资源类型

期刊论文 413

会议视频 7

年份

2023 68

2022 78

2021 45

2020 46

2019 31

2018 20

2017 33

2016 13

2015 13

2014 4

2013 5

2012 7

2011 8

2010 2

2009 8

2008 3

2007 4

2006 3

2005 1

2002 1

展开 ︾

关键词

机器学习 27

深度学习 15

人工智能 12

代理模型 2

增材制造 2

强化学习 2

材料设计 2

结构健康监测 2

高层建筑 2

2D—3D配准 1

3D打印 1

6G 1

9 %~12 % Cr 钢 1

&prime 1

&gamma 1

ARM 1

CAN总线 1

CCUS 1

CDMA 1

展开 ︾

检索范围:

排序: 展示方式:

Multiple fault separation and detection by joint subspace learning for the health assessment of wind

Zhaohui DU, Xuefeng CHEN, Han ZHANG, Yanyang ZI, Ruqiang YAN

《机械工程前沿(英文)》 2017年 第12卷 第3期   页码 333-347 doi: 10.1007/s11465-017-0435-0

摘要:

The gearbox of a wind turbine (WT) has dominant failure rates and highest downtime loss among all WT subsystems. Thus, gearbox health assessment for maintenance cost reduction is of paramount importance. The concurrence of multiple faults in gearbox components is a common phenomenon due to fault induction mechanism. This problem should be considered before planning to replace the components of the WT gearbox. Therefore, the key fault patterns should be reliably identified from noisy observation data for the development of an effective maintenance strategy. However, most of the existing studies focusing on multiple fault diagnosis always suffer from inappropriate division of fault information in order to satisfy various rigorous decomposition principles or statistical assumptions, such as the smooth envelope principle of ensemble empirical mode decomposition and the mutual independence assumption of independent component analysis. Thus, this paper presents a joint subspace learning-based multiple fault detection (JSL-MFD) technique to construct different subspaces adaptively for different fault patterns. Its main advantage is its capability to learn multiple fault subspaces directly from the observation signal itself. It can also sparsely concentrate the feature information into a few dominant subspace coefficients. Furthermore, it can eliminate noise by simply performing coefficient shrinkage operations. Consequently, multiple fault patterns are reliably identified by utilizing the maximum fault information criterion. The superiority of JSL-MFD in multiple fault separation and detection is comprehensively investigated and verified by the analysis of a data set of a 750 kW WT gearbox. Results show that JSL-MFD is superior to a state-of-the-art technique in detecting hidden fault patterns and enhancing detection accuracy.

关键词: joint subspace learning     multiple fault diagnosis     sparse decomposition theory     coupling feature separation     wind turbine gearbox    

Finite element model updating of a large structure using multi-setup stochastic subspace identification

Reza KHADEMI-ZAHEDI, Pouyan ALIMOURI

《结构与土木工程前沿(英文)》 2019年 第13卷 第4期   页码 965-980 doi: 10.1007/s11709-019-0530-x

摘要: In the present contribution, operational modal analysis in conjunction with bees optimization algorithm are utilized to update the finite element model of a solar power plant structure. The physical parameters which required to be updated are uncertain parameters including geometry, material properties and boundary conditions of the aforementioned structure. To determine these uncertain parameters, local and global sensitivity analyses are performed to increase the solution accuracy. An objective function is determined using the sum of the squared errors between the natural frequencies calculated by finite element method and operational modal analysis, which is optimized using bees optimization algorithm. The natural frequencies of the solar power plant structure are estimated by multi-setup stochastic subspace identification method which is considered as a strong and efficient method in operational modal analysis. The proposed algorithm is efficiently implemented on the solar power plant structure located in Shahid Chamran university of Ahvaz, Iran, to update parameters of its finite element model. Moreover, computed natural frequencies by numerical method are compared with those of the operational modal analysis. The results indicate that, bees optimization algorithm leads accurate results with fast convergence.

关键词: operational modal analysis     solar power plant structure     multi-setup stochastic subspace     bees optimization algorithm     sensitivity analysis    

基于代价敏感学习的实体-关系联合知识嵌入 Article

Sheng-kang YU, Xue-yi ZHAO, Xi LI, Zhong-fei ZHANG

《信息与电子工程前沿(英文)》 2017年 第18卷 第11期   页码 1867-1873 doi: 10.1631/FITEE.1601255

摘要: 我们将实体嵌入问题看作同时完成两个不同但相关的嵌入任务(实体嵌入和关系嵌入)的联合优化问题,并在联合嵌入框架下求解该问题。在该嵌入框架下,我们设计了联合评分函数,用以对实体和关系间的相关性实例进行量化评价,并将评分函数融入最大间隔学习方法中,使用知识库中的上下文信息学习实体与关系的嵌入向量。通过求解联合优化问题,我们的设计有效地表达了嵌入空间的固有拓扑结构。实验结果证实了我们的嵌入框架在表达不同关系的语义相关性和进行知识推理中的关系预测时的有效性。

关键词: 知识嵌入;联合嵌入;代价敏感学习    

Analytical algorithms of compressive bending capacity of bolted circumferential joint in metro shield

《结构与土木工程前沿(英文)》   页码 901-914 doi: 10.1007/s11709-023-0915-8

摘要: The integrity and bearing capacity of segment joints in shield tunnels are associated closely with the mechanical properties of the joints. This study focuses on the mechanical characteristics and mechanism of a bolted circumferential joint during the entire bearing process. Simplified analytical algorithms for four stress stages are established to describe the bearing behaviors of the joint under a compressive bending load. A height adjustment coefficient, α, for the outer concrete compression zone is introduced into a simplified analytical model. Factors affecting α are determined, and the degree of influence of these factors is investigated via orthogonal numerical simulations. The numerical results show that α can be specified as approximately 0.2 for most metro shield tunnels in China. Subsequently, a case study is performed to verify the rationality of the simplified theoretical analysis for the segment joint via numerical simulations and experiments. Using the proposed simplified analytical algorithms, a parametric investigation is conducted to discuss the factors affecting the ultimate compressive bending capacity of the joint. The method for optimizing the joint flexural stiffness is clarified. The results of this study can provide a theoretical basis for optimizing the design and prediciting the damage of bolted segment joints in shield tunnels.

关键词: shield tunnel     segment joint     joint structural model     failure mechanism    

联合局部学习和组稀疏回归的无监督特征选择 Regular Papers

Yue WU, Can WANG, Yue-qing ZHANG, Jia-jun BU

《信息与电子工程前沿(英文)》 2019年 第20卷 第4期   页码 538-553 doi: 10.1631/FITEE.1700804

摘要: 近十年,特征选择备受关注。通过挑选特征子集,可有效提升学习算法效率。由于难以获取标签信息,无监督特征选择算法相较于有监督特征选择算法应用更为广泛,其关键在于找出更能反映数据分布的特征集合。由于数据集中存在冗余和噪声,使用全部特征并不能很好展现数据的真实分布。为解决这一问题,本文提出联合局部学习和组稀疏回归的无监督特征选择算法。将基于局部学习聚类方法与组稀疏回归算法有机整合,选出有效反映数据流形分布同时保持组稀疏结构的特征。通过迭代算法,回归系数汇聚到重要特征上,选出能得到更优聚类效果的特征。对多个实际数据集(图像、声音和网页)的实验证明了该算法的有效性。

关键词: 无监督;局部学习;组稀疏回归;特征选择    

Finite element analysis on the seismic behavior of side joint of Prefabricated Cage System in prefabricated

Yunlin LIU, Shitao ZHU

《结构与土木工程前沿(英文)》 2019年 第13卷 第5期   页码 1095-1104 doi: 10.1007/s11709-019-0538-2

摘要: The Prefabricated Cage System (PCS) has the advantages of high bearing capacity and good ductility. Meanwhile, it is convenient for factory production and it is beneficial to the cost savings, construction period shortening. Side joint is the weak region of PCS concrete frame and has great influence on seismic behavior of the whole structure. Thus systematically study on the seismic behavior of PCS concrete side joint is necessary. This paper presents a finite element study on behavior of the side joint under seismic loading. In the finite element model, PCS concrete and the reinforced concrete (RC) is modeled by the solid element and fiber-beam element, respectively. The numerical results is compared with the experimental results and it is found that the results of model based on fiber-beam element is in better agreement with the experimental results than solid element model. In addition, the overall seismic behavior of the side joints in PCS concrete is better than that of the RC with the same strength.

