Temperature control method and system for supersonic speed thermal spraying
Through the registration and depth estimation of infrared and visible images, precise temperature control during supersonic thermal spraying is achieved, solving the problem of unstable traditional manual control methods, and improving production safety and product quality.
Patent Information
- Application Number
- CN202410963593.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-18
- Publication Date
- 2024-11-08
AI Technical Summary
During supersonic thermal spraying processing, traditional temperature control methods rely on manual temperature measurement and manual adjustment, which are easily affected by the operator's skill level and subjective awareness, resulting in unstable temperature control effects and difficult to monitor and adjust in real time.
By obtaining the infrared image and visible light image of the workpiece to be processed, image registration and depth estimation are performed, the temperature of each pixel point is calculated, and the proportional valve of the gas injection cooling device is adjusted using the control system to achieve accurate temperature control.
Accurate control of the temperature of the workpiece to be processed without contacting the workpiece surface, improving the production safety and product quality of the spray room, and reducing occupational injuries to operators.
Smart Images

Figure CN118915844A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of temperature control technology, and in particular to a temperature control method and system for supersonic thermal spraying. Background Art
[0002] In the process of supersonic thermal spraying, it is very important to accurately control the temperature of the workpiece to prevent overheating and quality degradation or even damage of the workpiece. The traditional temperature control method mainly relies on manual temperature measurement and manual adjustment of the cold air valve to control the temperature. This method is easily affected by the operator's skill level and subjective consciousness, and the temperature control effect is unstable and difficult to monitor and adjust in real time. Summary of the invention
[0003] To solve the above problems, an object of the present invention is to provide a temperature control method and system for supersonic thermal spraying.
[0004] A temperature control method for supersonic thermal spraying, comprising:
[0005] Step 1: Obtain infrared images and visible light images of the workpiece to be processed;
[0006] Step 2: Estimate the depth of each pixel on the visible light image to obtain the distance of each pixel on the visible light image;
[0007] Step 3: Register the infrared image and the visible light image to obtain the distance of each pixel in the infrared image;
[0008] Step 4: Use the infrared image to calculate the temperature displayed at each pixel;
[0009] Step 5: Use the distance of each pixel point of the infrared image to calibrate the temperature displayed by each pixel point to obtain the calibrated temperature;
[0010] Step 6: Calculate the difference between the calibrated temperature and the preset temperature, and use the control system to adjust the proportional valve of the gas jet cooling device to minimize the difference.
[0011] Preferably, the step 2: estimating the depth of each pixel on the visible light image to obtain the distance of each pixel on the visible light image includes:
[0012] Step 2.1: Perform multi-level decomposition on the visible light image to obtain wavelet coefficients;
[0013] Step 2.2: performing threshold processing on the wavelet coefficients to obtain processed wavelet coefficients;
[0014] Step 2.3: reconstructing the processed wavelet coefficients to obtain a denoised visible light image;
[0015] Step 2.4: extracting a feature map from the denoised visible light image, and inputting the feature map as a sample into a reinforcement learning network for training to obtain an image depth estimation model;
[0016] Step 2.5: Use the image depth estimation model to estimate the depth of each pixel on the visible light image to obtain the distance of each pixel on the visible light image.
[0017] Preferably, the step 2.2: performing thresholding processing on the wavelet coefficients to obtain processed wavelet coefficients comprises:
[0018] Step 2.2.1: When the value of the wavelet coefficient is greater than or equal to the processing threshold, the wavelet coefficient is processed by using the first coefficient processing function to obtain the processed wavelet coefficient;
[0019] Among them, the first coefficient processing function is:
[0020]
[0021] Where u is the first adjustment coefficient, sgn() is the sign function, and w j,l is the lth wavelet coefficient under the jth decomposition level, λ is the processing threshold, α is the second adjustment coefficient, β is the third adjustment coefficient, γ is the fourth adjustment coefficient, and p is the wavelet decomposition level;
[0022] Step 2.2.2: When the value of the wavelet coefficient is less than the processing threshold, the wavelet coefficient is processed by a second coefficient processing function to obtain a processed wavelet coefficient;
[0023] Among them, the second coefficient processing function is:
[0024]
[0025] Preferably, the processing threshold calculation formula is:
[0026]
[0027] Wherein, λ is the processing threshold, δ is the standard deviation of Gaussian noise, M is the length of the visible light image, N is the width of the visible light image, and z is the preset coefficient.
