Pipeline detection system and method based on deep learning and unmanned aerial vehicle

A pipeline inspection system and deep learning technology, applied in the field of industrial robots, can solve problems such as incomplete inspection automation, and achieve the effects of saving labor costs, high efficiency and high accuracy

Active Publication Date: 2020-06-26
HARBIN INST OF TECH +1
View PDF10 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The patent "A UAV-Based Oil and Gas Pipeline Inspection System and Inspection Method" proposes a UAV-based oil and gas pipeline inspection system and inspection method, which can conduct large-scale and efficient oil and gas pipeline inspections , but the detected data are only sent back to the ground station, requiring people to conduct pipeline inspections in person, and the detection automation has not been fully realized

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
  • Pipeline detection system and method based on deep learning and unmanned aerial vehicle
  • Pipeline detection system and method based on deep learning and unmanned aerial vehicle
  • Pipeline detection system and method based on deep learning and unmanned aerial vehicle

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0075] Embodiment one: if Figure 1-2 As shown, this embodiment involves a pipeline inspection system based on deep learning and UAV. The UAV inspection system is divided into two parts: the on-board inspection system and the ground station inspection system, wherein the on-board inspection system It is composed of four subsystems: UAV, detection, wireless communication and data management (such as figure 2 shown).

[0076] The ground station system is the command center of the entire line inspection system. Its main tasks are flight control, route planning, receiving image information of line inspection and displaying it in real time, wireless communication, and data transmission and processing.

[0077] The UAV subsystem is mainly the selection and control of the UAV body. UAVs are mainly divided into three categories: fixed-wing UAVs, unmanned helicopters, and multi-rotor UAVs. The characteristics and applicable places of each type of UAVs are different. The comparative ...

Embodiment 2

[0094] Embodiment two: if Figure 3-10 As shown, a pipeline detection method based on deep learning and unmanned aerial vehicles involved in this embodiment, the oil pipeline detection subsystem based on deep learning, mainly processes the pictures of oil pipelines collected by unmanned aerial vehicles, through The trained neural network model marks the possible leak areas in it, so as to realize the automation of detection. The scheme is as follows image 3 shown.

[0095] The specific steps are implemented as follows:

[0096] (1) Image preprocessing

[0097]Bilateral filtering is used to denoise the image. Since the cracks in the oil pipeline are relatively sharp, the requirements for edge preservation are relatively high. The Gaussian filter function based on the spatial distribution of the bilateral filter can achieve very good edge preservation. It is near the edge and far away. The pixels will not have much effect on the values ​​of the pixels on the edge. Based on ...

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 provides a pipeline detection system and method based on deep learning and an unmanned aerial vehicle, and belongs to the field of industrial robots. A ground station part comprises a data management module and a first wireless communication module. An airborne part comprises a second wireless communication module, a visible light camera, an infrared camera, a detection system airborne control part and a memory. The method comprises steps of adopting a bilateral filter to denoise an image; carrying out edge detection on the image by adopting a Canny operator and then mapping theimage back to the original image to carry out sharpening operation; simplifying the convolution and pooling operation into a feature map which can be recognized by a feature extraction network; constructing an RPN network to perform prediction regression on a target box in the feature map; carrying out standard post-processing through SoftNMS, and reserving a prediction box with the highest prediction score as detection output; and generating a target mask image, namely a final pipeline detection image. The oil pipeline electric leakage identification accuracy and efficiency are high; automatic detection of the oil pipeline is realized, the labor cost is saved, and the working efficiency is improved.

Description

technical field [0001] The invention relates to a pipeline detection system and method based on deep learning and unmanned aerial vehicles, belonging to the field of industrial robots. Background technique [0002] In the thesis "Design and Implementation of Intelligent Inspection System for Oil and Gas Pipelines", based on the daily inspection and maintenance requirements of oil pipelines, the intelligent inspection management of oil and gas pipelines is realized by using GPS positioning technology, GIS (Geographic Information System) and data transmission technology . Utilize the existing GIS data of oil fields and oil pipelines to visually display the inspection distance of oil pipeline inspectors and the fault points to be tested in the form of graphics, and use GPS to monitor the inspection personnel of oil pipelines. The route and location are positioned, so that the working status of the oil pipeline inspection personnel can be monitored in a timely manner; for oil p...

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): G06K9/00G06K9/32G06K9/62G06N3/04G06N3/08G06T7/00G06T7/11G06T7/13G06T5/00G05D1/10
CPCG06T7/0004G06T7/11G06T7/13G06T5/002G06T5/003G06N3/084G05D1/101G06T2207/10004G06T2207/20016G06T2207/30164G06V20/13G06V10/25G06N3/045G06F18/241
Inventor 夏红伟田震李莉马广程裘水军张利强裴敏
Owner HARBIN INST OF TECH
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap