Steam jet de-icing vehicle nozzle heading angle intelligent correction control method and system

Abstract

The application discloses a steam jet deicing vehicle nozzle heading angle intelligent deviation correction control method and system, and the control method steps are as follows: S1, visual sensor image acquisition; S2, the collected image is grayed, filtered and image enhanced; S3, the nozzle and the wing are respectively subjected to feature extraction and segmentation; S4, the nozzle and the wing heading straight line equation is obtained through a straight line identification algorithm; S5, according to the straight line equation, the nozzle and the wing heading angle difference value is calculated; S6, the controller sends a control instruction to adjust the heading angle of the nozzle, so that the heading of the nozzle is consistent with the wing heading. The application solves the problems of low efficiency and poor precision of manual deviation correction, and improves the deicing efficiency.

Description

Technical Field

[0001] This invention relates to the field of aircraft de-icing, and more particularly to a method and system for intelligent correction control of nozzle heading angle for steam jet de-icing vehicles. Background Technology

[0002] Aircraft de-icing vehicles are essential equipment for aircraft ground support. Steam jet de-icing vehicles, due to their high efficiency, environmental friendliness, and low cost, have become a key development direction for next-generation aircraft de-icing equipment. Currently, mature or under-development aircraft de-icing equipment on the market relies on manual operation of the boom or nozzles for de-icing, resulting in low de-icing efficiency and errors in control precision. Steam jet de-icing devices, in particular, require even higher precision in nozzle attitude and control.

[0003] Referring to the invention patent with publication number CN 109987247 A, a multi-functional steam jet aircraft de-icing vehicle is disclosed. This de-icing vehicle includes a vehicle body, a steam generator, a steam conveying device, a de-icing execution device, and a de-icing control system. It is equipped with a hybrid working boom and an adaptive adjustment nozzle, and can achieve horizontal extension and retraction, vertical lifting and lowering, horizontal translation, and movement along a specific trajectory of the nozzle with one button, making operation simpler and more efficient. However, when de-icing the wing, the nozzle's heading angle must be consistent with the wing's heading angle to ensure efficient coverage of the wing surface and guarantee de-icing efficiency. However, when calibrating the nozzle's heading angle against the wing's heading angle, operators must manually and repeatedly adjust the nozzle's heading attitude based on visual observation, which is cumbersome and prone to human error.

[0004] Therefore, in order to solve the above problems, it is urgent to develop an intelligent correction and calibration system to achieve efficient and high-precision correction and calibration, thereby ensuring the efficiency and effectiveness of de-icing.

[0005] In conclusion, it is necessary to propose an intelligent correction control method and system for the heading angle of steam jet de-icing truck nozzles. Summary of the Invention

[0006] The technical solution of this invention, for hybrid steam jet de-icing trucks, addresses the problems of low efficiency and poor accuracy in manual calibration of nozzle and wing heading angles, and proposes an intelligent correction control method and system for the heading angle of steam jet de-icing truck nozzles.

[0007] To address the aforementioned technical problems, this invention provides an intelligent correction control method for the nozzle heading angle of a steam jet de-icing vehicle. The specific control process is as follows: S1, Image Acquisition: Acquire image information of the relative position of the nozzle and the wing through a vision sensor; S2, Image Preprocessing: Grayscale conversion, filtering, and image enhancement are performed on the acquired image; S3, Feature Extraction and Segmentation: Extract the nozzle and wing respectively, and perform binarization and edge detection; S4, Line Recognition: Obtain the heading line equation of the nozzle and the wing through the line recognition algorithm; S5, Heading Angle Calculation: Calculate the difference in heading angle between the nozzle and the wing based on the straight line equation; S6, Correction Execution: The controller adjusts the nozzle's heading angle based on the heading angle difference, so that the nozzle's heading is consistent with the wing's heading.

[0008] Specifically, step S2, image preprocessing, includes: Step S2.1: Convert the image captured by the camera to grayscale. Step S2.2: Perform median filtering on the grayscale image to eliminate the influence of noise points; Step S2.3: Perform a linear transformation on the filtered grayscale image to enhance the contrast between effective features and background features.

