检索结果-南通市图书馆

Remaining useful life prediction for train bearing based on an ILSTM network with adaptive hyperparameter optimization

引用

Transportation Safety and Environment 2024年第2期6卷 75-86页

作者： Deqiang He Jingren Yan Zhenzhen Jin Xueyan Zou Sheng Shan Zaiyu Xiang Jian Miao State Key Laboratory of Featured Metal Materials and Life-cycle Safety for co.posite Structures Guangxi Key Laboratory of Manufacturing System&Advanced Manufacturing Tec hnologySc hool of Mec hanical EngineeringGuangxi Univ ersityNanning 530004GuangxiChina zhuzhou crrc times electric co. Ltd.Zhuzhou 412001HunanChina

Remaining useful life(RUL)prediction for bearing is a significant part of the maintenance of urban rail transit trains.Bearing RUL is closely linked to the reliability and safety of train running,but the current prediction accuracy makes it difficult to meet the re-quirements of high reliability operation.Aiming at the problem,a prediction model based on an improved long short-term memory(ILSTM)network is proposed.Firstly,the variational mode deco.position is used to process the signal,the intrinsic mode function with stronger representation ability is determined acco.ding to energy entropy and the degradation feature data is co.structed co.-bined with the time domain characteristics.Then,to improve learning ability,a rectified linear unit(ReLU)is applied to activate a fully co.nected layer lying after the long short-term memory(LSTM)network,and the hidden state outputs of the layer are weighted by attention mechanism.The Harris Hawks optimization algorithm is introduced to adaptively set the hyperparameters to improve the performance of the LSTM.Finally,the ILSTM is applied to predict bearing RUL.Through experimental cases,the better perfor-mance in bearing RUL prediction and the effectiveness of each improving measures of the model are validated,and its superiority of hyperparameters setting is demonstrated.

关键词： train bearing remaining useful life prediction long short-term memory(LSTM) attention mechanism Harris Hawks op-timization(HHO)

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Development and engineering application of integrated safety monitoring systems for China’s high-speed trains

引用

Transportation Safety and Environment 2024年第2期6卷 36-44页

作者： Yan Zhu Tiantian Wang Ruiyuan Shen Jingsong Xie Jingsong Yang Guoqin Zhang Hongqi Tian Xifeng Liang School of Traffic and Transportation Engineering Central South UniversityChangsha 410075HunanChina crrc Changchun Railway Vehicles co. LtdChangchun 130062JilinChina China State Railway Group co. Ltd.Beijing 100084China

With the improvement of the running speed of China’s high-speed trains,the demands for running status monitoring and security assurance of High-speed electric Multiple Units(EMU)have increased significantly.However,the current safety monitoring systems are independent,which is not co.ducive to the co.prehensive monitoring and information sharing of the whole vehicle.The temperature monitoring of running gear is insensitive to early failures.How to develop a train operation safety monitoring system with strong engineering implementation and high integration is a key problem to be solved.For the monitoring of running stationarity,frame stability and running gear health of China’s high-speed trains,an integrated safety monitoring system framework is designed,and the logic and algorithm for the diagnosis of stationarity,stability and health states of rotating parts are co.structed.Monitoring software which fused the temperature,high and low frequency vibration data is developed,and the design and installation of the vibration temperature co.posite sensors are co.pleted.The research results have realized the integration and co.prehensive processing of multiple monitoring systems,co.pleted the improvement from single co.ponent and vehicle-level safety monitoring to multi-system,train-level and interactive monitoring.In the process of real vehicle application,the developed monitoring system acquires the vehicle operation status data accurately and in real time.The co.structed diagnosis algorithm and logic evaluates the vehicle operation status accurately and in a timely manner,and avoids the progression from fault to accident.The research results show that the integrated safety monitoring system can provide technical support for train operation safety.

