Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Multifunctional electric power image intelligent analysis device based on AI deep learning

An intelligent analysis and deep learning technology, applied in the field of power systems, can solve the problems of increasing useless information in image processing, small image data collection, and inability to meet deep learning, so as to improve recognition accuracy, quality, and fault diagnosis efficiency. Effect

Pending Publication Date: 2021-11-05
福建睿思特科技股份有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since the promotion and application of helicopters, drones and intelligent robots is not long, the amount of image data collected for some fault types is small, which cannot meet the needs of deep learning.
[0003] Due to the influence of many factors such as the imager, imaging environment, and the characteristics of the imaging object itself, there are often differences between the captured device image and the original device, resulting in a significant decline in the quality of the obtained image, and poor image quality will increase the quality of the image processing process. Useless information in , reduce useful information, and ultimately affect the recognition results

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
  • Multifunctional electric power image intelligent analysis device based on AI deep learning
  • Multifunctional electric power image intelligent analysis device based on AI deep learning
  • Multifunctional electric power image intelligent analysis device based on AI deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] Below in conjunction with accompanying drawing and embodiment the present invention will be further described:

[0043] Such as Figure 1-5 As shown, in a specific embodiment of the present invention, a multifunctional power image intelligent analysis device based on AI deep learning is provided, and the device includes:

[0044] Image acquisition module 100, used for real-time acquisition of electric power images to be detected at the power system site;

[0045] Image noise reduction module 200, configured to perform noise reduction processing on the power image to be detected; wherein, perform noise reduction processing on the power image to be detected based on a mean value filter algorithm;

[0046] The image preprocessing module 300 is used to perform a segmentation on the power image to be detected after noise reduction processing to form a device edge map; determine each core area Φ in the device edge map i ; Among them, i is a positive integer;

[0047] A reg...

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 multifunctional electric power image intelligent analysis device based on AI deep learning. The multifunctional electric power image intelligent analysis device comprises an image acquisition module, an image noise reduction module, an image preprocessing module, a region growing module, a gray mapping enhancement contrast module, a target image recognition module, an image feature extraction and recognition module, an equipment recognition module and a comparative analysis module. The region growing module is used for growing each core region phi i to obtain a control region corresponding to each core region phi i, and the gray mapping enhancement contrast module is used for sequentially mapping the initial gray value of each pixel point in each core region phi i into a first intermediate gray value to enhance the region contrast. According to the device, the contrast ratio of the electric power image can be improved, the edge information and detail information of the electric power image can be effectively protected, the collected image is effectively enhanced, the image quality is improved, and the recognition accuracy of the electric power image is improved.

Description

technical field [0001] The present invention relates to the technical field of power systems, in particular to a multifunctional power image intelligent analysis device based on AI deep learning. Background technique [0002] With the development and promotion of artificial intelligence technology, the research of image recognition method using deep learning in power fault diagnosis is gradually attracting attention. Different from traditional machine learning, deep learning requires a large number of positive samples for training, so that the machine can learn enough features to achieve inferences from one instance, so as to prevent the phenomenon of overfitting that is prone to occur when the data set is too small. However, since the promotion and application of helicopters, drones and intelligent robots is not long, the amount of image data collected for some fault types is small, which cannot meet the needs of deep learning. [0003] Due to the influence of many factors...

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): G06T7/12G06T7/181G06T7/136G06T7/194G06T5/00G06K9/62
CPCG06T7/12G06T7/181G06T7/136G06T7/194G06T2207/10024G06T2207/20081G06F18/241G06T5/70
Inventor 廖兴旺
Owner 福建睿思特科技股份有限公司
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
Eureka Blog
Learn More
PatSnap group products