Method for identifying and positioning fault of key air cooler tube bundle in unmanned aerial vehicle inspection

A positioning method and fault identification technology, applied in character and pattern recognition, instruments, computer parts and other directions, can solve the problem of wasting manpower and material resources, air cooler tube bundle fault target identification and positioning without a complete system and method, detection is not easy. Detailed and comprehensive problems, to achieve the effect of reducing maintenance costs, realizing long-term operation, and saving manpower and material resources

Pending Publication Date: 2022-02-11
CHINA PETROLEUM & CHEM CORP
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At this stage, the general air cooler tube bundle inspection is mostly carried out by hand-held infrared thermal imagers near the air cooler tube bundle, but this method can only detect part of the entire air cooler tube bundle. This method is not only incomplete and comprehensive, but also A lot of manpower and material resources are wasted. Therefore, it is particularly necessary to develop a computer vision-based UAV inspection air cooler tube bundle fault target recognition and positioning method.
So far, there is no complete system and method for identifying and locating fault targets of air cooler tube bundles in large petrochemical plants

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
  • Method for identifying and positioning fault of key air cooler tube bundle in unmanned aerial vehicle inspection
  • Method for identifying and positioning fault of key air cooler tube bundle in unmanned aerial vehicle inspection
  • Method for identifying and positioning fault of key air cooler tube bundle in unmanned aerial vehicle inspection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] Next, a charting method of a drone inspection key empty cooler tube bundle of the present invention will be described in connection with the examples.

[0020] A transposition method of a transparent air cooler tube buffer in the present invention includes the following steps:

[0021] 1) Establishing a critical evaluation criterion for the air-cooler in the service, and the key evaluation of the service empty device is determined according to the evaluation results; including:

[0022] Select the importance of production, its own importance, service status, maintenanceability, and failure, the degree of failure is used as five evaluation indicators for evaluating the key level of the air cooler tube bundle, and score each empty cooler tube bundle according to the five indicators. A comprehensive evaluation of the critical degree of air cooler according to the score results. Where:

[0023] (1) Score based on the importance of production

[0024] After the air censor is fad...

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 method comprises the following steps: establishing a key evaluation standard of an in-service air cooler of a petrochemical enterprise, carrying out key evaluation on the in-service air cooler, and determining the key air cooler; collecting a tube bundle infrared thermal imaging image of a key air cooler through an infrared thermal imager carried by an unmanned aerial vehicle, preprocessing the infrared thermal imaging image, and establishing a standard data set file; constructing a key air cooler tube bundle infrared thermal imaging image feature extraction neural network, and performing training to obtain an image feature map; building a key air cooler tube bundle infrared thermal imaging image fault target recognition and fault area positioning detection neural network, using an image feature graph for training to form a model, and detecting and identifying infrared visual images collected by an infrared video collection device; and controlling a water supply valve according to a detection and identification result, formulating a maintenance strategy, and carrying out preventive maintenance on the key air cooler. Detection of the air cooler tube bundle in the operation stage is more comprehensive and meticulous, and a large amount of manpower and material resources are saved.

Description

Technical field [0001] The present invention relates to an air cooler tube bundle fault identification and a positioning method. In particular, there is a method of failure identification and positioning method for a drone inspection key empty cooler. Background technique [0002] The petrochemical industry is a high energy-consuming industry, and a small improvement in the production process will bring huge economic benefits. The air cooler is one of the most commonly used equipment in petrochemical production. The air censor is caused by a large blower to generate a lateral flow of air and an air-cooler tube to cool the tube medium, and the velvet in the petrochemical device is mostly cooling hydrogenated reaction distillate. High-pressure empty censor, working in high pressure, hydrogen production and corrosion media, the conditions of conditions are more demanding, especially in recent years, petrochemical enterprises have multi-sulfur crude oil, hydrocarbon reactor in high-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): G06V20/17G06V10/82G06V10/774G06V10/25G06N3/04G06T7/00G06T7/73
CPCG06T7/0004G06T7/73G06T2207/10048G06T2207/20081G06T2207/20084G06N3/045
Inventor 刘景明李洪涛高丽岩孙全胜荆瑞静王艳丽李梦瑶郭拂娟曹德成
Owner CHINA PETROLEUM & CHEM CORP
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