[0009] Specifically, step S3, feature extraction and segmentation, includes: Step S3.1: Use the multi-threshold segmentation method to segment the wing and nozzle separately, and then perform binarization. Step S3.2: Perform edge detection on the segmented image based on the Canny edge detection operator to obtain the edge information of the image; Step S3.3: Obtain image information of the upper edges of the wing and nozzle by scanning zeroing method.

[0010] The scanning zeroing method in step S3.3 is as follows: If the number of pixels in the vision camera is M*N, then we obtain an m*n mathematical matrix about the pixels. Let this matrix be f(x, y), where x∈[0, m-1] and y∈[0, n-1]. According to the column-first scanning method, if the first pixel of each column has a value of 1, then the pixel values ​​of the next 4 consecutive pixels in this column are retained, and the values ​​of all other pixels in this column are set to 0. That is, assuming the j-th column is detected, starting from the 0th row, if f(i,j)=1 when the i-th row is detected, that is, f(0,j), f(1,j)......f(i-1,j) are all equal to 0, then the values ​​of pixels f(i+1,j), f(i+2,j), f(i+3,j), and f(i+4,j) are retained, while the values ​​of pixels f(i+5,j), f(i+6,j)......f(m-1,j) are all 0.

[0011] In step S4, line identification involves using the least squares method to fit lines and obtain the linear equations of the edges of the wing and nozzle.

[0012] The method for calculating the heading angle difference in step S5, which combines the arctangent function, is as follows: Assuming the fitted straight line equation for the upper edge of the wing is y1=k1x1+a1, and the fitted straight line equation for the upper edge of the nozzle is y2=k2x2+a2, then the formula for calculating the heading angle difference is: α=arctank2-arctank1.

[0013] The correction process in step S6 is performed as follows: Step S6.1: Determine the heading angle adjustment direction. If α > 0.5, adjust the nozzle heading clockwise; if α < -0.5, adjust the nozzle heading counterclockwise. Step S6.2: Using the motor position control algorithm, calculate the pulse control signal corresponding to the specific angle that the motor needs to move. In step S6.3, the controller sends a pulse count + direction control command to the motor driver to control the motor.

[0014] The specific algorithm for the motor position control in step S6.2 is as follows: P=|α|RP t / 360, where R is the reduction ratio of the reducer and is the encoder resolution of the motor.

[0015] A smart heading angle correction system for a steam jet de-icing truck includes: a vision sensor, a vision sensor bracket, a drive motor, a motor driver, and a controller. The vision sensor is fixed to the nozzle bracket via the vision sensor bracket, with its lens facing the nozzle to ensure the acquisition of necessary information about the nozzle and the wing. It is electrically connected to the controller to acquire and process images, feeding back the heading angle difference information to the controller. The controller is installed on the vehicle and electrically connected to both the vision sensor and the motor driver. By acquiring the feedback signal from the vision sensor, it determines the motor rotation direction and calculates the number of pulses, and sends control commands to the motor driver. The motor driver is installed on the vehicle and electrically connected to both the controller and the drive motor. The drive motor is solidly connected to the nozzle bracket, driving the nozzle to adjust its heading.

[0016] Implementing the embodiments of the present invention has the following beneficial effects: The intelligent correction control method and system for the heading angle of the steam jet de-icing truck nozzle of the present invention, based on the existing steam jet de-icing technology structure, integrates machine vision technology, and can calculate the difference in heading angle between the nozzle and the wing based on the relative position image information of the nozzle and the wing. By controlling the drive motor, it can quickly and intelligently correct the heading angle, thereby improving the efficiency and accuracy of the correction and enhancing the operating efficiency of the de-icing truck. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the intelligent correction control method for the nozzle heading angle of a steam jet de-icing vehicle provided by the present invention; Figure 2 This is a schematic diagram of the intelligent heading angle correction hardware system for a steam jet de-icing vehicle provided by the present invention.

[0019] In the diagram: 1. Vision sensor; 2. Controller; 3. Motor driver; 4. Drive motor; 5. Reducer; 6. Sensor bracket; 7. Nozzle bracket.

[0020] Figure 3 This is a specific embodiment of the intelligent correction control method for the nozzle heading angle of a steam jet de-icing vehicle provided by the present invention.

[0021] In the figure: a) acquired image, b) image preprocessing, c) nozzle feature extraction and segmentation map, d) wing feature extraction and segmentation map, e) nozzle line detection, f) wing line detection. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] Please see Figure 1 , Figure 1 This is a flowchart of the intelligent heading angle correction control method for the nozzle of the steam jet de-icing vehicle provided by the present invention. The specific control process is as follows: S1, Image Acquisition: Acquire image information of the relative position of the nozzle and the wing through a vision sensor; S2, Image Preprocessing: Grayscale conversion, filtering, and image enhancement are performed on the acquired image; S3, Feature Extraction and Segmentation: Extract the nozzle and wing respectively, and perform binarization and edge detection; S4, Line Recognition: Obtain the heading line equation of the nozzle and the wing through the line recognition algorithm; S5, Heading Angle Calculation: Calculate the difference in heading angle between the nozzle and the wing based on the straight line equation; S6, Correction Execution: The controller adjusts the nozzle's heading angle based on the heading angle difference, so that the nozzle's heading is consistent with the wing's heading.

[0024] The image preprocessing step S2 specifically includes: Step S2.1: Convert the image captured by the camera to grayscale. Step S2.2: Perform median filtering on the grayscale image to eliminate the influence of noise points; Step S2.3: Perform a linear transformation on the filtered grayscale image to enhance the contrast between effective features and background features.

[0025] The feature extraction and segmentation step S3 specifically includes: Step S3.1: Use the multi-threshold segmentation method to segment the wing and nozzle separately, and then perform binarization. Step S3.2: Perform edge detection on the segmented image based on the Canny edge detection operator to obtain the edge information of the image; Step S3.3: Obtain image information of the upper edges of the wing and nozzle by scanning zeroing method; The scanning zeroing method in step S3.3 is as follows: If the number of pixels in the vision camera is M*N, then we obtain an m*n mathematical matrix about the pixels. Let this matrix be f(x, y), where x∈[0, m-1] and y∈[0, n-1]. According to the column-first scanning method, if the first pixel of each column has a value of 1, then the pixel values ​​of the next 4 consecutive pixels in this column are retained, and the values ​​of all other pixels in this column are set to 0. That is, assuming the j-th column is detected, starting from the 0th row, if f(i,j)=1 when the i-th row is detected, that is, f(0,j), f(1,j)......f(i-1,j) are all equal to 0, then the values ​​of pixels f(i+1,j), f(i+2,j), f(i+3,j), and f(i+4,j) are retained, while the values ​​of pixels f(i+5,j), f(i+6,j)......f(m-1,j) are all 0.

[0026] Step S4, line identification, uses the least squares method to fit lines and obtain the line equations of the upper edges of the wing and nozzle.

[0027] The method for calculating the heading angle difference in step S5, which combines the arctangent function, is as follows: Assuming the fitted straight line equation for the upper edge of the wing is y1=k1x1+a1, and the fitted straight line equation for the upper edge of the nozzle is y2=k2x2+a2, then the formula for calculating the heading angle difference is: α=arctank2-arctank1.

[0028] The specific method for performing step S6, correction, is as follows: Step S6.1: Determine the heading angle adjustment direction. If α > 0.5, adjust the nozzle heading clockwise; if α < -0.5, adjust the nozzle heading counterclockwise. Step S6.2: Using the motor position control algorithm, calculate the pulse control signal corresponding to the specific angle that the motor needs to move. In step S6.3, the controller sends a pulse count + direction control command to the motor driver to control the motor.

