Titanium alloy forming defect detection method and system

Abstract

The invention relates to the technical field of image analysis, in particular to a titanium alloy forming defect detection method and system.The method comprises the steps that optical image data and thermal imaging image data of the surface of a titanium alloy in the titanium alloy hot rolling process are obtained; identifying a defect area in the optical image data, and determining a suspected defect area in the optical image data in combination with the thermal imaging image data; determining the real defect probability of the suspected defect area based on the temperature change of the suspected defect area in the corresponding area in the thermal imaging image data; and determining the defect type of the suspected defect area based on the real defect probability. According to the method, titanium alloy surface defect detection is carried out by combining the color features in the optical image and the temperature change features in the thermal imaging image data at the same time, and the defect detection precision is effectively improved.

Description

Technical Field

[0001] This invention relates to the field of image analysis technology, and specifically to a method and system for detecting forming defects in titanium alloys. Background Technology

[0002] Titanium alloys, due to their high strength, low density, and excellent corrosion resistance, are widely used in high-end manufacturing fields such as aero-engine blades and aerospace structural components. However, during the forming process of hot-rolled titanium alloy sheets, defects such as surface cracks, inclusions, and oxide scale indentation are highly likely to occur due to the complex plastic deformation of the material, intense high-temperature oxidation, and fluctuations in process parameters. Taking aero-engine blades as an example, their service environment has extremely low tolerance for internal material defects; even a crack as small as 0.2 mm can lead to catastrophic failure. Therefore, the accuracy and real-time nature of defect detection are crucial to ensuring the reliability and safety of equipment.

[0003] There are several existing methods for detecting defects in titanium alloy forming: ultrasonic testing detects internal defects by reflecting high-frequency sound waves; eddy current testing is based on the principle of electromagnetic induction and identifies defects by differences in electrical conductivity; infrared thermal imaging locates defects by monitoring differences in the material's heat dissipation rate, for example, the temperature drop rate in the crack area is abnormal due to increased thermal resistance; machine vision inspection analyzes surface color or texture anomalies based on RGB images, such as dark spots on oxide scale or linear features in cracks.

[0004] However, existing detection methods have the following drawbacks: Limited detection parameters: relying solely on a single parameter such as color, temperature, or electromagnetic properties, they cannot eliminate environmental interference (such as oxide stains or hot-rolling temperature fluctuations), resulting in a false detection rate >10%; Inability to perform simultaneous verification: traditional step-by-step detection requires stopping the machine and switching equipment, making real-time comparison of data from the same location before and after hot rolling impossible; Confusion regarding defect types: oxide scale indentation and internal cracks are visually similar, making them indistinguishable by a single detection method, requiring manual re-inspection. Summary of the Invention

[0005] To address the technical problem of high error rates resulting from relying solely on a single parameter such as color, temperature, or electromagnetic properties for titanium alloy forming defect detection, the present invention aims to provide a method and system for detecting titanium alloy forming defects. The specific technical solution adopted is as follows:

[0006] In a first aspect, the present invention provides a method for detecting forming defects in titanium alloys, comprising the following steps:

[0007] Acquire optical and thermal imaging data of the titanium alloy surface during the hot rolling process;

[0008] Defect areas in the optical image data are identified, and combined with the thermal imaging image data, suspected defect areas in the optical image data are determined.

[0009] Based on the temperature change of the corresponding area of ​​the suspected defect area in the thermal imaging image data, the actual defect probability of the suspected defect area is determined.

[0010] Based on the actual defect probability, the defect type of the suspected defect area is determined.

[0011] In conjunction with the first aspect above, in some possible implementations, determining suspected defect areas in the optical image data includes:

[0012] Defect regions in the target frame optical image of the optical image data are identified to determine the color difference regions;

[0013] Several target frame thermal imaging images are determined from the thermal imaging image data, wherein the target frame thermal imaging images correspond to the same titanium alloy surface area as the target frame optical image;

[0014] In the thermal imaging image of the target frame, determine the local temperature difference between the region corresponding to the color difference region and the normal region;

[0015] When any local temperature difference exceeds a set local temperature difference threshold, the corresponding color difference area is identified as a suspected defect area.

[0016] In conjunction with the first aspect mentioned above, among some possible implementation methods, the color difference area is determined, including:

[0017] The optical image of the target frame is converted to the CIELAB color space to obtain a LAB image;

[0018] Determine the average pixel value of the LAB image in each channel;

[0019] Based on the difference between the pixel value of each pixel in each channel and the corresponding pixel mean in the LAB image, the color difference value of each pixel in the LAB image is determined;

[0020] Based on the color difference value, the LAB image is thresholded to obtain the color difference region.

[0021] In conjunction with the first aspect above, in some possible implementations, determining the local temperature difference between the region corresponding to the color difference region and the normal region in the target frame thermal imaging image includes:

[0022] In the target frame thermal imaging image, determine the reference area of ​​the rolling region where the color difference region corresponds to the region;

[0023] The area in the reference region other than the area corresponding to the color difference region is taken as the reference normal region;

[0024] The average pixel value of all pixels in the region corresponding to the color difference region in the thermal imaging image of the target frame is determined to obtain the temperature pixel of the color difference region.

[0025] The average pixel value of all pixels in the reference normal region is determined to obtain the temperature pixel of the normal region.

[0026] Based on the difference between the temperature pixels in the color difference region and the temperature pixels in the normal region, the local temperature difference between the color difference region and the normal region is determined.

[0027] In conjunction with the first aspect above, in some possible implementations, determining the true defect probability of the suspected defect region includes:

[0028] Based on the magnitude of the local temperature difference of the suspected defect area in the thermal imaging images of several target frames, and the difference in the local temperature difference in the thermal imaging images of adjacent target frames, the first defect probability of the suspected defect area is determined.

[0029] Based on the difference in temperature pixels of the color difference region in the suspected defect region in the thermal imaging images of adjacent target frames, and the changing trend of local temperature difference in the thermal imaging images of several target frames, the second defect probability of the suspected defect region is determined.

[0030] Based on the first defect probability and the second defect probability, the actual defect probability of the suspected defect area is determined.

[0031] In conjunction with the first aspect above, in some possible implementations, determining the first defect probability of the suspected defective region includes:

[0032] The cumulative value of the local temperature difference in the suspected defect area in the thermal imaging images of the target frames is determined to obtain the cumulative value of the local temperature difference;

[0033] The mean difference in local temperature difference of the suspected defect area in each pair of adjacent target frame thermal imaging images is determined to obtain the mean difference in local temperature difference.

[0034] Based on the cumulative value of the local temperature difference and the average value of the local temperature difference, the first defect probability of the suspected defect area is determined.

[0035] In conjunction with the first aspect above, in some possible implementations, determining the second defect probability of the suspected defect region includes:

[0036] Based on the difference in temperature pixels of the color difference region in each two adjacent target frame thermal imaging images of the suspected defect area, the stability of the temperature change in the color difference region is determined.

[0037] Based on the local temperature difference variation trend of the suspected defect area in the thermal imaging images of several target frames, the thermal imaging image of the frame to be analyzed with the most abnormal local temperature difference trend is determined.

[0038] Based on the difference between the local temperature difference of the suspected defect area in the thermal imaging image of the frame to be analyzed and the local temperature difference in the thermal imaging image of other target frames, the local temperature difference retention is determined.

[0039] Based on the temperature change stability of the color difference region and the local temperature difference retention, the second defect probability of the suspected defect region is determined.

[0040] In conjunction with the first aspect mentioned above, among some possible implementation methods, the thermal imaging frame of the analysis frame with the most abnormal local temperature difference trend is identified, including:

[0041] The local temperature difference of the suspected defect area in the thermal imaging images of the target frames is fitted by a polynomial to obtain the fitted local temperature difference.

[0042] The maximum value among the residuals of all the local temperature differences and the corresponding fitted local temperature differences is obtained to obtain the maximum residual;

[0043] The thermal imaging image of the target frame corresponding to the maximum residual is determined as the thermal imaging image of the frame to be analyzed with the most abnormal local temperature difference trend change.

[0044] In conjunction with the first aspect above, in some possible implementations, determining the defect type of the suspected defective region includes:

[0045] If the actual defect probability is greater than the high-risk probability threshold, then it is determined that there is a high-risk defect in the corresponding suspected defect area;

[0046] If the actual defect probability is less than or equal to the high-risk probability threshold and greater than the low-risk probability threshold, then it is determined that there is a medium-risk defect in the corresponding suspected defect area.

[0047] Otherwise, it is determined that there is no risk defect in the corresponding suspected defect area.

[0048] Secondly, the present invention also provides a titanium alloy forming defect detection device, the device comprising:

[0049] The image data acquisition module is used to acquire optical image data and thermal imaging image data of the titanium alloy surface during the hot rolling process of titanium alloy;

[0050] The suspected defect area acquisition module is used to identify defect areas in the optical image data and, in conjunction with the thermal imaging image data, determine suspected defect areas in the optical image data.

[0051] The defect probability acquisition module is used to determine the actual defect probability of the suspected defect area based on the temperature change of the corresponding area of ​​the suspected defect area in the thermal imaging image data.

[0052] The defect type determination module is used to determine the defect type of the suspected defect area based on the actual defect probability.

[0053] Thirdly, the present invention also provides a titanium alloy forming defect detection system, the system comprising a memory and a processor. The memory is used to store executable computer program code, and the processor is used to call and run the executable computer program code from the memory, causing the system to perform the methods in the first aspect or any possible implementation thereof.

[0054] Fourthly, the present invention also provides a computer program product comprising: computer program code, which, when run on a computer, causes the computer to perform the method described in the first aspect or any possible implementation thereof.

[0055] Fifthly, the present invention also provides a computer-readable storage medium storing computer program code that, when executed on a computer, causes the computer to perform the method described in the first aspect or any possible implementation thereof.

[0056] This invention offers the following advantages: By acquiring optical and thermal image data of the titanium alloy surface during hot rolling, defect areas in the optical image data are identified, and combined with the thermal image data, suspected defect areas are determined. Based on the temperature change of the corresponding area in the thermal image data, the actual defect probability of the suspected defect area is determined. Based on the actual defect probability, the defect type of the suspected defect area is determined. This invention achieves titanium alloy forming defect detection by acquiring multimodal image data of the titanium alloy surface during hot rolling—that is, simultaneously acquiring optical and thermal image data—and combining color features in the optical images with temperature change features in the thermal image data. This effectively improves the accuracy of defect detection. Attached Figure Description

[0057] To more clearly illustrate the technical solutions and advantages 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.

[0058] Figure 1 This is a flowchart illustrating the steps of a titanium alloy forming defect detection method according to an embodiment of the present invention.

[0059] Figure 2 This is a flowchart illustrating the steps for determining a suspected defective region according to an embodiment of the present invention;

[0060] Figure 3 This is a flowchart illustrating the steps for determining the true defect probability of a suspected defect area according to an embodiment of the present invention.

[0061] Figure 4 This is a schematic diagram of the structure of a titanium alloy forming defect detection device according to an embodiment of the present invention;

[0062] Figure 5 This is a schematic diagram of a titanium alloy forming defect detection system according to an embodiment of the present invention. Detailed Implementation

[0063] To clearly illustrate the technical features of this solution, the invention will be described in detail below through specific embodiments and in conjunction with the accompanying drawings.

[0064] Embodiments of the present invention will now be described in more detail with reference to the accompanying drawings. While some embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the invention. It should be understood that the accompanying drawings and embodiments are for illustrative purposes only and are not intended to limit the scope of protection of the invention.

[0065] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0066] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0067] It should be noted that the concepts of "first" and "second" mentioned in this invention are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0068] Although operations or steps are described in a specific order in the accompanying drawings in the embodiments of the present invention, this should not be construed as requiring these operations or steps to be performed in the specific order or serial order shown, or requiring all of the shown operations or steps to be performed to obtain the desired result. In the embodiments of the present invention, these operations or steps may be performed serially; they may be performed in parallel; or a portion of these operations or steps may be performed.

[0069] Furthermore, it is understood that the data involved in the technical solutions of this invention (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions. Unless otherwise defined, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains, and all parameters or indicators in the formulas involved in this invention are normalized values ​​that have eliminated the influence of dimensions.

[0070] To address the issue of high error rates resulting from relying solely on single parameters such as color, temperature, or electromagnetic properties for titanium alloy forming defect detection, this invention provides a method and system for detecting titanium alloy forming defects. By acquiring optical and thermal image data of the titanium alloy surface during hot rolling, and simultaneously combining color features from the optical images with temperature change features from the thermal images, the accuracy of titanium alloy surface defect detection is effectively improved.

[0071] The following will describe in detail, with reference to the accompanying drawings, a method and system for detecting forming defects in titanium alloys provided by embodiments of the present invention.

[0072] Figure 1 This diagram illustrates the basic flow chart of a titanium alloy forming defect detection method provided by an embodiment of the present invention. Figure 1 As shown, the method specifically includes the following steps:

[0073] Step S100: Acquire optical image data and thermal imaging image data of the titanium alloy surface during the hot rolling process;

[0074] Step S200: Identify the defect areas in the optical image data and, in conjunction with the thermal imaging image data, determine the suspected defect areas in the optical image data;

[0075] Step S300: Based on the temperature change of the corresponding area in the thermal imaging image data of the suspected defect area, determine the actual defect probability of the suspected defect area;

[0076] Step S400: Based on the actual defect probability, determine the defect type of the suspected defect area.

[0077] The titanium alloy forming defect detection method provided in this embodiment of the invention acquires multimodal image data of the titanium alloy surface during the hot rolling process and achieves online accurate detection of titanium alloy forming defects through correlation analysis of dynamic temperature field changes and optical color anomalies, effectively improving the defect detection accuracy.

[0078] The specific steps of the titanium alloy forming defect detection method provided in the embodiments of the present invention will be described in detail below.

[0079] Step S100: Acquire optical image data and thermal imaging image data of the titanium alloy surface during the hot rolling process.

[0080] Specifically, the surface temperature distribution of titanium alloys after hot rolling is related to internal defects. However, neither thermal imaging nor optical inspection can take into account both high-temperature interference and surface details. Therefore, this invention deploys an array of equidistant thermal imaging cameras to continuously capture the dynamic evolution of the temperature field of titanium alloys. At the same time, it deploys optical cameras to acquire high-resolution surface optical images to compensate for the lack of spatial resolution in thermal imaging. The collaboration of the two types of image data can ensure spatiotemporal alignment of the data and cover the entire area without blind spots.

[0081] In a specific example, multiple equidistant thermal imaging cameras are deployed in the conveyor belt area of ​​a titanium alloy hot rolling production line. At the end of the entire column of thermal imaging cameras (i.e., the last thermal imaging camera), a conventional optical camera is synchronously installed to ensure that the acquisition range of the optical camera is consistent with that of the last thermal imaging camera. The installation distance between any two adjacent thermal imaging cameras is set to L, and the sampling time interval between the thermal imaging cameras is determined to be t0 (t0 = L / v when the conveyor belt speed is v) to ensure that the shooting areas of adjacent thermal imaging cameras are continuous and non-overlapping. The models of the thermal imaging cameras and optical cameras can be reasonably selected according to needs. For example, a mid-wave infrared thermal imager (FLIR A8300sc) can be selected as the thermal imaging camera because the mid-wave band (3-5μm) is more sensitive to the radiation of high-temperature titanium alloys, with a temperature measurement accuracy of ±1℃; a high dynamic range industrial camera (Basler ace 2) can be selected as the optical camera, whose wide dynamic range (>120dB) can overcome strong light reflection and retain details in both bright and dark areas.

[0082] During the hot rolling process of titanium alloy, the thermal imaging camera and optical camera installed above are used to collect thermal imaging images and optical images (i.e. RGB images) of the surface area of ​​titanium alloy, thereby obtaining optical image data and thermal imaging image data of the titanium alloy surface during the hot rolling process.

[0083] Step S200: Identify defective areas in the optical image data and, in conjunction with thermal imaging image data, determine suspected defective areas in the optical image data.

[0084] Specifically, the abnormal heat conduction in the defect area of ​​titanium alloy can lead to different temperature distributions, while surface deformation can cause changes in optical reflection characteristics. Therefore, by locating the color abnormal area through end optical imaging and tracing its temperature evolution pattern in thermal imaging data, it is possible to distinguish between real defects and interference such as oxide scale, thereby improving the accuracy of defect identification.

[0085] Furthermore, in one possible implementation, such as Figure 2 As shown, the suspected defect area is identified, including:

[0086] Step S201: Identify the defect areas in the optical image of the target frame in the optical image data and determine the color difference areas.

