A method, device, equipment and medium for detecting spray quality of fuel injector

Abstract

The present invention relates to the field of image processing technology, and in particular to a method, device, apparatus, and medium for detecting the spray quality of a fuel injector. In this application, the position of the spray root in a target spray image is determined. Based on the position of the spray root, the distance between each target pixel in a segmented image and the spray root is calculated. Based on the distance, a dilation matrix corresponding to each target pixel is determined. Morphological dilation processing is performed on the segmented image according to the dilation matrix, improving the adaptability of the dilation matrix so that when the segmented image is morphologically dilated according to the dilation matrix, target pixels that are far from the nozzle can be connected to ensure the integrity of the spray. The spray quality is classified based on the number of sprays, the spray area of each target area, the spray angle of each target area, and the spray deflection angle of each target area. This takes into account the weight and morphology of the spray, thereby improving the accuracy of spray quality detection.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a method, device, equipment and medium for detecting the spray quality of a fuel injector. Background Art

[0002] Industrial development has triggered environmental and energy crises. While diesel engines have made significant contributions to industrial development, their emissions also have a certain impact on the environment. Therefore, improving diesel engine fuel combustion quality is particularly important. Fuel injectors, as a crucial component of the engine's fuel supply system, significantly impact combustion integrity and emissions. Common methods for testing spray quality involve manual observation of multiple injections or using a collection device such as an oil pan containing a certain number of small holes to collect the injected fuel spray. The spray pattern distribution is then determined by weighing the fuel mass at each hole. This distribution is then used to determine the spray cone angle. However, manual testing is prone to misidentification, resulting in low accuracy. Therefore, improving the accuracy of injector spray quality testing has become an urgent issue. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method, device, equipment, and medium for detecting the spray quality of a fuel injector, so as to solve the problem of low detection accuracy during the detection of the spray quality of a fuel injector.

[0004] In a first aspect, an embodiment of the present invention provides a method for detecting the spray quality of a fuel injector, the method comprising:

[0005] Acquiring a target spray image for detecting spray quality, and performing segmentation processing on the target spray image to obtain a segmented image;

[0006] Determine the position of the spray root in the target spray image based on the segmented image, calculate the distance between each target pixel in the segmented image and the spray root based on the position of the spray root, determine the expansion matrix corresponding to each target pixel based on the distance, perform morphological expansion processing on the segmented image based on the expansion matrix, and obtain the target area and spray quantity of the corresponding spray;

[0007] The spray area, spray angle and spray deflection angle of each target area are calculated;

[0008] The spray characteristics of the target spray image are determined according to the spray quantity, the spray area of each target area, the spray angle of each target area, and the spray deflection angle of each target area. The spray quality is classified according to the spray characteristics to obtain a classification result.

[0009] In a second aspect, an embodiment of the present invention provides a spray quality detection device for a fuel injector, the spray quality detection device comprising:

[0010] an acquisition module, configured to acquire a target spray image for detecting spray quality, and segment the target spray image to obtain a segmented image;

[0011] a processing module, configured to determine, based on the segmented image, a position of a spray root in the target spray image; calculate, based on the position of the spray root, a distance between each target pixel in the segmented image and the spray root; determine, based on the distance, a dilation matrix corresponding to each target pixel; and perform morphological dilation processing on the segmented image based on the dilation matrix to obtain a target area and a spray quantity corresponding to the spray;

[0012] A calculation module is used to calculate the spray area, spray angle and spray deflection angle of each target area;

[0013] A classification module is used to determine the spray characteristics of the target spray image according to the spray quantity, the spray area of each target area, the spray angle of each target area and the spray deflection angle of each target area, and classify the spray quality according to the spray characteristics to obtain a classification result.

[0014] In a third aspect, an embodiment of the present invention provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the spray quality detection method as described in the first aspect when executing the computer program.

[0015] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the spray quality detection method described in the first aspect is implemented.

