Transformer substation intelligent unmanned aerial vehicle inspection method based on visual navigation
A visual navigation and substation technology, applied in computer parts, instruments, character and pattern recognition, etc., can solve the problems of high labor consumption, long time-consuming inspection, and inaccurate judgment, so as to reduce the implementation cost and improve the level of intelligence. and efficiency, the effect of promoting application
Pending Publication Date: 2021-12-03
XINJIANG UNIVERSITY
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
At present, the current substation inspection generally adopts the manual inspection method on foot, and there are four outstanding problems: (1) manual inspection by station and equipment by foot, which takes a long time, consumes a lot of manpower, and is inefficient; (2) The manual inspection method of "observing with the naked eye and judging by experience" is prone to unrecognized defects and inappropriate judgments. The overall inspection quality is low, and there are many missed and wrong judgments; Development is restricted by manpower. Regular inspections are conducted once a month. Defects can develop during the "blank period" of inspections, and there are hidden dangers; (4) There is a lot of inspection data, and manual errors are prone to errors. The data processing method of "on-site collection, return input", It is easy to reduce the reliability of system 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 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 1
[0029] Workflow diagram such as figure 1 As shown, the specific operation steps are as follows:
[0030] S1: First, collect the substation manual inspection channel image, construct the RCE neural network classification algorithm based on the HSI color space, and segment the substation manual inspection channel from it. In this way, the substation images collected by the UAV camera are segmented. The schematic diagram of substation manual inspection channel segmentation is as follows: figure 2 shown.
[0031] S2: After obtaining the segmentation result, traverse the segmented image column to obtain the segmentation points whose segmented pixel values are significantly different from the surrounding pixels.
[0032] S3: Then use the obtained segmentation points to fit the substation manual inspection channel through the least square method.
[0033] S4: Finally, through the conversion of the image coordinate system to the ground three-dimensional coordinate system, the d...
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
The invention relates to a transformer substation intelligent unmanned aerial vehicle inspection method based on visual navigation. The transformer substation intelligent unmanned aerial vehicle inspection method based on visual navigation comprises the following steps: (1) acquiring a transformer substation manual inspection channel image, and segmenting the transformer substation image acquired by an unmanned aerial vehicle camera; (2) traversing the segmentation result to segment image columns to obtain segmentation points; (3) fitting the segmentation points to obtain a transformer substation manual patrol channel; and (4) through conversion from an image coordinate system to a ground three-dimensional coordinate system, establishing an autonomous safe flight trajectory space of the unmanned aerial vehicle. According to the transformer substation intelligent unmanned aerial vehicle inspection method based on visual navigation, on one hand, the intelligent level and efficiency of transformer substation inspection by the unmanned aerial vehicle can be improved, and on the other hand, application of artificial intelligence in intelligent inspection of power transmission and transformation equipment can be promoted.
Description
technical field [0001] The invention specifically relates to a visual navigation-based intelligent UAV inspection method for substations. Background technique [0002] In recent years, the scale of the power grid has continued to expand, substations and equipment have grown rapidly, and the situation of insufficient inspection personnel has become increasingly severe, and the carrying capacity is facing great challenges. At present, the current substation inspection generally adopts the manual inspection method on foot, and there are four outstanding problems: (1) manual inspection by station and equipment by foot, which takes a long time, consumes a lot of manpower, and is inefficient; (2) The manual inspection method of "observing with the naked eye and judging by experience" is prone to unrecognized defects and inappropriate judgments. The overall inspection quality is low, and there are many missed and wrong judgments; Development is restricted by manpower. Regular insp...
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 Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/34G06K9/46G06K9/62G06Q50/06
CPCG06Q50/06G06F18/24
Inventor 李宇恒郑炅董一博冯中涵
Owner XINJIANG UNIVERSITY