Control method and device suitable for seawater pipeline coating removing robot

Abstract

The invention belongs to the technical field of pipeline robots, and particularly relates to a control method and device suitable for a seawater pipeline coating removing robot, and the control method comprises the steps: 1, obtaining the walking data of the robot in a pipeline, and controlling the walking route of the robot; 2, a high-pressure water gun is adopted for spraying the seawater pipeline to remove a coating, a pipeline inner wall image sprayed by the robot is captured and captured in real time, and the sprayed pipeline inner wall image is obtained; 3, performing digital image processing on the sprayed pipeline inner wall image to obtain a digital image analysis result; 4, the cleaning effect of the robot is judged according to the digital image analysis result; 5, according to the cleaning effect of the robot, whether the moving speed of the robot and the cleaning frequency of the high-pressure water gun are adjusted or not is judged. The visual module with a visual detection function is adopted, the inner wall of the cleaned pipeline can be captured in time, images are processed, and the moving speed and the cleaning frequency of the robot are adjusted according to the processing result.

Description

Technical Field

[0001] The present invention belongs to the technical field of pipeline robots, and in particular relates to a control method and device suitable for a seawater pipeline coating removal robot. Background Art

[0002] There is an anti-corrosion coating inside the seawater pipeline. Years of use will cause the anti-corrosion coating to age and fall off. At this time, the pipeline needs to be de-coated and re-sprayed with anti-corrosion paint.

[0003] Currently, the design of pipeline decoating robots faces numerous challenges. Most robots use scrapers to clean the inner walls of pipes, which can damage the pipes and reduce their service life. Furthermore, the robot cannot monitor the cleaning results while decoating, and cannot adjust the robot's speed or frequency in real time.

[0004] Therefore, it is urgent to develop a control method and device for a seawater pipeline decoating robot that can effectively overcome the current problems of the seawater pipeline decoating robot. Summary of the Invention

[0005] The purpose of the present invention is to provide a control method and device suitable for a seawater pipeline decoating robot. The method adopts a visual module with a visual detection function, which can timely capture the inner wall of the pipeline after cleaning, process the image, and adjust the robot's movement speed and cleaning frequency according to the processing results.

[0006] The technical solution for achieving the purpose of the present invention is as follows:

[0007] A control method for a seawater pipeline decoating robot, the method comprising:

[0008] Step 1: Obtain the robot's walking data in the pipeline and control the robot's walking route;

[0009] Step 2: Use a high-pressure water gun to spray the seawater pipeline to remove the coating, and capture and take a snapshot of the inner wall of the pipeline after the robot sprays it in real time to obtain an image of the inner wall of the pipeline after spraying;

[0010] Step 3: Perform digital image processing on the image of the inner wall of the pipe after spraying to obtain a digital image analysis result;

[0011] Step 4: Determine the cleaning effect of the robot based on the digital image analysis results;

[0012] Step 5: Based on the robot's cleaning effect, determine whether to adjust the robot's moving speed and the high-pressure water gun cleaning frequency.

[0013] The walking data includes: moving direction, moving speed, acceleration, and the walking route includes: moving direction, moving speed, acceleration.

[0014] In step 1, if the deflection angle of the robot's walking path exceeds a predetermined deflection range, the robot's walking path is corrected so that the robot's walking path returns to a predetermined track.

[0015] The predetermined deflection range of the robot's walking route is -10°<θ<10°, where θ is the deflection angle, clockwise deflection is positive, and counterclockwise deflection is negative.

[0016] The step 3 is specifically as follows:

[0017] Step 3.1, convert the RGB image to HSV image space;

[0018] Step 3.2: Use the multi-scale Retinex image algorithm to enhance the image;

[0019] Step 3.3, according to the color of the paint after normal spraying, set the threshold of the H hue channel of the paint area;

[0020] Step 3.4: Use the threshold of the H hue channel of the paint area to perform pixel segmentation on the painted image to obtain the number of pixels in the unpainted area.

[0021] Step 3.5: Calculate the ratio of the pixels in the unpainted area to the pixels in the original image based on the number of pixels in the unpainted area to obtain a digital image analysis result.