[0028] Preferably, the step 3: registering the infrared image and the visible light image to obtain the distance of each pixel point of the infrared image includes:
[0029] Step 3.1: Take any point on the visible light image or infrared image as the center point and take 24 adjacent pixels as the corner point evaluation area;
[0030] Step 3.2: Calculate the pixel contrast of the corner point evaluation area;
[0031] Step 3.3: When the pixel contrast of the corner point evaluation area is greater than the threshold, the center point is taken as the visible light corner point and the infrared image corner point;
[0032] Step 3.4: Calculate the change direction and amplitude of each visible light corner point and infrared image corner point;
[0033] Step 3.5: extracting visible light corner points and infrared image corner points whose change directions and amplitudes are within a preset range to form visible light feature points and infrared image feature points;
[0034] Step 3.6: Use feature matching algorithm to complete the matching of visible light feature points and infrared image feature points to obtain the registered infrared image and visible light image;
[0035] Step 3.7: Based on the registered infrared image and visible light image, the distance from each pixel on the infrared image to the workpiece to be processed is obtained.
[0036] Preferably, the step 3.2: calculating the pixel contrast of the corner point evaluation area includes:
[0037] Step 3.2.1: Calculate the pixel mean of the corner point evaluation area;
[0038] Step 3.2.2: Calculate the pixel contrast of the corner point evaluation area based on the pixel mean;
[0039]
[0040] Where w represents the width of the corner point evaluation area, h represents the height of the corner point evaluation area, I(x,y) represents the pixel value at the position (x,y) within the corner point evaluation area, and μ lw×h represents the pixel mean, I 25 represents 25 pixels in the corner point evaluation area, and G represents pixel contrast.
[0041] Preferably, the step 3.4: calculating the change direction and amplitude of each visible light corner point and infrared image corner point includes:
[0042] Using the formula:
[0043]
[0044] Calculate the change direction and amplitude of each visible light corner point and infrared image corner point; where M(x,y) represents the change amplitude, θ(x,y) represents the change direction, L(x+1,y) represents the pixel value at the position (x+1,y), and L(x,y+1) represents the pixel value at the position (x,y+1).
[0045] Preferably, step 5: using the distance of each pixel point of the infrared image to calibrate the temperature displayed by each pixel point to obtain the calibrated temperature, comprises:
[0046] The temperature displayed by each pixel is calibrated using the empirical distance formula to obtain the calibrated temperature; wherein the empirical distance formula is:
[0047] t0=t x e xa
[0048] Where t0 represents the temperature after calibration, t x It represents the temperature displayed by the pixel on the infrared image, x represents the distance between the pixel on the infrared image, and a represents the empirical coefficient.
[0049] The present invention also provides a temperature control system for supersonic thermal spraying, comprising:
[0050] An image acquisition module, used to acquire infrared images and visible light images of the workpiece to be processed;
[0051] A pixel depth calculation module is used to estimate the depth of each pixel on the visible light image to obtain the distance of each pixel on the visible light image;
[0052] A registration module is used to register the infrared image and the visible light image to obtain the distance of each pixel point of the infrared image;
[0053] A temperature display module is used to calculate the temperature displayed at each pixel using infrared images;
[0054] A calibration module, used to calibrate the temperature displayed by each pixel using the distance of each pixel of the infrared image to obtain a calibrated temperature;
[0055] The control module is used for calculating the difference between the calibrated temperature and the preset temperature, and adjusting the proportional valve of the gas jet cooling device by using the control system to minimize the difference.
[0056] The present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps in the above-mentioned temperature control method for supersonic thermal spraying are implemented.
[0057] The beneficial effect of a temperature control method and system for supersonic thermal spraying provided by the present invention is that: compared with the prior art, the present invention calculates the temperature through infrared images, and can accurately capture the temperature of the scanning area of the workpiece to be processed without contacting the surface of the workpiece, so that the spray room can be closed for production and reduce occupational hazards to operators.
[0058] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0059] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0060] Figure 1 A flow chart of a temperature control method for supersonic thermal spraying provided by an embodiment of the present invention is shown;
[0061] Figure 2 The schematic diagram of the temperature control system for supersonic thermal spraying provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION
[0062] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.
[0063] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.
