检索结果-内蒙古大学图书馆

Compound-Gaussian Spatial-Temporal Correlated Complex Clutter Simulation Based on a Two-Step data-driven method

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2023年第6期59卷 9512-9526页

作者： Liao, Xingxing Xie, Junhao Zhou, Jie Harbin Inst Technol Sch Elect & Informat Engn Harbin 150001 Peoples R China

In this work, aiming to simulate random complex clutter with the similar spatial-temporal correlation and amplitude distribution to the measured clutter, a two-step data-driven method as an alternative to statistical methods is proposed. First, a complex data matrix with the desired spatial-temporal correlation is generated via the sliding-window filtering (SWF) from the measured clutter. Based on the compound-Gaussian model, it is explained that the SWF guarantees that the complex data matrix can roughly reproduce the amplitude distribution of the measured clutter. Second, to further improve the amplitude distribution reproducing performance, a scheme combining the amplitude-phase separation technique and the correlation transfer method is introduced to process the complex data matrix generated by the SWF. The experimental results show that the clutter generated by the two-step method can reproduce the main statistical characteristics observed in the measured clutter.

关键词： Clutter Correlation Sea measurements Radar clutter Doppler effect Radar detection Radar measurements Amplitude-phase separation (APS) clutter simulation correlation transfer (CT) data-driven method sliding-window filtering (SWF) spatial-temporal correlation

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Time-Adaptive data-driven method for Sensor Fault Diagnosis in Induction Motor Drive System

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2019年第12期66卷 9817-9827页

作者： Gou, Bin Xu, Yan Xia, Yang Wilson, Gary Liu, Shuyong Nanyang Technol Univ Singapore 639798 Singapore Rolls Royce Singapore 797565 Singapore

Three-phase pulsewidth modulation inverter fed induction motor drive system is widely applied in high power drive applications. Sensor faults are very common in the drive system, which, once occur, might result in degraded system performance or even system shutdown. In order to rapidly and accurately diagnose the sensor faults, this paper proposes an intelligent time-adaptive data-driven method to identify the fault location and fault type of sensors in the drive system. An emerging machine learning technology named extreme learning machine (ELM) is applied to learn the sensor fault dataset;an ensemble ELM classifier is then designed to improve diagnostic accuracy, based on which a time-adaptive fault diagnosis process is proposed to achieve a high and balanced diagnostic accuracy and speed. As a data-driven method, the proposed method only employs the phase current, dc-link voltage, and speed signals as the inputs to the ensemble ELM classifiers and requires no additional sensors and other hardware. Simulated and experimental tests show that the proposed method can rapidly and accurately detect the fault sensor location and identify offset fault, stuck fault, and noise faults with an average diagnostic accuracy of 98% and the average decision time of 10 ms after the fault occurs. Moreover, such diagnosis method is robust to the fluctuation of catenary voltage and dc-link voltage, fault severity, and variation of model parameters, speed, and load.

关键词： data-driven method fault diagnosis sensor fault three-phase inverter time-adaptive diagnosis process

来源：评论

学校读者我要写书评

暂无评论

Cerebrovascular segmentation from TOF-MRA using model- and data-driven method via sparse labels

引用

NEUROCOMPUTING 2020年第0期380卷 162-179页

作者： Zhang, Baochang Liu, Shuting Zhou, Shoujun Yang, Jian Wang, Cheng Li, Na Wu, Zonghan Xia, Jun Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Tsinghua Univ Sch Grad Sch Shenzhen Shenzhen Peoples R China Beijing Inst Technol Sch Opt & Elect Beijing Peoples R China Shenzhen Univ Shenzhen Second Peoples Hosp Hlth Sci Ctr Dept RadiolAffiliated Hosp 1 Shenzhen Peoples R China