[0087] Specifically, image preprocessing is performed on the target frame optical image (i.e., any frame of optical image) in the optical image data, such as performing non-local mean filtering to reduce random noise under high-temperature conditions, thereby obtaining the preprocessed target frame optical image. Then, defect region identification is performed on the preprocessed target frame optical image to determine the color difference regions that may be defective regions.

[0088] Furthermore, in one possible implementation, determining the color difference region includes: converting the optical image of the target frame to the CIELAB color space to obtain a LAB image; determining the pixel mean of the LAB image in each channel; determining the color difference value of each pixel in the LAB image based on the difference between the pixel value of each pixel in each channel and the corresponding pixel mean; and performing threshold segmentation on the LAB image based on the color difference value to obtain the color difference region.

[0089] In a specific example, the optical image of the target frame (RGB image) is converted to the CIELAB color space to obtain a LAB image. The pixel mean values ​​of the LAB image in the CIELAB color space are calculated in the L, A, and B channels, and denoted as follows: The pixel value L of any i-th pixel in the L channel of the LAB image is... i A channel pixel value A i And the pixel value of the B channel B iThe color difference value of any i-th pixel in the LAB image is calculated by comparing it with the pixel mean of the corresponding channel.

[0090] Furthermore, based on the color difference value ΔE of each pixel in the LAB image, the color difference region is extracted. This involves using an adaptive threshold k for image binary segmentation. If ΔE > k, the corresponding pixel is identified as a pixel in the color difference region; otherwise, it is identified as a pixel in the normal region. The continuous region formed by the pixels in the color difference region is then determined, and morphological closing operations are used to fill any holes within this continuous region, ultimately yielding the color difference region in the target frame's optical image.

[0091] Step S202: Determine several target frame thermal imaging images from the target frame optical image data, wherein the target frame thermal imaging images and the target frame optical images correspond to the same titanium alloy surface area.

[0092] Specifically, when determining surface defects in titanium alloys based on chromatic aberration areas in optical images, misjudgments may occur due to interference from factors such as surface oxide scale. To more accurately verify the likelihood of a defect, previously captured thermal imaging images can be reviewed, and temperature differences at the corresponding locations can be observed. If abnormal temperature changes are also found in the thermal imaging images, then the presence of a defect in that area can be further confirmed.

[0093] In a specific example, from the thermal imaging image data collected by 9 thermal imaging cameras, 9 thermal imaging images corresponding to the same titanium alloy surface area as the target frame optical image are identified, and these 9 thermal imaging images are used as the target frame thermal imaging images of the target frame optical image. For example, when the acquisition time corresponding to the target frame optical image is t, then the thermal imaging image collected by the last thermal imaging camera at time t is used as one target frame thermal imaging image, the thermal imaging image collected by the thermal imaging camera before the last thermal imaging camera at time t-t0 is used as one target frame thermal imaging image, the thermal imaging image collected by the thermal imaging camera before the last thermal imaging camera at time t-2×t0 is used as one target frame thermal imaging image, and so on, thus obtaining 9 target frame thermal imaging images of the target frame optical image.

[0094] Step S203: Determine the local temperature difference between the region corresponding to the color difference region and the normal region in the thermal imaging image of the target frame.

[0095] Specifically, the chromatic aberration region in the target optical image is mapped onto the target frame thermal imaging image to obtain the corresponding region. In a specific example, the chromatic aberration region in the target optical image is extracted, and its geometric center point A is determined. Subsequently, the coordinates of point A are precisely determined in nine target frame thermal imaging images. Then, based on the coordinates of point A, the chromatic aberration region is located in these nine target frame thermal imaging images, ensuring that the coordinates of the chromatic aberration region in the target optical image and the corresponding point in each target frame thermal imaging image are precisely matched. Thus, the corresponding region of the chromatic aberration region can be determined in all target frame thermal imaging images.

[0096] In the thermal imaging image of the target frame, the temperature of the area corresponding to the color difference region is compared with that of the normal region. Since titanium alloy has poor thermal conductivity, there is a significant temperature difference in the entire image, resulting in a large local temperature difference between the area corresponding to the color difference region and the normal region.

[0097] Furthermore, in one possible implementation, determining the local temperature difference between the region corresponding to the color difference region and the normal region in the thermal imaging image of the target frame includes: determining a reference region in the rolling area where the region corresponding to the color difference region is located in the thermal imaging image of the target frame; taking the region in the reference region other than the region corresponding to the color difference region as the reference normal region; determining the average pixel value of all pixels in the region corresponding to the color difference region in the thermal imaging image of the target frame to obtain the temperature pixel of the color difference region; determining the average pixel value of all pixels in the reference normal region to obtain the temperature pixel of the normal region; and determining the local temperature difference between the color difference region and the normal region based on the difference between the temperature pixels of the color difference region and the temperature pixels of the normal region.

[0098] In a specific example, within any target frame thermal imaging image, a normal region can be selected from the region rolled simultaneously with the chromatic difference region for temperature comparison. In the target frame thermal imaging image, a two-dimensional coordinate system is constructed with the rolling direction (i.e., the conveyor belt transport direction) as the abscissa and the direction perpendicular to the rolling direction as the ordinate. Regions rolled simultaneously are represented by the same abscissa in the image. Therefore, the maximum value X of the abscissa corresponding to the current chromatic difference region is first determined in the target frame thermal imaging image. max With minimum value X min Then determine two lines x = X parallel to the vertical axis. max and x = X min Next, the area between the two straight lines is used as the reference area for the rolling area corresponding to the color difference area. Finally, the area in the reference area other than the area corresponding to the color difference area is used as the reference normal area. The reference normal area maintains the same rolling sequence as the color difference area.

