System and method for excavating abnormal features of time series data

A technology of time series data and data, which is applied in the direction of electrical digital data processing, other database retrieval, other database query, etc., and can solve problems such as difficulty in direct observation.

Inactive Publication Date: 2015-12-30
XI AN JIAOTONG UNIV +1
View PDF0 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Time series data has a lot of abnormal information hidden behi

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • System and method for excavating abnormal features of time series data
  • System and method for excavating abnormal features of time series data
  • System and method for excavating abnormal features of time series data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The following are preferred implementation examples of the present invention.

[0040] refer to figure 1 , a mining system for abnormal features of time series data in the present invention, comprising a data preprocessing module 1-1, an adaptive acquisition period module 1-2, an acquisition feature vector module 1-3, a TK-Means clustering module 1-4 and a feature String generation modules 1-5.

[0041] The data preprocessing module is used to clean and interpolate the original time series data to obtain effective data forms for subsequent mining work.

[0042] The data preprocessing module includes removing outliers, generating a single parameter file (cleaning), equal interval processing (difference processing) and normalization processing; "Delete invalid outliers in the original data and keep valid values. Specifically, the upper and lower limits are set for each data, and the value greater than the upper limit becomes the upper limit, and the value smaller than ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a system and a method for excavating abnormal features of time series data. A minimum complete period having obvious periodic data can be acquired in a self-adaptive manner, so that a feature observation window is determined; then the Fourier feature, the principal component analysis feature, the statistic feature and the wavelet feature are extracted from the observation window respectively; finally, clustering is performed on single feature vectors respectively with a KT-Means method, and various features are abstracted and expressed as feature characters. The problem of fuzzy matching of data can be better solved by expressing features of the time series data with the feature characters in a formalized manner, and establishment of a feature library is facilitated for rapid judgment and retrieval of an abnormal process. With the adoption of the method, various feature information is contained, the abnormal process of the time series data can be known more comprehensively and integrally, and the applicability and the generalization ability of a system for abnormity monitoring and fault diagnosis of the time series data can be improved.

Description

【Technical field】 [0001] The invention belongs to the field of intelligent information processing and computer technology, and in particular relates to a mining system and method for abnormal characteristics of time series data. 【Background technique】 [0002] Time series data has a lot of abnormal information hidden behind the appearance of the data, which is difficult to observe directly. It is necessary to extract different characteristics of time series data from multiple angles, and reveal the nature of anomalies in time series data from different angles. Rich feature information is helpful for a more comprehensive, complete, and deeper understanding of the abnormal change process of time series, which helps to improve the accuracy of anomaly detection, and improves the generalization ability and applicability of detection tools. This plays an important role in systems such as real-time monitoring, fault diagnosis, and rapid early warning / forecast. [0003] Abnormal c...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F17/30G06K9/62
CPCG06F16/903G06F18/23213
Inventor 鲍军鹏樊恒海杨天社齐勇张海龙王小乐高波杨冬毅
Owner XI AN JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap