Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method and system for intelligent recognition of underground engineering targets based on ground penetrating radar

A target recognition and ground penetrating radar technology, which is applied in the field of intelligent recognition of underground engineering targets, can solve problems such as consumption of large manpower and material resources, low detection efficiency, and abnormality, and achieve the effect of ensuring model accuracy and ensuring complete and accurate extraction.

Active Publication Date: 2022-03-25
SHANDONG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the detection of underground structures is mainly to analyze the data collected by ground-penetrating radar, find abnormalities through the reflection of radar waves, and use artificial experts to explain what objects the abnormalities in the ground-penetrating radar detection data belong to or are related to the ground-penetrating radar detection data. Matching the database to judge requires a lot of manpower and material resources, making the detection efficiency extremely low
[0004] Although deep learning methods have been applied to the identification of ground penetrating radar detection data, they are mainly concentrated in specific research fields. Moreover, the identification results are whether there is anomaly, and the location of the anomaly cannot be accurately given.
Moreover, before the model is established, a large amount of ground-penetrating radar detection data covering different types of anomalies needs to be collected in advance. However, the coverage of anomaly types is very large, the data collection is cumbersome, and the built models are often poor in scope.

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
  • A method and system for intelligent recognition of underground engineering targets based on ground penetrating radar
  • A method and system for intelligent recognition of underground engineering targets based on ground penetrating radar
  • A method and system for intelligent recognition of underground engineering targets based on ground penetrating radar

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] This embodiment discloses a method for intelligent identification of underground engineering targets based on ground penetrating radar, such as figure 1 shown, including the following steps:

[0046] Step S1, acquiring a computer simulation data set, where the data set includes multiple sets of GPR data profile-target body label map data pairs.

[0047] The identification method of this embodiment is mainly aimed at hidden abnormal bodies or diseases, including broken underground engineering, geological abnormal bodies such as karst caves and faults, concrete steel bars and structural diseases, pavement cracks, settlements and other pavement diseases, and various underground pipelines. Each type of object is assigned a unique type identification code.

[0048] figure 2 and image 3 They are the label map of the hidden target and the data profile of the ground penetrating radar in the computer simulation data set, respectively. The method of constructing multiple se...

Embodiment 2

[0062] An underground engineering target recognition system based on ground penetrating radar, such as Image 6 As shown, including: host-antenna integrated ground penetrating radar, embedded control module, touch screen. Wherein, the integrated ground penetrating radar is connected with the embedded control module, the touch screen is connected with the embedded control module, and the ground penetrating radar intelligent identification model is embedded in the embedded control module.

[0063] The integrated ground penetrating radar is connected with the embedded control module through two data transmission modes of Ethernet or wireless Wifi.

[0064] The touch screen and the embedded control module are connected through USB to realize two-way communication and human-computer interaction.

[0065] The embedded control module has an extended communication interface, the PCIe interface is connected to the 4G module, and Wifi or 4G is used to transmit the real-time ground pene...

Embodiment 3

[0075] The purpose of this embodiment is to provide an electronic device.

[0076] An electronic device, comprising a memory, a processor and a computer program stored on the memory and running on the processor, the processor implements the following steps when executing the program, including:

[0077] Obtaining a computer simulation data set, the data set includes multiple sets of ground penetrating radar data profile-target volume label map data pairs;

[0078] Using a deep learning network, a target body recognition model is obtained based on the data set training;

[0079] The radar detection data collected in real time is acquired, and the target body recognition model is used to perform target body recognition.

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 a ground-penetrating radar-based intelligent identification method and system for an underground engineering target body. The method includes: acquiring a computer simulation data set, the data set including multiple groups of ground-penetrating radar data profiles-target body label diagrams pair of data; using a deep learning network to train a target recognition model based on the data set; acquiring real-time collected radar detection data, and using the target recognition model to perform target recognition. The invention can realize the real-time identification and output of the target body for the ground-penetrating radar data.

Description

technical field [0001] The invention relates to the technical fields of geological detection technology and artificial intelligence, in particular to a method and system for intelligent identification of underground engineering targets based on ground penetrating radar. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] At present, the detection of underground structures is mainly to analyze the data collected by the ground penetrating radar, find abnormalities through the reflection of radar waves, and use artificial experts to explain what objects the abnormality in the ground penetrating radar detection data belongs to or is related to the ground penetrating radar detection data. It takes a lot of manpower and material resources to match the database to judge, which makes the detection efficiency extremely low. [0004] Although deep lea...

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 Patents(China)
IPC IPC(8): G01S7/41G01S13/88G06N3/04
CPCG01S13/885G01S7/41G06N3/045
Inventor 刘斌王正方蒋鹏王静张佳琪杨森林
Owner SHANDONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products