资源类型

期刊论文 141

年份

2023 10

2022 5

2021 9

2020 7

2019 17

2018 10

2017 13

2016 8

2015 8

2013 3

2012 2

2011 7

2010 2

2009 1

2008 4

2007 5

2006 8

2005 3

2004 5

2003 4

展开 ︾

关键词

可拓集合 5

机器学习 3

CAPP 2

人工智能 2

人脸识别 2

可拓学 2

数据挖掘 2

特征抽取 2

2 Mb/s高速信令 1

2019-nCoV 1

2D—3D配准 1

Agent 1

CAD 1

CAM 1

COVID-19 1

IKPCA 1

IgG 1

KPCA 1

展开 ︾

检索范围：

排序： 展示方式：

Regional wind power forecasting model with NWP grid data optimized

Zhao WANG, Weisheng WANG, Bo WANG

《能源前沿（英文）》 2017年 第11卷 第2期   页码 175-183 doi: 10.1007/s11708-017-0471-9

摘要： Unlike the traditional fossil energy, wind, as the clean renewable energy, can reduce the emission of the greenhouse gas. To take full advantage of the environmental benefits of wind energy, wind power forecasting has to be studied to overcome the troubles brought by the variable nature of wind. Power forecasting for regional wind farm groups is the problem that many power system operators care about. The high-dimensional feature sets with redundant information are frequently encountered when dealing with this problem. In this paper, two kinds of feature set construction methods are proposed which can achieve the proper feature set either by selecting the subsets or by transforming the original variables with specific combinations. The former method selects the subset according to the criterion of minimal-redundancy-maximal-relevance (mRMR), while the latter does so based on the method of principal component analysis (PCA). A locally weighted learning method is also proposed to utilize the processed feature set to produce the power forecast results. The proposed model is simple and easy to use with parameters optimized automatically. Finally, a case study of 28 wind farms in East China is provided to verify the effectiveness of the proposed method.

关键词： regional wind power forecasting     feature set     minimal-redundancy-maximal-relevance (mRMR)     principal component analysis (PCA)     locally weighted learning model    

HTML PDF 收藏

Level set band method: A combination of density-based and level set methods for the topology optimization

Peng WEI, Wenwen WANG, Yang YANG, Michael Yu WANG

《机械工程前沿（英文）》 2020年 第15卷 第3期   页码 390-405 doi: 10.1007/s11465-020-0588-0

摘要： The level set method (LSM), which is transplanted from the computer graphics field, has been successfully introduced into the structural topology optimization field for about two decades, but it still has not been widely applied to practical engineering problems as density-based methods do. One of the reasons is that it acts as a boundary evolution algorithm, which is not as flexible as density-based methods at controlling topology changes. In this study, a level set band method is proposed to overcome this drawback in handling topology changes in the level set framework. This scheme is proposed to improve the continuity of objective and constraint functions by incorporating one parameter, namely, level set band, to seamlessly combine LSM and density-based method to utilize their advantages. The proposed method demonstrates a flexible topology change by applying a certain size of the level set band and can converge to a clear boundary representation methodology. The method is easy to implement for improving existing LSMs and does not require the introduction of penalization or filtering factors that are prone to numerical issues. Several 2D and 3D numerical examples of compliance minimization problems are studied to illustrate the effects of the proposed method.

关键词： level set method     topology optimization     density-based method     level set band    

HTML PDF 收藏

统计不相关最佳鉴别矢量集的本质研究

吴小俊,杨静宇,王士同,刘同明,Josef Kittler

《中国工程科学》 2004年 第6卷 第2期   页码 44-47

摘要：

对统计不相关最佳鉴别矢量集的本质进行研究，在基于总体散布矩阵特征分解的基础上，构造了一种白化变换，使得变换后的样本空间中的总体散布矩阵为单位矩阵，这样使得传统的最佳鉴别矢量集算法得到的均是具有统计不相关的最佳鉴别矢量集，从而揭示了统计不相关最佳鉴别变换的本质——白化变换加普通的线性鉴别变换。该方法的最大优点在于所获得的最优鉴别矢量同时具有正交性和统计不相关性。该方法对代数特征抽取具有普遍适用性。用ORL人脸数据库的数值实验，验证了该方法的有效性。