Cerebrovascular segmentation from time-of-flight magnetic resonance angiography (TOF-MRA) data is of great importance in blood supply structure analysis, diagnosis, and treatment of cerebrovascular pathologies. However, complete and accurate segmentation is still a challenge due to the complex image context and vascular morphology. The existing model-driven methods are often difficult to obtain prominent accuracy and robustness. Deep-learning based technology has achieved unimaginable success, but always faces the problem of insufficient labeled data. In this paper, a novel strategy is proposed to automate cerebrovascular segmentation, which integrates model- and data-driven methods. Firstly, the TOF-MRA data are sparsely labeled by three radiologists. Secondly, a semi-supervised mixture probability model is proposed to fit the cerebrovascular intensity distribution precisely, which starts from the sparse annotations and generates massive labeled points. Thirdly, mislabeled points are corrected by a Clean-Mechanism model, to acquire a well-labeled point-set of good quality. Finally, we construct and train a dilated dense convolution network (DD-CNN) by the resultant labeled point-set. The proposed method is validated on 109 clinical TOR-MRA data from a public dataset. Compared with the other state-of-the-art segmentation methods, our method segments cerebrovascular structure with better completeness and sensibility, especially for slender vascularity. The experimental results show that our method reaches an average dice score of 93.20%, which also indicates that the DD-CNN is very competent for cerebrovascular segmentation from TOF-MRA volume. (C) 2019 The Authors. Published by Elsevier B.V.

关键词： Cerebrovascular segmentation Deep-learning Dilated convolution Sparse label Model-driven method data-driven method

来源：评论

学校读者我要写书评

暂无评论

Current sensor fault diagnosis and fault-tolerant control for single-phase PWM rectifier based on a hybrid model-based and data-driven method

引用

IET POWER ELECTRONICS 2020年第18期13卷 4150-4157页

作者： Xia, Yang Xu, Yan Gou, Bin Nanyang Technol Univ Sch Elect & Elect Engn Singapore Singapore Southwest Jiaotong Univ Sch Elect Engn Chengdu Peoples R China

In this study, a hybrid model-based and data-driven method is proposed for the current sensor fault diagnosis used in single-phase pulse width modulation (PWM) rectifier. According to the principle of model-based methods, the proposed diagnostic method is based on signal prediction and residual generation. Differently, instead of a mathematical model, the signal prediction model is developed based on a data-driven method. Non-linear autoregressive exogenous learning model, randomised learning technique, and extreme learning machine are utilised to generate the data-driven prediction model. Once the fault is detected, fault-tolerant control is activated by substituting the predicted signal for the information of faulty sensors. The offline test shows that the proposed method is able to predict the sensor signal accurately with the root mean square error of 4.276 x 10(-5). In addition, hardware-in-the-loop tests are conducted to verify the feasibility and reliability of the proposed method in the real-time application.

关键词： autoregressive processes learning (artificial intelligence) electric sensing devices PWM rectifiers fault diagnosis fault tolerant control data handling feedforward neural nets control engineering computing current sensor fault diagnosis fault-tolerant control single-phase PWM rectifier data-driven method single-phase pulse width modulation rectifier model-based methods diagnostic method mathematical model signal prediction model nonlinear autoregressive exogenous learning model data-driven prediction model sensor signal prediction hybrid model-based method residual generation randomised learning extreme learning machine hardware-in-the-loop tests real-time application

来源：评论

学校读者我要写书评

暂无评论

A data-driven method for feature assessment of historical settlements: A case study of Northeast Hubei, China

引用

Frontiers of Architectural Research 2024年第2期13卷 387-405页

作者： Gangyi Tan Zhanxiang Chen Jiangkun Zhu Kai Wang School of Architecture&Urban Planning Huazhong University of Science and TechnologyWuhan 430074China Hubei Engineering and Technology Research Center of Urbanization Wuhan 430074China Hubei Rural Construction Center Wuhan 430074China HUST Built Heritage Research Center Wuhan 430074China

