检索结果-南通市图书馆

第36届中国控制会议

作者： Baoqi Liu Jinxue Xu Yuan Li College of Information Science and Technology Dalian Maritime University College of Information Engineering Shenyang University of Chemical Technology

ISBN: (纸本)9781538629185

To reduce data-storage costs and enhance high accuracy of industrial process fault detection,a data driven fault diagnosis method is proposed based on diffusion maps and hidden Markov ***,the correlation dimension of sample data is ***,the high-dimensional eigenvectors are extracted into low-dimensional manifold space by diffusion ***,the low-dimensional eigenvectors are regarded as the observation sequence of hidden Markov model for fault pattern *** effectiveness of this new method is proved by TE process *** addition,the fault identification results are demonstrated to be superior to the traditional identification approach of hidden Markov model.

关键词： Fault Diagnosis diffusion maps Hidden Markov Model TE Process

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

A Fault Detection Method with Mahalanobis Metric Learning Based on diffusion maps

A Fault Detection Method with Mahalanobis Metric Learning Ba...

引用

第37届中国控制会议

作者： Wenzhi Ma Jinxue Xu Yuan Li College of Marine Electrical Engineering Dalian Maritime University College of Information Engineering Shenyang University of Chemical Technology

In the process of industrial production, the occurrence of equipment failures is inevitable. If failure cannot be detected and eliminated in time and accurately, it can cause serious consequences. As diffusion mapping can keep manifold structure between data, it can be used to reduce the dimension of data. The diffusion distance is robust to noise as it is an average over all paths connecting two points. In view of the non-linear characteristics of the chemical process data and the noise interference in the process of data acquisition, diffusion mapping is investigated. The Gaussian kernel function is used in the diffusion maps to measure the similarity between the sample points. In order to measure the similarity between samples accurately, a metric learning method based on Mahalanobis distance is proposed. The goal of the algorithm is to learn a Mahalanobis matrix such that the distances of the point pairs with the same type are as small as possible, while those with the different type are as large as possible. Then a more accurate weight matrix is obtained to improve fault detection. Since SVM has the good generalization performance, and is specially good for treating the data of some nonlinearity. Finally SVM is adopted to fault identification. TE process data is used to verify the validity of the method, and the result shows that the new algorithm makes different type samples separated, and can improve the level of fault detection.

关键词： Faulty Detection diffusion maps Mahalanobis Metric Learning

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Fuzzy diffusion Distance Learning for Cartoon Similarity Estimation

引用

Journal of Computer Science & Technology 2011年第2期26卷 203-216页

作者：俞俊谢福顺 School of Computer Engineering Nanyang Technological University

In this paper, a novel method called fuzzy diffusion maps （FDM） is proposed to evaluate cartoon similarity, which is critical to the applications of cartoon recognition, cartoon clustering and cartoon reusing. We find that the features from heterogeneous sources have different influence on cartoon similarity estimation. In order to take all the features into consideration, a fuzzy consistent relation is presented to convert the preference order of the features into preference degree, from which the weights are calculated. Based on the features and weights, the sum of the squared differences （L2） can be calculated between any cartoon data. However, it has been demonstrated in some research work that the cartoon dataset lies in a low-dimensional manifold, in which the L2 distance cannot evaluate the similarity directly. Unlike the global geodesic distance preserved in Isomap, the local neighboring relationship preserved in Locally Linear Embedding, and the local similarities of neighboring points preserved in Laplacian Eigenmaps, the diffusion maps we adopt preserve diffusion distance summing over all paths of length connecting the two data. As a consequence, this diffusion distance is very robust to noise perturbation. Our experiment in cartoon classification using Receiver Operating Curves shows fuzzy consistent relation＇s excellent performance on weights assignment. The FDM＇s performance on cartoon similarity evaluation is tested on the experiments of cartoon recognition and clustering. The results show that FDM can evaluate the cartoon similarity more precisely and stably compared with other methods.

关键词： fuzzy diffusion maps similarity diffusion distance cartoon recognition cartoon clustering

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

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

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

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：