Blade ablation damage grade determination method, device, equipment and readable storage medium
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- DONGFENG COMML VEHICLE CO LTD
- Filing Date
- 2022-09-27
- Publication Date
- 2026-07-03
Smart Images
Figure CN115564722B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of detection technology, and in particular to a method, apparatus, equipment, and readable storage medium for determining the degree of blade ablation damage. Background Technology
[0002] The turbine blades of a turbocharger operate in a high-temperature region. Due to uneven heating, the blades are prone to localized ablation, leading to turbocharger malfunctions. Therefore, to ensure stable turbocharger operation, it is necessary to perform flaw detection tests on the turbine blades to determine the extent of damage.
[0003] Currently, when conducting flaw detection tests on turbine blades, ultrasonic testing of the rotor must be performed manually, which is not only labor-intensive but also has a long testing cycle. Summary of the Invention
[0004] The main objective of this invention is to provide a method, apparatus, device, and readable storage medium for determining the level of blade ablation damage, aiming to solve the technical problem of time-consuming and labor-intensive manual flaw detection testing of turbine blades in the prior art.
[0005] In a first aspect, the present invention provides a method for determining the level of blade ablation damage, the method comprising:
[0006] Obtain the leaf area, leaf centroid coordinates, and leaf image;
[0007] The ablation region detection is performed on the blade image to obtain the number of ablation regions, the ablation region image corresponding to each ablation region, the area of the ablation region, and the centroid coordinates of the ablation region.
[0008] Obtain the RGB values and shape labels of each ablation region image;
[0009] Based on the blade area, blade centroid coordinates, ablation area area corresponding to each ablation region, ablation centroid coordinates, RGB values of each ablation region image, and ablation region shape label, ablation feature index values are obtained.
[0010] The ablation damage level of the blade is determined based on the number of ablation zones and the ablation characteristic index values.
[0011] Optionally, the steps of obtaining the leaf area, leaf centroid coordinates, and leaf image include:
[0012] Leaf detection is performed on the original image to obtain the leaf boundary coordinates, leaf area, and leaf centroid coordinates. The original image is an image captured of the leaf.
[0013] The coordinates of the minimum bounding rectangle of the blade are obtained from the blade boundary coordinates;
[0014] The leaf image is cropped from the original image based on the coordinates of the minimum bounding rectangle of the leaf.
[0015] Optionally, the step of obtaining the ablation feature index value based on the blade area, blade centroid coordinates, ablation area area corresponding to each ablation region, ablation region centroid coordinates, RGB values of each ablation region image, and ablation region shape label includes:
[0016] Based on the RGB values of each ablation region image, color feature index values are obtained;
[0017] Based on the area of the ablation zone of each ablation zone, the area characteristic index value is obtained;
[0018] The density characteristic index value is obtained based on the blade area and the ablation area of each ablation zone;
[0019] Based on the centroid coordinates of the ablation zone for each ablation zone, the location characteristic index value is obtained;
[0020] Based on the centroid coordinates of the blade and the centroid coordinates of the ablation zone of each ablation zone, discrete characteristic index values are obtained;
[0021] Based on the shape label of the ablation region in each ablation region image, the shape feature index value is obtained.
[0022] Optionally, the step of obtaining the color feature index value based on the RGB values of each ablation region image includes:
[0023] The RGB values of all ablation region images are summed to obtain the RGB sum value;
[0024] The average value of the RGB values is used as the color feature index value.
[0025] Optionally, the step of obtaining the area characteristic index value based on the ablation area of each ablation region includes:
[0026] Calculate the average and variance based on the area of the ablation zone for each ablation zone;
[0027] Abnormal ablation area is removed, wherein the difference between the abnormal ablation area and the average value is less than the product of the variance and a first preset value, or greater than the product of the variance and a second preset value.
[0028] The maximum value is selected from the remaining ablation area and used as the area characteristic index value.
[0029] Optionally, the step of obtaining the density characteristic index value based on the blade area and the ablation area of each ablation region includes:
[0030] The areas of all ablation zones are summed to obtain the sum of the areas.
[0031] The ratio of the sum of the areas to the leaf area is calculated, and this ratio is used as the density characteristic index value.