[0099] In any target frame thermal imaging image, the average temperature of all pixels within the region corresponding to the μ-th chromatic difference region is calculated to obtain the pixel temperature T of the chromatic difference region. μ,1 Simultaneously, the average temperature of all pixels within the reference normal region corresponding to the μ-th color difference region is calculated to obtain the normal region temperature pixel T. μ,2 Calculate the temperature T of the color difference region in pixels. μ,1 and normal area temperature pixel T μ,2 The absolute value of the difference is used to obtain the local temperature difference ΔT between the color difference area and the normal area. μ At this time, the local temperature difference ΔT μ =|T μ,1 -T μ,2 |

[0100] Using the above method, the local temperature difference between the chromatic difference region and the normal region in any target frame thermal imaging image can be determined.

[0101] Step S204: When any local temperature difference exceeds the set local temperature difference threshold, the corresponding color difference area is identified as a suspected defect area.

[0102] Specifically, a local temperature difference threshold γ is preset, which needs to be determined based on the actual working conditions. The local temperature difference ΔT between the color difference area and the normal area is then calculated. μ Compared with the local temperature difference threshold γ, when a local temperature difference ΔT exists in any target frame thermal imaging image... μ If the value is greater than γ, the corresponding color difference area is identified as a suspected defect area; otherwise, it indicates that the corresponding color difference area may be due to interference from oxide scale, and no further analysis is performed.

[0103] The above step S200 determines the color difference region in the optical image data and maps the color difference region to the thermal imaging image data, thereby determining the local temperature difference between the corresponding area of ​​the color difference region and the normal area. Based on the local temperature difference, the suspected defect area is accurately identified, avoiding the interference of oxide scale.

[0104] Step S300: Determine the actual defect probability of the suspected defect area based on the temperature change of the suspected defect area in the thermal imaging image data.

[0105] Specifically, during the hot rolling and cooling process of titanium alloys, the temperature change trend is a key consideration in assessing the likelihood of defects. Under standard cooling conditions, the temperature field should decrease smoothly following a predetermined uniform descent path. However, if defects exist within the material, such as microcracks or inhomogeneous microstructures, the temperature change trend in these areas will differ significantly from that of normal areas. For example, due to impaired heat conduction, the cooling rate in cracked areas may be lower than that of the surrounding normal areas, resulting in an abnormal lag or fluctuation in the temperature decrease trend. Based on this, by analyzing the temperature changes of suspected defect areas in thermal imaging data, the probability that a suspected defect area is a real defect can be inferred.

[0106] Furthermore, in one possible implementation, such as Figure 3 As shown, determining the true defect probability of a suspected defect area includes:

[0107] Step S301: Based on the magnitude of the local temperature difference of the suspected defect area in several target frame thermal imaging images, and the difference in the local temperature difference in adjacent target frame thermal imaging images, determine the first defect probability of the suspected defect area.

[0108] Specifically, during the hot rolling and cooling of titanium alloys, the local temperature difference in the actual defect area should be persistent. The higher the local temperature difference in a suspected defect area, and the worse the trend of this local temperature difference change (i.e., the larger the local temperature difference variation), the higher the probability that it is a real defect. Therefore, by analyzing the magnitude of the local temperature difference in each suspected defect area across several target frame thermal imaging images, and the difference in local temperature difference between adjacent target frame thermal imaging images, the first defect probability of that suspected defect area can be determined.

[0109] Furthermore, in one possible implementation, determining the first defect probability of the suspected defect area includes: determining the cumulative value of the local temperature difference of the suspected defect area in several target frame thermal imaging images to obtain the cumulative value of the local temperature difference; determining the average difference of the local temperature difference of the suspected defect area in each pair of adjacent target frame thermal imaging images to obtain the average value of the local temperature difference; and determining the first defect probability of the suspected defect area based on the cumulative value of the local temperature difference and the average value of the local temperature difference.

[0110] In a specific example, for any μ-th suspected defect region in a target frame optical image (i.e., any frame of optical image) of optical image data, the local temperature difference of this μ-th suspected defect region in all target frame thermal imaging images of the target frame optical image can be determined. The local temperature differences are arranged in chronological order of acquisition time of the target frame thermal imaging images, thus determining a local temperature difference sequence. The larger the sum of all local temperature differences in the local temperature difference sequence, the higher the probability that the μ-th suspected defect region is a real defect. Therefore, the cumulative sum of all local temperature differences in the local temperature difference sequence is calculated, and this cumulative sum is used as the cumulative value of the local temperature difference. Simultaneously, the absolute value of the difference between each local temperature difference in the local temperature difference sequence and its subsequent local temperature difference is determined to obtain the local temperature difference variation. The average of the variations corresponding to all local temperature differences is then calculated to obtain the mean local temperature difference variation. The cumulative value of local temperature difference and the mean value of local temperature difference are positively fused. That is, the product of the cumulative value of local temperature difference and the mean value of local temperature difference is calculated, and the product is normalized to the range [0,1] using the maximum and minimum value normalization method, so as to obtain the first defect probability P1 of the μth suspected defect region.

[0111] The above step S301 analyzes the magnitude of the local temperature difference in several target frame thermal imaging images for each suspected defect area, as well as the difference in the local temperature difference in adjacent target frame thermal imaging images, to determine the cumulative value of the local temperature difference and the average value of the local temperature difference. Based on the cumulative value of the local temperature difference and the average value of the local temperature difference, the first defect probability of the suspected defect area can be accurately determined.

[0112] Step S302: Based on the difference in temperature pixels of the color difference region in the thermal imaging images of adjacent target frames of the suspected defect region, and the changing trend of local temperature difference in several target frame thermal imaging images, determine the second defect probability of the suspected defect region.

[0113] Specifically, analyzing the temperature changes of suspected defect areas during the cooling process reveals that the more stable the temperature changes in a suspected defect area are across all thermal imaging images, the greater the probability that it is a genuine defect. Simultaneously, analyzing the retention of local temperature differences in suspected defect areas during cooling shows that if the rate of temperature change in a suspected defect area deviates significantly at a certain moment during the titanium alloy cooling process, and the corresponding change in local temperature difference in the thermal imaging taken at that time is also relatively large, then the probability that the suspected defect area is a genuine defect is higher. Therefore, by analyzing the difference in temperature pixels of the color difference region in adjacent target frame thermal imaging images for each suspected defect area, as well as the trend of local temperature difference changes across all target frame thermal imaging images and the differences in local temperature difference across different target frame thermal imaging images, the probability of a second defect for that suspected defect area can be determined.

[0114] Furthermore, in one possible implementation, determining the second defect probability of the suspected defect region includes: determining the temperature change stability of the color difference region based on the difference in temperature pixels of the color difference region in each pair of adjacent target frame thermal imaging images; determining the thermal imaging image of the frame to be analyzed with the most abnormal local temperature difference trend based on the local temperature difference change trend of the suspected defect region in several target frame thermal imaging images; determining the local temperature difference retention degree based on the difference between the local temperature difference of the suspected defect region in the thermal imaging image of the frame to be analyzed and the local temperature difference in other target frame thermal imaging images; and determining the second defect probability of the suspected defect region based on the temperature change stability of the color difference region and the local temperature difference retention degree.

[0115] Furthermore, in one possible implementation, determining the thermal imaging image of the frame to be analyzed with the most abnormal local temperature difference trend includes: performing polynomial fitting on the local temperature difference of the suspected defect area in several target frame thermal imaging images to obtain the fitted local temperature difference; determining the maximum value among the residuals of all local temperature differences and the corresponding fitted local temperature difference to obtain the maximum residual; and determining the target frame thermal imaging image corresponding to the maximum residual as the thermal imaging image of the frame to be analyzed with the most abnormal local temperature difference trend.

[0116] In a specific example, for any μ-th suspected defect region in the target frame optical image (i.e., any frame optical image) of the optical image data, the chromatic difference region temperature pixel T of the μ-th suspected defect region in all target frame thermal imaging images of the target frame optical image can be determined. μ,1 The color difference area temperature pixel T μ,1 Arrange the thermal imaging images of the target frame in chronological order of acquisition time to determine a color difference region temperature pixel sequence. Calculate the sum of squares of the differences between each color difference region temperature pixel and its next counterpart in this sequence, and then sum all the sums and take the reciprocal to obtain the color difference region temperature change stability U. A larger value for U indicates higher temperature change stability, and a greater probability that the μ-th suspected defect region is a real defect.

[0117] Simultaneously, based on the local temperature difference sequence corresponding to the μth suspected defect region, and the acquisition time of the target frame thermal imaging image corresponding to each local temperature difference in the local temperature difference sequence, a polynomial fitting is performed on the local temperature difference sequence that changes with the acquisition time to obtain any local temperature difference ΔT in the local temperature difference sequence. μ The corresponding fitted local temperature difference ΔT′ μ For the μth suspected defect region, if the local temperature difference ΔT in the thermal imaging image of the i-th target frame... μ,i Local temperature difference ΔT′ after deviation from polynomial fitting and theoretical fitting μThe larger the value (the larger the regression difference), the greater the local temperature difference ΔT in the thermal imaging image of the target frame acquired at the corresponding time. μ,i Local temperature difference ΔT between the thermal imaging image of the j-th target frame and any other target frame μ,j The greater the difference, the higher the local temperature difference retention of the μth suspected defect region, and the higher the probability that the μth suspected defect region is a real defect. Therefore, the local temperature difference ΔT of any i-th target frame thermal imaging image is calculated. μ,i The corresponding fitted local temperature difference ΔT′ μ,i The absolute value of the difference between them is used to obtain the residual, and then the maximum residual R among the residuals corresponding to all target frame thermal imaging images is found. max And the maximum residual R max The corresponding target frame thermal imaging image is taken as the thermal imaging image of the frame to be analyzed, where the local temperature difference trend is most abnormal. The local temperature difference in this thermal imaging image is denoted as maxΔT. μ And calculate the maxΔT μ Local temperature difference ΔT in thermal images of other target frames μ The absolute value of the difference is used to obtain the local temperature difference. The sum of all local temperature difference differences is calculated to obtain the local temperature difference retention degree F. The larger the value of the local temperature difference retention degree F, the higher the degree of local temperature difference retention, and the greater the probability that the μ-th suspected defect area is a real defect.

[0118] Furthermore, the temperature change stability U and local temperature difference retention F of the color difference region corresponding to the μth suspected defect region are positively integrated. That is, the product of the temperature change stability U and the local temperature difference retention F of the color difference region is calculated, and the product is normalized to the range [0,1] using the maximum and minimum value normalization method, thereby obtaining the second defect probability P2 of the μth suspected defect region.

[0119] Step S302 above analyzes the temperature change and local temperature difference retention of the suspected defect area during the cooling process to determine the temperature change stability and local temperature difference retention of the color difference area corresponding to the suspected defect area, thereby accurately determining the second defect probability of the suspected defect area.

[0120] Step S303: Based on the first defect probability and the second defect probability, determine the actual defect probability of the suspected defect area.