[0016] Compared with the prior art, the present invention has the following beneficial effects:

[0017] In the present application, the target spray image is segmented to determine the position of the spray root in the target spray image. Based on the position of the spray root, the distance between each target pixel in the segmented image and the spray root is calculated. Based on the distance, the expansion matrix corresponding to each target pixel is determined. The segmented image is morphologically expanded according to the expansion matrix to improve the adaptability of the expansion matrix so that when the segmented image is morphologically expanded according to the expansion matrix, the target pixels that are far away from the nozzle can be connected to ensure the integrity of the spray. The spray characteristics of the target spray image are determined based on the number of sprays, the spray area of each target area, the spray angle of each target area and the spray deflection angle of each target area. The spray quality is classified according to the spray characteristics, taking into account the weight and shape of the spray, thereby improving the accuracy of spray quality detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 1 is a schematic diagram of an application environment of a method for detecting the spray quality of a fuel injector provided by an embodiment of the present invention;

[0020] Figure 2 1 is a flow chart of a method for detecting the spray quality of a fuel injector provided by one embodiment of the present invention;

[0021] Figure 3 is a schematic diagram of a target spray image provided by an embodiment of the present invention;

[0022] Figure 4 is a schematic diagram of a denoised spray image provided by an embodiment of the present invention;

[0023] Figure 5 1 is a schematic structural diagram of a spray quality detection device for a fuel injector provided by one embodiment of the present invention;

[0024] Figure 6 It is a structural diagram of a computer device provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0026] In the following description, specific details such as particular system structures and techniques are provided for purposes of illustration, not limitation, to facilitate a thorough understanding of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

[0027] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0028] It will also be understood that the term "and / or" used in the present description and appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0029] As used in the present specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0030] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0031] References to "one embodiment" or "some embodiments" in the present specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present invention. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in yet other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0032] Embodiments of the present invention can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) refers to the theories, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0033] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0034] It should be understood that the order of execution of the steps in the following embodiments does not necessarily mean the order in which they are executed. The order in which each process is executed should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0035] In order to illustrate the technical solution of the present invention, specific embodiments are provided below.

[0036] An embodiment of the present invention provides a method for detecting the spray quality of a fuel injector, which can be applied in the following situations: Figure 1 In the application environment, Figure 1 This is a schematic diagram of the application environment of a method for detecting the spray quality of a fuel injector, provided by one embodiment of the present invention. The client communicates with the server to address the low accuracy of injector spray quality testing. The client, also known as the user end, refers to the program that corresponds to the server and provides local services to clients. The client can be installed on, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices. The server can be implemented as a standalone server or a server cluster consisting of multiple servers.

[0037] See also Figure 2 , is a flow chart of a method for detecting the spray quality of a fuel injector provided by an embodiment of the present invention, in which the method is applied Figure 1 The server in the example is used as an example, and the steps are as follows:

[0038] S201: Acquire a target spray image for detecting spray quality, and segment the target spray image to obtain a segmented image.

[0039] In step S201, the target spray image is a stable image collected during the injector spray period, that is, the number of sprays in the target spray image is equal to the number of injector nozzles. Edge detection is performed on the target spray image to detect pixels with obvious brightness changes in the target spray image. The region of interest is the area containing the spray, and the number of sprays is the number of regions of interest.

[0040] In this embodiment, a target spray image for detecting spray quality is determined from the collected sequence spray images of the injector during spraying. Figure 3 , is a schematic diagram of a target spray image provided by an embodiment of the present invention, wherein the number of spray beams in the image is equal to the number of injector nozzles.

[0041] The target spray image is segmented to obtain a segmented image. During the segmentation process, a corresponding pixel threshold is set. When the pixel value of a pixel in the target spray image is greater than the pixel threshold, the pixel is determined to be the target pixel. When the pixel value of a pixel in the target spray image is not greater than the pixel threshold, the pixel value of the pixel is set to 0, thereby obtaining a corresponding segmented image. The pixel threshold can be set based on actual conditions and is not limited in this embodiment.

[0042] In this embodiment, a target spray image for detecting spray quality is acquired, and the target spray image is segmented to obtain a segmented image, so as to determine the spray area according to the segmented image, and thus determine the corresponding spray characteristics according to the spray area.

[0043] Optionally, obtaining a target spray image for detecting spray quality includes:

[0044] Acquire a sequence of spray images of sprays ejected from the injector, and extract the number of peaks in a waveform of a current spray image in the sequence of spray images;

[0045] Obtain the number of nozzle holes in the sprayer and determine whether the number of nozzle holes is equal to the number of wave peaks;

[0046] If the number of nozzle holes is equal to the number of wave peaks, the current spray image is determined as the target spray image.

[0047] In this embodiment, a sequence of spray images of the injector spray is captured. The sequence of spray images includes all images from the start to the end of the injector spray. To capture these images, the high-pressure fuel supply system controls the injector drive device, driving the injector to spray fuel. A high-speed camera is mounted in front of the injector, separated by plexiglass, to capture the injector spray images. The camera is positioned perpendicular to the injector axis, and the distance and focal length are adjusted to capture a 10 cm x 10 cm area in the plane of the injector axis. Due to the extremely short exposure time, an array light source is required to provide fill light for capturing transient spray images.

