Part curing temperature detection method and equipment

By acquiring and registering three-dimensional reconstruction diagrams and heat field temperature diagrams from multiple perspectives, the problem of low temperature detection accuracy during the curing process of composite parts is solved, and higher precision temperature monitoring and process control is achieved, and curing quality is improved.

CN118918154APending Publication Date: 2024-11-08CHENGDU AIRCRAFT INDUSTRY GROUP

Patent Information

Application Number
CN202410972268.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-19
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

In the prior art, the temperature detection accuracy of composite parts is low during curing, the detection data of thermocouple sensors is low and prone to failure, and cannot accurately reflect the internal temperature distribution of the parts.

Method used

The three-dimensional reconstruction diagram and the heat field temperature diagram are obtained by multi-view angles. Through image registration and feature point matching, the region of interest is extracted, and the real-time three-dimensional surface temperature information of the parts is obtained, and the temperature detection accuracy is improved.

Benefits of technology

It effectively improves the accuracy of curing temperature detection, accurately grasps the changes in the surface temperature of the parts, and improves the reliability of curing quality and process control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118918154A_ABST
    Figure CN118918154A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a part curing temperature detection method and equipment, and relates to the technical field of composite material processing, and the method comprises the steps: obtaining a three-dimensional reconstruction diagram and a thermal field temperature diagram based on different visual angles of a target part in an autoclave; registering the three-dimensional reconstruction image and the thermal field temperature image to obtain registration images respectively; extracting a region of interest according to the registration image; and obtaining target temperature information according to the region of interest. According to the method, the views of the part are obtained from different visual angles, the surface of the whole part is covered for three-dimensional reconstruction, the thermal field temperature diagram of the part is combined, the three-dimensional reconstruction diagram and the temperature field are registered, then real-time three-dimensional surface temperature information of the part can be obtained, data are visualized through a pattern model, and the real-time three-dimensional surface temperature information of the part can be obtained. After the region of interest is extracted, interference of other regions is eliminated, only target temperature information corresponding to the process temperature measurement point is concerned, the temperature detection precision during curing is effectively improved, and the change condition of the cured part is accurately mastered.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of composite material processing, and in particular to a method and device for detecting the curing temperature of a part. Background Art

[0002] Composite materials have the advantages of high specific strength, high specific stiffness, and designability of mechanical properties. They are ideal materials for lightweight and efficient structural design. Due to their excellent properties, composite materials are increasingly used in the modern aviation manufacturing industry. At present, the most common composite curing molding process is hot autoclave molding. The curing process is a key stage in the manufacture of composite parts. The final quality of the parts depends on the control of the temperature in the tank during the curing process, and directly determines the quality of the aircraft.

[0003] At present, the temperature detection during the curing process is usually carried out by directly sticking thermocouple sensors on the surface of the parts. However, during the entire curing process, it is impossible to verify whether the maximum temperature value responded by the thermocouple is indeed the maximum temperature value of the part. The detection accuracy of the thermocouple sensor is also low. The collected data is a value within the surrounding range, resulting in low temperature detection accuracy. In addition, due to the influence of the working temperature, the thermocouple may fail during the temperature change process, making temperature detection impossible. Summary of the invention

[0004] The main purpose of the present application is to provide a method and device for detecting the curing temperature of a part, aiming to solve the problem of low temperature detection accuracy during the curing process of a part in the prior art.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of the present application are as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for detecting a curing temperature of a part, comprising the following steps:

[0007] Based on different viewing angles of the target part in the autoclave, three-dimensional reconstruction images and thermal field temperature images are obtained respectively;

[0008] The three-dimensional reconstruction image is registered with the thermal field temperature image to obtain registered images respectively;

[0009] Extract the region of interest based on the registered image;

[0010] According to the region of interest, the target temperature information is obtained.

[0011] In a possible implementation of the first aspect, based on different viewing angles of the target part in the autoclave, respectively obtaining a three-dimensional reconstruction image and a thermal field temperature image includes:

[0012] Based on different viewing angles of the target part in the autoclave, obtain thermal field temperature map and depth map;

[0013] Transforming the data of the depth map from the camera coordinate system to the global coordinate system to obtain a second depth map;

[0014] Projecting the vertices scanned by the camera onto the second depth map to obtain the plane coordinates of the vertices;

[0015] According to the plane coordinates of the vertices, the second depth map is mapped to the world coordinate system to obtain a three-dimensional reconstructed image.

[0016] In a possible implementation of the first aspect, based on different viewing angles of the target part in the autoclave, respectively obtaining a three-dimensional reconstruction image and a thermal field temperature image includes:

[0017] Based on different viewing angles of the target part in the autoclave, a 3D reconstruction image and thermal radiation lines of the target part are obtained;

[0018] According to the thermal radiation lines, the thermal field temperature map is obtained.

[0019] In a possible implementation of the first aspect, registering the three-dimensional reconstruction image with the thermal field temperature image to obtain registered images respectively includes:

[0020] Extract feature points from the three-dimensional reconstruction image and the thermal field temperature image to obtain feature point sets respectively;

[0021] Extract the feature points in the same target interval from the feature point set to obtain feature point subsets respectively;

[0022] Perform feature point matching on the feature point subsets to obtain corresponding feature point pairs;

[0023] According to the corresponding feature point pairs, the transformation parameters are obtained;

[0024] The three-dimensional reconstruction image and the thermal field temperature image are registered according to the transformation parameters to obtain registered images.

[0025] In a possible implementation of the first aspect, feature points are extracted from the three-dimensional reconstruction image and the thermal field temperature image to obtain feature point sets, respectively, including:

[0026] Extract feature points from the three-dimensional reconstruction image and the thermal field temperature image to obtain several feature points;

[0027] Taylor expansion is performed at the characteristic points of the three-dimensional reconstruction image and the thermal field temperature image to obtain the second characteristic point;

[0028] According to the second feature points, feature point sets are obtained respectively.

[0029] In a possible implementation of the first aspect, before extracting feature points from the three-dimensional reconstruction image and the thermal field temperature image to obtain feature point sets respectively, the part curing temperature detection method further includes:

[0030] Performing saliency detection on the three-dimensional reconstruction image and the thermal field temperature image to obtain a three-dimensional reconstruction saliency image and a thermal field temperature saliency image;

[0031] Feature points are extracted from the 3D reconstruction image and the thermal field temperature image to obtain feature point sets, including:

[0032] Feature points are extracted from the three-dimensional reconstruction saliency map and the thermal field temperature saliency map to obtain feature point sets respectively.

[0033] In a possible implementation of the first aspect, after performing saliency detection on the three-dimensional reconstruction image and the thermal field temperature image, and obtaining the three-dimensional reconstruction saliency image and the thermal field temperature saliency image, the part curing temperature detection method further includes:

[0034] The three-dimensional reconstruction saliency map and the thermal field temperature saliency map are standardized by using a Gaussian function to obtain a first three-dimensional reconstruction saliency map and a first thermal field temperature saliency map;

[0035] Feature points are extracted from the 3D reconstruction saliency map and the thermal field temperature saliency map to obtain feature point sets, including:

[0036] Feature points are extracted from the first three-dimensional reconstructed saliency map and the first thermal field temperature saliency map to obtain feature point sets respectively.

[0037] In a possible implementation manner of the first aspect, obtaining target temperature information according to the region of interest includes:

[0038] Using the calibration template, the region of interest on the thermal field temperature map is calculated to obtain the temperature value of each pixel in the region of interest;

[0039] The target temperature information is obtained according to the mode of the temperature values ​​of the pixel points.

[0040] In a possible implementation of the first aspect, after calculating the region of interest on the thermal field temperature map using the calibration template and obtaining the temperature value of each pixel in the region of interest, the part curing temperature detection method further includes:

[0041] Remove the pixels whose temperature value is lower than the average temperature value in the region of interest to obtain the temperature value of the target pixel;

[0042] According to the mode of the temperature values ​​of the pixel points, the target temperature information is obtained, including:

[0043] The target temperature information is obtained according to the mode of the temperature values ​​of the target pixel points.

[0044] In a second aspect, an embodiment of the present application provides a part curing temperature detection device, comprising:

[0045] A plurality of RGB-D cameras, wherein the plurality of RGB-D cameras are arranged on the inner wall of the autoclave and are evenly distributed around the axis of the autoclave, and the plurality of RGB-D cameras are used to obtain a three-dimensional reconstruction image as provided in any one of the first aspects above based on different viewing angles of the target part in the autoclave;

[0046] A plurality of thermal infrared cameras are arranged on the inner wall of the autoclave and evenly distributed around the axis of the autoclave, and the plurality of thermal infrared cameras are used to obtain a thermal field temperature map as provided in any one of the first aspects above based on different viewing angles of the target part in the autoclave.

[0047] Compared with the prior art, the beneficial effects of this application are:

[0048] The embodiment of the present application proposes a method and device for detecting the curing temperature of a part, the method comprising: obtaining a three-dimensional reconstruction image and a thermal field temperature map based on different viewing angles of the target part in the autoclave; aligning the three-dimensional reconstruction image with the thermal field temperature map to obtain registered images respectively; extracting the region of interest according to the registered image; and obtaining the target temperature information according to the region of interest. The method of the present application obtains views of the part from different viewing angles, covers the entire surface of the part to perform three-dimensional reconstruction, and aligns the three-dimensional reconstruction image and the temperature field in combination with the thermal field temperature map of the part, thereby obtaining the real-time three-dimensional surface temperature information of the part, and visualizes the data through a pattern model. Since the temperature at different positions is different, after extracting the region of interest, the interference of other regions is excluded, and only the target temperature information corresponding to the process temperature measurement point is focused on, which effectively improves the accuracy of temperature detection during curing, accurately grasps the changes in the cured parts, and can make adjustments accordingly to improve the curing quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A schematic diagram of a process for detecting the curing temperature of a part provided in an embodiment of the present application;

[0050] Figure 2 A schematic diagram of signal conversion and transmission in a method for detecting curing temperature of a part provided in an embodiment of the present application;

[0051] Figure 3 A schematic diagram of the principle of detecting the thermal field of an object in the method for detecting the curing temperature of a part provided in an embodiment of the present application;

[0052] Figure 4 A schematic diagram of the structure of a part curing temperature detection device provided in an embodiment of the present application;

[0053] Figure 5 A schematic diagram of the installation of a thermal infrared camera in a part curing temperature detection device provided in an embodiment of the present application;

[0054] Markings in the figure: 1-thermal infrared camera, 2-cable, 3-sealant, 4-second hollow steel pipe, 5-thread, 6-first hollow steel pipe, 7-autoclave, 8-weld, 9-stage, 10-parts, 11-RGB-D camera, 12-radiation line, 13-lens, 14-grating, 15-detector, 16-thermal field temperature diagram. DETAILED DESCRIPTION

[0055] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] The main solution of the embodiment of the present application is: to propose a method and equipment for detecting the curing temperature of a part, the method comprising: obtaining a three-dimensional reconstruction image and a thermal field temperature map based on different viewing angles of the target part in the autoclave; registering the three-dimensional reconstruction image and the thermal field temperature map to obtain registered images; extracting a region of interest based on the registered image; and obtaining target temperature information based on the region of interest.

[0057] Composite materials have the advantages of high specific strength, high specific stiffness, and designability of mechanical properties. They are ideal materials for lightweight and efficient structural design. Due to their excellent properties, composite materials are increasingly used in the modern aviation manufacturing industry. The performance of composite parts is closely related to the curing and process, and is very sensitive to changes in the process. In addition to quality requirements, aviation products also have strict requirements on the stability of product performance. Process control is often required to ensure the final quality and performance stability of the parts.

[0058] The most common composite material curing molding process is autoclave molding. Autoclave curing molding refers to placing a composite material part blank formed by stacking a single layer of prepreg (a mixture of metal and metal, metal and non-metal, non-metal and non-metal, etc.) layer by layer in a predetermined direction on a stage in an autoclave, and then performing processes such as vacuuming, pressurizing and heating the part, and completing the curing process by adjusting the temperature and pressure. The curing process is a key stage in the manufacture of composite parts. The final quality of the parts depends on the control of the temperature in the tank during the curing process and directly determines the quality of the aircraft. Therefore, it is of great significance to study the effect of precise temperature control of the curing process on the curing uniformity during the composite autoclave molding process.

[0059] At present, the method of detecting temperature is to paste multiple thermocouple sensors on the surface of the part. For some softer composite materials, in order not to damage the part molding, the thermocouple sensors are only pasted on the edge of the part. During the insulation process, according to the process requirements, the thermocouple sensor with the lowest or highest temperature value is selected to reach the set value and then the insulation time is calculated. The disadvantages of this type of detection method are: it is impossible to verify whether the lowest or highest temperature value of the thermocouple sensor is indeed the maximum temperature of the entire part, because the temperature value of the thermocouple sensor at one point represents the temperature values ​​of many surrounding points, and the accuracy is very low; during a certain temperature change process, some thermocouple values ​​may fail, and the temperature value of the point cannot be transmitted, which will directly affect the curing time of the part, and then affect the reliability of the part.

[0060] To this end, the present application provides a solution by acquiring views of the part from different perspectives, covering the entire surface of the part for three-dimensional reconstruction, and combining the thermal field temperature map of the part to align the three-dimensional reconstruction map and the temperature field, so as to obtain the real-time three-dimensional surface temperature information of the part, and visualize the data through a pattern model. Since the temperature at different positions is different, after extracting the area of ​​interest, the interference of other areas is excluded, and only the target temperature information corresponding to the process temperature measurement point is focused on, which effectively improves the accuracy of temperature detection during curing, accurately grasps the changes in the cured parts, and then can make adjustments accordingly to improve the curing quality.