[0064] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0065] See also Figure 1-2 , a temperature control method for supersonic thermal spraying, comprising:
[0066] Step 1: Obtain infrared images and visible light images of the workpiece to be processed;
[0067] Step 2: Estimate the depth of each pixel on the visible light image to obtain the distance of each pixel on the visible light image;
[0068] Furthermore, the step 2 comprises:
[0069] Step 2.1: Perform multi-level decomposition on the visible light image to obtain wavelet coefficients;
[0070] Step 2.2: performing threshold processing on the wavelet coefficients to obtain processed wavelet coefficients;
[0071] Wherein, the step 2.2 comprises:
[0072] Step 2.2.1: When the value of the wavelet coefficient is greater than or equal to the processing threshold, the wavelet coefficient is processed by using the first coefficient processing function to obtain the processed wavelet coefficient;
[0073] Among them, the first coefficient processing function is:
[0074]
[0075] Where u is the first adjustment coefficient, sgn() is the sign function, and w j,l is the lth wavelet coefficient under the jth decomposition level, λ is the processing threshold, α is the second adjustment coefficient, β is the third adjustment coefficient, γ is the fourth adjustment coefficient, and p is the wavelet decomposition level;
[0076] Step 2.2.2: When the value of the wavelet coefficient is less than the processing threshold, the wavelet coefficient is processed by a second coefficient processing function to obtain a processed wavelet coefficient;
[0077] Among them, the second coefficient processing function is:
[0078]
[0079] In step 2.2, the processing threshold calculation formula is:
[0080]
[0081] Wherein, λ is the processing threshold, δ is the standard deviation of Gaussian noise, M is the length of the visible light image, N is the width of the visible light image, and z is the preset coefficient.
[0082] This method can reduce the constant deviation between the original wavelet coefficients and the estimated wavelet coefficients by increasing the adjustment coefficient. By changing the adjustment coefficient, the form of the processing function can be continuously adjusted so that the processing function can better denoise the noisy wavelet coefficients.
[0083] Step 2.3: reconstructing the processed wavelet coefficients to obtain a denoised visible light image;
[0084] Step 2.4: extracting a feature map from the denoised visible light image, and inputting the feature map as a sample into a reinforcement learning network for training to obtain an image depth estimation model;
[0085] Step 2.5: Use the image depth estimation model to estimate the depth of each pixel on the visible light image to obtain the distance of each pixel on the visible light image.
[0086] Step 3: Register the infrared image and the visible light image to obtain the distance of each pixel in the infrared image;
[0087] Furthermore, step 3 includes:
[0088] Step 3.1: Take any point on the visible light image or infrared image as the center point and take 24 adjacent pixels as the corner point evaluation area;
[0089] Step 3.2: Calculate the pixel contrast of the corner point evaluation area;
[0090] Among them, step 3.2 includes:
[0091] Step 3.2.1: Calculate the pixel mean of the corner point evaluation area;
[0092] Step 3.2.2: Calculate the pixel contrast of the corner point evaluation area based on the pixel mean;
[0093]
[0094] Where w represents the width of the corner point evaluation area, h represents the height of the corner point evaluation area, I(x,y) represents the pixel value at the position (x,y) within the corner point evaluation area, and μ lw×h represents the pixel mean, I 25 represents 25 pixels in the corner point evaluation area, and G represents pixel contrast.
[0095] Step 3.3: When the pixel contrast of the corner point evaluation area is greater than the threshold, the center point is taken as the visible light corner point and the infrared image corner point;
[0096] Step 3.4: Calculate the change direction and amplitude of each visible light corner point and infrared image corner point;
[0097] In step 3.4, the present invention may adopt the formula:
[0098]
[0099] Calculate the change direction and amplitude of each visible light corner point and infrared image corner point; where M(x,y) represents the change amplitude, θ(x,y) represents the change direction, L(x+1,y) represents the pixel value at the position (x+1,y), and L(x,y+1) represents the pixel value at the position (x,y+1).
[0100] Step 3.5: extracting visible light corner points and infrared image corner points whose change directions and amplitudes are within a preset range to form visible light feature points and infrared image feature points;
[0101] Step 3.6: Use feature matching algorithm to complete the matching of visible light feature points and infrared image feature points to obtain the registered infrared image and visible light image;
[0102] Step 3.7: Based on the registered infrared image and visible light image, the distance from each pixel on the infrared image to the workpiece to be processed is obtained.
[0103] The present invention can accurately obtain the distance from each pixel to the workpiece by registering the infrared image and the visible light image, which is convenient for subsequent calibration of the workpiece temperature.