关键词: PCS concrete side joint     numerical simulation     fiber-beam element joint model     solid element joint model     seismic behavior    

基于随机矩阵理论的子空间加权改良算法 Research Articles

高雨濛1,李姜辉2,柏业超1,王琼1,张兴敢1

《信息与电子工程前沿(英文)》 2020年 第21卷 第9期   页码 1302-1307 doi: 10.1631/FITEE.1900463

摘要: 在低信噪比及信号相关情况下,加权子空间拟合(WSF)算法的性能优于多信号分类(MUSIC)算法。本文使用随机矩阵理论(RMT)改善加权子空间拟合。随机矩阵理论研究随机矩阵维数以同速率增加时,矩阵特征值和特征向量的渐近规律。加权子空间拟合中,运用近似一阶扰动计算样本协方差矩阵特征向量的统计特性。利用随机矩阵理论中关于样本协方差矩阵信号子空间向真实信号投影的范数的渐进结果,获得加权子空间拟合计算方法。仿真结果表明,在低快拍数及低信噪比情况下,本文所提方法具有优越性。

关键词: 波达方向;信号子空间;随机矩阵理论    

利用子空间的投影和跟踪改进OFDM信道估计

董亮,曹秀英,毕光国

《中国工程科学》 2006年 第8卷 第11期   页码 86-93

摘要:

OFDM系统的LS信道估计可看作真实信道频率响应的一个有噪观察值,因此可采用子空间投影方法对噪声进行压缩。分析了利用子空间投影方法改进LSOFDM信道估计性能的实质,给出了利用子空间投影改进OFDM信道估计的一般框架,在此基础上将子空间投影推广到非LS信道估计方法。当信号子空间随时间变化时,需要采用子空间跟踪技术保持对信号子空间的良好估计,因此提出了一种基于子空间跟踪的参数化信道估计方法,仿真表明这种方法在性能上优于非参数化时的相应方法。

关键词: OFDM     子空间     投影     跟踪     信道估计    

基于子空间的离散时滞系统辨识 Article

Qiang LIU,Jia-chen MA

《信息与电子工程前沿(英文)》 2016年 第17卷 第6期   页码 566-575 doi: 10.1631/FITEE.1500358

摘要: 本文研究了具有未知时延的线性随机时滞系统的辨识问题。时滞系统被表达为具有单一时延的时滞差分方程。首先利用状态增广方法将时滞系统转化为一个等价的线性时不变系统,然后采用传统的子空间辨识方法来估计增广系统矩阵。本文提出了一种ACS算法,从而得到时滞系统的状态空间模型。最后,基于ACS算法得到的相似变换,重新得到卡尔曼状态序列。采用最小二乘法,利用卡尔曼状态序列和输入输出数据,得出相同状态空间下的时滞系统矩阵。仿真结果表明了这种算法的有效性。

关键词: 辨识问题;时滞系统;子空间辨识方法;ACS算法;最小二乘法    

Dynamic characteristics of a magnetorheological pin joint for civil structures

Yancheng LI,Jianchun LI

《机械工程前沿(英文)》 2014年 第9卷 第1期   页码 15-33 doi: 10.1007/s11465-014-0283-0

摘要:

Magnetorheological (MR) pin joint is a novel device in which its joint moment resistance can be controlled in real-time by altering the applied magnetic field. The smart pin joint is intended to be used as a controllable connector between the columns and beams of a civil structure to instantaneously shift the structural natural frequencies in order to avoid resonance and therefore to reduce unwanted vibrations and hence prevent structural damage. As an intrinsically nonlinear device, modelling of this MR fluid based device is a challenging task and makes the design of a suitable control algorithm a cumbersome situation. Aimed at its application in civil structure, the main purpose of this paper is to test and characterise the hysteretic behaviour of MR pin joint. A test scheme is designed to obtain the dynamic performance of MR pin joint in the dominant earthquake frequency range. Some unique phenomena different from those of MR damper are observed through the experimental testing. A computationally-efficient model is proposed by introducing a hyperbolic element to accurately reproduce its dynamic behaviour and to further facilitate the design of a suitable control algorithm. Comprehensive investigations on the model accuracy and dependences of the proposed model on loading condition (frequency and amplitude) and input current level are reported in the last section of this paper.

