Power grid line specific foreign matter intelligent inspection method
A technology of intelligent inspection and power grid, applied in the field of balloon detection and specific foreign objects in power grid lines, such as kites, can solve the problems of inconvenient equipment operation, maintenance and management, confusing description and results, etc., to improve the detection effect and the level of intelligence , The effect of improving the level of intelligence and reducing workload
Pending Publication Date: 2020-11-13
SHANGHAI MUNICIPAL ELECTRIC POWER CO +1
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
With the rapid development of UAV / vehicle inspection technology, computer technology and communication technology, image accumulation has become a routine phenomenon in the State Grid in recent years, and its trend is intensifying. There is a bottleneck in the image learning of the design, and the description and results are often different from person to person, which is easy to cause confusion, which brings inconvenience to equipment operation and maintenance and management
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0037] Power Grid Specific Foreign Objects—Kite Detection:
[0038] The kite has the characteristics of rich colors and various shapes. The various suspension states of the kite on the grid line, the long-term exposure to the sun and rain in the natural environment, and the different shooting angles make the kite appear on the image. Diversity, which increases the difficulty of target detection.
[0039] In this embodiment, 60 pictures of foreign matter of kites on grid lines, 40 pictures of flying kites outdoors (in various scenarios), and 40 pictures of kites from different angles were selected. In order to further increase the sample size, 140 pictures were rotated , brightness, color saturation, and contrast changes, and image data enhancement is performed on the training set to expand the data set and improve the performance of the model to a certain extent. The images in the training set are transformed as follows:
[0040]
[0041] The original 140 pictures in the ...
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
Login to View More Abstract
An intelligent inspection method for specific foreign matters of a power grid line belongs to the field of line detection. A power grid and the sky are used as backgrounds by adopting a manual manner / unmanned vehicle / unmanned aerial vehicle, and pictures are automatically shot, collected and transmitted upwards below a power grid line; automatic preprocessing is carried out on the image through apicture scale zooming algorithm and the image is stored into a target detection image folder; based on a training set data enhancement method, the performance of a Faster-RCNN detection model when thenumber of original training set pictures is insufficient is greatly improved, and a detection result is obtained after a to-be-detected image is subjected to model detection. In combination with existing manual / unmanned vehicle / unmanned aerial vehicle inspection, a specific-angle shooting target is provided to simplify the image background and improve the detection effect; the workload of manualimage processing is reduced by compiling an automatic image size processing algorithm, automatic fault recognition is achieved based on the computer vision technology, the intelligent level of the whole inspection process is improved, and the labor cost is saved. The method can be widely applied to the intelligent inspection field of grid lines.
Description
technical field [0001] The invention belongs to the field of power grid line detection, and in particular relates to a detection method for power grid line specific foreign objects such as kites and balloons. Background technique [0002] Various foreign objects may be hung on the grid lines, especially bird nests, kites, balloons, etc. The existence of foreign objects poses a threat to the insulation of the grid lines, which may cause short-circuit faults on the lines and large-scale power outages, which will affect people's normal production and life. It may even cause huge economic losses. Foreign matter hanging on the line is an important potential hidden danger that threatens the safe and stable operation of the power grid. [0003] With the rapid development of my country's power grid, the total length of transmission lines has exceeded 1.18 million kilometers, ranking first in the world in scale. However, transmission lines are scattered, large in area, complex in te...
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
Login to View More IPC IPC(8): G06K9/00G06N3/04G06Q50/06G07C1/20
CPCG06Q50/06G07C1/20G06V20/13G06N3/045
Inventor 朱洪志徐昊屈冬豪潘成杰袁思远艾芊贺兴张冲
Owner SHANGHAI MUNICIPAL ELECTRIC POWER CO