关键词： 模式识别     特征抽取     鉴别分析     广义最佳鉴别矢量集     人脸识别    

HTML PDF 收藏

采用背景人声简化特征集的说话人识别直方图均衡化方法 Article

Myung-jae KIM, Il-ho YANG, Min-seok KIM, Ha-jin YU

《信息与电子工程前沿（英文）》 2017年 第18卷 第5期   页码 738-750 doi: 10.1631/FITEE.1500380

摘要： 本文提出了一种用于说话人识别技术的直方图均衡化方法。该方法采用了一套增补简化特征集，用以在训练数据和测试数据较短时改进说话人识别的效果。该增补特征集采用选择算法或聚类算法从背景人声中派生得到。当输入语音数据样本不足时，本文提出的方法可作为构建直方图的特征归一化方法使用。另外，该方法作为一种i-vector归一化方法，源于一种目前较为先进的基于i-vector的概率线性判别分析（Probabilistic linear discriminant analysis, PLDA）说话人识别系统。在输入语音和增补集中，用于直方图均衡化的样本值序号均按升序进行估计。新的序列号则按不同种类的序号之和进行排列。随后，该方法采用最新的序列号得出了测试语音样本的累积分布函数。本文将这一方法与倒谱均值归一化（Cepstral mean normalization, CMN）方法、倒谱均值和方差归一化（Cepstral mean and variance normalization, MVN）方法、直方图均衡化（Histogram equalization, HEQ）方法和欧洲电信标准协会模拟前端方法进行了比较。此外，在一具体算例中将该方法性能与采用模糊C-means和K-means算法的贪婪选择算法进行了比较。采用YOHO和ETRI数据库对特征空间进行评估。测试集采用Opus VoIP编码器进行了模拟。本文还采用了2008美国国家标准技术研究所说话人识别评测语料库对该i-vector系统进行了评测。试验结果表明，与传统特征归一化方法相比，当采用所提出的方法时，平均系统性能可得到有效提提升。

关键词： 说话人识别；直方图均衡化；i-vector    

HTML PDF 收藏

Imbalanced fault diagnosis of rotating machinery using autoencoder-based SuperGraph feature learning

《机械工程前沿（英文）》 2021年 第16卷 第4期   页码 829-839 doi: 10.1007/s11465-021-0652-4

摘要： Existing fault diagnosis methods usually assume that there are balanced training data for every machine health state. However, the collection of fault signals is very difficult and expensive, resulting in the problem of imbalanced training dataset. It will degrade the performance of fault diagnosis methods significantly. To address this problem, an imbalanced fault diagnosis of rotating machinery using autoencoder-based SuperGraph feature learning is proposed in this paper. Unsupervised autoencoder is firstly used to compress every monitoring signal into a low-dimensional vector as the node attribute in the SuperGraph. And the edge connections in the graph depend on the relationship between signals. On the basis, graph convolution is performed on the constructed SuperGraph to achieve imbalanced training dataset fault diagnosis for rotating machinery. Comprehensive experiments are conducted on a benchmarking publicized dataset and a practical experimental platform, and the results show that the proposed method can effectively achieve rotating machinery fault diagnosis towards imbalanced training dataset through graph feature learning.

关键词： imbalanced fault diagnosis     graph feature learning     rotating machinery     autoencoder    

HTML PDF 收藏

Maximum independent set in planning freight railway transportation

Gainanov Damir N., Mladenovic NENAD, Rasskazova V. A.

《工程管理前沿（英文）》 2018年 第5卷 第4期   页码 499-506 doi: 10.15302/J-FEM-2018031

摘要：

This work is devoted to the problem of planning of freight railway transportation. We define a special conflict graph on the basis of a set of acceptable train routes. The investigation aims to solve the classical combinatorial optimization problem in relation to the maximum independent set of vertices in undirected graphs. The level representation of the graph and its tree are introduced. With use of these constructions, the lower and upper bounds for the number of vertices in the maximum independent set are obtained.