[0032] Optionally, the step of determining the blade ablation damage level based on the number of ablation zones and ablation characteristic index values includes:
[0033] The ablation damage coefficient of the blade is obtained by weighting the number of ablation regions, color characteristic index value, area characteristic index value, density characteristic index value, location characteristic index value, discrete characteristic index value, and shape characteristic index value.
[0034] The blade ablation damage level is determined based on the blade ablation damage coefficient.
[0035] Secondly, the present invention also provides a blade ablation damage level determination device, the blade ablation damage level determination device comprising:
[0036] The first acquisition module is used to acquire the leaf area, the centroid coordinates of the leaf, and the leaf image;
[0037] The detection module is used to detect ablation areas in the blade image and obtain the number of ablation areas, the ablation area image corresponding to each ablation area, the area of the ablation area, and the centroid coordinates of the ablation area.
[0038] The second acquisition module is used to acquire the RGB values of each ablation region image and the shape label of the ablation region;
[0039] The calculation module is used to obtain ablation feature index values based on blade area, blade centroid coordinates, ablation area corresponding to each ablation region, ablation region centroid coordinates, RGB values of each ablation region image, and ablation region shape label.
[0040] The grading module is used to determine the ablation damage level of the blades based on the number of ablation zones and the ablation characteristic index values.
[0041] Thirdly, the present invention also provides a blade ablation damage level determination device, the blade ablation damage level determination device including a processor, a memory, and a blade ablation damage level determination program stored in the memory and executable by the processor, wherein when the blade ablation damage level determination program is executed by the processor, the steps of the blade ablation damage level determination method as described above are implemented.
[0042] Fourthly, the present invention also provides a readable storage medium storing a blade ablation damage level determination program, wherein when the blade ablation damage level determination program is executed by a processor, the steps of the blade ablation damage level determination method as described above are implemented.
[0043] In this invention, the blade area, blade centroid coordinates, and blade image are acquired. The blade image is then subjected to ablation region detection to obtain the number of ablation regions, the corresponding ablation region image, the ablation region area, and the centroid coordinates of the ablation region. The RGB values and shape labels of each ablation region image are obtained. Based on the blade area, blade centroid coordinates, the corresponding ablation region area, the centroid coordinates of the ablation region, the RGB values of each ablation region image, and the shape labels of the ablation region, ablation feature index values are obtained. The blade ablation damage level is determined based on the number of ablation regions and the ablation feature index values. This invention, with equipment as the primary driver, automatically determines the blade ablation damage level, reducing manual intervention and improving the efficiency of blade flaw detection testing. Attached Figure Description
[0044] Figure 1 This is a schematic diagram of the hardware structure of the blade ablation damage level determination device involved in the embodiment of the present invention;
[0045] Figure 2 This is a flowchart illustrating an embodiment of the blade ablation damage level determination method of the present invention;
[0046] Figure 3 This is a schematic diagram of the functional modules of an embodiment of the blade ablation damage level determination device of the present invention.
[0047] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0048] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
[0049] In a first aspect, embodiments of the present invention provide a blade ablation damage level determination device, which can be a personal computer (PC), laptop computer, server or other device with data processing capabilities.
[0050] Reference Figure 1 , Figure 1This is a schematic diagram of the hardware structure of the blade ablation damage level determination device involved in an embodiment of the present invention. In this embodiment, the blade ablation damage level determination device may include a processor 1001 (e.g., a Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize communication between these components; the user interface 1003 may include a display screen or an input unit such as a keyboard; the network interface 1004 may optionally include a standard wired interface or a wireless interface (e.g., Wireless Fidelity, Wi-Fi interface); the memory 1005 may be high-speed random access memory (RAM) or stable memory (non-volatile memory), such as a disk storage device; the memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001. Those skilled in the art will understand that… Figure 1 The hardware structure shown does not constitute a limitation of the invention and may include more or fewer components than shown, or combine certain components, or have different component arrangements.
[0051] Continue to refer to Figure 1 , Figure 1 The memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a blade ablation damage level determination program. The processor 1001 can call the blade ablation damage level determination program stored in the memory 1005 and execute the blade ablation damage level determination method provided in this embodiment of the invention.
[0052] Secondly, embodiments of the present invention provide a method for determining the level of blade ablation damage.