[0104] Step 4: Use the infrared image to calculate the temperature displayed at each pixel;
[0105] Step 5: Use the distance of each pixel point of the infrared image to calibrate the temperature displayed by each pixel point to obtain the calibrated temperature;
[0106] Furthermore, in step 5, the present invention can use an empirical distance formula to calibrate the temperature displayed by each pixel to obtain a calibrated temperature; wherein the empirical distance formula is:
[0107] t0=t x e xa
[0108] Where t0 represents the temperature after calibration, t x It represents the temperature displayed by the pixel on the infrared image, x represents the distance between the pixel on the infrared image, and a represents the empirical coefficient.
[0109] Step 6: Calculate the difference between the calibrated temperature and the preset temperature, and use the control system to adjust the proportional valve of the gas jet cooling device to minimize the difference.
[0110] The present invention can reduce the difference between the workpiece temperature and the preset temperature to the greatest extent by adjusting the proportional valve of the gas jet cooling device using a control system, thereby improving product quality.
[0111] The present invention also provides a temperature control system for supersonic thermal spraying, comprising:
[0112] An image acquisition module, used to acquire infrared images and visible light images of the workpiece to be processed;
[0113] A pixel depth calculation module is used to estimate the depth of each pixel on the visible light image to obtain the distance of each pixel on the visible light image;
[0114] A registration module is used to register the infrared image and the visible light image to obtain the distance of each pixel point of the infrared image;
[0115] A temperature display module is used to calculate the temperature displayed at each pixel using infrared images;
[0116] A calibration module, used to calibrate the temperature displayed by each pixel using the distance of each pixel of the infrared image to obtain a calibrated temperature;
[0117] The control module is used for calculating the difference between the calibrated temperature and the preset temperature, and adjusting the proportional valve of the gas jet cooling device by using the control system to minimize the difference.
[0118] The present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps in the above-mentioned temperature control method for supersonic thermal spraying are implemented.
[0119] The beneficial effect of a temperature control method and system for supersonic thermal spraying provided by the present invention is that: compared with the prior art, the present invention calculates the temperature through infrared images, and can accurately capture the temperature of the scanning area of the workpiece to be processed without contacting the surface of the workpiece, so that the spray room can be closed for production and reduce occupational hazards to operators.
[0120] The present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps in the above-mentioned temperature control method for supersonic thermal spraying are implemented.
[0121] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technical solution that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.
Claims
1. A temperature control method for supersonic thermal spraying, characterized in that: include: Step 1: Obtain infrared images and visible light images of the workpiece to be processed; Step 2: Estimate the depth of each pixel on the visible light image to obtain the distance of each pixel on the visible light image; Step 3: Register the infrared image and the visible light image to obtain the distance of each pixel in the infrared image; Step 4: Use the infrared image to calculate the temperature displayed at each pixel; Step 5: Use the distance of each pixel point of the infrared image to calibrate the temperature displayed by each pixel point to obtain the calibrated temperature; Step 6: Calculate the difference between the calibrated temperature and the preset temperature, and use the control system to adjust the proportional valve of the gas jet cooling device to minimize the difference.
2. A temperature control method for supersonic thermal spraying according to claim 1, characterized in that: The step 2: estimating the depth of each pixel on the visible light image to obtain the distance of each pixel on the visible light image includes: Step 2.1: Perform multi-level decomposition on the visible light image to obtain wavelet coefficients; Step 2.2: performing threshold processing on the wavelet coefficients to obtain processed wavelet coefficients; Step 2.3: reconstructing the processed wavelet coefficients to obtain a denoised visible light image; Step 2.4: extracting a feature map from the denoised visible light image, and inputting the feature map as a sample into a reinforcement learning network for training to obtain an image depth estimation model; Step 2.5: Use the image depth estimation model to estimate the depth of each pixel on the visible light image to obtain the distance of each pixel on the visible light image.
3. A temperature control method for supersonic thermal spraying according to claim 2, characterized in that: The step 2.2: performing thresholding processing on the wavelet coefficients to obtain processed wavelet coefficients, comprises: Step 2.2.1: When the value of the wavelet coefficient is greater than or equal to the processing threshold, the wavelet coefficient is processed by using the first coefficient processing function to obtain the processed wavelet coefficient; Among them, the first coefficient processing function is: Where u is the first adjustment coefficient, sgn() is the sign function, and w j,l is the lth wavelet coefficient under the jth decomposition level, λ is the processing threshold, α is the second adjustment coefficient, β is the third adjustment coefficient, γ is the fourth adjustment coefficient, and p is the wavelet decomposition level; Step 2.2.2: When the value of the wavelet coefficient is less than the processing threshold, the wavelet coefficient is processed by a second coefficient processing function to obtain a processed wavelet coefficient; Among them, the second coefficient processing function is:
4. A temperature control method for supersonic thermal spraying according to claim 3, characterized in that: The calculation formula for the processing threshold is: Wherein, λ is the processing threshold, δ is the standard deviation of Gaussian noise, M is the length of the visible light image, N is the width of the visible light image, and z is the preset coefficient.
