Method for modeling image characteristic data of power equipment

A technology of power equipment and image features, applied in the field of knowledge databases, can solve the problems of image data waste, inability to make accurate judgments, and inability to store permanently, to ensure safe and stable operation, facilitate visual inspection, and improve the effect of operation and maintenance.

Inactive Publication Date: 2020-01-17

GUIZHOU POWER GRID CO LTD

12 Cites 2 Cited by

AI-Extracted Technical Summary

Problems solved by technology

[0004] Problem 1. A large amount of image data collected by inspection is wasted

Part of the intelligent inspection equipment uses local direct image recognition and detection, and does not save the inspection pictures; another method is to temporarily store them in the inspection background system, but it cannot be permanently stored (background server hard disk space factors, need to regularly clean up old pictures )

[0006] In short, a large amount of image data of power equipment cannot be effectively saved and recorded, resulting in a waste of a large amount of historical inspection operation and maintenance image data

[0007] Question 2. The detection department does not have a quantitative criterion for the image recognition...

Abstract

The invention discloses a method for modeling image characteristic data of power equipment. The method comprises the following step: after the pictures of the power equipment collected in the regularpatrol process of the intelligent equipment of AR wearing equipment or a patrol robot are recognized, carrying out definition specification of the image characteristic data of the power equipment withuniform appearance by adopting a D language to form structured table data, wherein the power equipment comprises primary field equipment, secondary field equipment and metering field equipment. According to the method, the collected image characteristics of the power equipment are subjected to unified and standardized data modeling, so that on the basis for forming large data of an image libraryof the power equipment, the fault statistics of the power equipment are facilitated, the intelligent identification accuracy of the power equipment is improved, the operation and maintenance effects of the power equipment are greatly improved, the safe and stable operation of a power system is further guaranteed, the structured data is converted, the image data is greatly compressed, the image data is conveniently stored in a database, and mining analysis of large data in later period is facilitated.

Application Domain

Checking time patrolsData processing applications +1

Technology Topic

Power equipmentFeature data +10

Image

Examples

Experimental program(1)

Example Embodiment

[0025] Embodiment 1: A method for modeling image feature data of power equipment, the method is: after the identification of the power equipment pictures collected during the regular inspection process of the smart equipment of the AR wearable device or the inspection robot, the unified appearance of the power The image feature data of the equipment adopts D language to define and standardize the image features, forming structured table data. Power equipment includes primary field equipment, secondary field equipment and metering field equipment.

[0026] The definition specification of image features of power equipment includes feature attribute items, attribute items English name, dimension, feature data type and attribute requirements. Feature attribute items include feature extraction time, equipment manufacturer, equipment model and other information on the equipment panel. Features Data types include string S, floating-point number F, and integer I.

[0027] The power equipment image feature data modeling language D formed by this patent can define and standardize the image features of various main power equipment (with unified appearance) in the power system, for example:

[0028] 1. Primary field: transformer, high voltage line, circuit breaker, switchgear, switch cabinet, ring main cabinet;

[0029] 2. Secondary areas: fault indicator, distribution transformer terminal FTU/DTU, line protection device, main transformer protection device;

[0030] 3. Measurement fields: electric meters, digital meters, concentrators, transformers, collectors, meters.

[0031] Take the concentrator equipment in the measurement field as an example, as shown in the following table:

[0032] Concentrator: Field type: S stands for string, F stands for floating point number, I stands for integer, the same below.

[0033]

[0034] Collector class: Field type: S means string, F means floating point number, I means integer, the same below.

[0035]

[0036] Meter: Field type: S means string, F means floating point number, I means integer, the same below.

[0037]

[0038]

[0039] In the same way, the image feature data model of this type of equipment as shown in the table above can be formed based on the image features of high-voltage lines, 10kV switch cabinets and other power equipment.

[0040] After a large number of images of power equipment collected during regular inspections of smart devices such as AR wearable devices and inspection robots are recognized, the image feature data in them is stored in the above data format to form the image feature data of the device. After extracting features, a large number of pictures are converted into structured data, which greatly "compresses" the image data and is easy to store in the database, thus forming a unified data model basis for image big data of power equipment.

PUM

Description & Claims & Application Information

We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.

Classification and recommendation of technical efficacy words

improve accuracy

Method for modeling image characteristic data of power equipment

AI-Extracted Technical Summary

Problems solved by technology

Abstract

Image

Examples

Example Embodiment

PUM

Description & Claims & Application Information

Similar technology patents

Techniques for sentiment analysis of data using a convolutional neural network and a co-occurrence network

Color interpolation method

Emotion classifying method fusing intrinsic feature and shallow feature

Video monitoring method and system

Scene semantic segmentation method based on full convolution and long and short term memory units

Classification and recommendation of technical efficacy words

Golf club head with adjustable vibration-absorbing capacity

Stent delivery system with securement and deployment accuracy

Method for improving an HS-DSCH transport format allocation

Catheter systems

Gaming Machine And Gaming System Using Chips