Underground pipe gallery monitoring method and system based on multi-source heterogeneous data fusion

A technology of multi-source heterogeneous data and underground pipe corridors, applied in image data processing, neural learning methods, neural architecture, etc., can solve the problems of insufficient utilization and analysis of operation and maintenance data, low efficiency and exacerbation of isolated operations, and achieve Improving state awareness and penetrating power

Pending Publication Date: 2020-09-01
国网河北省电力有限公司雄安新区供电公司 +4
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] With the exponential growth of the operation of the comprehensive utility tunnel and its inspection data, the problems of discretization of state data, serious isolation and low operation efficiency have been further aggravated
However, due to the low level of automation and intelligence of the inspection technology, the operation and maintenance personnel cannot grasp the operation status of the power cabin and cable lines

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
  • Underground pipe gallery monitoring method and system based on multi-source heterogeneous data fusion
  • Underground pipe gallery monitoring method and system based on multi-source heterogeneous data fusion
  • Underground pipe gallery monitoring method and system based on multi-source heterogeneous data fusion

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0034] Example 1

[0035] Combine figure 1 with image 3 As shown, this embodiment is an underground pipe gallery monitoring method based on multi-source heterogeneous data fusion, including:

[0036] Real-time collection and acquisition of comprehensive pipeline gallery monitoring related data, the monitoring related data including structured data and unstructured data;

[0037] Preprocessing the monitoring-related data;

[0038] Perform feature value extraction on the preprocessed structured data;

[0039] Use the pre-processed unstructured data as the input of the first deep learning neural network built in advance;

[0040] Use the extracted structured data feature values ​​and the output of the first deep learning neural network as the input of the second deep learning neural network built in advance;

[0041] Determine whether there is an abnormality in the comprehensive corridor according to the output of the second deep learning neural network;

[0042] Real-time output of abnormal...

Example Embodiment

[0049] Example 2

[0050] Using the same inventive concept as the embodiment 1, this embodiment is an underground pipe gallery monitoring system based on multi-source heterogeneous data fusion, including:

[0051] The data collection module is used for real-time collection and acquisition of integrated pipe gallery monitoring related data, the monitoring related data including structured data and unstructured data;

[0052] A data preprocessing module for preprocessing the monitoring related data;

[0053] The feature value extraction module is used to perform feature value extraction on the preprocessed structured data;

[0054] The unstructured data recognition module is used to use the pre-processed unstructured data as the input of the first deep learning neural network constructed in advance;

[0055] The comprehensive recognition module is used to use the extracted structured data feature values ​​and the output of the first deep learning neural network as the input of the second 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

No PUM Login to view more

Abstract

The invention discloses an underground pipe gallery monitoring method and system based on multi-source heterogeneous data fusion, and the method comprises the steps: collecting and obtaining comprehensive pipe gallery monitoring related data in real time, wherein the monitoring related data comprises structural data and unstructural data; preprocessing the monitoring related data; carrying out feature value extraction on the preprocessed structural data; taking the preprocessed unstructured data as the input of a pre-constructed first deep learning neural network, and taking the extracted structured data feature value and the output of the first deep learning neural network as the input of a pre-constructed second deep learning neural network; determining whether the comprehensive pipe gallery is abnormal or not according to the output of the second deep learning neural network; and outputting abnormal judgment result information in real time. According to the invention, fusion processing and anomaly analysis and identification of images, videos, operation states and other related service data of power cabin channel section monitoring can be realized.

Description

technical field [0001] The invention relates to the technical field of comprehensive utility gallery monitoring, in particular to an underground utility gallery monitoring method and system based on multi-source heterogeneous data fusion. Background technique [0002] The comprehensive pipe gallery integrates various engineering pipelines such as electricity, communication, gas, heating, water supply and drainage, and has been more and more used in urban construction, becoming an important infrastructure and "lifeline" to ensure urban operation. The power cabin of the comprehensive pipe gallery is different from the ordinary cable channel, the cabin body is buried deeper, and the operating environment is more complicated. Problems such as fire, external damage, water accumulation, subsidence, air turbidity, and lighting difficulties are more prominent, and due to serious phenomena such as condensed water in the power cabin, it is difficult for monitoring equipment to operate...

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
IPC IPC(8): G06K9/54G06K9/62G06N3/04G06N3/08G06T7/00G06T7/194
CPCG06N3/08G06T7/0004G06T7/194G06T2207/20084G06V10/20G06N3/045G06F18/25
Inventor 丁斌刘敬文黄超庄玉林龚志丹李永海李强谷志成赵辉李国鹏李伟刚王学彬
Owner 国网河北省电力有限公司雄安新区供电公司
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
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