[0061] Refer to the attached Figure 1 , an embodiment of the present application provides a method for detecting the curing temperature of a part, comprising the following steps:

[0062] S10: Based on different viewing angles of the target part in the autoclave, a three-dimensional reconstruction image and a thermal field temperature image are obtained respectively.

[0063] In the specific implementation process, the target part is the part to be cured, the autoclave is a device for hot pressing and curing molding, and the target part is placed on the stage inside the autoclave. In order to avoid one-sided extraction of information, a real-time part image can be obtained by using a shooting device based on multiple different perspectives of the part in the autoclave. For example, in the embodiment of the present application, the part is three-dimensionally reconstructed through the depth information of the RGB-D camera to obtain a three-dimensional structural model of the part, and then a thermal image of the part is obtained through an infrared camera, a thermal imager and other equipment, that is, a thermal field temperature map, which reflects the surface temperature field of the part.

[0064] In one embodiment, the steps of obtaining the 3D reconstruction image are as follows:

[0065] Obtain a depth map based on different viewing angles of the target part in the autoclave;

[0066] Transforming the data of the depth map from the camera coordinate system to the global coordinate system to obtain a second depth map;

[0067] Projecting the vertices scanned by the camera onto the second depth map to obtain the plane coordinates of the vertices;

[0068] According to the plane coordinates of the vertices, the second depth map is mapped to the world coordinate system to obtain a three-dimensional reconstructed image.

[0069] In the specific implementation process, an RGB-D camera specifically refers to a camera that measures distance physically, and obtains an RGB image + a depth image. {Sr, Dr} represents an RGB-D image sequence, where r represents a frame index, Sr represents a color image, and Dr represents the depth image corresponding to the image. For each depth map generated by the camera, a 4×4 transformation matrix can be used to transform all data from the camera coordinate system to the global coordinate system. The transformed data is the second depth map, and the corresponding transformation matrix T is called the camera pose:

[0070]

[0071] Where R is a 3×3 rotation matrix and m is a 3×1 translation vector.

[0072] Through the pinhole imaging principle, the vertex V = (x, y, z)T scanned by the RGB-D camera is projected onto the depth map of the depth image, that is, onto the second depth map, namely:

[0073]

[0074] Where (j, k) is the pixel coordinates corresponding to the projection of the three-dimensional point V onto the image plane, and f x 、f y are the focal lengths of the camera in the x and y directions, c x ,c y is the center coordinate of the camera optical center.

[0075] The process of converting the depth map into a 3D point cloud is to map the point coordinates (j, k) of the plane image to the world coordinate system point G (x w ,y w ,z w ), the conversion process is expressed by the formula:

[0076]

[0077] Where (j, k) is the pixel coordinate corresponding to the image plane, j0 and k0 are the center pixel coordinates corresponding to the image, respectively; Zc is the Z-axis value of the camera coordinate, that is, the distance from the part surface to the camera lens, and T is a 3×1 translation matrix.

[0078] In one embodiment, the steps of obtaining the thermal field temperature map are as follows:

[0079] Based on different viewing angles of the target part in the autoclave, the thermal radiation lines of the target part are obtained;

[0080] According to the thermal radiation lines, the thermal field temperature map is obtained.

[0081] In the specific implementation process, as shown in the attached Figure 3 The figure shows the principle of thermal infrared camera 1 detecting the thermal field of an object. The composite material part emits thermal radiation 12, which is sensed by lens 13 and refracted to grating 14. The radiation 12 passes through grating 14 and irradiates detector 15, eventually forming the thermal field temperature map 16 of the part. The working mode of signal transmission of thermal infrared camera 1, that is, the principle of signal conversion transmission, is shown in the attached figure. Figure 2 As shown, the thermal field of the parts generated by the movement of the thermal infrared camera 1 in the autoclave 7 is transmitted to the signal conversion module via Modbus communication, and the converted electrical signal is transmitted to the computer via Ethernet communication for analysis and calculation of the temperature value.

[0082] S20: registering the three-dimensional reconstruction image with the thermal field temperature image to obtain registered images.

[0083] In the specific implementation process, since the 3D reconstruction image and the thermal field temperature map are based on the same part and have different parameter expressions, the 3D reconstruction image and the thermal field temperature map are aligned. For example, the two images are aligned through edge features or point pair features so that the information of the thermal field temperature map can be displayed in combination with the 3D structure, and finally a registered image that can reflect the surface temperature information of the real-time 3D structure of the part is obtained.