[0022] The specific steps of step 4 are as follows: judging the cleaning effect of the robot according to the ratio of pixels of the unsprayed area to pixels of the original image: if the unsprayed area is less than 10% and the sprayed area is greater than 90%, the cleaning effect of the robot is judged to be good; if the unsprayed area is greater than 10% and the sprayed area is less than 90%, the cleaning effect of the robot is judged to be poor.

[0023] Specifically, step 5 is as follows: if the robot cleaning effect is good, continue to work according to the current robot movement speed and high-pressure water gun cleaning frequency; if the robot cleaning effect is poor, readjust the robot movement speed and high-pressure water gun cleaning frequency, and return to step 2 to use the high-pressure water gun to spray the inner wall of the seawater pipe to remove the coating.

[0024] A control device for a seawater pipeline decoating robot, comprising: a high-pressure water gun, a vision module, and an IMU module;

[0025] High-pressure water guns are used to spray and remove coatings from the inner walls of seawater pipelines;

[0026] The visual module is used to capture and take pictures of the inner wall of the pipe after cleaning by the robot in real time, and perform digital image processing on the image to obtain digital image analysis results;

[0027] The IMU module is connected to the robot, high-pressure water gun, and vision module to measure and control the robot's movement direction, speed, and acceleration in the pipeline in real time; based on the digital image analysis results of the vision module, the robot's movement direction, speed, acceleration, and high-pressure water gun cleaning frequency are adjusted.

[0028] The high-pressure water guns are installed at the front of the robot, with the nozzles of the two high-pressure water guns arranged at 180 degrees; the vision module is installed at the front end of the robot.

[0029] The beneficial technical effects of the present invention are:

[0030] 1. The present invention provides a control method for a seawater pipeline decoating robot. The method uses a visual module to capture and photograph the inner wall of the pipeline being cleaned by the robot, analyzes the photographed images, and adjusts parameters such as the robot's movement speed and the frequency of high-pressure water gun cleaning based on the analysis results. There is no need to use ranging sensors and accelerometers at the same time, which simplifies the control process. The method evaluates the cleaning effect of the inner wall of the pipeline and obtains feedback to make adjustments to the robot, which can effectively improve the robot's cleaning effect.

[0031] 2. The present invention provides a control method suitable for a seawater pipeline decoating robot. By real-time measuring the robot's walking data in the pipeline, the robot's walking route is controlled. The controlled walking route includes not only the robot's travel direction (movement direction), but also the robot's movement speed and the speed of decoating the inner wall of the pipeline with high-pressure water (i.e., the cleaning frequency of the high-pressure water gun, for example: spray gun speed, spray gun pressure). This realizes real-time correction of the robot's walking route and can effectively control the robot's movement speed, spray gun speed, spray gun pressure, etc.

[0032] 3. The present invention provides a control method for a seawater pipeline decoating robot. By performing digital image processing on the captured image of the inner wall of the pipeline after spraying, the method achieves the effect of extracting color difference image analysis, eliminates problems such as shadows and uneven lighting in the image, facilitates observation, and makes the observation results more intuitive.

[0033] 4. The present invention provides a control device suitable for a seawater pipeline decoating robot. The high-pressure water gun used can effectively remove impurities on the inner wall of the pipeline while ensuring that the inner wall of the pipeline is not scratched, and the impurities flushed down can also be flushed out by high-pressure water. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a flow chart of a control method for a seawater pipeline decoating robot provided by the present invention;

[0035] Figure 2This is a schematic diagram of the moving coordinates of the pipeline robot provided by the present invention;

[0036] Figure 3 This is a cross-sectional view of the pipeline robot provided by the present invention;

[0037] Figure 4 This is a digital image processing flow chart for a control method for a seawater pipeline decoating robot provided by the present invention;

[0038] Figure 5 Schematic diagram of pipeline inner wall image processing in an embodiment of the present invention;

[0039] Figure 6 This is a schematic diagram of complete coating removal of a pipeline in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0041] like Figure 1 As shown, the present invention provides a control method for a seawater pipeline decoating robot, which decoats the inner wall of a seawater pipeline and specifically includes the following steps:

[0042] Step 1: Obtain the robot's walking data in the pipeline and control the robot's walking route

[0043] Step 1.1: Real-time measurement of the robot's walking data in the pipeline (moving direction, moving speed, acceleration)

[0044] The IMU module is used to measure and record the robot's speed, acceleration and other parameters in the XYZ coordinate system in the pipeline in real time. Figure 2 shown.