[0121] Specifically, for any μ-th suspected defect region, the true defect probability Q of that μ-th suspected defect region is determined by combining its corresponding first defect probability P1 and second defect probability P2. In a specific example, the true defect probability Q of that μ-th suspected defect region is calculated using the following formula:

[0122] Q = ω1P1 + ω2P2;

[0123] In the formula: ω1 and ω2 are weight coefficients, which are determined by the relative magnitudes of the cumulative sums of residuals obtained by performing polynomial fitting on the local temperature difference sequence and the temperature pixel sequence of the color difference region. If the cumulative sum of residuals obtained by performing polynomial fitting on the local temperature difference sequence is R1, and the cumulative sum of residuals obtained by performing polynomial fitting on the temperature pixel sequence of the color difference region is R2, then: ω2 = 1 - ω1.

[0124] In the above step S300, by analyzing the temperature change in the corresponding region of the suspected defect region in the thermal imaging image data, the first defect probability and the second defect probability of the suspected defect region are determined, and then the probability Q that the suspected defect region is a real defect is calculated.

[0125] Step S400: Determine the defect type of the suspected defect region based on the real defect probability.

[0126] Specifically, according to the real defect probability of each suspected defect region, the specific defect type corresponding to each suspected defect region is determined. Among them, the larger the value of the real defect probability, the more likely the corresponding suspected defect region is a defect region with a high defect risk.

[0127] Furthermore, in a possible implementation manner, determining the defect type of the suspected defect region includes: if the real defect probability is greater than the high-risk probability threshold, it is determined that there is a high-risk defect in the corresponding suspected defect region; if the real defect probability is less than or equal to the high-risk probability threshold and greater than the low-risk probability threshold, it is determined that there is a medium-risk defect in the corresponding suspected defect region; otherwise, it is determined that there is no risk defect in the corresponding suspected defect region. Among them, the specific values of the high-risk probability threshold and the low-risk probability threshold need to be determined according to the actual situation.

[0128] In a specific example, determining the defect type of the suspected defect region includes:

[0129] First, perform defect threshold calibration:

[0130] Based on the distribution of the real defect probability Q values of historical qualified samples and defect samples, determine the optimal segmentation threshold Q through the ROC curve crit . For example, when Q > 0.7, the defect probability exceeds 95%, then set 0.7 as the high-risk probability threshold; when 0.4 < Q ≤ 0.7, it is medium risk, and when Q ≤ 0.4, it is low risk, then set 0.4 as the low-risk probability threshold.

[0131] Second, perform defect type mapping:

[0132] High-risk area (Q > 0.7): There are high-risk defects in the corresponding area, that is, there may be serious defects such as cracks and inclusions, and emergency shutdown is required for treatment.

[0133] Medium-risk area (0.4 < Q ≤ 0.7): There are medium-risk defects in the corresponding area, that is, there may be oxide scale pressing in or microcracks, and local process adjustment is required.

[0134] Low-risk area (Q ≤ 0.4): There are no risk defects in the corresponding area, that is, it belongs to the normal production area, and monitoring is maintained.

[0135] Finally, real-time defect type determination and process control:

[0136] Based on the true defect probability Q of the suspected defect area in the optical image data obtained in real time during the hot rolling process of titanium alloy, compare this true defect probability Q with the high-risk probability threshold and low-risk probability threshold determined by the above defect threshold calibration, determine the specific defect type of the suspected defect area, mark the risk areas with high-risk defects and medium-risk defects, and at the same time trigger the titanium alloy hot rolling control system to adjust the rolling parameters. Subsequently, based on the true defect probability Q of the suspected defect area in the optical image data obtained in real time after the rolling parameters are adjusted, verify whether it returns to the safety threshold. If the value of the true defect probability Q continues to be high, trigger a secondary alarm and notify manual intervention.

[0137] Based on the same inventive concept, an embodiment of the present invention further provides a titanium alloy forming defect detection device, as Figure 4 shown, the device includes:

[0138] An image data acquisition module for acquiring optical image data and thermal imaging image data on the surface of titanium alloy during the hot rolling process of titanium alloy;

[0139] A suspected defect area acquisition module for identifying the defect area in the optical image data and determining the suspected defect area in the optical image data in combination with the thermal imaging image data;

[0140] A defect probability acquisition module for determining the true defect probability of the suspected defect area based on the temperature change of the corresponding area of the suspected defect area in the thermal imaging image data;

[0141] A defect type determination module for determining the defect type of the suspected defect area based on the true defect probability.

[0142] It should be noted that the apparatus provided in the above embodiments is only an example of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. In addition, the embodiment of the titanium alloy forming defect detection method provided in the above embodiments belongs to the same concept, and its specific implementation process can be found in the method embodiments, which will not be repeated here.

[0143] Based on the same inventive concept, embodiments of the present invention also provide a titanium alloy forming defect detection system, such as... Figure 5 As shown, the system includes: a memory 501, a processor 502, and computer program code 503 stored in the memory 501 and running on the processor 502, wherein when the processor 502 executes the computer program code 503, the system can perform any of the titanium alloy forming defect detection methods described above.

[0144] In this embodiment of the invention, the system can be divided into functional modules according to the above method example. For example, each module can correspond to a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0145] Based on the same inventive concept, embodiments of the present invention also provide a computer program product, which includes: computer program code, which, when run on a computer, causes the computer to execute any of the titanium alloy forming defect detection methods described above.

[0146] Based on the same inventive concept, embodiments of the present invention also provide a computer-readable storage medium storing computer program code, which, when executed on a computer, causes the computer to perform any of the titanium alloy forming defect detection methods described above.