关键词: Magnetorheological pin joint     hyperbolic hysteresis model experimental testing frequency dependence    

基于人体髋关节转动中心分析的髋关节外骨骼仿生设计 Article

Wei YANG,Can-jun YANG,Ting XU

《信息与电子工程前沿(英文)》 2016年 第17卷 第8期   页码 792-802 doi: 10.1631/FITEE.1500286

摘要: 为了改善外骨骼穿戴舒适性,本文提出了一种基于人机物理交互优化的外骨骼设计方法。该方法通过设计外骨骼髋关节,使其保证人体髋关节运动时外骨骼髋关节转动中心能跟随人体髋关节转动中心的运动轨迹。当人体髋关节运动时,通过实验测量和计算可以得到其转动中心轨迹。本文设计的外骨骼髋关节运动机构能在人体髋关节屈曲/伸展和外展/内收时,保证转动中心都能够包容人体髋关节转动中心运动范围。同时,所设计的外骨骼髋关节被应用到下肢步行康复训练外骨骼中。通过人机接触力实验可知,与传统设计外骨骼髋关节进行相比,本文设计的仿生髋关节外骨骼在髋关节屈曲/伸展和内收/外展时分别可以减小24.1%和76.0%的人机接触力。这一结果证明仿生设计髋关节外骨骼更具穿戴舒适性,更符合人机工程学的设计要求。最后,本文通过建立人机闭式链模型进一步分析了仿生设计对于人体髋关节内力的影响,并验证该设计能减少关节内力作用。

关键词: 髋关节外骨骼;髋关节中心;柔顺关节;人机交互力    

Identification of dynamic stiffness matrix of bearing joint region

Feng HU, Bo WU, Youmin HU, Tielin SHI

《机械工程前沿(英文)》 2009年 第4卷 第3期   页码 289-299 doi: 10.1007/s11465-009-0064-3

摘要: The paper proposes an identification method of the dynamic stiffness matrix of a bearing joint region on the basis of theoretical analysis and experiments. The author deduces an identification model of the dynamic stiffness matrix from the synthetic substructure method. The dynamic stiffness matrix of the bearing joint region can be identified by measuring the matrix of frequency response function (FRFs) of the substructure (axle) and whole structure (assembly of the axle, bearing, and bearing housing) in different positions. Considering difficulty in measuring angular displacement, applying moment, and directly measuring relevant FRFs of rotational degree of freedom, the author employs an accurately calibrated finite element model of the unconstrained structure for indirect estimation. With experiments and simulation analysis, FRFs related with translational degree of freedom, which is estimated through the finite element model, agrees with experimental results, and there is very high reliability in the identified dynamic stiffness matrix of the bearing joint region.

关键词: frequency response function (FRFs)     dynamic stiffness     finite element     synthetic substructure method     joint region    

Joint slip investigation based on finite element modelling verified by experimental results on wind turbine

Saleh YAGHOOBI, Ahmad SHOOSHTARI

《结构与土木工程前沿(英文)》 2018年 第12卷 第3期   页码 341-351 doi: 10.1007/s11709-017-0393-y

摘要:

Slippage corresponds to the relative displacement of a bolted joint subjected to shear loads since the construction clearance between the bolt shank and the bolthole at assembly can cause joint slip. Deflections of towers with joint slippage effects is up to 1.9 times greater than the displacements obtained by linear analytical methods. In this study, 8 different types of joints are modelled and studied in the finite element program, and the results are verified by the experimental results which have been done in the laboratory. Moreover, several types of joints have been modelled and studied and load-deformation curves have also been presented. Finally, joint slip data for different types of angles, bolt diameter and bolt arrangements are generated. Thereupon, damping ratios (z) for different types of connections are reported. The study can be useful to help in designing of wind turbine towers with a higher level of accuracy and safety.

关键词: Joint slip     cyclic loading     Finite element modelling     Experimental joint behavior     damping ratios (   

General closed-form inverse kinematics for arbitrary three-joint subproblems based on the product of

《机械工程前沿(英文)》 2022年 第17卷 第2期 doi: 10.1007/s11465-022-0681-7

摘要: The inverse kinematics problems of robots are usually decomposed into several Paden–Kahan subproblems based on the product of exponential model. However, the simple combination of subproblems cannot solve all the inverse kinematics problems, and there is no common approach to solve arbitrary three-joint subproblems in an arbitrary postural relationship. The novel algebraic geometric (NAG) methods that obtain the general closed-form inverse kinematics for all types of three-joint subproblems are presented in this paper. The geometric and algebraic constraints are used as the conditions precedent to solve the inverse kinematics of three-joint subproblems. The NAG methods can be applied in the inverse kinematics of three-joint subproblems in an arbitrary postural relationship. The inverse kinematics simulations of all three-joint subproblems are implemented, and simulation results indicating that the inverse solutions are consistent with the given joint angles validate the general closed-form inverse kinematics. Huaque III minimally invasive surgical robot is used as the experimental platform for the simulation, and a master–slave tracking experiment is conducted to verify the NAG methods. The simulation result shows the inverse solutions and six sets given joint angles are consistent. Additionally, the mean and maximum of the master–slave tracking experiment for the closed-form solution are 0.1486 and 0.4777 mm, respectively, while the mean and maximum of the master–slave tracking experiment for the compensation method are 0.3188 and 0.6394 mm, respectively. The experiments results demonstrate that the closed-form solution is superior to the compensation method. The results verify the proposed general closed-form inverse kinematics based on the NAG methods.

