检索结果-内蒙古大学图书馆

gradient descent algorithm Inspired Adaptive Time Synchronization in Wireless Sensor Networks

IEEE SENSORS JOURNAL 2016年第13期16卷 5463-5470页

作者： Yildirim, Kasim Sinan Delft Univ Technol Embedded Software Grp NL-2628 CD Delft Netherlands Ege Univ Dept Comp Engn TR-35100 Izmir Turkey

This paper proposes another direction to implement a lightweight synchronization service for wireless sensor nodes. To this end, we present gradient descent synchronization (GraDeS), a novel multi-hop time synchronization protocol based upon gradient descent algorithm. We give details about our implementation of GraDeS and present its experimental evaluation in our testbed of MICAz sensor nodes. Our observations indicate that GraDeS is scalable, and it has identical memory and processing overhead, better convergence time, and comparable synchronization performance as compared with the existing lightweight solutions.

关键词： Wireless sensor networks time synchronization least-squares gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

gradient descent algorithm-Based Adaptive NN Control Design for an Induction Motor

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2021年第2期51卷 1027-1034页

作者： Yang, Xuebo Zheng, Xiaolong Harbin Inst Technol Res Inst Intelligent Control & Syst Sch Astronaut Harbin 150001 Peoples R China

This paper investigates the position tracking control problem for an induction motor with completely unknown nonlinearities. A novel control scheme is presented by using the gradient descent algorithm, adaptive backstepping technique, neural networks (NNs), and extended differentiators. Differing from some existing results which only designed the adaption of weights of NNs, our proposed control strategy provides training for all the parameters of NNs, including the basis functions' widths and centers. With the help of the gradient descent algorithm and Lyapunov stability criterion, the convergence of both the NN approximation error and the system tracking error can be guaranteed. Finally, a simulation example shows the advantages of our proposed method compared with direct adaptive NN control strategy.

关键词： Backstepping gradient descent algorithm induction motor neural networks (NNs)

来源：评论

学校读者我要写书评

暂无评论

gradient descent algorithm for Small UAV Parameter Estimation System

引用

Transactions of Nanjing University of Aeronautics and Astronautics 2017年第6期34卷 680-687页

作者： Guo Jiandong Liu Qingwen Wang Kang Key Laboratory of Unmanned Aerial Vehicle Technology of the Ministry of Industry and Information Technology Nanjing University of Aeronautics and AstronauticsNanjing 210016P.R.China College of Automation Engineering Nanjing University of Aeronautics and AstronauticsNanjing 210016P.R.China

A gradient descent algorithm with adjustable parameter for attitude estimation is developed,aiming at the attitude measurement for small unmanned aerial vehicle(UAV)in real-time flight *** accelerometer and magnetometer are introduced to construct an error equation with the gyros,thus the drifting characteristics of gyroscope can be compensated by solving the error equation utilized by the gradient descent *** of the presented algorithm is evaluated using a self-proposed micro-electro-mechanical system(MEMS)based attitude heading reference system which is mounted on a tri-axis *** on-ground,turntable and flight experiments indicate that the estimation attitude has a good ***,the presented system is compared with an open-source flight control system which runs extended Kalman filter(EKF),and the results show that the attitude control system using the gradient descent method can estimate the attitudes for UAV effectively.

关键词： gradient descent algorithm attitude estimation quaternions small unmanned aerial vehicle(UAV)

来源：评论

学校读者我要写书评

暂无评论

Maximum Torque Per Ampere Control for IPMSM Using gradient descent algorithm Based on Measured Speed Harmonics

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2018年第4期14卷 1424-1435页

作者： Lai, Chunyan Feng, Guodong Mukherjee, Kaushik Tjong, Jimi Kar, Narayan C. Univ Windsor Dept Elect & Comp Engn Windsor ON N9B 3P4 Canada Indian Inst Engn Sci & Technol Sibpur 711103 Howrah India

This paper proposes a novel gradient descent based maximum torque per ampere (MTPA) control algorithm for interior permanent magnet synchronous machines (IPMSMs) by using the measured speed harmonics. The proposed approach does not require machine parameters and thus is not influenced by the machine and drive nonlinearities. Hence, the proposed approach can ensure a robust MTPA control under different loading conditions. Specifically, in the proposed approach, a small q-axis harmonic voltage is injected into the machine to induce a small harmonic component in the machine speed. Based on the PMSM torque equation, the mathematical relation between the induced speed harmonic and the output torque is derived, which shows that the magnitude of the induced speed harmonic is proportional to the output torque of an IPMSM. Therefore, the speed harmonic is explored to seek the MTPA angle, in which the MTPA angle is found when the speed harmonic magnitude is maximized. In particular, the gradient descent algorithm is employed to detect the MTPA angle, which is computationally efficient and converges quickly. The proposed approach is evaluated with both simulations and experiments based on a laboratory IPMSM drive system.