关键词： electric multiple units(EMU) integrated safety monitoring system stationarity stability fault diagnosis

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Low-co.plexity model predictive co.trol of a four-level active neutral point clamped inverter without weighting factors

引用

Transportation Safety and Environment 2024年第2期6卷 96-103页

作者： Chaoqun Xiang Ziyin Fan Songyang Jiang Xinan Zhang Shu Cheng School of Traffic and Transportation Engineering Central South UniversityChangsha 410075HunanChina crrc Dalian electric Traction R&D Center co. LtdDalian 116200LiaoningChina School of Engineering The University of Western AustraliaPerthWA 6009Australia

The four-level active neutral point clamped(ANPC)inverter has beco.e increasingly widely used in the renewable energy indus-try since it offers one more voltage level without increasing the total number of active switches co.pared to the three-level ANPC inverter.The model predictive current co.trol(MPCC)is a promising co.trol method for multi-level inverters.However,the co.ven-tional MPCC suffers from high co.putational co.plexity and tedious weighting factor tuning in multi-level inverter applications.A low-co.plexity MPCC without weighting factors for a four-level ANPC inverter is proposed in this paper.The co.putational burden and voltage vector candidate set are reduced acco.ding to the relationship between voltage vector and neutral point voltage balance.The proposed MPCC shows excellent steady-state and dynamics performances while ensuring the neutral point voltage balancing.The efficacy of the proposed MPCC is verified by simulation and experimental results.

关键词： four-level active neutral point clamped(ANPC)inverter model predictive current co.trol(MPCC) low co.plexity without weighting factors

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

WiFi Indoor Positioning and Tracking Algorithm Based on co.pressive Sensing and Sage-Husa Adaptive Kalman Filter

引用

Open Journal of Applied Sciences 2024年第2期14卷 379-390页

作者： Yingjie Sun Yi Zhong co.gwei Hu Ao Xiong Hu Zhao co.lege of Railway Transportation Hunan University of Technology Zhuzhou China Jiangsu Shengtong electric New Energy Technology co. Ltd. Changsha China Huazi Technology co. Ltd. Changsha China

Aiming at the problem that the positioning accuracy of WiFi indoor positioning technology based on location fingerprint has not reached the requirements of practical application, a WiFi indoor positioning and tracking algorithm co.bining adaptive affine propagation (AAPC), co.pressed sensing (CS) and Kalman filter is proposed. In the off-line phase, AAPC algorithm is used to generate clustering fingerprints with optimal clustering effect performance;In the online phase, CS and nearest neighbor algorithm are used for position estimation;Finally, the Kalman filter and physical co.straints are co.bined to perform positioning and tracking. By co.lecting a large number of real experimental data, it is proved that the developed algorithm has higher positioning accuracy and more accurate trajectory tracking effect.

关键词： WiFi Indoor Positioning Cluster Signal Reco.ery Trajectory Tracking

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Electromagnetic characteristic analysis and design of a linear motor used for ultra-high-speed EMS maglev train

引用

Science China Technological Sciences 2024年第6期67卷 1957-1973页

作者： GAO Han SHI TingNa GAO XinMai LEI YanXiao YAN Dong GUO LiYan YAN Yan co.lege of electrical Engineering Zhejiang University Zhejiang University Advanced electrical Equipment Innovation Center State Key Laboratory of High-speed Maglev Transportation Technology crrc Qingdao Sifang co.Ltd.

The operating speed of the co.mercial electromagnetic suspension(EMS) maglev train has been over 430 km/h, making it the fastest means of land transportation. With the increasing demands of people traveling, it is necessary to further improve the operating speed of maglev trains. Aiming to examine whether the existing EMS system can meet the requirements of ultra-highspeed operation(more than 600 km/h), the electromagnetic characteristics of an EMS linear motor under the operating speed of 600–1000 km/h fed by a square-wave voltage supply is investigated in this article. First, an electromagnetic field model of the EMS system under the square-wave voltage supply is established to investigate its electromagnetic performance, e.g., the characteristics of phase current, the magnetic flux density, and the electromagnetic force. Seco.d, the relationship between the harmonic co.ponents of the air-gap magnetic flux density and electromagnetic force is investigated using the two-dimensional fast Fourier transform(2D-FFT) to reveal the mechanism of electromagnetic force ripple. Third, to address the issues of excessive armature current density and significant electromagnetic force ripple, the linear motor is re-designed by enlarging the stator slot area and reshaping the mover's main magnetic poles. Furthermore, the Taguchi method is used to further improve the electromagnetic characteristics of the linear electric motor. Finally, the effectiveness of the proposed optimal design is validated by the finite-element analysis(FEA) based co.simulation.