关键词: inverse kinematics     Paden–Kahan subproblems     three-joint subproblems     product of exponential     closed-form solution    

Multi-omics joint analysis revealed the metabolic profile of retroperitoneal liposarcoma

《医学前沿(英文)》 doi: 10.1007/s11684-023-1020-z

摘要: Retroperitoneal liposarcoma (RLPS) is the main subtype of retroperitoneal soft sarcoma (RSTS) and has a poor prognosis and few treatment options, except for surgery. The proteomic and metabolic profiles of RLPS have remained unclear. The aim of our study was to reveal the metabolic profile of RLPS. Here, we performed proteomic analysis (n = 10), metabolomic analysis (n = 51), and lipidomic analysis (n = 50) of retroperitoneal dedifferentiated liposarcoma (RDDLPS) and retroperitoneal well-differentiated liposarcoma (RWDLPS) tissue and paired adjacent adipose tissue obtained during surgery. Data analysis mainly revealed that glycolysis, purine metabolism, pyrimidine metabolism and phospholipid formation were upregulated in both RDDLPS and RWDLPS tissue compared with the adjacent adipose tissue, whereas the tricarboxylic acid (TCA) cycle, lipid absorption and synthesis, fatty acid degradation and biosynthesis, as well as glycine, serine, and threonine metabolism were downregulated. Of particular importance, the glycolytic inhibitor 2-deoxy-D-glucose and pentose phosphate pathway (PPP) inhibitor RRX-001 significantly promoted the antitumor effects of the MDM2 inhibitor RG7112 and CDK4 inhibitor abemaciclib. Our study not only describes the metabolic profiles of RDDLPS and RWDLPS, but also offers potential therapeutic targets and strategies for RLPS.

关键词: RLPS     proteomics     metabolomics     lipidomics     metabolism    

标题 作者 时间 类型 操作

Multiple fault separation and detection by joint subspace learning for the health assessment of wind

Zhaohui DU, Xuefeng CHEN, Han ZHANG, Yanyang ZI, Ruqiang YAN

期刊论文

Finite element model updating of a large structure using multi-setup stochastic subspace identification

Reza KHADEMI-ZAHEDI, Pouyan ALIMOURI

期刊论文

基于代价敏感学习的实体-关系联合知识嵌入

Sheng-kang YU, Xue-yi ZHAO, Xi LI, Zhong-fei ZHANG

期刊论文

Analytical algorithms of compressive bending capacity of bolted circumferential joint in metro shield

期刊论文

联合局部学习和组稀疏回归的无监督特征选择

Yue WU, Can WANG, Yue-qing ZHANG, Jia-jun BU

期刊论文

Finite element analysis on the seismic behavior of side joint of Prefabricated Cage System in prefabricated

Yunlin LIU, Shitao ZHU

期刊论文

基于随机矩阵理论的子空间加权改良算法

高雨濛1,李姜辉2,柏业超1,王琼1,张兴敢1

期刊论文

利用子空间的投影和跟踪改进OFDM信道估计

董亮,曹秀英,毕光国

期刊论文

基于子空间的离散时滞系统辨识

Qiang LIU,Jia-chen MA

期刊论文

Dynamic characteristics of a magnetorheological pin joint for civil structures

Yancheng LI,Jianchun LI

期刊论文

基于人体髋关节转动中心分析的髋关节外骨骼仿生设计

Wei YANG,Can-jun YANG,Ting XU

期刊论文

Identification of dynamic stiffness matrix of bearing joint region

Feng HU, Bo WU, Youmin HU, Tielin SHI

期刊论文

Joint slip investigation based on finite element modelling verified by experimental results on wind turbine

Saleh YAGHOOBI, Ahmad SHOOSHTARI

期刊论文

General closed-form inverse kinematics for arbitrary three-joint subproblems based on the product of

期刊论文

Multi-omics joint analysis revealed the metabolic profile of retroperitoneal liposarcoma

期刊论文