关键词： gradient descent algorithm interior permanent magnet synchronous machine (IPMSM) maximum torque per ampere (MTPA) control speed harmonic

来源：评论

学校读者我要写书评

暂无评论

Improved specular point prediction precision using gradient descent algorithm

引用

ADVANCES IN SPACE RESEARCH 2020年第6期65卷 1568-1579页

作者： Tian, Yusen Xia, Junming Sun, Yueqiang Wang, Xianyi Du, Qifei Bai, Weihua Wang, Dongwei Cai, Yuerong Wu, Chunjun Li, Fu Qiao, Hao Chinese Acad Sci Natl Space Sci Ctr 1 Nanertiao Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Beijing Key Lab Space Environm Explorat Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Sci & Technol Space Environm Situat Aware Beijing 100190 Peoples R China

Global Navigation Satellite Systems Reflectometry (GNSS-R) utilizes GNSS signals reflected off the Earth surface for remote sensing applications. Due to weak power of reflected signals, GNSS-R receiver needs to track reflected signals by open loop. The first step is to calculate the position of specular point. The specular point position error of the existing algorithm-Quasi-Spherical Earth (QSE) Approach-is about 3 km which may cause troubles in data post-processing. In this paper, gradient descent algorithm is applied to calculate position of specular point and the calculation is based on World Geodetic System 1984 (WGS 84) ellipsoid in geodetic coordinate. The benefit of this coordinate is that it is easy to investigate the effect of real surface's altitude. Learning rate-the key parameter of the algorithm-is adaptively adjusted according to initial error, latitude and gradient descent rate. With self-adaptive learning rate strategy, the algorithm converges fast. Through simulation and test on Global Navigation Satellite System Occultation Sounder II (GNOS II), the performances of the algorithm are validated. The specular point position error of the proposed algorithm is about 10 m. The speed of the proposed algorithm is competitive compared with the existing algorithm. The test on GNOS II shows that the proposed algorithm has good real-time performance. (C) 2019 Published by Elsevier Ltd on behalf of COSPAR.

关键词： GNSS-R Specular point gradient descent algorithm Self-adaptive learning rate

来源：评论

学校读者我要写书评

暂无评论

Distributed kernel gradient descent algorithm for minimum error entropy principle

引用

APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS 2020年第1期49卷 229-256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 Sch Data Sci Kowloon Hong Kong Peoples R China City Univ Hong Kong Dept Math Kowloon Hong Kong Peoples R China

Distributed learning based on the divide and conquer approach is a powerful tool for big data processing. We introduce a distributed kernel gradient descent algorithm for the minimum error entropy principle and analyze its convergence. We show that the L-2 error decays at a minimax optimal rate under some mild conditions. As a tool we establish some concentration inequalities for U-statistics which play pivotal roles in our error analysis. Published by Elsevier Inc.

关键词： Distributed learning Minimum error entropy gradient descent algorithm Kernel method

来源：评论

学校读者我要写书评

暂无评论

Parametric Tracking of Electrical Current Components Using gradient descent algorithm

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE 2022年第16期236卷 8834-8841页

作者： Frini, Marouane Choqueuse, Vincent Auger, Francois Univ Nantes IREENA 37 Blvd Univ F-44600 St Nazaire France Univ Bretagne Occidentale LAB STICC Brest France

In the last few years, Motor Current Signature Analysis (MCSA) has proven to be an effective method for electrical machines condition monitoring. Indeed, compared to vibration and temperature analysis, current measurement proves to be a convenient and non-invasive alternative. Moreover, it has proven to be a reliable method since many mechanical and electrical faults manifest as side-band spectral components generated around the fundamental frequency component of the motor's current. These components are called interharmonics and they are a major focus of fault detection using MCSA. However, the main drawback of this approach is that the interference of other more prevalent components such as the fundamental and noise components can obstruct the effect of interharmonics in the spectrum and may therefore affect fault detection accuracy. Thus, we propose in this paper an alternative approach that aims to decompose the different current components using a model based on a Vandermonde matrix, in order to monitor each component independently. Then, the tracking of each distinct component in time and spectral domains is implemented. This is achieved by estimating their respective relevant parameters using the gradient descent algorithm. This method has been favorably compared to an existing estimation algorithm (MUSIC) and its efficiency has been validated. The results of this work prove to be promising and establish the parametric tracking of the electrical current components using the gradient descent algorithm as a reliable monitoring approach.