[0045] Step 1.2: Control the robot's walking route based on the measured walking data (moving direction, moving speed, acceleration) of the robot in the pipeline

[0046] The robot receives the moving direction, moving speed, and acceleration data measured and recorded in real time by the IMU module. Based on the moving direction, moving speed, and acceleration data measured and recorded in real time by the IMU module, the robot's walking route (including moving direction, moving speed, and acceleration) in the pipeline is controlled by the IMU module. If the deflection angle θ of the robot's walking route exceeds the predetermined deflection range, the robot's walking route is corrected by the IMU module to return the robot's walking route to the predetermined track.

[0047] In a specific embodiment, the predetermined deflection range of the robot's walking path is -10°<θ<10°, with clockwise deflection being positive and counterclockwise deflection being negative. Figure 3 shown.

[0048] Step 2: Use a high-pressure water gun to spray the seawater pipeline to remove the coating, and capture and take pictures of the inner wall of the pipeline after the robot sprays it in real time to obtain the image of the inner wall of the pipeline after spraying.

[0049] A high-pressure water gun is used to spray and de-coat seawater pipes. Reaching a maximum pressure of 48 MPa, the gun is capable of removing dirt, marine life, rust, and other impurities from the pipe's interior. The gun utilizes a three-way pipe with two outlets spaced 180 degrees apart, effectively offsetting the pressure from the two outlets. Driven by a motor, the gun rotates 360 degrees within the pipe, spraying water at a speed of 25 to 100 rpm, with a maximum rotation of 0.6 seconds. The gun achieves an impurity removal rate of 99%. After the gun is operational, the vision module captures and captures images of the pipe's interior after cleaning, providing an image of the sprayed surface.

[0050] Step 3: Use the visual module to perform digital image processing on the image of the inner wall of the pipe after spraying to obtain the digital image analysis results, such as Figure 4 As shown, this step includes:

[0051] Step 3.1. Convert the RGB image to the HSV image space.

[0052] First, the RGB values ​​are normalized to the 0-1 range. The maximum and minimum values, as well as their difference, are then calculated for each pixel. Next, the hue (H) is calculated based on the color channel containing the maximum value. The saturation (S) is calculated using the difference and maximum value, and the maximum value is used directly as the value (V). Finally, the resulting HSV value is used to convert each pixel from RGB to HSV space.

[0053] Step 3.2: Use the multi-scale Retinex image algorithm to enhance the image.

[0054] The Multiscale Retinex image enhancement algorithm applies Retinex theory at different scales to separate and adjust the illumination and reflection components of an image, thereby improving the image's dynamic range and contrast. Specifically, the algorithm smoothes the image at multiple scales and then compares the original image with these smoothed results to enhance image detail and color, resulting in a clearer and more natural visual effect.

[0055] Since the light inside the pipeline is dark and the image has more shadows, the multi-scale Retinex image algorithm is used to enhance the image while keeping the H hue channel unchanged. Figure 5 As shown, this is to eliminate problems such as shadows and uneven lighting in the image and facilitate observation.

[0056] Step 3.3: According to the color of the paint after normal spraying, set the threshold of the H color (H in the HSV color channel) phase channel of the paint area.

[0057] Based on the normal color of the paint after spraying, the HSV value of that color, particularly the hue (H) value, must be collected first. Then, a reasonable range can be determined. This range can be set through actual observation and experimentation, usually within a certain range of values ​​that fluctuate around the H value. For example, if the H value of the paint after spraying is 120 degrees, a range of 110 to 130 degrees can be set as the H hue channel threshold range for the painted area to ensure accurate recognition and coverage of all variations of that color in real-world applications.

[0058] Step 3.4: Use the threshold of the H hue channel of the paint area to perform pixel segmentation on the painted image to obtain the number of pixels in the unpainted area.

[0059] First, perform image preprocessing, read the sprayed image into memory, and convert the image from RGB space to HSV space;

[0060] The second step is to set the threshold range. According to the H hue value and floating range of the paint after normal spraying, set the lower and upper limits of the H channel.

[0061] H lower =H normal -ΔH

[0062] H upper =H normal +ΔH

[0063] Where H lower is the lower limit of the H channel, H upper is the upper limit of the H channel, H normal is the H value of the paint area after normal spraying, and △H is the floating value of the H channel;

[0064] The third step is pixel segmentation. According to the set H hue threshold range, a binary mask is created. The pixels in the mask that meet the threshold range are set to 1 (representing the sprayed area), and those that do not meet the threshold range are set to 0 (representing the unsprayed area).

[0065] The fourth step is to calculate the number of pixels in the unpainted area. By counting the number of pixels with a median value of 0 in the mask, the number of pixels in the unpainted area can be obtained.

[0066] Step 3.5: Calculate the ratio of the pixels in the unpainted area to the pixels in the original image based on the number of pixels in the unpainted area to obtain a digital image analysis result;

[0067] Number of pixels in the unpainted area:

[0068]

[0069] Total pixels:

[0070] P total =M×N

[0071] Percentage of unpainted area:

[0072]

[0073] Where, P unpainted is the number of pixels in the unpainted area, P total is the total number of pixels in the image, R unpainted is the ratio of the unsprayed area, mask(i,j) represents the value of the mask at the pixel position (i,j), M and N are the height and width of the image respectively. Step 4: According to the digital image analysis results, judge the cleaning effect of the robot

[0074] The cleaning effect of the robot is judged based on the ratio of pixels in the unsprayed area to pixels in the original image.

[0075] If the unsprayed area is less than 10% and the sprayed area is greater than 90%, the robot cleaning effect is judged to be good; if the unsprayed area is greater than 10% and the sprayed area is less than 90%, the robot cleaning effect is judged to be poor.

[0076] Step 5: Based on the robot cleaning effect, determine whether to adjust the robot's moving speed and the high-pressure water gun cleaning frequency.

[0077] If the robot cleaning effect is good, continue to work according to the current robot movement speed and high-pressure water gun cleaning frequency; if the robot cleaning effect is poor, readjust the robot movement speed and high-pressure water gun cleaning frequency (spray gun speed, spray gun pressure), and return to step 2 to use a high-pressure water gun to spray the inner wall of the seawater pipe to remove the coating.

[0078] In a specific embodiment, the robot's movement speed is reduced and the high-pressure water gun cleaning frequency is increased. When the robot detects that the proportion of the unsprayed area is greater than or equal to 90%, the robot's movement speed is reduced to half, the high-pressure water gun's rotation speed is doubled, and the water pressure of the high-pressure water gun is increased by 10 MPa, thereby improving the robot's cleaning frequency and efficiency.

[0079] After the seawater pipeline is de-coated, the schematic diagram of the pipeline is completely de-coated as shown below: Figure 6 shown.

[0080] The present invention provides a control device suitable for a seawater pipeline decoating robot, comprising: a high-pressure water gun, a vision module, and an IMU module. The high-pressure water gun is installed at the front of the robot and is used to spray the inner wall of the seawater pipeline to remove the coating. The nozzles of the two high-pressure water guns are arranged at 180 degrees, which can effectively offset the recoil generated by the high-pressure water gun. The vision module is installed at the front end of the robot. The vision module is used to capture and take pictures of the inner wall of the pipeline after cleaning by the robot in real time, and perform digital image processing on the image to obtain digital image analysis results. The IMU module is connected to the robot, the high-pressure water gun, and the vision module, and is used to measure and control the movement direction, movement speed, and acceleration of the robot in the pipeline in real time; according to the digital image analysis results of the vision module, the robot's movement direction, movement speed, acceleration and the cleaning frequency of the high-pressure water gun are adjusted.

