检索结果-内蒙古大学图书馆

5th International Conference on Mechatronics Technology and Intelligent Manufacturing (ICMTIM)

作者： Yang, Jian Xie, Jinghang Zhou, Jingyang Pang, Huatong Wang, Yaying Liang, Tianwei Cent South Univ Sch Automat Changsha Peoples R China

ISBN: (纸本)9798350363272;9798350363265

The paper proposes an initial rotor position detection strategy for permanent magnet synchronous motors (PMSMs) based on high-frequency elliptical voltage injection. By analyzing the response current model of PMSM, the strategy utilizes the improved gradient descent algorithm to update and optimize the skew angle of the elliptical voltage, thereby analyzing the variation characteristics of the response current and obtaining the initial position of the rotor from it. Compared with traditional methods of initial rotor position detection, this strategy has a simpler structure, does not require specific motor parameters, and no longer relies on the cooperation of multiple filters to obtain positional information from the response current. It avoids the impact of filters on the current amplitude and reduces phase shifts caused by signal processing. The proposed initial rotor position detection strategy has been validated through simulation.

关键词： Initial Rotor Position Detection PMSM Sensorless Control High Frequency Signal Injection gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Identification of Hammerstein-Wiener time-delay systems with maximum likelihood and gradient descent algorithm 41

Hierarchical Identification of Hammerstein-Wiener time-delay...

引用

第41届中国控制会议

作者： Yizhe Jiang Weicheng Song Jie Chu Junhong Li School of Electrical Engineering Nantong University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In this paper,the parameter estimation for Hammerstein-Wiener nonlinear systems with unknown delay is *** on the hierarchical identification principle and two-step identification,the maximum likelihood recursive algorithm is used to identify the parameters of the system,and the gradient descent method is used to identify the time ***,the algorithm is verified by a numerical example,and the simulation results show that the algorithm has the characteristics of fast convergence speed and high identification accuracy.

关键词： system identification Hammerstein-Wiener systems maximum likelihood algorithm gradient descent algorithm hierarchical identification

来源：评论

学校读者我要写书评

暂无评论

On-line modification of T-S fuzzy models based on gradient descent algorithm 33

On-line modification of T-S fuzzy models based on gradient d...

引用

33rd Chinese Control and Decision Conference (CCDC)

作者： Feng Haodong Wei Dong Jiao Huanyan Beijing Univ Civil Engn & Architecture Sch Elect & Informat Engn Beijing 100044 Peoples R China Beijing Municipal Sci & Technol Commiss Beijing Key Lab Intelligent Proc Bldg Big Data Beijing 100044 Peoples R China

ISBN: (纸本)9781665440899

The gradient descent algorithm is applied to the model parameter correction algorithm in view of the shortcoming that T-S fuzzy model cannot be used for real-time adaptive parameter correction. In this paper, an online model correction method combining T-S fuzzy model with gradient descent algorithm is proposed, and the operation data of a subway air-conditioning system in Wuhan is used for verification. The experimental results show that the T-S fuzzy model modified by gradient descent algorithm has better accuracy and higher operational efficiency.

关键词： T-S fuzzy model gradient descent algorithm Air conditioning system model

来源：评论

学校读者我要写书评

暂无评论

Backflow Power Optimization of DAB with gradient descent algorithm Based Extended-Phase-Shift Control in EER Application 3

Backflow Power Optimization of DAB with Gradient Descent Alg...

引用

3rd IEEE International Electrical and Energy Conference (CIEEC)

作者： Zhou, Bingkai Yang, Xiaofeng Zhang, Zhi Li, Zejie Zheng, Trillion Q. You, Xiaojie Beijing Jiaotong Univ Sch Elect Engn Beijing Peoples R China

ISBN: (纸本)9781728116754

To reduce the backflow power of dual-active-bridge (DAB) DC-DC converter and improve the operating efficiency, this paper proposes a gradient descent algorithm (GD-EPS) based extended-phase-shift (EPS) control. Firstly, the transmission and backflow power models of DAB converter with EPS and single-phase-shift (SPS) control are established, and the influencing factors of backflow power are analyzed. Secondly, according to the backflow power model, the gradient descent algorithm for solving the optimal solution of backflow power is obtained. On this basis, the output voltage closed-loop control is added to derive the DAB overall optimal control scheme. At last, the simulation models of DAB converter with GD-EPS and SPS control are built and compared, it is verified that the GD-EPS control can optimize the backflow power better than the SPS control when the load and input voltage change.