Formulating criteria for the assessment system of historic settlements is challenging due to complex geographical conditions and evaluator knowledge limitations, leading to subjective bias in the assessment process. To address this issue, this study proposes a data-driven method for assessing the features of historical settlements to carry out scientific and refined assessment and result analysis. Focusing on Northeast Hubei as the study area, this paper selects 3 historical settlements for validation and analysis. The results of the study show that (1) the data-driven method expands the methodological chain of assessing historical settlement features, and improves the assessment efficiency and scientificity of the assessment results by applying it to the new assessment process;(2) Through comparing the assessment results of the validation cases and data samples, the study establishes a comprehensive quantitative ranking of the assessment of historical settlement features and identifies the main influencing factors, thus enhancing the precision of result analysis;(3) By comparing the resulting assessment framework with the current assessment system, this study confirms the advantages of the proposed framework in identifying nuanced features and aligning with geographical conditions, thereby verifying the effectiveness of the data-driven method.

关键词： Historical settlement Feature assessment data-driven method Northeast Hubei

来源：评论

学校读者我要写书评

暂无评论

Research on Heterogeneous Computation Resource Allocation based on data-driven method 6

Research on Heterogeneous Computation Resource Allocation ba...

引用

6th International Conference on data-driven Optimization of Complex Systems (DOCS)

作者： Tang, Xirui Wang, Zeyu Cai, Xiaowei Su, Honghua Wei, Changsong Northeastern Univ Coll Comp Sci Boston MA 02115 USA Yale Univ Yale Sch Management New Haven CT USA Washington Univ St Louis Olin Business Sch St Louis MO USA Digital Financial Informat Technol Co LTD Chengdu Sichuan Peoples R China

ISBN: (纸本)9798350377859;9798350377842

The rapid development of the mobile Internet and the Internet of Things is leading to a diversification of user devices and the emergence of new mobile applications on a regular basis. Such applications include those that are computationally intensive, such as pattern recognition, interactive gaming, virtual reality, and augmented reality. However, the computing and energy resources available on the user's equipment are limited, which presents a challenge in effectively supporting such demanding applications. In this work, we propose a heterogeneous computing resource allocation model based on a data-driven approach. The model first collects and analyzes historical workload data at scale, extracts key features, and builds a detailed data set. Then, a data-driven deep neural network is used to predict future resource requirements. Based on the prediction results, the model adopts a dynamic adjustment and optimization resource allocation strategy. This strategy not only fully considers the characteristics of different computing resources, but also accurately matches the requirements of various tasks, and realizes dynamic and flexible resource allocation, thereby greatly improving the overall performance and resource utilization of the system. Experimental results show that the proposed method is significantly better than the traditional resource allocation method in a variety of scenarios, demonstrating its excellent accuracy and adaptability.

关键词： heterogeneous computation resource allocation deep neural network data-driven method

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis in Analog Electrical Circuits: data-driven method

Fault Diagnosis in Analog Electrical Circuits: Data-Driven M...

引用

International Conference on Process Control (PC)

作者： Zhirabok, A. Baranov, A. Far Eastern Fed Univ Dept Automat & Control Sukhanova St 8 Vladivostok Russia

ISBN: (纸本)9781479909261;9781479909278

The paper is devoted to the problem of fault detection in analog electrical circuits described by linear or nonlinear polynomial models. So-called data-driven method for fault detection is considered. This method assumes that parameters of the circuit under consideration may be unknown. It does not use methods of identification and allows checking whether or not parameters of some elements deviate considerably from their nominal values.

关键词： electrical circuit linear models polynomial models fault detection data-driven method

来源：评论

学校读者我要写书评

暂无评论

data-driven method for Response Control of Nonlinear Random Dynamical Systems

引用

JOURNAL OF APPLIED MECHANICS-TRANSACTIONS OF THE ASME 2021年第4期88卷 041012页

作者： Tian, Yanping Jin, Xiaoling Wu, Lingling Yang, Ying Wang, Yong Huang, Zhilong Hangzhou Dianzi Univ Coll Mech Engn Hangzhou 310018 Peoples R China Zhejiang Univ Dept Engn Mech Hangzhou 310027 Peoples R China Arizona State Univ Sch Engn Matter Transport & Energy Tempe AZ 85287 USA