[0053] In one embodiment, reference is made to Figure 2 , Figure 2 This is a flowchart illustrating an embodiment of the blade ablation damage level determination method of the present invention. Figure 2 As shown, the methods for determining the level of blade ablation damage include:
[0054] Step S10: Obtain the leaf area, leaf centroid coordinates, and leaf image;
[0055] In this embodiment, the leaf is first photographed, and then image processing is performed on the photographed image to obtain the leaf area, centroid coordinates, and leaf image of the leaf in the image.
[0056] Further, in one embodiment, step S10 includes:
[0057] Step S101: Perform leaf detection on the original image to obtain the leaf boundary coordinates, leaf area, and leaf centroid coordinates. The original image is an image obtained by taking pictures of the leaf.
[0058] In this embodiment, the leaf to be detected is first photographed to obtain the original image. Then, the original image is segmented using a leaf segmentation model to obtain the leaf boundary coordinates, the leaf area S0, and the leaf centroid coordinates O. xy = (x0, y0). The blade segmentation model is obtained through training, and the network structure of the blade segmentation model can be Unet++.
[0059] Step S102: Obtain the coordinates of the minimum bounding rectangle of the blade based on the blade boundary coordinates;
[0060] In this embodiment, the coordinates of the minimum bounding rectangle of the blade can be obtained from the blade boundary coordinates.
[0061] Step S103: Crop the leaf image from the original image according to the coordinates of the minimum bounding rectangle of the leaf.
[0062] In this embodiment, the leaf image defined by the minimum bounding rectangle coordinates of the leaf can be cropped from the original image.
[0063] Step S20: Detect ablation areas in the blade image to obtain the number of ablation areas, the ablation area image corresponding to each ablation area, the area of the ablation area, and the centroid coordinates of the ablation area.
[0064] In this embodiment, an ablation region segmentation model can be used to detect ablation regions in the blade image, thereby determining each ablation region in the blade image and obtaining the number of ablation regions M, the boundary coordinates, area, and centroid coordinates P of each ablation region. i =(x i ,y i Then, based on the boundary coordinates of each ablation region, the image of each ablation region is cropped from the blade image. The ablation region segmentation model is obtained through training, and its network structure can be Unet++.
[0065] Step S30: Obtain the RGB values and shape labels of each ablation region image;
[0066] In this embodiment, the RGB values of each ablation region image can be obtained through an image processing program (such as the getcolors() method built into PIL). The RGB values of the ablation region image can be the overall RGB values of the ablation region image, or the RGB values of each pixel in the ablation region image.
[0067] Each ablation region image is identified using an ablation region shape recognition model, resulting in a shape label for each ablation region. For example, if the model's recognition results include near-circular and irregular shapes, the corresponding shape label for the ablation region will be either a near-circular label or an irregular label. The ablation region shape recognition model is trained, and its network structure can be VGG16.
[0068] Step S40: Based on the blade area, blade centroid coordinates, ablation area area corresponding to each ablation area, ablation centroid coordinates, RGB values of each ablation area image, and ablation area shape label, obtain ablation feature index values.
[0069] In this embodiment, ablation characteristic index values are obtained based on the blade area, blade centroid coordinates, ablation area area corresponding to each ablation region, ablation centroid coordinates, RGB values of each ablation region image, and ablation region shape labels, according to a specific calculation method. This calculation method is designed according to actual needs and is not limited here.
[0070] Further, in one embodiment, step S40 includes:
[0071] Step S401: Obtain color feature index values based on the RGB values of each ablation region image;
[0072] In this embodiment, taking the ablation region images including ablation region image 1, ablation region image 2, ablation region image 3, ablation region image 4, and ablation region image 5 as an example, and taking the RGB value of each ablation region image as the RGB value of each pixel in each ablation region image, the process of obtaining the color feature index value can be as follows:
[0073] The maximum value of R from each pixel in ablated region image 1 is selected and denoted as R1; the maximum value of G from each pixel in ablated region image 1 is selected and denoted as G1; the maximum value of B from each pixel in ablated region image 1 is selected and denoted as B1; the maximum value of R from each pixel in ablated region image 2 is selected and denoted as R2; the maximum value of G from each pixel in ablated region image 2 is selected and denoted as G2; the maximum value of B from each pixel in ablated region image 2 is selected and denoted as B2, and so on, to obtain R3, R4, R5, G3, G4, G5, B3, B4, and B5. The sum of R1+R2+R3+R4+R5+G1+G2+G3+G4+G5+B1+B2+B3+B4+B5 is calculated, and then this sum is divided by (3*M). The resulting value is used as the color feature value label. C Where M represents the total number of ablation region images.