[0081] The present invention has been described in detail above with reference to the accompanying drawings and embodiments. However, the present invention is not limited to the above embodiments. Various modifications can be made within the scope of knowledge possessed by those skilled in the art without departing from the spirit of the present invention. Any content not described in detail in the present invention may be adapted from existing technologies.

Claims

1. A control method for a seawater pipeline decoating robot, characterized in that: The method comprises: Step 1: Obtain the walking data of the robot in the pipeline and control the walking route of the robot; Step 2: Use a high-pressure water gun to spray the seawater pipeline to remove the coating, and capture and take a snapshot of the inner wall of the pipeline after the robot sprays it in real time to obtain the image of the inner wall of the pipeline after spraying; Step 3, performing digital image processing on the image of the inner wall of the pipe after spraying to obtain a digital image analysis result; Step 4: judging the cleaning effect of the robot according to the digital image analysis results; Step 5: According to the cleaning effect of the robot, determine whether to adjust the robot's moving speed and the cleaning frequency of the high-pressure water gun.

2. A control method for a seawater pipeline decoating robot according to claim 1, characterized in that: The walking data includes: moving direction, moving speed, and acceleration, and the walking route includes: moving direction, moving speed, and acceleration.

3. A control method for a seawater pipeline decoating robot according to claim 2, characterized in that: In the step 1, if the deflection angle of the robot's walking route exceeds a predetermined deflection range, the robot's walking route is corrected so that the robot's walking route returns to a predetermined track.

4. A control method for a seawater pipeline decoating robot according to claim 3, characterized in that: The predetermined deflection range of the robot's walking route is -10°<θ<10°, θ is the deflection angle, clockwise deflection is positive, and counterclockwise deflection is negative.

5. The control method for a seawater pipeline decoating robot according to claim 1, characterized in that: The step 3 is specifically as follows: Step 3.1, convert the RGB image to HSV image space; Step 3.2, using multi-scale Retinex image algorithm to enhance the image; Step 3.3, according to the color of the paint after normal spraying, set the threshold of the H hue channel of the paint area; Step 3.4, using the threshold of the H hue channel of the paint area after setting, pixel segmentation is performed on the painted image to obtain the number of pixels in the unpainted area; Step 3.5: Calculate the ratio of the pixels in the unpainted area to the pixels in the original image based on the number of pixels in the unpainted area to obtain a digital image analysis result.

6. A control method for a seawater pipeline decoating robot according to claim 5, characterized in that: The specific step 4 is as follows: judging the cleaning effect of the robot according to the ratio of pixels of the unsprayed area to pixels of the original image: if the unsprayed area is less than 10% and the sprayed area is greater than 90%, judging that the cleaning effect of the robot is good; if the unsprayed area is greater than 10% and the sprayed area is less than 90%, judging that the cleaning effect of the robot is poor.

7. A control method for a seawater pipeline decoating robot according to claim 6, characterized in that: The step 5 is specifically as follows: if the robot cleaning effect is good, continue to work according to the current robot moving speed and high-pressure water gun cleaning frequency; if the robot cleaning effect is poor, readjust the robot moving speed and high-pressure water gun cleaning frequency, and return to step 2 to use a high-pressure water gun to spray the inner wall of the seawater pipe to remove the coating.

8. A control device suitable for a seawater pipeline decoating robot, characterized in that: The device includes: a high-pressure water gun, a vision module, and an IMU module; High-pressure water guns are used to spray the inner wall of seawater pipes to remove coatings; The visual module is used to capture and take pictures of the inner wall of the pipe after cleaning by the robot in real time, and perform digital image processing on the image to obtain digital image analysis results; The IMU module is connected to the robot, high-pressure water gun, and vision module to measure and control the robot's moving direction, moving speed, and acceleration in the pipeline in real time; according to the digital image analysis results of the vision module, the robot's moving direction, moving speed, acceleration, and high-pressure water gun cleaning frequency are adjusted.

9. A control device for a seawater pipeline decoating robot according to claim 8, characterized in that: The high-pressure water guns are installed at the front of the robot, and the nozzles of the two high-pressure water guns are arranged at 180 degrees; the vision module is installed at the front end of the robot.

Images