[0084] In one embodiment, registering the three-dimensional reconstruction image with the thermal field temperature image to obtain registered images respectively includes:

[0085] Extract feature points from the three-dimensional reconstruction image and the thermal field temperature image to obtain feature point sets respectively;

[0086] Extract the feature points in the same target interval from the feature point set to obtain feature point subsets respectively;

[0087] Perform feature point matching on the feature point subsets to obtain corresponding feature point pairs;

[0088] According to the corresponding feature point pairs, the transformation parameters are obtained;

[0089] The three-dimensional reconstruction image and the thermal field temperature image are registered according to the transformation parameters to obtain registered images.

[0090] In the specific implementation process, the feature extraction method combining point pair features and edge features is adopted for the dual-source images of the parts, namely the three-dimensional reconstruction image and the thermal field temperature image, and the feature edges, feature points, etc. are preferentially selected as the matching feature quantities. Feature point detection and extraction are performed on the thermal infrared camera and RGB-D camera images respectively to obtain the ORB feature point sets of the two images, and then [-π / 2, π / 2] is divided into n intervals. According to the direction of the feature points, the feature points in the same interval are divided into a feature point subset. When matching the feature points, the two groups of subsets in the same interval of the two images are grouped to calculate the Hamming distance of the feature points to achieve feature point matching. The corresponding feature point pairs of the two images are obtained through the group matching strategy, and the transformation parameters of the images can be calculated to achieve image registration.

[0091] In one embodiment, feature points are extracted from the three-dimensional reconstruction image and the thermal field temperature image to obtain feature point sets, including:

[0092] Extract feature points from the three-dimensional reconstruction image and the thermal field temperature image to obtain several feature points;

[0093] Taylor expansion is performed at the characteristic points of the three-dimensional reconstruction image and the thermal field temperature image to obtain the second characteristic point;

[0094] According to the second feature points, feature point sets are obtained respectively.

[0095] In the specific implementation process, since the overall distribution of pixels in the image is random, but the feature points detected by the ORB algorithm have local correlation, it is necessary to obtain and retain feature points with strong correlation to enhance the stability of the algorithm. Taylor expansion is performed at the feature point (x, y) of the image:

[0096]

[0097] Where D(x,y) is the first-order derivative at the initial feature point (x0,y0); D(x0,y0) is the value at the feature point (x0,y0); is the first-order remainder.

[0098] Perform Taylor quadratic expansion on the feature points, and obtain the extreme value of the feature point position as:

[0099]

[0100] If the extreme value is greater than the set threshold, the stability is strong and the feature point is retained; if it is less than the threshold, the feature point has low contrast and is unstable, so it is deleted.

[0101] In one embodiment, before extracting feature points from the three-dimensional reconstruction image and the thermal field temperature image to obtain feature point sets respectively, the part curing temperature detection method further includes:

[0102] Performing saliency detection on the three-dimensional reconstruction image and the thermal field temperature image to obtain a three-dimensional reconstruction saliency image and a thermal field temperature saliency image;

[0103] Feature points are extracted from the 3D reconstruction image and the thermal field temperature image to obtain feature point sets, including:

[0104] Feature points are extracted from the three-dimensional reconstruction saliency map and the thermal field temperature saliency map to obtain feature point sets respectively.

[0105] In the specific implementation process, the two images are respectively subjected to saliency detection by the histogram contrast (HC) algorithm to obtain a saliency structure diagram. In the HC algorithm, the color information of the image itself is mainly used. In the infrared image generated by the thermal infrared camera, red is mainly used as the salient target color. The saliency of a pixel is determined by the difference between the pixel color and other colors. The saliency value of the pixel color can be expressed by the formula:

[0106]

[0107] Where n is the total number of colors contained in the image; c j For pixel I i The color value of D(c l ,c j ) is the color distance metric between two pixels in the color space; f j For color c j Frequency of occurrence.

[0108] In the RGB-D space, according to the different sensitivities of the human eye to the three primary colors, the weights of the three primary colors are adjusted respectively, and the color distance is calculated using the weighted Euclidean distance to optimize the color distance formula:

[0109]

[0110] Where ΔG, ΔR, and ΔB are the color differences of each channel of the RGB-D camera image and the thermal infrared image, respectively; (c l ,c j ) represents the image color of the thermal infrared camera and RGB-D camera.