[0074] It should be noted that the above is only an illustrative explanation of the calculation of color feature index values and does not constitute a limitation on the calculation of color feature index values. The specific calculation method of color feature index values can be designed according to actual needs.
[0075] Further, in one embodiment, step S401 includes:
[0076] The RGB values of all ablation area images are summed to obtain the RGB sum value; the average value of the RGB sum value is used as the color feature index value.
[0077] In this embodiment, the RGB values of the ablation region image can be the overall RGB values of the ablation region image or the RGB values of each pixel in the ablation region image. The RGB values of all ablation region images are summed to obtain the RGB sum value; then, the RGB sum value is divided by 3 to obtain the average RGB sum value. This average RGB sum value is then used as the color feature index value, label. C .
[0078] Step S402: Obtain the area characteristic index value based on the area of the ablation zone of each ablation zone;
[0079] In this embodiment, the maximum value among the ablation areas of all ablation areas can be selected as the area feature index value label. S Alternatively, the area of all ablation zones can be summed, and the sum can be used as the area feature index value (label). S .
[0080] Further, in one embodiment, step S402 includes:
[0081] Step S4021: Calculate the average value and variance based on the ablation area of each ablation region;
[0082] In this embodiment, it is assumed that the ablation areas of ablation area 1 to ablation area M are S1, S2…S1, S2, S3, S4, S5, S6, S7, S8, S9, S1 ...1, S1, S2, S3, S4, S5, S M The average value is:
[0083]
[0084] The variance is:
[0085]
[0086] Step S4022: Remove abnormal ablation area areas, wherein the difference between the abnormal ablation area and the average value is less than the product of the variance and the first preset value, or greater than the product of the variance and the second preset value.
[0087] In this embodiment, if S i -S mean <-2×S std or S i -S mean >2×S std Then determine S i The area of the abnormal ablation zone is defined, and S is excluded. i , where i takes values from 1 to M. It should be noted that this is only an illustrative explanation of the first and second preset values, and the first and second preset values should be set according to actual needs.
[0088] Step S4023: Select the maximum value from the remaining ablation area as the area characteristic index value.
[0089] In this embodiment, after removing the abnormal ablation area according to step S4022, the maximum value is selected from the remaining ablation area area as the area feature index value label. S .
[0090] Step S403: Obtain the density characteristic index value based on the blade area and the ablation area of each ablation region;
[0091] Further, in one embodiment, step S403 includes:
[0092] The areas of all ablation zones are summed to obtain a total area value; the ratio of this total area value to the blade area is calculated, and this ratio is used as the density characteristic index value (label). m .
[0093] In this embodiment, it is assumed that the ablation areas of ablation area 1 to ablation area M are S1, S2…S1, S2, S3, S4, S5, S6, S7, S8, S9, S1 ...1, S1, S2, S3, S4, S5, SM The sum of the areas of all ablation zones is obtained by accumulating the areas of all ablation zones. Then, the ratio of the sum of the areas to the leaf area is calculated, and this ratio is used as the density characteristic index value (label). m .
[0094] In another embodiment, it is assumed that the ablation areas of ablation region 1 to ablation region M are S1, S2…S… M After removing the abnormal ablation areas according to step S4023 above, the remaining ablation areas are: S1, S2…S N Then, the areas of the remaining ablation zones are summed to obtain the sum of the areas. Then, the ratio of the sum of the areas to the leaf area is calculated, and this ratio is used as the density characteristic index value (label). m .
[0095] Step S404: Obtain the location feature index value based on the centroid coordinates of the ablation area of each ablation area;
[0096] In this embodiment, the centroid coordinates of each ablation region are: Then the ordinate of the centroid coordinate of each ablation region can be obtained. Assuming there are 5 ablation zones, the ordinates of the centroids of these zones are L1, L2, L3, L4, and L5, respectively. The maximum value among L1, L2, L3, L4, and L5 is used as the location feature index value, labeled. L .
[0097] Step S405: Based on the centroid coordinates of the blade and the centroid coordinates of the ablation zone of each ablation zone, obtain the discrete characteristic index values;
[0098] In this embodiment, the centroid coordinate of the blade is 0. xy = (x0, y0), then the distance between the centroid of the ablation region and the centroid of the blade in each ablation region is:
[0099]
[0100] Suppose there are 5 ablation regions, and the distances from the centroid of the 5 ablation regions to the centroid of the blade are r1, r2, r3, r4, and r5, respectively. Then, perform specific operations on r1, r2, r3, r4, and r5, such as calculating the standard deviation, calculating the average, etc., and use the calculated values as the discrete feature index value label. r .
[0101] Step S406: Obtain shape feature index values based on the shape label of the ablation region in each ablation region image.
[0102] In this embodiment, it is assumed that there are 5 ablation region images, and the shape labels of the ablation regions in the 5 ablation region images are nearly circular, nearly circular, nearly circular, irregular, and irregular, respectively. The correspondence between the ablation region shape labels and label values is shown in Table 1:
[0103] ablation area shape label Tag value Near-circular label 0 Irregular labels 1
[0104] The label values corresponding to the five ablation region images are 0, 0, 0, 1, and 1, respectively. These label values are then summed, and the sum is used as the shape feature index value (label). x It should be noted that,
[0105] The above correspondence between the shape labels and label values of ablation regions is for illustrative purposes only and does not constitute a limitation on the correspondence between the shape labels and label values of ablation regions. The above calculation method for the label values corresponding to all ablation region images is for illustrative purposes only; the specific calculation method can be designed according to actual needs.
[0106] Step S50: Determine the ablation damage level of the blade based on the number of ablation areas and the ablation characteristic index values.
[0107] In this embodiment, the number of ablation zones and the ablation characteristic index values are calculated in a specific manner to obtain the blade ablation damage coefficient, and the blade ablation damage level is determined based on the blade ablation damage coefficient.
[0108] Further, in one embodiment, step S50 includes:
[0109] The ablation damage coefficient of the blade is obtained by weighting the number of ablation regions, color characteristic index value, area characteristic index value, density characteristic index value, location characteristic index value, discrete characteristic index value, and shape characteristic index value; the ablation damage level of the blade is determined based on the ablation damage coefficient.
[0110] In this embodiment, the number of ablation regions (M if no removal operation is performed, N if a removal operation is performed) and the color feature index value label are specified. C Area characteristic index value label S Density feature index value label m Location feature index value label L Discrete feature index value label r and shape feature index value label x Weighted calculations are performed to obtain the blade ablation damage coefficient A, which is:
[0111] A = λ1·M or N + λ2·label C +λ3·label S +λ4·label m +λ5·label L +λ6·label r +λ7·label x
[0112] Wherein, λ1, λ2, λ3, λ4, λ5, λ6, and λ7 are weight values, obtained by training machine learning models such as decision trees and random forests.
[0113] If A ≤ the first threshold, the blade ablation damage level is determined to be mild; if the first threshold < A ≤ the second threshold, the blade ablation damage level is determined to be moderate; if the second threshold < A, the blade ablation damage level is determined to be severe. This completes the determination of the blade ablation damage level.
[0114] In this embodiment, the blade area, blade centroid coordinates, and blade image are acquired. Ablation region detection is performed on the blade image to obtain the number of ablation regions, the image of each ablation region, the area of each ablation region, and the centroid coordinates of each ablation region. The RGB values and shape labels of each ablation region image are obtained. Based on the blade area, blade centroid coordinates, the area of each ablation region, the centroid coordinates of each ablation region, the RGB values of each ablation region image, and the shape labels of each ablation region, ablation feature index values are obtained. The blade ablation damage level is determined based on the number of ablation regions and the ablation feature index values. This embodiment, with equipment as the primary driver, automatically determines the blade ablation damage level, reducing manual intervention and improving the efficiency of blade flaw detection testing.
[0115] Thirdly, embodiments of the present invention also provide a device for determining the level of blade ablation damage.