[0048] After acquiring a sequence of spray images of the injector spray, one of the spray images is used as the current spray image. The waveform of the current spray image is extracted, and the number of peaks in the waveform is determined. The number of nozzle holes in the sprayer is then determined to determine whether the number of nozzle holes and the number of peaks are equal. If the number of nozzle holes and the number of peaks are equal, the current spray image is determined as the target spray image. The waveform is the frequency domain waveform of the current spray image.

[0049] In this embodiment, the target spray image is determined by judging whether the number of nozzle holes is equal to the number of wave peaks, so as to ensure that the target spray image is the image of the injector when spraying stably, thereby improving the accuracy of spray quality detection based on the target spray image.

[0050] Optionally, segmenting the target spray image to obtain a segmented image includes:

[0051] determining the spray image preceding the target spray image in the sequence spray image as the target sequence spray image;

[0052] Obtain a background image, determine the first image in the target sequence spray image as the target image, and calculate the pixel difference between each pixel corresponding to the target image and the background image;

[0053] If there is a pixel point difference greater than the preset difference threshold, the background image is determined as the target background image;

[0054] If there is no pixel difference greater than the preset difference threshold, the target image is determined as the background image, the first image of the remaining images in the target sequence spray image is determined as the target image, and the step of calculating the pixel difference between the target image and the background image is performed until the target background image is obtained;

[0055] Perform background denoising on the target spray image according to the target background image to obtain a denoised spray image;

[0056] The denoised spray image is segmented to obtain a segmented image.

[0057] In this embodiment, to improve the segmentation accuracy of the segmented image, background denoising is performed on the target spray image, and then segmentation is performed on the denoised spray image. The spray image preceding the target spray image in the sequence of spray images is identified as the target sequence spray image. A background image is acquired, and the first image in the target sequence of spray images is identified as the target image. The pixel difference between each corresponding pixel in the target image and the background image is calculated. This difference is used to determine whether to initiate spraying. The size of the original background image is equal to that of the target spray image.

[0058] It should be noted that when calculating the pixel difference between the target image and the background image, the pixel values of the corresponding pixels in the target image and the background image are subtracted to obtain the pixel difference between each pixel. For example, the pixel difference between the pixel value in the third row and third column of the target image and the pixel value in the third row and third column of the background image is calculated.

[0059] A determination is made as to whether the pixel difference between each pixel is greater than a preset difference threshold. If a pixel difference is greater than the preset difference threshold, spray is deemed to have appeared in the target image, the background image is no longer updated, and the background image is determined to be the target background image. If a pixel difference is not greater than the preset difference threshold, spray is deemed to have not appeared in the target image. The pixel difference that does appear may be due to environmental noise, which is considered to be present in the target image. When segmenting the target spray image, the corresponding background noise needs to be removed. Therefore, the target image is determined to be the background image, so that background noise can be removed when background denoising is performed on the background image and the target spray image. The preset difference threshold can be determined based on actual conditions and is not limited in this embodiment.

[0060] After the target image is determined as the background image, a new target image is determined, the first image among the remaining images in the target sequence spray image is determined as the target image, the step of calculating the pixel difference between the target image and the background image is performed, and it is determined whether there is a pixel difference value greater than a preset difference threshold. If there is a pixel difference value greater than the preset difference threshold, the background image is determined as the target background image; if there is no pixel difference value greater than the preset difference threshold, the target image is determined as the background image, the first image among the remaining images in the target sequence spray image is determined as the target image, and the step of calculating the pixel difference between the target image and the background image is performed until the target background image is obtained.

[0061] The target spray image is subjected to background denoising based on the target background image to obtain a denoised spray image. When performing background denoising, the target background image is subtracted from the target spray image. Figure 4 , which is a schematic diagram of a denoised spray image provided by one embodiment of the present invention. The denoised spray image is segmented to obtain a segmented image. The segmentation process is identical to the above-described segmentation process and will not be described further in this embodiment.

[0062] In this embodiment, when segmenting the target spray image, background denoising is performed on the target spray image. A target background image is determined using a time-series-based progressive background. This is used to remove environmental interference from the spray image acquisition process. This prevents the noise region from being identified as the spray region when the pixel values of the spray region and the noise region are similar during segmentation. This ensures that the segmented image contains only the spray region, improving the segmentation accuracy of the segmented image.