[0147] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for detecting forming defects in titanium alloys, characterized in that, Includes the following steps: Acquire optical and thermal imaging data of the titanium alloy surface during the hot rolling process; Defect areas in the optical image data are identified, and combined with the thermal imaging image data, suspected defect areas in the optical image data are determined. Based on the temperature change of the corresponding area of ​​the suspected defect area in the thermal imaging image data, the actual defect probability of the suspected defect area is determined. Based on the actual defect probability, the defect type of the suspected defect area is determined.

2. The method for detecting forming defects in titanium alloys according to claim 1, characterized in that, Identifying suspected defect areas in the optical image data includes: Defect regions in the target frame optical image of the optical image data are identified to determine the color difference regions; Several target frame thermal imaging images are determined from the thermal imaging image data, wherein the target frame thermal imaging images correspond to the same titanium alloy surface area as the target frame optical image; In the thermal imaging image of the target frame, determine the local temperature difference between the region corresponding to the color difference region and the normal region; When any local temperature difference exceeds a set local temperature difference threshold, the corresponding color difference area is identified as a suspected defect area.

3. The method for detecting forming defects in titanium alloys according to claim 2, characterized in that, Determine the color difference area, including: The optical image of the target frame is converted to the CIELAB color space to obtain a LAB image; Determine the average pixel value of the LAB image in each channel; Based on the difference between the pixel value of each pixel in each channel and the corresponding pixel mean in the LAB image, the color difference value of each pixel in the LAB image is determined; Based on the color difference value, the LAB image is thresholded to obtain the color difference region.

4. The method for detecting forming defects in titanium alloys according to claim 2, characterized in that, Determining the local temperature difference between the region corresponding to the color difference region and the normal region in the target frame thermal imaging image includes: In the target frame thermal imaging image, determine the reference area of ​​the rolling region where the color difference region corresponds to the region; The area in the reference region other than the area corresponding to the color difference region is taken as the reference normal region; The average pixel value of all pixels in the region corresponding to the color difference region in the thermal imaging image of the target frame is determined to obtain the temperature pixel of the color difference region. The average pixel value of all pixels in the reference normal region is determined to obtain the temperature pixel of the normal region. Based on the difference between the temperature pixels in the color difference region and the temperature pixels in the normal region, the local temperature difference between the color difference region and the normal region is determined.

5. The method for detecting forming defects in titanium alloys according to claim 4, characterized in that, Determining the actual defect probability of the suspected defect area includes: Based on the magnitude of the local temperature difference of the suspected defect area in the thermal imaging images of several target frames, and the difference in the local temperature difference in the thermal imaging images of adjacent target frames, the first defect probability of the suspected defect area is determined. Based on the difference in temperature pixels of the color difference region in the suspected defect region in the thermal imaging images of adjacent target frames, and the changing trend of local temperature difference in the thermal imaging images of several target frames, the second defect probability of the suspected defect region is determined. Based on the first defect probability and the second defect probability, the actual defect probability of the suspected defect area is determined.

6. The method for detecting forming defects in titanium alloys according to claim 5, characterized in that, Determining the first defect probability of the suspected defect region includes: The cumulative value of the local temperature difference in the suspected defect area in the thermal imaging images of the target frames is determined to obtain the cumulative value of the local temperature difference; The mean difference in local temperature difference of the suspected defect area in each pair of adjacent target frame thermal imaging images is determined to obtain the mean difference in local temperature difference. Based on the cumulative value of the local temperature difference and the average value of the local temperature difference, the first defect probability of the suspected defect area is determined.

7. The method for detecting forming defects in titanium alloys according to claim 5, characterized in that, Determining the second defect probability of the suspected defect region includes: Based on the difference in temperature pixels of the color difference region in each two adjacent target frame thermal imaging images of the suspected defect area, the stability of the temperature change in the color difference region is determined. Based on the local temperature difference variation trend of the suspected defect area in the thermal imaging images of several target frames, the thermal imaging image of the frame to be analyzed with the most abnormal local temperature difference trend is determined. Based on the difference between the local temperature difference of the suspected defect area in the thermal imaging image of the frame to be analyzed and the local temperature difference in the thermal imaging image of other target frames, the local temperature difference retention is determined. Based on the temperature change stability of the color difference region and the local temperature difference retention, the second defect probability of the suspected defect region is determined.

8. The method for detecting forming defects in titanium alloys according to claim 7, characterized in that, Identify the thermal imaging frames to be analyzed that exhibit the most anomalous local temperature difference trends, including: The local temperature difference of the suspected defect area in the thermal imaging images of the target frames is fitted by a polynomial to obtain the fitted local temperature difference. The maximum value among the residuals of all the local temperature differences and the corresponding fitted local temperature differences is obtained to obtain the maximum residual; The thermal imaging image of the target frame corresponding to the maximum residual is determined as the thermal imaging image of the frame to be analyzed with the most abnormal local temperature difference trend change.

9. The method for detecting forming defects in titanium alloys according to claim 1, characterized in that, Determining the defect type of the suspected defect area includes: If the actual defect probability is greater than the high-risk probability threshold, then it is determined that there is a high-risk defect in the corresponding suspected defect area; If the actual defect probability is less than or equal to the high-risk probability threshold and greater than the low-risk probability threshold, then it is determined that there is a medium-risk defect in the corresponding suspected defect area. Otherwise, it is determined that there is no risk defect in the corresponding suspected defect area.

10. A titanium alloy forming defect detection system, characterized in that, The device includes a memory, a processor, and executable computer program code stored in the memory and executable on the processor. When the processor executes the computer program code, it performs a method for detecting forming defects in titanium alloys as described in any one of claims 1 to 9.

Images