[0116] In one embodiment, reference is made to Figure 3 , Figure 3 This is a schematic diagram of the functional modules of an embodiment of the blade ablation damage level determination device of the present invention. Figure 3 As shown, the blade ablation damage level determination device includes:
[0117] The first acquisition module 10 is used to acquire the blade area, the blade centroid coordinates, and the blade image;
[0118] The detection module 20 is used to detect ablation areas in the blade image and obtain the number of ablation areas, the ablation area image corresponding to each ablation area, the area of the ablation area, and the centroid coordinates of the ablation area.
[0119] The second acquisition module 30 is used to acquire the RGB values of each ablation region image and the shape label of the ablation region;
[0120] The calculation module 40 is used to obtain ablation feature index values based on the blade area, blade centroid coordinates, ablation area area corresponding to each ablation area, ablation centroid coordinates, RGB values of each ablation area image, and ablation area shape label.
[0121] The grading module 50 is used to determine the ablation damage level of the blade based on the number of ablation areas and the ablation characteristic index values.
[0122] Furthermore, in one embodiment, the first acquisition module 10 is configured to:
[0123] Leaf detection is performed on the original image to obtain the leaf boundary coordinates, leaf area, and leaf centroid coordinates. The original image is an image captured of the leaf.
[0124] The coordinates of the minimum bounding rectangle of the blade are obtained from the blade boundary coordinates;
[0125] The leaf image is cropped from the original image based on the coordinates of the minimum bounding rectangle of the leaf.
[0126] Furthermore, in one embodiment, the calculation module 40 is used for:
[0127] Based on the RGB values of each ablation region image, color feature index values are obtained;
[0128] Based on the area of the ablation zone of each ablation zone, the area characteristic index value is obtained;
[0129] The density characteristic index value is obtained based on the blade area and the ablation area of each ablation zone;
[0130] Based on the centroid coordinates of the ablation zone for each ablation zone, the location characteristic index value is obtained;
[0131] Based on the centroid coordinates of the blade and the centroid coordinates of the ablation zone of each ablation zone, discrete characteristic index values are obtained;
[0132] Based on the shape label of the ablation region in each ablation region image, the shape feature index value is obtained.
[0133] Furthermore, in one embodiment, the calculation module 40 is used for:
[0134] The RGB values of all ablation region images are summed to obtain the RGB sum value;
[0135] The average value of the RGB values is used as the color feature index value.
[0136] Furthermore, in one embodiment, the calculation module 40 is used for:
[0137] Calculate the average and variance based on the area of the ablation zone for each ablation zone;
[0138] Abnormal ablation area is removed, wherein the difference between the abnormal ablation area and the average value is less than the product of the variance and a first preset value, or greater than the product of the variance and a second preset value.
[0139] The maximum value is selected from the remaining ablation area and used as the area characteristic index value.
[0140] Furthermore, in one embodiment, the calculation module 40 is used for:
[0141] The areas of all ablation zones are summed to obtain the sum of the areas.
[0142] The ratio of the sum of the areas to the leaf area is calculated, and this ratio is used as the density characteristic index value.
[0143] Furthermore, in one embodiment, the classification module 50 is used for:
[0144] The ablation damage coefficient of the blade is obtained by weighting the number of ablation regions, color characteristic index value, area characteristic index value, density characteristic index value, location characteristic index value, discrete characteristic index value, and shape characteristic index value.
[0145] The blade ablation damage level is determined based on the blade ablation damage coefficient.
[0146] The functions of each module in the blade ablation damage level determination device correspond to the steps in the embodiment of the blade ablation damage level determination method. Their functions and implementation processes will not be described in detail here.
[0147] Fourthly, embodiments of the present invention also provide a readable storage medium.
[0148] The present invention stores a blade ablation damage level determination program on a readable storage medium, wherein when the blade ablation damage level determination program is executed by a processor, the steps of the blade ablation damage level determination method described above are implemented.
[0149] The method implemented when the blade ablation damage level determination procedure is executed can be referred to in various embodiments of the blade ablation damage level determination method of the present invention, and will not be repeated here.
[0150] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.
[0151] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0152] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of the present invention.
[0153] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.