[0029] The specific algorithm for the motor position control in step S6.2 is as follows: P=|α|RP t / 360, where R is the reduction ratio of the reducer and is the encoder resolution of the motor; Please see Figure 2 , Figure 2 This is a hardware schematic diagram of the intelligent heading angle correction system for a steam jet de-icing truck provided by the present invention. Specifically, it includes: a vision sensor 1, a controller 2, a motor driver 3, a drive motor 4, a reducer 5, a sensor bracket 6, and a nozzle bracket 7. The vision sensor 1 is fixed to the nozzle bracket 7 via the vision sensor bracket 6, with its lens facing the nozzle to ensure the acquisition of necessary information about the nozzle and the wing. It is electrically connected to the controller 2 to achieve image acquisition and processing, and feeds back the heading angle difference information to the controller 2. The controller 2 is installed on the vehicle and electrically connected to both the vision sensor 1 and the motor driver 3. By acquiring the feedback signal from the vision sensor 1, it determines the motor rotation direction and calculates the pulse count, and sends control commands to the motor driver 3. The motor driver 3 is installed on the vehicle and electrically connected to both the controller 1 and the drive motor 4. The drive motor 4 is solidly connected to the nozzle bracket 7 via the reducer 5, driving the nozzle to adjust its heading.

[0030] Example: The following is a specific example to verify the feasibility of the method provided by the present invention, such as... Figure 3 As shown, S1, Image Acquisition: The relative position graphics of the wing and the nozzle are obtained by 3D software simulation of vision sensor 1, where the angle between the nozzle and the wing is 5°, as shown in Figure a; S2, Image preprocessing: Perform grayscale conversion, filtering, image enhancement, and other processing on image a to obtain image b; S3, Feature Extraction and Segmentation: Based on Figure b, the binary images of the nozzle and the wing are obtained through threshold segmentation and binarization, as shown in Figures c and d respectively; S4, Line Recognition: The line recognition algorithm is used to obtain the upper edge lines of the nozzle and the wing respectively, as shown in Figures e and f, and the obtained upper edge equations of the wing are y1=0.0017x1-186 and y2=0.0893x2-172. S5, Heading Angle Calculation: Based on the straight line equation, calculate the difference in heading angle between the nozzle and the wing, α = arctank² - arctank. 1= arctan0.0893-arctan0.0017=5.11°-0.97°=5.04°; S6, Correction Execution: Controller 2 then adjusts the heading angle based on the heading angle difference of 5.025° fed back by vision sensor 1. Assuming the reduction ratio of reducer 5 is 3 and the encoder resolution of drive motor 6 is 10000, the specific adjustment is as follows: S6.1 Controller 2 first determines the rotation direction of drive motor 3. Assuming that drive motor 3 rotates forward and the nozzle rotates clockwise, and drive motor 3 rotates in reverse and the nozzle rotates counterclockwise, since α>0.5, the motor rotates forward. S6.2 Controller 2 calculates the pulse number P based on the motor position control algorithm, P=|α|RP t / 360=5025; S6.3 The motor driver 4 controls the drive motor 3 to rotate forward for 5025 pulses according to the instructions of the controller 3.

[0031] The key to the intelligent heading angle correction control method and system for steam jet de-icing truck nozzles of the present invention lies in the ability to identify and calculate the heading angle difference between the nozzle and the wing. The method provided by the present invention achieves a heading angle difference error of 0.8%, which verifies the feasibility of the method and enables rapid intelligent heading correction.

[0032] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligent correction and control of the heading angle of a steam jet de-icing truck nozzle, characterized in that, Includes the following steps: S1, Image Acquisition: Acquire image information of the relative position of the nozzle and the wing through a vision sensor; S2, Image Preprocessing: Grayscale conversion, filtering, and image enhancement are performed on the acquired image; S3, Feature Extraction and Segmentation: Extract the nozzle and wing respectively, and perform binarization and edge detection; S4, Line Recognition: Obtain the heading line equation of the nozzle and the wing through the line recognition algorithm; S5, Heading Angle Calculation: Calculate the difference in heading angle between the nozzle and the wing based on the straight line equation; S6, Correction Execution: The controller adjusts the nozzle's heading angle based on the heading angle difference, so that the nozzle's heading is consistent with the wing's heading.