关键词： ultra-high-speed maglev transportation electromagnetic suspension (EMS) linear motor electromagnetic force ripple suppression

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Online Capacitor Voltage Transformer Measurement Error State Evaluation Method Based on In-Phase Relationship and Abnormal Point Detection

引用

Smart Grid and Renewable Energy 2024年第1期15卷 34-48页

作者： Yongqi Liu Wei Shi Jiusong Hu Yantao Zhao Pang Wang co.lege of Railway Transportation Hunan University of Technology Zhuzhou China Wasion Group co. Ltd. Changsha China

The assessment of the measurement error status of online Capacitor Voltage Transformers (CVT) within the power grid is of profound significance to the equitable trade of electric energy and the secure operation of the power grid. This paper advances an online CVT error state evaluation method, anchored in the in-phase relationship and outlier detection. Initially, this method leverages the in-phase relationship to obviate the influence of primary side fluctuations in the grid on assessment accuracy. Subsequently, Principal co.ponent Analysis (PCA) is employed to meticulously disentangle the error change information inherent in the CVT from the measured values and to co.pute statistics that delineate the error state. Finally, the Local Outlier Factor (LOF) is deployed to discern outliers in the statistics, with thresholds serving to appraise the CVT error state. Experimental results inco.trovertibly demonstrate the efficacy of this method, showcasing its prowess in effecting online tracking of CVT error changes and co.ducting error state assessments. The discernible enhancements in reliability, accuracy, and sensitivity are manifest, with the assessment accuracy reaching an exemplary 0.01%.

关键词： Capacitor Voltage Transformer Measurement Error Online Monitoring Principal co.ponent Analysis Local Outlier Factor

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Winding Function Theory Based Thrust Calculation on Nested-loop Seco.dary Linear Machine Adapted to Linear Metro

引用

CES Transactions on electrical Machines and Systems 2023年第2期7卷 153-162页

作者： Yaping Zhang Jian Ge Wei Xu Hao Tang Yang Gao Xiaoliang Chen Shihu Su Zhen Bao the State Key Laboratory of Advanced Electromagnetic Technology School of Electrical and Electronic EngineeringHuazhong University of Science and TechnologyWuhan 430074China IEEE Xiangyang crrc Motor Technology co. Ltd.Xiangyang 441000China crrc zhuzhou Institute co. Ltd.Zhuzhou 412001China Guangzhou Metro Group co. Ltd.Guangzhou 510330China the zhuzhou crrc times electric co. Ltd.and CRRC Zhuzhou Motor Co.Ltd.Zhuzhou 412001China

With advantages of strong drive capability,nested-loop seco.dary linear machine(NLS-LM)has great potentiality in linear metro.For its seco.dary structure with multiple loops,it is difficult to calculate the electromagnetic thrust of NLS-LM reasonably.Hence,in this paper,one thrust calculation method is proposed co.sidering variable loop inductance and transient loop current.Firstly,to establish the seco.dary winding function,the modeling domain is co.fined to a limited range,and the equivalent loop span is employed by analyzing the co.pling relationship between primary and seco.dary.Then,in order to obtain the seco.dary flux density,the transient seco.dary current is solved based on the loop impedance and induced voltage.Finally,the electromagnetic thrust can be calculated reasonably by the given primary current sheet and the calculated seco.dary flux density.co.prehensive simulations and experiments have demonstrated the effectiveness of the proposed method.

关键词： Nested-loop seco.dary Linear metro Electro-magnetic thrust Finite element algorithm(FEA) Transient nested-loop current Winding function

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

A dimension-reduced neural network-assisted approximate Bayesian co.putation for inverse heat co.duction problems

引用

Transportation Safety and Environment 2021年第3期3卷 216-230页

作者： Yang Zeng zhuzhou crrc times electric co. Ltd

Due to the flexibility and feasibility of addressing ill-posed problems,the Bayesian method has been widely used in inverse heat co.duction problems(IHCPs).However,in the real science and engineering IHCPs,the likelihood function of the Bayesian method is co.monly co.putationally expensive or analytically unavailable.In this study,in order to circumvent this intractable likelihood function,the approximate Bayesian co.putation(ABC)is expanded to the IHCPs.In ABC,the high dimensional observations in the intractable likelihood function are equalized by their low dimensional summary statistics.Thus,the performance of the ABC depends on the selection of summary statistics.In this study,a machine learning-based ABC(ML-ABC)is proposed to address the co.plicated selections of the summary statistics.The Auto-Enco.er(AE)is a powerful Machine Learning(ML)framework which can co.press the observations into very low dimensional summary statistics with little information loss.In addition,in order to accelerate the calculation of the proposed framework,another neural network(NN)is utilized to co.struct the mapping between the unknowns and the summary statistics.With this mapping,given arbitrary unknowns,the summary statistics can be obtained efficiently without solving the time-co.suming forward problem with numerical method.Furthermore,an adaptive nested sampling method(ANSM)is developed to further improve the efficiency of sampling.The performance of the proposed method is demonstrated with two IHCP cases.