Claims
1. A method for determining the degree of blade ablation damage, characterized in that, The method for determining the degree of blade ablation damage includes: Obtain the leaf area, leaf centroid coordinates, and leaf image; The ablation region detection is performed on the blade image to obtain the number of ablation regions, the ablation region image corresponding to each ablation region, the area of the ablation region, and the centroid coordinates of the ablation region. Obtain the RGB values and shape labels of each ablation region image; The RGB values of all ablation region images are summed to obtain the RGB sum value; The average value of the RGB values is used as the color feature index value; Calculate the average value and variance based on the area of each ablation region; remove abnormal ablation regions, wherein the difference between the abnormal ablation region area and the average value is less than the product of the variance and a first preset value, or greater than the product of the variance and a second preset value; select the maximum value from the remaining ablation regions as the area characteristic index value. The areas of all ablation zones are summed to obtain the sum of the areas. Calculate the ratio of the sum of the areas to the leaf area, and use the ratio as the density characteristic index value; Based on the centroid coordinates of the ablation zone for each ablation zone, the location characteristic index value is obtained; Based on the centroid coordinates of the blade and the centroid coordinates of the ablation zone of each ablation zone, discrete characteristic index values are obtained; Based on the shape label of the ablation region in each ablation region image, the shape feature index value is obtained; The ablation damage level of the blade is determined based on the number of ablation areas and the ablation characteristic index values, which include color characteristic index values, area characteristic index values, density characteristic index values, location characteristic index values, discrete characteristic index values, and shape characteristic index values.
2. The method for determining the degree of blade ablation damage as described in claim 1, characterized in that, The steps for obtaining the blade area, blade centroid coordinates, and blade image include: Leaf detection is performed on the original image to obtain the leaf boundary coordinates, leaf area, and leaf centroid coordinates. The original image is an image captured of the leaf. The coordinates of the minimum bounding rectangle of the blade are obtained from the blade boundary coordinates; The leaf image is cropped from the original image based on the coordinates of the minimum bounding rectangle of the leaf.
3. The method for determining the degree of blade ablation damage as described in claim 1, characterized in that, The steps for determining the blade ablation damage level based on the number of ablation zones and ablation characteristic index values include: The ablation damage coefficient of the blade is obtained by weighting the number of ablation regions, color characteristic index value, area characteristic index value, density characteristic index value, location characteristic index value, discrete characteristic index value, and shape characteristic index value. The blade ablation damage level is determined based on the blade ablation damage coefficient.
4. A device for determining the level of blade ablation damage, characterized in that, The blade ablation damage level determination device includes: The first acquisition module is used to acquire the leaf area, the centroid coordinates of the leaf, and the leaf image; The detection module is used to detect ablation areas in the blade image and obtain the number of ablation areas, the ablation area image corresponding to each ablation area, the area of the ablation area, and the centroid coordinates of the ablation area. The second acquisition module is used to acquire the RGB values of each ablation region image and the shape label of the ablation region; The calculation module is used to sum the RGB values of all ablation area images to obtain the RGB sum value; the average value of the RGB sum value is used as the color feature index value. Calculate the average value and variance based on the area of each ablation region; remove abnormal ablation regions, wherein the difference between the abnormal ablation region area and the average value is less than the product of the variance and a first preset value, or greater than the product of the variance and a second preset value; select the maximum value from the remaining ablation regions as the area characteristic index value. The areas of all ablation zones are summed to obtain the sum of areas; the ratio of the sum of areas to the blade area is calculated, and the ratio is used as the density characteristic index value. Based on the centroid coordinates of the ablation zone for each ablation zone, the location characteristic index value is obtained; Based on the centroid coordinates of the blade and the centroid coordinates of the ablation zone of each ablation zone, discrete characteristic index values are obtained; Based on the shape label of the ablation region in each ablation region image, the shape feature index value is obtained; The grading module is used to determine the ablation damage level of the blade based on the number of ablation areas and the ablation characteristic index values, which include color characteristic index values, area characteristic index values, density characteristic index values, location characteristic index values, discrete characteristic index values, and shape characteristic index values.
5. A device for determining the level of blade ablation damage, characterized in that, The blade ablation damage level determination device includes a processor, a memory, and a blade ablation damage level determination program stored in the memory and executable by the processor, wherein when the blade ablation damage level determination program is executed by the processor, it implements the steps of the blade ablation damage level determination method as described in any one of claims 1 to 3.
6. A readable storage medium, characterized in that, The readable storage medium stores a blade ablation damage level determination program, wherein when the blade ablation damage level determination program is executed by the processor, it implements the steps of the blade ablation damage level determination method as described in any one of claims 1 to 3.