关键词： motor current signal analysis current components decomposition parametric model estimation gradient descent algorithm

来源：评论

学校读者我要写书评

暂无评论

Maximum Efficiency Control of PMSM Drives Considering System Losses Using gradient descent algorithm Based on DC Power Measurement

引用

IEEE TRANSACTIONS ON ENERGY CONVERSION 2018年第4期33卷 2240-2249页

作者： Balamurali, Aiswarya Feng, Guodong Lai, Chunyan Tjong, Jimi Kar, Narayan C. Univ Windsor Dept Elect & Comp Engn Windsor ON N9B 3P4 Canada

This paper proposes a novel method of efficiency improvement in a vector controlled permanent magnet synchronous motors (PMSM) through system level maximum efficiency point determination using current angle as a control variable. Loss models for the inverter and the motor fundamental and harmonic losses, which are capable of being solved online using available terminal measurements in the system are initially developed. The loss models and dc-link power measurement are then used to seek the maximum efficiency angle for different operating conditions using a gradient descent optimization algorithm. The developed method is robust against changes in inductances due to saturation and cross saturation with loading conditions as well as temperature effects. The effectiveness of the developed method in improving the system efficiency is verified and compared with conventional maximum torque per ampere method. The proposed strategy has been validated on a laboratory interior PMSM, and the efficiency has been calculated for different speed and torque conditions. The experimental validations confirm the effectiveness of the proposed solution in improving the motor drive system energy efficiency.

关键词： Current angle DCpower losses gradient descent algorithm maximum efficiency permanent magnet motor

来源：评论

学校读者我要写书评

暂无评论

Comparing the performance of neural networks developed by using Levenberg-Marquardt and Quasi-Newton with the gradient descent algorithm for modelling a multiple response grinding process

引用

EXPERT SYSTEMS WITH APPLICATIONS 2012年第3期39卷 2397-2407页

作者： Mukherjee, Indrajit Routroy, Srikanta Indian Inst Technol Shailesh J Mehta Sch Management Bombay 400076 Maharashtra India Birla Inst Technol & Sci Dept Mech Engn Pilani 333031 Rajasthan India

Monitoring and control of multiple process quality characteristics (responses) in grinding plays a critical role in precision parts manufacturing industries. Precise and accurate mathematical modelling of multiple response process behaviour holds the key for a better quality product with minimum variability in the process. Artificial neural network (ANN)-based nonlinear grinding process model using backpropagation weight adjustment algorithm (BPNN) is used extensively by researchers and practitioners. However, suitability and systematic approach to implement Levenberg-Marquardt (L-M) and Boyden, Fletcher, Gold-farb and Shanno (BFGS) update Quasi-Newton (Q-N) algorithm for modelling and control of grinding process is seldom explored. This paper provides L-M and BEGS algorithm-based BPNN models for grinding process, and verified their effectiveness by using a real life industrial situation. Based on the real life data, the performance of L-M and BFGS update Q-N are compared with an adaptive learning (A-L) and gradient descent algorithm-based BPNN model. The results clearly indicate that L-M and BEGS-based networks converge faster and can predict the nonlinear behaviour of multiple response grinding process with same level of accuracy as A-L based network. (C) 2011 Elsevier Ltd. All rights reserved.

关键词： Back propagation neural network gradient descent algorithm Levenberg-Marquardt algorithm Multiple response Quasi-Newton algorithm

来源：评论

学校读者我要写书评

暂无评论

A High-Order Neutrosophic-Neuro-gradient descent algorithm-Based Expert System for Time Series Forecasting

引用

INTERNATIONAL JOURNAL OF FUZZY SYSTEMS 2019年第7期21卷 2245-2257页

作者： Singh, Pritpal Huang, Yo-Ping Natl Taipei Univ Technol Dept Elect Engn Taipei 10608 Taiwan Natl Taipei Univ Dept Comp Sci & Informat Engn New Taipei 23741 Taiwan

This article proposed a novel hybrid time series forecasting model using neutrosophic set (NS) theory, artificial neural network (ANN) and gradient descent algorithm. This study deals with three main problems of time series dataset, viz., representation of time series dataset using NS, three degrees of memberships of NS together, and generation of the forecasting results. To resolve these three domain specific problems, this study advocated the application of neutrosophic-neuro-gradient approach. NS theory was utilized to represent the uncertainty associated with time series dataset and was referred to as neutrosophic time series (NTS). In NTS, various decision rules were created in the form of IF-THEN rules, which were termed as neutrosophic entropy decision rules (NEDRs). An ANN-based architecture took NEDRs as input to evolve the forecasting results. To improve the performance of ANN and to obtain optimal forecasting results, this study additionally utilized the gradient descent algorithm to minimize the differences between the calculated and target output values during the simulation. The proposed model was verified and validated with three different datasets, including TAIFEX index, university enrollment dataset of Alabama and Taiwan Stock Exchange Corporation (TSEC) weighted index. Experimental results showed that the proposed model outperformed existing benchmark models with average forecasting error rates of 1.02%, 0.74% and 1.27% for the TAIFEX, university enrollment and TSEC, respectively.

关键词： Neutrosophic set Artificial neural network gradient descent algorithm Entropy Time series forecasting

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：