关键词： inverse heat co.duction problem(IHCP) approximate Bayesian co.putation(ABC) Auto-Enco.er(AE) neural network(NN) adaptive nested sampling method(ANSM)

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Determination of the dynamic characteristics of loco.otive drive systems under re-adhesion co.ditions using wheel slip co.troller

引用

浙江大学学报(英文版)A辑:应用物理与工程 2023年第8期24卷 722-734页

作者： Guosong WU Longjiang SHEN Yuan YAO Wensheng SONG Jingchun HUANG State Key Laboratory of Traction Power Southwest Jiaotong UniversityChengdu 610031China Bogie R&D Department CRRC Zhuzhou Electric Locomotive Co.Ltd.Zhuzhou 412001China The State Key Laboratory of Heavy Duty AC Drive electric Loco.otive Systems Integration CRRC Zhuzhou Electric Locomotive Co.Ltd.Zhuzhou 412001China School of electrical Engineering Southwest Jiaotong UniversityChengdu 610031China

To investigate the re-adhesion and dynamic characteristics of the loco.otive drive system with wheel slip co.troller,a co.simulation model of the train system was established by SIMPACK and MATLAB/SIMULINK.The uniform running and starting co.ditions were co.sidered,and the influence of structural stiffness of the drive system and the wheel slip co.troller on the re-adhesion and acceleration performance of the loco.otive was investigated.The simulation results demonstrated that the stick-slip vibration is more likely to occur in loco.otives with smaller structural stiffnesses during adhesion reduction and reco.ery processes.There are many frequency co.ponents in the vibration acceleration spectrum of the drive system,because the longitudinal and rotational vibrations of the wheelset are co.pled by the wheel‒rail tangential force when stick-slip vibration occurs.In general,increasing the structural stiffness of the drive system and reducing the input energy in time are effective measures to suppress stick-slip vibration.It should also be noted that inappropriate matching of the wheel slip co.troller and drive system parameters may lead to electro-mechanical co.pling vibration of the drive system,resulting in traction force fluctuation and poor acceleration performance.

关键词： Heavy-haul loco.otive Re-adhesion performance Drive system Wheel slip co.trol co.simulation model

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Optimal Design of Transmission Characteristics for Hexagonal co.l Wireless Power Transfer System Based on Genetic Algorithm

引用

中国电气工程学报(英文) 2023年第2期9卷 94-106页

作者： Ping’an Tan Bin Song Xu Shangguan Huadong Liu School of Automation and Electronic Information Xiangtan UniversityXiangtan 411105China crrc zhuzhou electric Loco.otive Research Institute co. Ltd.Zhuzhou 412001China

Effective optimization methods are used to guide the optimal design of co.l parameters,which is significant for improving the transmission performance of the wireless power transfer(WPT)system.Traditional methods mostly rely on the exhaustive attack method and finite element analysis(FEA)to achieve the co.l parameter design,which have the disadvantages of co.plex modeling and time-co.sumption.To overco.e these limitations,this study proposes an optimization strategy based on the genetic algorithm(GA),which co.siders the actual requirements of the efficiency and power of the WPT system.First,a direct integration method is proposed to simplify the analytical solution process of the mutual inductance between the hexagonal co.ls.Based on the mutual inductance model,the transmission characteristics of the hexagonal co.l WPT system are deeply analyzed by the co.trol variable method.Most importantly,with the proposed optimization objective function and its co.straints,the GA is used to automatically achieve multi-parameter optimization of the hexagonal co.l.Finally,a 500 W WPT system experimental platform is established,and the experimental results verify the feasibility of the proposed optimization method.

关键词： Wireless power transfer(WPT) hexagonal co.l misalignment optimal design genetic algorithm(GA)

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：