5. A temperature control method for supersonic thermal spraying according to claim 4, characterized in that: The step 3: registering the infrared image and the visible light image to obtain the distance of each pixel point of the infrared image includes: Step 3.1: Take any point on the visible light image or infrared image as the center point and take 24 adjacent pixels as the corner point evaluation area; Step 3.2: Calculate the pixel contrast of the corner point evaluation area; Step 3.3: When the pixel contrast of the corner point evaluation area is greater than the threshold, the center point is taken as the visible light corner point and the infrared image corner point; Step 3.4: Calculate the change direction and amplitude of each visible light corner point and infrared image corner point; Step 3.5: extracting visible light corner points and infrared image corner points whose change directions and amplitudes are within a preset range to form visible light feature points and infrared image feature points; Step 3.6: Use feature matching algorithm to complete the matching of visible light feature points and infrared image feature points to obtain the registered infrared image and visible light image; Step 3.7: Based on the registered infrared image and visible light image, the distance from each pixel on the infrared image to the workpiece to be processed is obtained.
6. A temperature control method for supersonic thermal spraying according to claim 5, characterized in that: The step 3.2: calculating the pixel contrast of the corner point evaluation area includes: Step 3.2.1: Calculate the pixel mean of the corner point evaluation area; Step 3.2.2: Calculate the pixel contrast of the corner point evaluation area based on the pixel mean; Where w represents the width of the corner point evaluation area, h represents the height of the corner point evaluation area, I(x,y) represents the pixel value at the position (x,y) within the corner point evaluation area, and μ lw×h represents the pixel mean, I 25 represents 25 pixels in the corner point evaluation area, and G represents pixel contrast.
7. A temperature control method for supersonic thermal spraying according to claim 6, characterized in that: The step 3.4: calculating the change direction and amplitude of each visible light corner point and infrared image corner point includes: Using the formula: Calculate the change direction and amplitude of each visible light corner point and infrared image corner point; where M(x,y) represents the change amplitude, θ(x,y) represents the change direction, L(x+1,y) represents the pixel value at the position (x+1,y), and L(x,y+1) represents the pixel value at the position (x,y+1).
8. A temperature control method for supersonic thermal spraying according to claim 7, characterized in that: Step 5: Use the distance of each pixel of the infrared image to calibrate the temperature displayed by each pixel to obtain the calibrated temperature, including: The temperature displayed by each pixel is calibrated using the empirical distance formula to obtain the calibrated temperature; wherein the empirical distance formula is: t0=t x e xa Where t0 represents the temperature after calibration, t x It represents the temperature displayed by the pixel on the infrared image, x represents the distance between the pixel on the infrared image, and a represents the empirical coefficient.
9. A temperature control system for supersonic thermal spraying, characterized in that: include: An image acquisition module, used to acquire infrared images and visible light images of the workpiece to be processed; A pixel depth calculation module is used to estimate the depth of each pixel on the visible light image to obtain the distance of each pixel on the visible light image; A registration module is used to register the infrared image and the visible light image to obtain the distance of each pixel point of the infrared image; A temperature display module is used to calculate the temperature displayed at each pixel using infrared images; A calibration module, used to calibrate the temperature displayed by each pixel using the distance of each pixel of the infrared image to obtain a calibrated temperature; The control module is used for calculating the difference between the calibrated temperature and the preset temperature, and adjusting the proportional valve of the gas jet cooling device by using the control system to minimize the difference.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the temperature control method for supersonic thermal spraying according to any one of claims 1 to 8 are implemented.
Citation Information
Patent Citations
Method for performing face recognition on sports crowd and temperature measurement equipment and equipment thereof
CN114764028A
Fine temperature calibration method for cold and hot impact test chamber
CN115115653A
Method for identifying axis track of hydroelectric generating set
CN115147651A
Quality discrimination method and system for multi-angle infrared image of transformer
CN117058095A
Smoke and fire detection early warning method and system for video stream monitoring
CN117893964A
