an MPC controller with a measurable disturbance input is used in the outer loop. Since the load torque is not measurable, an observer was used to estimate it. The proposed predictive control structure for the PMSM was implemented in Matlab-Simulink using MPC controllers from the MPC Toolbox. The Simulink control scheme was used for the performance testing against classical PI controllers.

关键词： Torque PI control Current measurement Velocity control Predictive models Observers Mathematical models Torque measurement Voltage control Predictive control

来源：评论

学校读者我要写书评

暂无评论

A Study On Suitable Electrodes For Low-Energy Power Generation From Carbon Waste in Factories

A Study On Suitable Electrodes For Low-Energy Power Generati...

引用

2023 International Electrical engineering Congress, iEECON 2023

作者： Channgamthiang, Surasak Nusukhon, Pheeraphat Chansri, Pakpoom King Mongkut's University of Technology Thonburi Dept. Electrical Technology Education Bangkok Thailand King Mongkut's University of Technology Thonburi Dept. Control System and Instrumentation Engineering Bangkok Thailand

ISBN: (纸本)9798350332360

Factory waste includes the incomplete combustion of industrial fuels that causes carbon to precipitate in vents. These carbons might be put to good use. Therefore, the impact of using waste carbon in factories to produce electricity is investigated in this study by evaluating electrical characteristics: the type of electrode material's suitability, the size of the electrode's carbon contact surface area, and the distance between the electrodes. According to the findings, the maximum open circuit voltage (Voc) was 1.09 V for copper (+) and zinc (-) electrode materials, 1.11 V for the electrode's carbon contact surface area, and 1.29 V for the electrodes' spacing. The maximum of Voc was 1.11 V, maximum on-load voltage and current were 0.64V, 124.65 mA for optimum electrode carbon contact surface size 40 cm2. Optimum electrode distance at 2 cm that maximum open circuit voltage (Voc) was 1.29 V. The maximum load voltage and current were 0.77V, 128.32mA. Factory waste carbon can be useful in some applications for producing electricity from waste carbon and assisting in the reduction of factory waste. © 2023 IEEE.

关键词： Carbon

来源：评论

学校读者我要写书评

暂无评论

Online PD Measurement by Detecting the Pulsed Compensating Current in High Voltage Equipment 8

Online PD Measurement by Detecting the Pulsed Compensating C...

引用

8th International Conference on engineering, Applied Sciences, and Technology, ICEAST 2022

作者： Srinangyam, Chissanupong Pannil, Pittaya Nimsanong, Phethai Chuayin, Chaitawat Thungsook, Kittisak Pattanadech, Norasage School of Engineering King Mongkut's Institute of Technology Ladkrabang Electrical Engineering Dept. Bangkok Thailand School of Engineering King Mongkut's Institute of Technology Ladkrabang Instrumentation and Control Engineering Dept. Bangkok Thailand Power System Operation and Control Section 2 Power System Control Dept. Metropolitan Electricity Authority Bangkok Thailand School of Engineering Rajamangala University of Technology Rattanakosin Electrical Engineering Dept. Bangkok Thailand

ISBN: (数字)9781665459198

ISBN: (纸本)9781665459198

This paper discusses the pulsed compensating current caused by partial discharge (PD) phenomena that flows inside the electrical equipment installed in the power system. Such electrical equipment like to be the capacitive coupler in the partial discharge test circuit. In order to study the pulsed compensating current of the PD measurement, artificial PD source such as corona, surface, and internal was used in this experiment. The electrical equipment like surge arrester combined with HFCT sensor utilized to detect the PD pulse current. Furthermore, this proposed technique has been applied for online PD measurement in substations. It was found that the surge arrester could compensate for the pulse current arising from the PD source. This study will be helpful information for online PD measurement. © 2022 IEEE.

关键词： Partial discharges

来源：评论

学校读者我要写书评

暂无评论

Study on Deep Reinforcement Learning for Mobile Robots Flocking control in Certainty Situations 19

Study on Deep Reinforcement Learning for Mobile Robots Flock...

引用

19th International Conference on Electrical engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2022

作者： Kheawkhem, Pontakorn Khuankrue, Issarapong King Mongkut's University of Technology Thonburi Dept. of Control System and Instrumentation Engineering Bangkok Thailand

ISBN: (纸本)9781665485845

Mobile robots are the widely used machines that will be a part of life. It can easily be scaled to meet the requirements of human uses and can move to different target areas freely. However, mobile robots have a problem with mobility, which needs to respond to human activities and obstacles. Reinforcement learning (RT) is a part of machine learning, which enables the machine to learn by themselves. It can develop in a real-world environment without machine teaching or patterns. This paper proposed the study on the flocking control simulation, which avoids the obstacles. Mobile robots in simulation presented by using Multi-Agent Deep Deterministic Policy Gradient (MAD-DPG). The proposed algorithm, the deep reinforcement learning algorithm, is the main navigation of robots, which find the target, maintain distance between robots, and avoid collision with obstacles by learning features and characteristics with certainty environment, obstacle, robots, and target. On the simulation, the authors operate all of the positions in the environment, and robots speed in the environment as the state. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Assessing Uncertainty in Space Weather Forecasting Using Quantile Regression and Complex Nonlinear systems Identification Techniques

Assessing Uncertainty in Space Weather Forecasting Using Qua...

引用

International Conference on Computing, Electronics & Communications engineering (iCCECE)

作者： Hua-Liang Wei Michael A. Balikhin Richard J. Boynton Simon N. Walker Dept. of Automatic Control and Systems Engineering The University of Sheffield Sheffield UK

Space weather forecasting is of global interest, and its importance is well established in research community and recognized by government, industries and stockholders. Over the past years, many types of predictive models have been developed in the literature. There is a general agreement that forecasting models should not only provide point prediction but also inform the uncertainty associated with the prediction. This study presents a novel method bases on quantile regression and complex dynamic modelling for measuring uncertainties in space weather forecasting. The approach is implemented using Quantile regression and Nonlinear AutoRegressive Moving Average with Exogenous inputs (NARMAX) methods (for short the approach is called Q-NARMAX). The method is applied to Disturbance storm index (Dst) observations to examine its interpretability and capability for uncertainty analysis. Results show that the proposed Q-NARX model can produce excellent predictions of the Dst index, and meanwhile provides a measure for assessing the uncertainty in the forecast. The innovative integration of quantile regression, complex dynamic modelling and nonlinear system identification techniques enables the proposed work to have following attractive advantages and properties: 1) it can produce excellent prediction accuracy for space weather forecasting, 2) it uses transparent models to approximate (represent) black-box systems, enabling to interpret the dependent relationship between space weather indices (system outputs) and their drivers (system inputs), and 3) more importantly, it allows for uncertainty assessment and analysis of models and forecasts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tuning the Feedback controller Gains is a Simple Way to Improve Autonomous Driving Performance

Tuning the Feedback Controller Gains is a Simple Way to Impr...

引用

UKACC International Conference on control (control)

作者： Wenyu Liang Pablo R. Baldivieso Ross Drummond Donghwan Shin Dept. of Automatic Control and Systems Engineering University of Sheffield Sheffield UK Dept. of Computer Science University of Sheffield Sheffield UK

ISBN: (数字)9798350374261

ISBN: (纸本)9798350374278

Typical autonomous driving systems are a combination of machine learning algorithms (often involving neural networks) and classical feedback controllers. Whilst significant progress has been made in recent years on the neural network side of these systems, only limited progress has been made on the feedback controller side. Often, the feedback control gains are simply passed from paper to paper with little re-tuning taking place, even though the changes to the neural networks can alter the vehicle's closed loop dynamics. The aim of this paper is to highlight the limitations of this approach; it is shown that re-tuning the feedback controller can be a simple way to improve autonomous driving performance. To demonstrate this, the PID gains of the longitudinal controller in the TCP autonomous vehicle algorithm are tuned. This causes the driving score in CARLA to increase from 73.21 to 77.38, with the results averaged over 16 driving scenarios. Moreover, it was observed that the performance benefits were most apparent during challenging driving scenarios, such as during rain or night time, as the tuned controller led to a more assertive driving style. These results demonstrate the value of developing both the neural network and feedback control policies of autonomous driving systems simultaneously, as this can be a simple and methodical way to improve autonomous driving system performance and robustness.

关键词： Machine learning algorithms Neural networks control systems Robustness Feedback control control theory Adaptive control

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：