[0111] In one embodiment, after performing saliency detection on the three-dimensional reconstruction image and the thermal field temperature image to obtain the three-dimensional reconstruction saliency image and the thermal field temperature saliency image, the part curing temperature detection method further includes:

[0112] The three-dimensional reconstruction saliency map and the thermal field temperature saliency map are standardized by using a Gaussian function to obtain a first three-dimensional reconstruction saliency map and a first thermal field temperature saliency map;

[0113] In the specific implementation process, a preliminary saliency map will be obtained after HC detection, but the image details are blurred. It is necessary to adjust the histogram through Gaussian function to obtain an image with smooth histogram peaks and clear details, so as to optimize the image effect and improve the accuracy of temperature detection.

[0114] Based on the aforementioned standardized processing, feature points are extracted from the 3D reconstructed saliency map and the thermal field temperature saliency map to obtain feature point sets, including:

[0115] Feature points are extracted from the first three-dimensional reconstructed saliency map and the first thermal field temperature saliency map to obtain feature point sets respectively.

[0116] S30: Extracting a region of interest based on the registered image.

[0117] In the specific implementation process, the region of interest, that is, the area to be processed is outlined from the processed image in the form of a box, circle, ellipse, irregular polygon, etc., which is called the region of interest; various operators and functions are often used in machine vision software such as OpenCV and Matlab to obtain the region of interest and perform the next step of image processing.

[0118] S40: Obtain target temperature information according to the region of interest.

[0119] In the specific implementation process, the region of interest mentioned in this embodiment is determined based on the process temperature measurement point, which is to determine a measurement point, and then the temperature measurement of the entire curing process is carried out from this point, with a unified measurement standard. The target temperature information can include the maximum temperature, minimum temperature and average temperature, etc., accurately check the temperature values ​​of multiple parts of the parts, analyze according to the process requirements, and then accurately analyze the quality of the part curing process, providing an accurate judgment basis for the program execution of the processing process.

[0120] In one embodiment, obtaining target temperature information according to the region of interest includes:

[0121] Using the calibration template, the region of interest on the thermal field temperature map is calculated to obtain the temperature value of each pixel in the region of interest;

[0122] The target temperature information is obtained according to the mode of the temperature values ​​of the pixel points.

[0123] In the specific implementation process, in the actual part surface temperature detection process, the temperature at different positions is different. The temperature value of the process point in the area of ​​interest should be detected. For the area of ​​interest, a 5×5 template, that is, a calibration template, is used to calculate the thermal infrared image. The formula is expressed as follows:

[0124] q(i)=∑ i∈Bx(i)p(i)

[0125] Where x(i) is the temperature corresponding to pixel i in the thermal infrared image; p(i) is the mode of the temperature value in the sliding window represented by the function; q(i) is the temperature value of the pixel after calculation; B is the pixel that meets the conditions in the sliding window.

[0126] In one embodiment, after calculating the region of interest on the thermal field temperature map using the calibration template and obtaining the temperature value of each pixel in the region of interest, the part curing temperature detection method further includes:

[0127] Remove the pixels whose temperature is lower than the average temperature in the region of interest to obtain the temperature value of the target pixel.

[0128] In the specific implementation process, the region of interest on the surface of the part is detected in the RGB-D image, and an accurate image registration is achieved based on the affine transformation. The region of interest of the visible light image is mapped to the thermal infrared image in real time, and then the thermal infrared image is subjected to image operation. The operator for extracting the temperature of the region of interest first traverses each pixel point in the region of interest, calculates the average temperature in the region, and removes the pixels whose temperature is lower than the average temperature to reduce the interference with the final temperature. The mode of the temperature of the region of interest is calculated to represent the final temperature of the region of interest, that is, the target temperature information.

[0129] Based on the aforementioned removal step, the target temperature information is obtained according to the mode of the temperature values ​​of the pixel points, including:

[0130] The target temperature information is obtained according to the mode of the temperature values ​​of the target pixel points.

[0131] In this embodiment, three-dimensional reconstruction is performed by acquiring views of the part from different perspectives and covering the entire surface of the part. The three-dimensional reconstruction image and the temperature field are aligned in combination with the thermal field temperature map of the part, so that the real-time three-dimensional surface temperature information of the part can be obtained, and the data can be visualized through a pattern model. Since the temperature at different positions is different, after extracting the area of ​​interest, the interference of other areas is excluded, and only the target temperature information corresponding to the process temperature measurement point is focused on, which effectively improves the accuracy of temperature detection during curing, accurately grasps the changes in the cured parts, and can make adjustments accordingly to improve the curing quality.

[0132] Refer to the attached Figure 4 , 5 Based on the same inventive concept as in the above-mentioned embodiment, the embodiment of the present application further provides a part curing temperature detection device, the device comprising:

[0133] A plurality of RGB-D cameras 11, wherein the plurality of RGB-D cameras 11 are arranged on the inner wall of the autoclave 7 and are evenly distributed around the axis of the autoclave 7, and the plurality of RGB-D 11 cameras are used to obtain a three-dimensional reconstruction image as provided in the embodiment of the present application based on different viewing angles of the target part in the autoclave 7;

[0134] A plurality of thermal infrared cameras 1 are arranged on the inner wall of the autoclave 7 and are evenly distributed around the axis of the autoclave 7. The plurality of thermal infrared cameras 1 are used to obtain a thermal field temperature map as provided in an embodiment of the present application based on different viewing angles of the target part in the autoclave 7.

[0135] In the specific implementation process, as shown in the attached Figure 4 It is a structural schematic diagram when five RGB-D cameras 11 and five thermal infrared cameras 1 are set. In order to evenly and comprehensively cover the surface of the part 10, suitable holes are processed on the autoclave body, and five RGB-D cameras 11 and five high-precision high-temperature resistant thermal infrared cameras 1 are installed at 30°, 60°, 90°, 120° and 150° respectively. The composite material part 10 is placed on the workbench 9 for work, and the thermal field temperature diagram and structure diagram of the part at five different angles are taken through the camera positions at five different angles.

[0136] In one embodiment, a method for installing a thermal infrared camera 1 is provided to facilitate data transmission in a high temperature and high pressure environment, while taking into account stability and sealing. Specifically:

[0137] Process appropriate holes in the autoclave 7, install the first hollow steel pipe 6 with threads 5, and perform welding and sealing. The weld 8 after welding is shown in the figure. Install the second hollow steel pipe 4 with threads 5 in the first hollow steel pipe 6, so that the two steel pipes are screwed together, such as setting internal threads on the first hollow steel pipe 6 and external threads on the second hollow steel pipe 4. The second hollow steel pipe 4 is welded inside the tank to connect the bracket to fix the thermal infrared camera 1. The cable 2 of the thermal infrared camera passes through the second hollow steel pipe 4 to transmit the signal to the outside of the tank. The two are sealed with a high-temperature resistant sealant 3.

[0138] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0139] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0140] In summary, the present application provides a method and device for detecting the curing temperature of a part, including: obtaining a three-dimensional reconstruction image and a thermal field temperature map based on different viewing angles of the target part in the autoclave; aligning the three-dimensional reconstruction image with the thermal field temperature map to obtain registered images; extracting the region of interest according to the registered image; and obtaining the target temperature information according to the region of interest. The method of the present application obtains views of the part from different viewing angles, covers the entire surface of the part for three-dimensional reconstruction, and aligns the three-dimensional reconstruction image and the temperature field in combination with the thermal field temperature map of the part, thereby obtaining the real-time three-dimensional surface temperature information of the part, and visualizes the data through a pattern model. Since the temperature at different positions is different, after extracting the region of interest, the interference of other regions is excluded, and only the target temperature information corresponding to the process temperature measurement point is focused on, which effectively improves the accuracy of temperature detection during curing, accurately grasps the changes in the cured parts, and can make adjustments accordingly to improve the curing quality.

[0141] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for detecting the curing temperature of a part, characterized in that: The following steps are involved: Based on different viewing angles of the target part in the autoclave, three-dimensional reconstruction images and thermal field temperature images are obtained respectively; Registering the three-dimensional reconstruction image with the thermal field temperature image to obtain registered images respectively; Extracting a region of interest according to the registered image; According to the region of interest, target temperature information is obtained.

2. The method for detecting the curing temperature of a part according to claim 1, characterized in that: The three-dimensional reconstruction image and the thermal field temperature image are obtained based on different viewing angles of the target part in the autoclave, including: Based on different viewing angles of the target part in the autoclave, obtain thermal field temperature map and depth map; Transforming the data of the depth map from the camera coordinate system to the global coordinate system to obtain a second depth map; Projecting the vertices scanned by the camera onto the second depth map to obtain the plane coordinates of the vertices; According to the plane coordinates of the vertices, the second depth map is mapped to a world coordinate system to obtain a three-dimensional reconstructed image.

3. The method for detecting the curing temperature of a part according to claim 1, characterized in that: The three-dimensional reconstruction image and the thermal field temperature image are obtained based on different viewing angles of the target part in the autoclave, including: Based on different viewing angles of the target part in the autoclave, a 3D reconstruction image and thermal radiation lines of the target part are obtained; A thermal field temperature diagram is obtained according to the thermal radiation lines.