关键词： independent set     algorithm     planning of transportation     two-sided estimate    

HTML PDF 收藏

Operating mechanism and set pair analysis model of a sustainable water resources system

Chaoyang DU,Jingjie YU,Huaping ZHONG,Dandan WANG

《环境科学与工程前沿（英文）》 2015年 第9卷 第2期   页码 288-297 doi: 10.1007/s11783-014-0642-4

摘要： There is no alternative to the world’s water resources, and their increasing scarcity is making it difficult to meet the world population’s water needs. This paper presents a sustainable water resources system (SWRS) and analyzes the operating mechanism that makes it possible to evaluate the status of such a system. A SWRS can be described as a complex coupling system that integrates water resources, social, economic and ecological systems into a whole. The SWRS’s operating mechanism is composed of dynamic, resistance and coordination components, and it interacts with and controls the system’s evolution process. The study introduces a new approach, set pair analysis theory, to measure the state of a SWRS, and an evaluation index system is established using the subsystems and operating mechanism of a SWRS. The evaluation index system is separated into three levels (goal level, criteria level and index level) and divides the index standard into five grades. An evaluation model of the SWRS based on set pair analysis theory is constructed, and an example of SWRS evaluation in Shanghai is presented. The connection degrees of the index in the three levels are calculated, and the connection degree of the goal index is calculated to be 0.342, which classifies the city’s SWRS condition as grade 2. The sustainable use of water resources in the region is determined to be at a relatively adequate level that meets the requirements of sustainable development.

关键词： sustainable water resources system     operating mechanism     set pair analysis model     Shanghai    

HTML PDF 收藏

Dynamic simulation of gas turbines via feature similarity-based transfer learning

Dengji ZHOU, Jiarui HAO, Dawen HUANG, Xingyun JIA, Huisheng ZHANG

《能源前沿（英文）》 2020年 第14卷 第4期   页码 817-835 doi: 10.1007/s11708-020-0709-9

摘要： Since gas turbine plays a key role in electricity power generating, the requirements on the safety and reliability of this classical thermal system are becoming gradually strict. With a large amount of renewable energy being integrated into the power grid, the request of deep peak load regulation for satisfying the varying demand of users and maintaining the stability of the whole power grid leads to more unstable working conditions of gas turbines. The startup, shutdown, and load fluctuation are dominating the operating condition of gas turbines. Hence simulating and analyzing the dynamic behavior of the engines under such instable working conditions are important in improving their design, operation, and maintenance. However, conventional dynamic simulation methods based on the physic differential equations is unable to tackle the uncertainty and noise when faced with variant real-world operations. Although data-driven simulating methods, to some extent, can mitigate the problem, it is impossible to perform simulations with insufficient data. To tackle the issue, a novel transfer learning framework is proposed to transfer the knowledge from the physics equation domain to the real-world application domain to compensate for the lack of data. A strong dynamic operating data set with steep slope signals is created based on physics equations and then a feature similarity-based learning model with an encoder and a decoder is built and trained to achieve feature adaptive knowledge transferring. The simulation accuracy is significantly increased by 24.6% and the predicting error reduced by 63.6% compared with the baseline model. Moreover, compared with the other classical transfer learning modes, the method proposed has the best simulating performance on field testing data set. Furthermore, the effect study on the hyper parameters indicates that the method proposed is able to adaptively balance the weight of learning knowledge from the physical theory domain or from the real-world operation domain.

关键词： gas turbine     dynamic simulation     data-driven     transfer learning     feature similarity    

HTML PDF 收藏

Build orientation determination of multi-feature mechanical parts in selective laser melting via multi-objective

《机械工程前沿（英文）》 2023年 第18卷 第2期 doi: 10.1007/s11465-022-0737-8

摘要： Selective laser melting (SLM) is a unique additive manufacturing (AM) category that can be used to manufacture mechanical parts. It has been widely used in aerospace and automotive using metal or alloy powder. The build orientation is crucial in AM because it affects the as-built part, including its part accuracy, surface roughness, support structure, and build time and cost. A mechanical part is usually composed of multiple surface features. The surface features carry the production and design knowledge, which can be utilized in SLM fabrication. This study proposes a method to determine the build orientation of multi-feature mechanical parts (MFMPs) in SLM. First, the surface features of an MFMP are recognized and grouped for formulating the particular optimization objectives. Second, the estimation models of involved optimization objectives are established, and a set of alternative build orientations (ABOs) is further obtained by many-objective optimization. Lastly, a multi-objective decision making method integrated by the technique for order of preference by similarity to the ideal solution and cosine similarity measure is presented to select an optimal build orientation from those ABOs. The weights of the feature groups and considered objectives are achieved by a fuzzy analytical hierarchy process. Two case studies are reported to validate the proposed method with numerical results, and the effectiveness comparison is presented. Physical manufacturing is conducted to prove the performance of the proposed method. The measured average sampling surface roughness of the most crucial feature of the bracket in the original orientation and the orientations obtained by the weighted sum model and the proposed method are 15.82, 10.84, and 10.62 μm, respectively. The numerical and physical validation results demonstrate that the proposed method is desirable to determine the build orientations of MFMPs with competitive results in SLM.

关键词： selective laser melting (SLM)     build orientation determination     multi-feature mechanical part (MFMP)     fuzzy analytical hierarchy process     multi-objective decision making (MODM)    

HTML PDF 收藏

提升KPCA方法特征抽取效率的算法设计

徐勇,杨静宇,陆建峰

《中国工程科学》 2005年 第7卷 第10期   页码 38-42

摘要：

在PCA基础上发展出的KPCA方法能抽取样本的非线性特征分量。然而, 基于KPCA的特征抽取需计算所有训练样本与待抽取特征的样本间的核函数, 因此, 训练集的大小制约着特征抽取的效率。为了提高效率，假设特征空间中变换轴可由一部分训练样本(节点)线性表出，并设计了改进的KPCA算法(IKPCA)。该算法抽取某样本特征时，只需计算该样本与节点间的核函数即可。实验结果显示，IKPCA在对应较好性能的同时，具有明显的效率上的优势。

关键词： KPCA     IKPCA     特征抽取     特征空间    

HTML PDF 收藏

XFEM schemes for level set based structural optimization

Li LI, Michael Yu WANG, Peng WEI

《机械工程前沿（英文）》 2012年 第7卷 第4期   页码 335-356 doi: 10.1007/s11465-012-0351-2

摘要：

In this paper, some elegant extended finite element method (XFEM) schemes for level set method structural optimization are proposed. Firstly, two- dimension (2D) and three-dimension (3D) XFEM schemes with partition integral method are developed and numerical examples are employed to evaluate their accuracy, which indicate that an accurate analysis result can be obtained on the structural boundary. Furthermore, the methods for improving the computational accuracy and efficiency of XFEM are studied, which include the XFEM integral scheme without quadrature sub-cells and higher order element XFEM scheme. Numerical examples show that the XFEM scheme without quadrature sub-cells can yield similar accuracy of structural analysis while prominently reducing the time cost and that higher order XFEM elements can improve the computational accuracy of structural analysis in the boundary elements, but the time cost is increasing. Therefore, the balance of time cost between FE system scale and the order of element needs to be discussed. Finally, the reliability and advantages of the proposed XFEM schemes are illustrated with several 2D and 3D mean compliance minimization examples that are widely used in the recent literature of structural topology optimization. All numerical results demonstrate that the proposed XFEM is a promising structural analysis approach for structural optimization with the level set method.

关键词： structural optimization     level set method     extended finite element method (XFEM)     computational accuracy and efficiency    

HTML PDF 收藏

Level set-based isogeometric topology optimization for maximizing fundamental eigenfrequency

Manman XU, Shuting WANG, Xianda XIE

《机械工程前沿（英文）》 2019年 第14卷 第2期   页码 222-234 doi: 10.1007/s11465-019-0534-1

摘要： Maximizing the fundamental eigenfrequency is an efficient means for vibrating structures to avoid resonance and noises. In this study, we develop an isogeometric analysis (IGA)-based level set model for the formulation and solution of topology optimization in cases with maximum eigenfrequency. The proposed method is based on a combination of level set method and IGA technique, which uses the non-uniform rational B-spline (NURBS), description of geometry, to perform analysis. The same NURBS is used for geometry representation, but also for IGA-based dynamic analysis and parameterization of the level set surface, that is, the level set function. The method is applied to topology optimization problems of maximizing the fundamental eigenfrequency for a given amount of material. A modal track method, that monitors a single target eigenmode is employed to prevent the exchange of eigenmode order number in eigenfrequency optimization. The validity and efficiency of the proposed method are illustrated by benchmark examples.

