Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Anomaly detection method and system for thermoelectric industry data based on adaptive fuzzy clustering

An adaptive fuzzy, industrial data technology, applied in the registration/indication of machine work, character and pattern recognition, registration/indication, etc. Problems such as anomaly detection accuracy and efficiency, to achieve the effect of improving accuracy and efficiency

Active Publication Date: 2022-03-25
UNIV OF JINAN
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the randomness and data volume of the thermal power industry data are very large and unpredictable, so it is difficult to cluster the thermal power industrial data with the usual method, which will affect the accuracy and efficiency of abnormal detection of the thermal power industrial data

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
  • Anomaly detection method and system for thermoelectric industry data based on adaptive fuzzy clustering
  • Anomaly detection method and system for thermoelectric industry data based on adaptive fuzzy clustering
  • Anomaly detection method and system for thermoelectric industry data based on adaptive fuzzy clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] figure 1 It is a flow chart of a thermoelectric industrial data anomaly detection method based on adaptive fuzzy clustering according to an embodiment of the present disclosure.

[0037] Such as figure 1 As shown, a method for detecting anomalies in thermoelectric industrial data based on adaptive fuzzy clustering in this embodiment includes:

[0038] S101: Obtain d-dimensional thermoelectric industry data in real time as samples, and store them in the data set S in chronological order;

[0039] For example: thermal power industry data includes 18 parameters including gas bag pressure, main steam temperature, material layer temperature, return material temperature, flue gas oxygen content, furnace differential pressure, and material layer differential pressure, so the dimension d is 18.

[0040] S102: Divide each dimension of the distribution space of the data set S into equal m interval segments to generate disjoint grids; where D. s is the standardized dispersion...

Embodiment 2

[0071] Such as figure 2 As shown, this embodiment provides a thermoelectric industry data anomaly detection system based on adaptive fuzzy clustering, including:

[0072] (1) a data acquisition module, which is used to acquire the thermoelectric industry data of d dimension in real time as a sample, and store it in the data set S in chronological order;

[0073] (2) grid division module, which is used to divide each dimension of the distributed space of data set S into equal m interval segments to generate disjoint grids; wherein D. s is the standardized dispersion of data set S; N is the number of samples in data set S;

[0074] In the grid division module, the normalized dispersion D of the data set S s for:

[0075]

[0076]

[0077] where: s j and X-means j are the standard deviation and mean value of the j-th dimension thermoelectric industry data; D j is the dispersion of the j-th dimension data of the data set S.

[0078] (3) Grid center of gravity calcu...

Embodiment 3

[0084] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the following figure 1 The steps in the adaptive fuzzy clustering-based anomaly detection method for thermoelectric industrial data are shown.

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 present disclosure provides a method and system for detecting anomalies in thermoelectric industrial data based on adaptive fuzzy clustering. Among them, the thermoelectric industrial data anomaly detection method includes acquiring d-dimensional thermoelectric industrial data in real time as a sample, and storing them in the data set S in chronological order; dividing each dimension of the space where the data set S is distributed into equal m interval segments , to generate disjoint grids; map the data set S to the grid to calculate the center of gravity of each grid, and use it as a new data point to represent the thermal power industry data contained in the corresponding grid, forming a grid center of gravity data set ;Use the adaptive fuzzy clustering algorithm to cluster the grid center of gravity data set P to obtain all cluster centers; calculate the thermal power industry data contained in the grid corresponding to each data point in the grid center of gravity data set and its nearest neighbor clusters The distance from the center is compared with the preset distance threshold to judge whether the thermoelectric industrial data is abnormal.

Description

technical field [0001] The disclosure belongs to the field of anomaly detection of thermal power industrial data, and in particular relates to a method and system for detecting abnormality of thermal power industrial data based on adaptive fuzzy clustering. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] Data is the raw material of this gluttonous feast in the intelligent age, and huge amounts of data contain rich information and knowledge. If we want to extract information from these data and put them into practical application, we must first perform cluster analysis on them. Clustering is a useful data analysis tool. It is a way to find the most similar data groups within the same cluster and the data groups that differ between different clusters. [0004] Thermal power industrial data refers to the data generated during the productio...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G07C3/00
CPCG07C3/005G06F18/23213G06F18/24147
Inventor 杜韬弭涛曲守宁李国昌李沁璐沈天宇
Owner UNIV OF JINAN
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com