4. The method for detecting the curing temperature of a part according to claim 1, characterized in that: The registering the three-dimensional reconstruction image with the thermal field temperature image to obtain registered images respectively includes: Extracting feature points from the three-dimensional reconstruction image and the thermal field temperature image to obtain feature point sets respectively; Extracting feature points located in the same target interval from the feature point set to obtain feature point subsets respectively; Performing feature point matching on the feature point subset to obtain corresponding feature point pairs; Obtaining transformation parameters according to the corresponding feature point pairs; The three-dimensional reconstruction image and the thermal field temperature image are registered according to the transformation parameters to obtain registered images.

5. The method for detecting the curing temperature of a part according to claim 4, characterized in that: The extracting feature points from the three-dimensional reconstruction image and the thermal field temperature image to obtain feature point sets respectively includes: Extracting feature points from the three-dimensional reconstruction image and the thermal field temperature image to obtain a number of feature points; Performing Taylor expansion at the characteristic points of the three-dimensional reconstruction image and the thermal field temperature image to obtain a second characteristic point; Feature point sets are obtained according to the second feature points.

6. The method for detecting the curing temperature of a part according to claim 4, characterized in that: Before extracting feature points from the three-dimensional reconstruction image and the thermal field temperature image to obtain feature point sets respectively, the part curing temperature detection method further includes: Performing saliency detection on the three-dimensional reconstruction image and the thermal field temperature image to obtain a three-dimensional reconstruction saliency image and a thermal field temperature saliency image; The extracting feature points from the three-dimensional reconstruction image and the thermal field temperature image to obtain feature point sets respectively includes: Feature points are extracted from the three-dimensional reconstructed saliency map and the thermal field temperature saliency map to obtain feature point sets respectively.

7. The method for detecting the curing temperature of a part according to claim 6, characterized in that: After performing significance detection on the three-dimensional reconstruction image and the thermal field temperature image to obtain the three-dimensional reconstruction significance image and the thermal field temperature significance image, the part curing temperature detection method further includes: Using a Gaussian function to perform regularization processing on the three-dimensional reconstruction saliency map and the thermal field temperature saliency map to obtain a first three-dimensional reconstruction saliency map and a first thermal field temperature saliency map; The extracting feature points from the three-dimensional reconstructed saliency map and the thermal field temperature saliency map to obtain feature point sets respectively includes: Feature points are extracted from the first three-dimensional reconstructed saliency map and the first thermal field temperature saliency map to obtain feature point sets respectively.

8. The method for detecting the curing temperature of a part according to claim 1, characterized in that: The step of obtaining target temperature information according to the region of interest includes: Using a calibration template, calculating the region of interest on the thermal field temperature map to obtain a temperature value of each pixel in the region of interest; The target temperature information is obtained according to the mode of the temperature values ​​of the pixel points.

9. The method for detecting the curing temperature of a part according to claim 8, characterized in that: After the calibration template is used to calculate the region of interest on the thermal field temperature map to obtain the temperature value of each pixel point in the region of interest, the part curing temperature detection method further includes: Remove the pixel points whose temperature value is lower than the average temperature value in the region of interest to obtain the temperature value of the target pixel point; The obtaining target temperature information according to the mode of the temperature values ​​of the pixel points includes: Target temperature information is obtained according to the mode of the temperature values ​​of the target pixel points.

10. A part curing temperature detection device, characterized in that: include: A plurality of RGB-D cameras, wherein the plurality of RGB-D cameras are arranged on the inner wall of the autoclave and are evenly distributed around the axis of the autoclave, and the plurality of RGB-D cameras are used to obtain a three-dimensional reconstruction image according to any one of claims 1 to 9 based on different viewing angles of the target part in the autoclave; A plurality of thermal infrared cameras are arranged on the inner wall of the autoclave and are evenly distributed around the axis of the autoclave, and the plurality of thermal infrared cameras are used to obtain the thermal field temperature map according to any one of claims 1 to 9 based on different viewing angles of the target part in the autoclave.

Citation Information

Patent Citations

  • Indoor three-dimensional reconstruction method based on infrared scanning

    CN106846473A

  • Personnel information detection method and system for indoor environment control

    CN110110629A

  • Three-dimensional measurement surface temperature field reconstruction method

    CN112614215A

  • Forging temperature field distribution and three-dimensional size integrated reconstruction method

    CN117557731A

Cited By

  • Autoclave infrared thermal imaging system and device

    CN120521736A

  • An autoclave infrared thermal imaging system and device

    CN120521736B