2. The intelligent correction control method for the heading angle of the steam jet de-icing truck nozzle according to claim 1, characterized in that, The image preprocessing step S2 specifically includes: Step S2.1: Convert the image captured by the camera to grayscale. Step S2.2: Perform median filtering on the grayscale image to eliminate the influence of noise points; Step S2.3: Perform a linear transformation on the filtered grayscale image to enhance the contrast between effective features and background features.

3. The intelligent correction control method for the heading angle of the steam jet de-icing truck nozzle according to claim 1, characterized in that, The feature extraction and segmentation step S3 specifically includes: Step S3.1: Use the multi-threshold segmentation method to segment the wing and nozzle separately, and then perform binarization. Step S3.2: Perform edge detection on the segmented image based on the Canny edge detection operator to obtain the edge information of the image; Step S3.3: Obtain image information of the upper edges of the wing and nozzle by scanning zeroing method.

4. The intelligent correction control method for the heading angle of the steam jet de-icing truck nozzle according to claim 1, characterized in that, The scanning zeroing method in step S3.3 is as follows: If the number of pixels in the vision camera is M*N, then we obtain an m*n mathematical matrix about the pixels. Let this matrix be f(x, y), where x∈[0, m-1] and y∈[0, n-1]. According to the column-first scanning method, if the first pixel of each column has a value of 1, then the pixel values ​​of the next 4 consecutive pixels in this column are retained, and the values ​​of all other pixels in this column are set to 0. That is, assuming the j-th column is detected, starting from the 0th row, if f(i,j)=1 when the i-th row is detected, that is, f(0,j), f(1,j)......f(i-1,j) are all equal to 0, then the values ​​of pixels f(i+1,j), f(i+2,j), f(i+3,j), and f(i+4,j) are retained, while the values ​​of pixels f(i+5,j), f(i+6,j)......f(m-1,j) are all 0.

5. The intelligent correction control method for the heading angle of the steam jet de-icing truck nozzle according to claim 1, characterized in that, Step S4, line identification, uses the least squares method to fit lines and obtain the line equations of the upper edges of the wing and nozzle.

6. The intelligent correction control method for the heading angle of the steam jet de-icing truck nozzle according to claim 1, characterized in that, The method for calculating the heading angle difference in step S5, which combines the arctangent function, is as follows: Assuming the fitted straight line equation for the upper edge of the wing is y1=k1x1+a1, and the fitted straight line equation for the upper edge of the nozzle is y2=k2x2+a2, then the formula for calculating the heading angle difference is: α=arctank2-arctank1.

7. The intelligent correction control method for the heading angle of the steam jet de-icing truck nozzle according to claim 1, characterized in that, The correction step S6 is performed as follows: Step S6.1: Determine the heading angle adjustment direction. If α > 0.5, adjust the nozzle heading clockwise; if α < -0.5, adjust the nozzle heading counterclockwise. Step S6.2: Using the motor position control algorithm, calculate the pulse control signal corresponding to the specific angle that the motor needs to move. In step S6.3, the controller sends a pulse count + direction control command to the motor driver to control the motor.

8. The intelligent correction control method for the heading angle of the steam jet de-icing truck nozzle according to claim 6, characterized in that, The motor position control algorithm in step S6.2 is as follows: P=|α|RP t / 360, where R is the reduction ratio of the reducer and is the encoder resolution of the motor.

9. A steam jet de-icing truck nozzle heading angle intelligent correction control system, characterized in that: The system includes a vision sensor, a vision sensor bracket, a drive motor, a motor driver, and a controller. The vision sensor is fixed to the nozzle bracket via the vision sensor bracket, with its lens facing the nozzle to ensure the acquisition of necessary information about the nozzle and the wing. It is electrically connected to the controller to acquire and process images, feeding back the heading angle difference information to the controller. The controller is mounted on the vehicle and electrically connected to both the vision sensor and the motor driver. By acquiring the feedback signal from the vision sensor, it determines the motor's rotation direction and calculates the number of pulses, sending control commands to the motor driver. The motor driver is mounted on the vehicle and electrically connected to both the controller and the drive motor. The drive motor is solidly connected to the nozzle bracket via a reducer, driving the nozzle to adjust its heading.

Images