KR20240025232A - Method and apparatus for determining a condition of plumbing - Google Patents

Abstract

A method and apparatus for determining the condition of a pipe are disclosed. A method of determining the state of a pipe according to one aspect of the technical idea of the present disclosure includes the steps of photographing at least one of an image inside the pipe or an image outside the pipe, acquiring data inside the pipe, the inside image of the pipe, and the outside image of the pipe. and determining a comparison result by comparing at least one of the pipe internal data with pipe information in a normal state, and determining a state of the pipe related to the pipe interior image or the pipe exterior image based on the determined comparison result. It is characterized by including.

Description

Method and apparatus for determining the condition of plumbing {METHOD AND APPARATUS FOR DETERMINING A CONDITION OF PLUMBING}

The technical idea of the present disclosure relates to a method and device for determining the state of a pipe, and more specifically, to a method and device for determining the state of a pipe based on a camera and a light detection and ranging sensor.

In order to provide water and sewage, gas, and hot water for heating, it is important to detect the condition of the pipes, that is, whether there are any abnormalities in the pipes.

Conventionally, pipe abnormalities, including defects, protrusions, cracks, surface damage, etc., were detected by considering only the intended use of the pipe. If external environmental factors such as the size and type of the pipe as well as the characteristics and climate requirements of the pipe installation area are not taken into consideration, there may be limitations in detecting abnormalities in the pipe.

And conventionally, the recognition rate for breakage and damage to pipes was measured using images obtained through cameras. The recognition rate for pipe breakage and damage based on flat data may be less accurate.

The problem that the technical idea of the present disclosure seeks to solve is to provide a method and device for determining the state of a pipe based on a camera and a lidar sensor.

The problem to be solved by the technical idea of the present disclosure is to provide a method and device for determining the state of a pipe based on elements related to the pipe.

The problem to be solved by the technical idea of the present disclosure is to provide a method and device for displaying the determined piping state as visual data.

The problem that the technical idea of the present disclosure seeks to solve is to provide a method and device for learning data about pipes obtained based on cameras and lidar sensors.

In order to achieve the above object, a method of determining the state of a pipe according to one aspect of the technical idea of the present disclosure includes the steps of photographing at least one of an image inside the pipe or an image outside the pipe, and acquiring internal pipe data. , determining a comparison result by comparing at least one of the pipe interior image, the pipe exterior image, and the pipe interior data with pipe information in a normal state, and based on the determined comparison result, the pipe interior image or the pipe exterior It is characterized in that it includes the step of determining the state of the pipe related to the image.

In addition, an apparatus for determining the state of a pipe according to one aspect of the technical idea of the present disclosure includes a transceiver and a processor connected to the transceiver, wherein the processor captures at least one of an image inside the pipe or an image outside the pipe, and Obtain internal data, determine a comparison result by comparing at least one of the pipe internal image, the pipe external image, and the pipe internal data with pipe information in a normal state, and determine the pipe internal image based on the determined comparison result. Or, it may be configured to determine the state of the pipe related to the external image of the pipe.

According to the technical idea of the present disclosure, there is an effect of increasing the accuracy of the state of the pipe based on elements related to the pipe.

Furthermore, according to the technical idea of the present disclosure, there is an effect of increasing the recognition rate of the status of the pipe based on the three-dimensional image acquired through the camera and radar sensor.

Furthermore, according to the technical idea of the present disclosure, there is an effect of monitoring the internal and external conditions of the pipe and providing the monitoring result as visual data.

Furthermore, according to the technical idea of the present disclosure, there is an effect of managing pipes based on the condition of the provided pipes.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1A to 1C are block diagrams showing the schematic configuration of a pipe condition measuring device according to an exemplary embodiment of the present disclosure.
Figure 2 is a flowchart showing a method of operating a pipe condition measuring device according to an exemplary embodiment of the present disclosure.
Figure 3 is a flowchart showing a method of determining the state of a pipe in a pipe state measuring device according to an exemplary embodiment of the present disclosure.
Figure 4 illustrates a screen providing data related to piping according to an exemplary embodiment of the present disclosure.
Figure 5 is a block diagram showing the schematic configuration of a pipe condition measuring robot according to an exemplary embodiment of the present disclosure.
6A and 6B exemplarily illustrate deep learning of a pipe condition measuring device according to an embodiment of the present disclosure.

Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings.

1A to 1C are block diagrams showing the schematic configuration of a pipe condition measuring device according to an exemplary embodiment of the present disclosure.

Referring to FIG. 1A , the pipe condition measuring device 100 includes a measurement and collection unit 110, a database unit 120, a status determination unit 130, and a visualization unit 140.

The measurement and collection unit 110 includes a camera 111 and a lidar sensor 112, as shown in FIG. 1B. The camera 111 captures images inside the pipe and images outside the pipe. Here, the pipe interior image and the pipe exterior image may be 2D (two-dimensional space) or 3D (three-dimensional space) images. The camera 111 is configured to enable angle of view, wide angle, and aperture control, tilt, and night-time ultraviolet and infrared photography. The measurement and collection unit 110 may include at least one camera 111.

The LiDAR sensor 112 outputs a laser pulse to the pipe and obtains the time when the laser pulse is reflected by the pipe and returns. By acquiring time, the LiDAR sensor 112 can determine data inside the pipe, such as the shape and curvature of the pipe, as well as spatial information such as the size and location of obstacles present within the pipe. The pipe internal data may be three-dimensional data of an image captured by the camera 111.

In the embodiment of the present invention, only the LiDAR sensor 112 is mentioned, but sensors other than the LiDAR sensor may also be used.

Although not shown in FIG. 1A, the pipe condition measuring device 100 may include a separate input device. The pipe condition measurement device 100 can set pipe condition measurement conditions through an input device. Piping condition measurement conditions include piping condition survey company (e.g., xx plant), piping condition survey location (e.g., Chuncheon-si, Gangwon-do), and type of pipe (e.g., carbon steel pipe for piping, galvanized steel pipe for water supply, stainless steel pipe, steel pipe for pressure piping). ), pipe size (e.g. external size and inner pipe size), and measurement results (e.g. corrosion, erosion, cracks, perforation), etc.

The camera 111 and the lidar sensor 112 may operate by considering the input pipe condition measurement conditions.

The camera 111 can adjust conditions such as the number of shots, aperture value, wide-angle shooting, and pixel adjustment of the camera 111 based on information stored in the database unit 120, that is, existing measurement data and previously stored pipe status information. there is. The lidar sensor 112 can adjust conditions such as tilting angle adjustment, optical aberration compensation, and reflection value control.

In particular, the detailed conditions for signal correction and noise filtering of the LiDAR sensor 112 may change depending on the pipe condition measurement conditions. Re-filming and re-sensing of the LiDAR sensor may be performed according to the results of the initially captured image or the measured pipe internal data of the previously sensed LiDAR sensor.

Referring to FIG. 1A , the database unit 120 stores images inside the pipe and images outside the pipe captured through the camera 111, and stores inside pipe data measured through the LiDAR sensor 112.

The database unit 120 may store piping information in a normal state. Additionally, the database unit 120 may store predetermined states that may occur depending on the type of pipe, such as carbon steel pipe for piping, galvanized steel pipe for water supply, stainless steel pipe, or steel pipe for pressure piping. At this time, the predetermined state may be numerical data, and may be a reference value by which the state determination unit 130, which will be described later, determines the state of the pipe.

Furthermore, the database unit 120 may store data processed based on data obtained from the measurement and collection unit 110.

The state determination unit 130 determines the pipe internal image, the pipe external image, and the pipe acquired from the measurement and collection unit 110 based on a predetermined state that may occur depending on the type of pipe, which is data previously stored in the database unit 120. Determine whether internal data is abnormal.

For example, when the pipe interior image, pipe exterior image, and pipe interior data are included in a predetermined state, the state determination unit 130 may determine the pipe state to be normal. On the other hand, if the pipe interior image, pipe exterior image, and pipe interior data do not conform to the predetermined state, the state determination unit 130 may determine the pipe state to be abnormal. At this time, the condition of the pipe may be corrosion, cracks, beads, defects, protrusions, cracks, deterioration, surface damage, etc., and may be graded or quantified depending on the degree and scope of the condition. The state determination unit 130 can determine the degree of aging of the pipe, defect measurement information, degree of corrosion, and remaining lifespan.

The status determination unit 130 may display the determination result through a viewer or visualization unit 140, which will be described later. The display includes color display, warning message display using text, alarm, vibration, etc.

The state determination unit 130 may perform deep learning using the pipe internal image, pipe external image, and pipe internal data acquired by the measurement and collection unit 110. In addition, the state determination unit 130 performs simulation to determine the state of the pipe, and can perform deep learning on its own by generating and modeling a random pipe interior image, a random pipe exterior image, and random pipe interior data. It can be configured so that Deep learning can include prediction of piping condition classification, range, and occurrence time of abnormal piping conditions. Accordingly, the state determination unit 130 may further include a modeling unit.

The state determination unit 130 learns not only from the pipe interior image, pipe exterior image, and pipe interior data acquired from the measurement and collection unit 110, but also from any pipe interior image, any pipe exterior image, and any pipe interior data. Since it also learns from data, various variables can be considered.

By performing deep learning as described above, the state determination unit 130 can reduce the error rate in judgment about the state of the pipe and increase the recognition rate for images and pipe internal data.

The visualization unit 140 displays images acquired through the measurement and collection unit 110, pipe internal data, data stored in the database unit 120, and pipe judgment results determined by the status determination unit 130. The visualization unit 140 can display visual data in colors, 3D, dots, shapes, numbers, etc. through compression, sampling, quantization, and pixel value conversion of the image acquired through the camera 111.

The visualization unit 140 may further include a map implementation unit. The map implementation unit may implement pipe information of the area where the pipe subject to condition determination is located in the form of a map, and may display the location of the pipe in an abnormal state so that it overlaps on the map.

The visualization unit 140 may further include a result output unit. The result output unit may output data stored in the database unit 120, the piping decision result determined by the status determination unit 130, and visual data determined by the visualization unit 140. Additionally, the result output unit may output data determined by the state determination unit 130. The form of output may be an electronic file (e.g. PDF) or paper. And the data output by the result output unit can be written manually or automatically.

Referring to FIG. 1B, the pipe condition measuring device 100 includes a transceiver 150, a processor 12, and a display 13.

The transceiver 150 is configured to transmit and receive data related to pipe status.

The processor 160 is configured to process data related to the pipe status and determine the pipe status.

The transceiver 150 and the processor 160 may include the measurement and collection unit 110 and the state determination unit 130 of FIG. 1A.

The memory 170 is configured to store data related to the piping state and the piping state. Memory 170 may include database 120 of FIG. 1A.

The display 180 is configured to display data related to the pipe condition and the measured pipe condition. The display 180 may include the visualization unit 140 of FIG. 1A.

Figure 2 is a flowchart showing a method of operating a pipe condition measuring device according to an exemplary embodiment of the present disclosure.

In S10, the pipe condition measuring device may capture at least one of an image inside the pipe or an image outside the pipe through a camera.

In S20, the pipe condition measurement device can acquire pipe internal data through the LiDAR sensor.

In S30, the pipe condition measuring device may store at least one of a pipe interior image, a pipe exterior image, or pipe interior data in the database unit.

In S40, the pipe status measuring device may determine the status of the pipe by comparing at least one of the pipe interior image, pipe exterior image, and pipe interior data with normal pipe information previously stored in the database unit.

In S50, the pipe condition measurement device can visualize the condition of the pipe.

Figure 3 is a flowchart showing a method of determining the state of a pipe in a pipe state measuring device according to an exemplary embodiment of the present disclosure.

In S41, the pipe condition measuring device may determine the primary state of the pipe based on the pipe interior image and pipe exterior image captured through the camera.

In S42, the pipe condition measurement device can determine the secondary state of the pipe based on pipe internal data acquired through the LiDAR sensor.

In S43, at least one of the determined primary state of the pipe, the determined secondary state of the pipe, the pipe interior image, the pipe exterior image, the pipe interior data, an arbitrary pipe interior image, a random pipe exterior image, and arbitrary pipe interior data. Based on this, deep learning can be performed.

Figure 4 illustrates a screen providing data related to piping according to an exemplary embodiment of the present disclosure.

Referring to FIG. 4, a piping condition measuring device can visualize and provide piping-related data.

The display of the piping condition measuring device may provide a viewer 200 that displays data related to piping.

The viewer 200 may display at least one of an image inside the pipe and an image outside the pipe acquired through a camera in the image window 210. At least one of the pipe interior image and the pipe exterior image may be a captured image from a camera, three-dimensional data acquired from a LiDAR sensor, or a combination of a captured image from a camera and three-dimensional data acquired from a LiDAR sensor.

The image window 210 may display the capture date and time 220 of at least one of the pipe interior image and the pipe exterior image. Furthermore, the image window 210 may display horizontal information about the camera, for example, tilt information 230 of the camera. If the pipe condition measurement device is not level due to obstacles or other conditions in the pipe, at least one of the pipe interior image and the pipe exterior image displayed in the image window 210 may be tilted relative to the upper and lower sides. Therefore, the slope information 230 is provided to solve the above problem.

The viewer 200 may display data 240 acquired through a LiDAR sensor. Here, the data 240 may include the area of the damaged pipe, the depth of the damaged pipe, and the distance of the damaged pipe.

The viewer 200 may display pipe survey information 250. Pipe survey information 250 may include the survey company (eg, xx plant) and survey location (eg, Chuncheon-si, Gangwon-do).

Additionally, the viewer 200 can display basic piping information 26. Basic piping information 260 includes piping type (e.g. carbon steel pipe for piping, galvanized steel pipe for water use, stainless steel pipe, steel pipe for pressure piping), piping size (e.g. piping exterior size, piping inner pipe size), and piping purpose (e.g. may include cold water, hot water, oil, steam, gas, and air).

Furthermore, the viewer 200 displays pipe condition-related data 270, that is, diagnosis results (e.g., corrosion, erosion, cracks, perforation, etc.) and special information.

The viewer 200 displays an additional function provision icon 280. The additional function provision icon 280 includes screen capture, screen recording, video replay, and report saving functions.

The viewer 200 can perform wired and wireless communication with a web server and connect with a deep learning server.

In this embodiment, the viewer 200 is described as being provided by a pipe condition measuring device, but the viewer 200 may also be provided through a device other than the pipe condition measuring device.

Figure 5 is a block diagram showing the schematic configuration of a pipe condition measuring robot according to an exemplary embodiment of the present disclosure.

Referring to FIG. 5, the pipe condition measuring device may be in the form of a robot. The pipe condition measuring robot 300 is an electrical driving means. In the case of the pipe condition measuring robot 300, it includes two or more wheels and may be configured with a camera and a lidar sensor in the body.

The pipe condition measuring robot 300 may be configured to include a PTC (Pan + Tilt + Camera) 310. The PTC 310 may include a camera 311, a liquid lens 312, a camera 313 that operates within 360 degrees of pan and 180 degrees of tilt, and a light emitting diode (LED) 314. The camera 311 may be a full high definition (FHD) camera, and the LED 314 may be a 2000 Lux LED, but are not limited thereto.

The pipe condition measuring robot 300 may be configured to include a crawler 320. The crawler 320 may include a driving unit and suspense unit 321 and an image and signal transmission cable 322. The pipe condition measuring robot 300 is equipped with a driving unit and a suspense unit 321, so that it can overcome or avoid obstacles such as vertical, horizontal, and curved surfaces. The crawler 320 can move forward, left, right, and rotationally inside and outside the pipe through control of the motor.

The pipe condition measuring robot 300 may be configured to include a monitoring system 330. The monitoring system 330 may include embedded H/W 331 and viewer S/W 332. The embedded H/W 331 includes a PC and a touch monitor and can be configured to control pan, tilt, crawler 320, LED 314, and power. The viewer S/W (332) performs functions such as camera preview (capture, recording, storage, playback), moisture removal, HDR (high dynamic range) image conversion, and lidar (position, distance, subject size, 3D). It can be configured.

6A and 6B exemplarily illustrate deep learning of a pipe condition measuring device according to an embodiment of the present disclosure.

Referring to FIG. 6A, the pipe condition measuring device can perform deep learning by combining data from a plurality of acquired images. Referring to data combination 610, specific items such as pipe size, pipe use, corrosion part, pipe location, and corrosion type are combined.

Referring to FIG. 6B, the pipe condition measuring device may classify data about pipes obtained based on the data classification table 620 and perform deep learning. The data classification table 620 may define specific items such as pipe size, corrosion type, inspection items, and pipe type.

As above, exemplary embodiments have been disclosed in the drawings and specification. In this specification, embodiments have been described using specific terms, but this is only used for the purpose of explaining the technical idea of the present disclosure and is not used to limit the meaning or scope of the present disclosure described in the claims. Therefore, those skilled in the art will understand that various modifications and other equivalent embodiments are possible therefrom. Therefore, the true technical protection scope of the present disclosure should be determined by the technical spirit of the attached claims.

Claims (12)

Taking at least one of an image inside the pipe or an image outside the pipe;
Obtaining pipe internal data;
determining a comparison result by comparing at least one of the pipe interior image, the pipe exterior image, and the pipe interior data with pipe information in a normal state; and
determining a state of a pipe related to the pipe interior image or the pipe exterior image based on the determined comparison result; Including,
method.
In claim 1,
The step of determining the condition of the pipe is,
If the determined comparison result is included in a predetermined state, the method further includes determining the state of the pipe as normal.
In claim 1,
Further comprising the step of displaying the determined state of the pipe,
The steps indicated above are:
A method of displaying at least one of the type of the pipe, the size of the pipe, the purpose of the pipe, and a status result of the pipe.
In claim 1,
The method further includes performing deep learning based on at least one of the pipe interior image, the pipe exterior image, the pipe interior data, an arbitrary pipe interior image, a random pipe exterior image, and arbitrary pipe interior data.
In claim 4,
The deep learning step is,
A method of deep learning by combining at least one of the size of the pipe, the purpose of the pipe, the corrosion part of the pipe, the location of the pipe, and the type of corrosion of the pipe.
In claim 1,
A method wherein the pipe internal data includes at least one of a shape within the pipe, a curvature, a size of an obstacle, and a location of the obstacle.
transceiver;
Including a processor connected to the transceiver,
The processor,
Take at least one image of the inside of the pipe or the outside of the pipe,
Acquire internal pipe data,
Determine a comparison result by comparing at least one of the pipe interior image, the pipe exterior image, and the pipe interior data with pipe information in a normal state,
Configured to determine the state of the pipe related to the pipe interior image or the pipe exterior image based on the determined comparison result,
Device.
In claim 7,
The processor,
The apparatus further configured to determine the state of the pipe as normal when the determined comparison result is included in the predetermined state.
In claim 7,
The processor,
Displaying the determined status of the piping,
The device is further configured to display at least one of a type of the pipe, a size of the pipe, a purpose of the pipe, and a status result of the pipe.
In claim 7,
The processor,
A device further configured to perform deep learning based on at least one of the pipe interior image, the pipe exterior image, the pipe interior data, an arbitrary pipe interior image, a random pipe exterior image, and arbitrary pipe interior data.
In claim 10,
The processor,
A device further configured to perform deep learning by combining at least one of the size of the pipe, the purpose of the pipe, the corrosion portion of the pipe, the location of the pipe, and the type of corrosion of the pipe.
In claim 7,
The device wherein the pipe internal data includes at least one of the shape, curvature, size of an obstacle, and location of the obstacle within the pipe.

Images