Power equipment image data warehouse and power equipment defect detection method

A technology for power equipment and image data, which is applied in the field of power equipment image data warehouse and power equipment defect detection, can solve the problems of data waste, low data value density, excessive time and energy, etc., to reduce pressure, improve efficiency and accuracy Sexual, easy-to-expand effect

Pending Publication Date: 2020-04-28
SHANGHAI MUNICIPAL ELECTRIC POWER CO +2
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, traditional manual inspection consumes more time and energy. Therefore, it is necessary to combine image recognition to detect equipment defects.
With the development of image detection of electric power equipment, the image data related to defect detection increases rapidly, the data volume is large, the data sources are diverse, the data value density is low, and the value is not fully utilized, resulting in data waste
It takes a lot of manpower and time to manage images in the form of folders, and it is difficult to add and expand, and it cannot fully interact with researchers who are not inspectors. The data openness is low, and it is difficult to carry out automatic discrimination research on power equipment status.

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
  • Power equipment image data warehouse and power equipment defect detection method
  • Power equipment image data warehouse and power equipment defect detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] This embodiment provides a power equipment image data warehouse, which stores detection images of multi-dimensional data star model organization modes, and each detection image is associated with a priori information features for the image analysis, including the corresponding The operating information, time information, geographical information, environmental monitoring information and detection information of the tested equipment, the operating information of the tested equipment, time information, geographic system corresponding information, environmental monitoring data and detection information have unique signs for indexing. The data storage structure of the data warehouse is as follows: figure 1 As shown, the data storage structure forms a multi-dimensional data star model organization mode with five dimensions of time, region, environment, equipment, and detection.

[0033] Data warehouse is a technology that can access various databases and integrate various so...

Embodiment 2

[0048] Such as figure 2 As shown, this embodiment provides a power equipment defect detection method based on the power equipment image data warehouse of Embodiment 1, including the following steps:

[0049] Constructing a sample library based on historical data in the data warehouse;

[0050] Training a support vector machine for defect detection based on the sample library;

[0051] Obtain the image features of the power equipment to be tested, integrate the environmental information features, and detect the information features through the trained support vector machine for detection and classification;

[0052] According to the detection results, the time and location of equipment defects are located through the index.

[0053] In another embodiment, the method further includes: storing the classified images into a data warehouse to complete the database.

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 relates to a power equipment image data warehouse and a power equipment defect detection method; detection images of a multi-dimensional data star model organization mode are stored in the data warehouse, and each detection image is associated with corresponding detected equipment operation information, time information, geographic information, environment monitoring information anddetection information; the defect detection method comprises the following steps: constructing a sample library based on historical data in the data warehouse; training a support vector machine for defect detection based on the sample library; acquiring image features of the to-be-detected power equipment, fusing the environment information features and the detection information features, and performing detection and classification through a trained support vector machine; and according to the detection result, positioning the equipment defect occurrence time and position through the index. Compared with the prior art, the method has the advantages of high defect detection efficiency and accuracy and the like.

Description

technical field [0001] The invention relates to the fields of distributed storage, database establishment and management, image recognition, and electric equipment defect detection, and in particular relates to a power equipment image data warehouse and a power equipment defect detection method. Background technique [0002] With the gradual improvement of the power grid structure, the number of power equipment is increasing year by year, and the maintenance workload is increasing day by day. Due to problems such as equipment quality and insufficient operation and maintenance, the number of equipment defects and failures also increase accordingly. The safe and stable operation of equipment plays a big role. However, traditional manual inspection consumes more time and energy. Therefore, it is necessary to combine image recognition to detect equipment defects. With the development of image detection of electric power equipment, the image data related to defect detection is i...

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 Applications(China)
IPC IPC(8): G06F16/51G06F16/215G06F16/25G06K9/62
CPCG06F16/51G06F16/215G06F16/258G06F18/2411G06F18/253
Inventor 高凯黄华许侃邓先钦金立军陆坡燕林温韬乔辛磊
Owner SHANGHAI MUNICIPAL ELECTRIC POWER CO
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