关键词： dual-active-bridge extended-phase-shift backflow power optimization gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Energy Management in Integrated Microgrids: An Optimal Schedule Controller Utilizing gradient descent algorithm

Energy Management in Integrated Microgrids: An Optimal Sched...

引用

2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023

作者： Abdolrasol, M.G.M. Ker, Pin Jern Hannan, M.A. Ayob, Afida Tiong, S.K. Universiti Tenaga Nasional Institute of Sustainable Energy Kajang43000 Malaysia Sunway University School of Engineering and Technology Petaling Jaya Bandar Sunway47500 Malaysia Universiti Kebangsaan Malaysia Department of Electrical Electronics and Sys. Eng. Bangi43600 Malaysia

ISBN: (纸本)9781665471640

This paper presents a new optimal controller using the Binary gradient descent (BGD) algorithm to manage distributed generations effectively in a grid network. The algorithm aims to minimize power consumption from the main grid and prioritize sustainable resource utilization over buying electricity from the local network grid. The proposed approach is evaluated on the IEEE fourteen bus test system with integrated Microgrids (MGs) and distributed generations, using real load demand data from Perlis, Malaysia, for 24-hour test case studies. Weather data, including wind, solar, fuel, and battery status, is integrated into the BGD algorithm for optimizing ON and OFF schedules. The results demonstrate a significant 46.3% reduction in energy consumption achieved by the BGD algorithm, contributing to the advancement of optimization algorithms for sustainable energy management. The developed BGD algorithm's effectiveness is further validated through a comparative analysis with conventional methods. © 2023 IEEE.

关键词： Efficient Energy Management Energy Scheduling gradient descent algorithm Integrated Microgrids Renewable Energy Integration Renewable Resources

来源：评论

学校读者我要写书评

暂无评论

A loss minimization control method for IPMSM drive system based on improved gradient descent algorithm

引用

IEICE ELECTRONICS EXPRESS 2022年第7期19卷 20220069-20220069页

作者： Yang, Hongyi Huang, Xiaoyan Shen, Qidi Li, Zhaokai Wu, Min Zhejiang Univ Polytechn Inst Hangzhou 310015 Peoples R China Zhejiang Univ Coll Elect Engn Zhejiang Prov Key Lab Elect Machine Syst Hangzhou 310027 Peoples R China Zhejiang Univ Coll Elect Engn Hangzhou Peoples R China

This paper proposes a loss minimization control method based on improved gradient descent algorithm (GDA) for interior permanent magnet synchronous machine (IPMSM). Since the power of PMSM is derived from the measured phase voltage and current, this method is independent from the iron loss model containing motor parameters. Meanwhile, it can guarantee the stability of PMSM system when entering the searching period. Both maximum torque per ampere (MTPA) and i(d) = 0 control are carried out to validate the effectiveness of the proposed method. The experimental results are demonstrated to verify the proposed approach.

关键词： loss minimization control gradient descent algorithm permanent magnet synchronous machine iron loss maximum torque per ampere

来源：评论

学校读者我要写书评

暂无评论

Combining expert weights for online portfolio selection based on the gradient descent algorithm

引用

KNOWLEDGE-BASED SYSTEMS 2021年 234卷 1页

作者： Zhang, Yong Lin, Hong Yang, Xingyu Long, Wanrong Guangdong Univ Technol Sch Management Guangzhou 510520 Guangdong Peoples R China

In this paper, we propose a new online portfolio selection strategy based on a weighted learning technique and an online gradient descent algorithm. Our strategy, named combination weights based on online gradient descent (CW-OGD), achieves improved robustness by integrating different expert strategies and overcomes the difficult problem of complex computational time. First, an expert system including many basic expert strategies, in which we choose the strategy that invests in a single stock as the basic expert strategy, is established. Second, we exploit the loss function to evaluate the performance of different basic expert strategies and use the OGD algorithm to update the weight vector for the experts based on their losses. In addition, we theoretically prove that the proposed strategy has a regret bound. Finally, extensive experiments conducted on four stock combinations and seven benchmark datasets show that our strategy can outperform some state-of-the-art strategies in terms of the return, risk and computational time metrics. Furthermore, our strategy can achieve higher returns even at certain transaction cost rates, which illustrates its effectiveness in the actual stock market. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Online portfolio selection gradient descent algorithm Combining weights Expert strategy