关键词： topology optimization     level set method     isogeometric analysis     eigenfrequency    

HTML PDF 收藏

composition differences between processed protein from different animal species by self-organizing feature

Xingfan ZHOU,Zengling YANG,Longjian CHEN,Lujia HAN

《农业科学与工程前沿（英文）》 2016年 第3卷 第2期   页码 171-179 doi: 10.15302/J-FASE-2016095

摘要： Amino acids are the dominant organic components of processed animal proteins, however there has been limited investigation of differences in their composition between various protein sources. Information on these differences will not only be helpful for their further utilization but also provide fundamental information for developing species-specific identification methods. In this study, self-organizing feature maps (SOFM) were used to visualize amino acid composition of fish meal, and meat and bone meal (MBM) produced from poultry, ruminants and swine. SOFM display the similarities and differences in amino acid composition between protein sources and effectively improve data transparency. Amino acid composition was shown to be useful for distinguishing fish meal from MBM due to their large concentration differences between glycine, lysine and proline. However, the amino acid composition of the three MBMs was quite similar. The SOFM results were consistent with those obtained by analysis of variance and principal component analysis but more straightforward. SOFM was shown to have a robust sample linkage capacity and to be able to act as a powerful means to link different sample for further data mining.

关键词： self-organizing feature maps     visualization     processed animal proteins (PAPs)     amino acid    

HTML PDF 收藏

Characteristics of plankton Hg bioaccumulations based on a global data set and the implications for aquatic

《环境科学与工程前沿（英文）》 2022年 第16卷 第3期 doi: 10.1007/s11783-021-1471-x

摘要：

• Hg bioaccumulation by phytoplankton varies among aquatic ecosystems.

关键词： Plankton     Hg bioaccumulation     Physiological characteristics     A cross-system analysis     Nutrient compositions     Global data set    

HTML PDF 收藏

The research on structural damage identification using rough set and integrated neural network

Juelong LI, Hairui LI, Jianchun XING, Qiliang YANG

《机械工程前沿（英文）》 2013年 第8卷 第3期   页码 305-310 doi: 10.1007/s11465-013-0259-5

摘要：

A huge amount of information and identification accuracy in large civil engineering structural damage identification has not been addressed yet. To efficiently solve this problem, a new damage identification method based on rough set and integrated neural network is first proposed. In brief, rough set was used to reduce attributes so as to decrease spatial dimensions of data and extract effective features. And then the reduced attributes will be put into the sub-neural network. The sub-neural network can give the preliminary diagnosis from different aspects of damage. The decision fusion network will give the final damage identification results. The identification examples show that this method can simplify the redundant information to reduce the neural network model, making full use of the range of information to effectively improve the accuracy of structural damage identification.

关键词： rough set     integrated neural network     damage identification     decision making fusion    

HTML PDF 收藏

标题 作者 时间 类型 操作

Regional wind power forecasting model with NWP grid data optimized

Zhao WANG, Weisheng WANG, Bo WANG

期刊论文

Level set band method: A combination of density-based and level set methods for the topology optimization

Peng WEI, Wenwen WANG, Yang YANG, Michael Yu WANG

期刊论文

统计不相关最佳鉴别矢量集的本质研究

吴小俊,杨静宇,王士同,刘同明,Josef Kittler

期刊论文

采用背景人声简化特征集的说话人识别直方图均衡化方法

Myung-jae KIM, Il-ho YANG, Min-seok KIM, Ha-jin YU

期刊论文

Imbalanced fault diagnosis of rotating machinery using autoencoder-based SuperGraph feature learning

期刊论文

Maximum independent set in planning freight railway transportation

Gainanov Damir N., Mladenovic NENAD, Rasskazova V. A.

期刊论文

Operating mechanism and set pair analysis model of a sustainable water resources system

Chaoyang DU,Jingjie YU,Huaping ZHONG,Dandan WANG

期刊论文

Dynamic simulation of gas turbines via feature similarity-based transfer learning

Dengji ZHOU, Jiarui HAO, Dawen HUANG, Xingyun JIA, Huisheng ZHANG

期刊论文

Build orientation determination of multi-feature mechanical parts in selective laser melting via multi-objective

期刊论文

提升KPCA方法特征抽取效率的算法设计

徐勇,杨静宇,陆建峰

期刊论文

XFEM schemes for level set based structural optimization

Li LI, Michael Yu WANG, Peng WEI

期刊论文

Level set-based isogeometric topology optimization for maximizing fundamental eigenfrequency

Manman XU, Shuting WANG, Xianda XIE

期刊论文

composition differences between processed protein from different animal species by self-organizing feature

Xingfan ZHOU,Zengling YANG,Longjian CHEN,Lujia HAN

期刊论文

Characteristics of plankton Hg bioaccumulations based on a global data set and the implications for aquatic

期刊论文

The research on structural damage identification using rough set and integrated neural network

Juelong LI, Hairui LI, Jianchun XING, Qiliang YANG

期刊论文