The response control of nonlinear random dynamical systems is an important but also difficult subject in scientific and industrial fields. This work merges the decomposition technique of feedback control and the data-driven identification method of stationary response probability density, converts the constrained functional extreme value problem associated with optimal control to an unconstrained optimization problem of multivariable function, and determines the optimal coefficients of preselected control terms by an optimization algorithm. This data-driven method avoids the difficulty of solving the stochastic dynamic programming equation or forward-backward stochastic differential equations encountered in classical control theories, the miss of the conservative mechanism in the nonlinear stochastic optimal control strategy, and the difficulty of judging the integrability and resonance of the controlled Hamiltonian systems encountered in the direct-control method. The application and efficacy of the data-driven method are illustrated by the random response control problems of the Duffing oscillator, van der Pol system, and a two degrees-of-freedom nonlinear system.

关键词： random response control nonlinear dynamical system data-driven method decomposition technique of feedback control optimization algorithm vibration

来源：评论

学校读者我要写书评

暂无评论

data-driven method for identifying the expression of the Lyapunov exponent from random data

引用

INTERNATIONAL JOURNAL OF NON-LINEAR MECHANICS 2023年 148卷

作者： Chen, Xi Jin, Xiaoling Huang, Zhilong Zhejiang Univ Dept Engn Mech Key Lab Soft Machines & Smart Devices Zhejiang Pro Hangzhou 310027 Peoples R China

A data-driven methodology is proposed to identify the expression of the largest Lyapunov exponent to determine the stochastic stability of the system. The method is carried out by two successive processes: one is to estimate the largest Lyapunov exponent from random discrete data , the other is to identify the simplest expression of the largest Lyapunov exponent which includes system , excitation parameters. The first process is based on a new definition of the Lyapunov exponent of the disturbed states by using the ensemble average in a finite time. The data of the disturbed states are obtained from the differences between the random data of a few samples of system states. The second process resorts to the dimensional analysis method and the sparse optimization algorithm. Five typical examples, including linear stochastic dynamical system, Duffing oscillator, viscoelastic system, nonlinear system with two degrees of freedom subjected to Gaussian white noise, and Duffing oscillator subjected to uniformly distributed excitation, are given to illustrate the effectiveness of the proposed data-driven method and the extensionality of the identified expression of the largest Lyapunov exponent including system and excitation parameters. Moreover, it is concluded that the proposed data-driven method needs a smaller amount of data by comparing the traditional method for estimating the largest Lyapunov exponent from random data.

关键词： data-driven method Largest Lyapunov exponent Stochastic stability Sparse optimization Dimensional analysis

来源：评论

学校读者我要写书评

暂无评论

A data-driven method for Operational Reliability Prediction on Electric Devices Considering Multiple Meteorological Factors

A Data-Driven Method for Operational Reliability Prediction ...

引用

IEEE International Conference on Probabilistic methods Applied to Power Systems (PMAPS)

作者： Chen, Xiaolin Chang, Qingqing Tang, Junjie Li, Wenyuan Chongqing Univ State Key Lab Power Transmiss Equipment & Syst Se Chongqing Peoples R China Shanghai Univ Finance & Econ Sch Informat Management & Engn Shanghai Peoples R China

ISBN: (纸本)9781538635964

The external weather conditions have significant effects on the normal operation of electric devices, such as overhead lines. A novel data-driven method for operational reliability prediction on overhead lines, with considering multiple meteorological factors, is proposed in this paper. This new method adopts the improved logistic regression model to fit the failure probability model of overhead line groups located in a same meteorological region, which can be hence used for prediction on real-time operational reliability of electric devices. The practical fault recording data of overhead lines provided by Shenzhen Power Supply Company of China Southern Power Grid, in combination with the relevant numerical meteorological data available, is exploited for demonstration and validation. The performance and advantages of the proposed method, compared to the existing methods, are shown and discussed based on the tests.

关键词： Operational reliability prediction multiple meteorological factors overhead line group data-driven method logistic regression method failure probability

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：