来源：评论

学校读者我要写书评

暂无评论

Improved grid mapping technology based on Rao-Blackwellized particle filters and the gradient descent algorithm

引用

SYSTEMS SCIENCE & CONTROL ENGINEERING 2019年第1期7卷 65-74页

作者： Zhang, Tengfei Wang, Chuanjiang Yuan, Zhen Zheng, Mingyue Shandong Univ Sci & Technol Coll Elect Engn & Automat Qingdao Shandong Peoples R China Shandong Univ Sch Control Sci & Engn Jinan Shandong Peoples R China

Recently, the Rao-Blackwellized particle filter (RBPF) has been used to solve the problem of simultaneous localization and mapping (SLAM). Using the odometer information of robot to calculate the proposed distribution requires a number of sampled particles, which increases the calculation complexity in the RBPF operation. In this paper, we integrate the odometer measurement and sensor observation into the proposed distribution, effectively reducing the particle sample scale. To reduce the inconsistency in the map model caused by the cumulative error of the odometer information of robot, we applied a gradient descent algorithm to fuse the sensor data to obtain the real-time attitude angle. This combination method, based on the robot operation system (ROS), runs on a platform of self-built mobile robot equipped with a laser rangefinder. The experimental results show that this method can realize the online real-time high-precision grid map which provides a new approach for robot navigation and SLAM.

关键词： RBPF proposal distribution gradient descent algorithm ROS

来源：评论

学校读者我要写书评

暂无评论

Self-tuning Grey Prediction Control System using gradient descent algorithm

International Journal of Uncertainty and Innovation Research

引用

International Journal of Uncertainty and Innovation Research 2020年第2期2卷 101-113页

作者： Ming-Feng Yeh Ti-Hung Chen Ming-Hung Chang

A typical grey prediction control system is composed of a proportional-integral-derivative controller and a grey predictor. Rather than using differential evolution algorithms to optimize the grey prediction control system as in our previous work, this study attempts to apply the gradient descent algorithm to derive the self-tuning rules for both the coefficients of proportional-integral-derivative controller and the parameters of grey model. This study also attempts to replace the original GM(1,1) with a simple equivalent GM(1,1) in order to reduce computational complexity. Analogously, an objective function in terms of the maximal overshoot, rising time, steady-state error, and settling time is used to evaluate the performance of the comparison control systems. While using the self-tuning rule, simulation results on two single-variable plants demonstrate that the grey prediction control system with equivalent GM(1,1) could perform better than the original grey prediction control system.

关键词： Differential evolution gradient descent algorithm Grey model PID control

来源：评论

学校读者我要写书评

暂无评论

Kernel gradient descent algorithm for information theoretic learning

引用

JOURNAL OF APPROXIMATION THEORY 2021年 263卷 105518-105518页

作者： Hu, Ting Wu, Qiang Zhou, Ding-Xuan Wuhan Univ Sch Math & Stat Wuhan 430072 Peoples R China Middle Tennessee State Univ Dept Math Sci Murfreesboro TN 37132 USA City Univ Hong Kong Liu Bie Ju Ctr Math Sci Sch Data Sci Dept MathKowloon Hong Kong Peoples R China

Information theoretic learning is a learning paradigm that uses concepts of entropies and divergences from information theory. A variety of signal processing and machine learning methods fall into this framework. Minimum error entropy principle is a typical one amongst them. In this paper, we study a kernel version of minimum error entropy methods that can be used to find nonlinear structures in the data. We show that the kernel minimum error entropy can be implemented by kernel based gradient descent algorithms with or without regularization. Convergence rates for both algorithms are deduced. Published by Elsevier Inc.

关键词： Information theoretic learning Minimum error entropy Kernel method gradient descent algorithm Regularization

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：