[0063] S202: Determine the position of the spray root in the target spray image based on the segmented image. Calculate the distance between each target pixel in the segmented image and the spray root based on the position of the spray root. Determine the expansion matrix corresponding to each target pixel based on the distance. Perform morphological expansion processing on the segmented image based on the expansion matrix to obtain the target area and spray quantity of the corresponding spray.

[0064] In step S202, the position of the spray root is the position of the nozzle, and the target pixel point is the pixel point segmented in the segmented image, that is, the pixel point whose pixel value is greater than the pixel threshold. The distance between each target pixel point in the segmented image and the spray root is calculated, that is, the distance between the spray area and the nozzle. According to the distance, the expansion matrix is used to expand the segmented image. The target area is the spray divergence area after the corresponding spray is ejected from the nozzle, and the number of sprays is the number of the corresponding target area.

[0065] In this embodiment, the location of the spray root in the target spray image is determined based on the segmented image. The spray root is the location of the injector's nozzle. When determining the nozzle location, the injector sprays oil from a very small hole, resulting in the spray appearing denser and sparser as it moves farther from the nozzle. Therefore, the farther away from the nozzle, the more diffuse the spray. Therefore, the location of the spray root, i.e., the nozzle location, can be determined based on the clustering of target pixels in the segmented image.

[0066] It should be noted that in this embodiment, when determining the location of the spray root in the target spray image, a density peak clustering method can be used. Specifically, based on the degree of clustering of target pixels in the target spray image, cluster points are determined, and the corresponding cluster points are determined as the spray root. Other methods can also be used for determination, and this embodiment does not limit this.

[0067] It should be noted that if the fuel injector includes multiple spray holes, the target spray image includes multiple spray roots, that is, the positions of multiple spray holes.

[0068] Based on the location of the spray base, the distance between each target pixel in the segmented image and the spray base is calculated. A target pixel is defined as one with a value greater than the pixel threshold, i.e., one containing the spray area. Based on this distance, the corresponding expansion matrix is determined for each target pixel. The size of the expansion matrix is related to the distance between the target pixel and the spray base: a larger expansion matrix corresponds to a larger distance, and a smaller expansion matrix corresponds to a smaller distance.

[0069] It should be noted that when there are multiple spray roots, the diverging area corresponding to the spray root can be first determined, and the distance between the target pixel and the spray root in the diverging area where the target pixel is located can be calculated. Alternatively, the distance between the target pixel and the nearest spray root can be calculated. Other methods can also be used to calculate the distance between the target pixel and the spray root, which is not limited in this embodiment.

[0070] It should be noted that when determining the expansion matrix corresponding to each target pixel point based on the distance, the distance is rounded up to obtain the rounded distance. The size of the expansion matrix can be , where D is the rounded distance. The size of the expansion matrix can also be determined according to actual conditions, which is not limited in this embodiment.

[0071] Morphological dilation is performed on the segmented image according to the dilation matrix to obtain the target area and the number of sprays. Morphological dilation is performed on the segmented image to connect the diverging spray areas to form a closed area, obtaining the target area of the spray. The number of sprays is determined based on the number of target areas. The number of sprays is equal to the number of target areas.

[0072] In this embodiment, the position of the spray root in the target spray image is determined based on the segmented image, that is, the position of the nozzle is determined, so as to calculate the distance between the target pixel point and the nozzle orifice and determine the degree of divergence of the spray from the nozzle. Based on the distance, the expansion matrix corresponding to each target pixel point is determined, so that the size of the expansion matrix is related to the size of the pixel point from the spray root, thereby avoiding the error caused by the expansion of the spray root. The segmented image is morphologically expanded according to the expansion matrix, so that discontinuous target pixels can be connected to form a corresponding closed target area.

[0073] Optionally, determining the dilation matrix corresponding to each target pixel point based on the distance includes:

[0074] Determine edge target pixels and non-edge target pixels in the segmented image;

[0075] Obtaining a first target distance coefficient of a non-edge target pixel point and a second target distance coefficient of an edge target pixel point;

[0076] The expansion matrix of each target pixel is calculated based on the first target distance coefficient, the second target distance coefficient, and the distance.

[0077] In this embodiment, it is determined whether the target pixel is located in the edge area of the segmented image, and edge target pixels and non-edge target pixels in the segmented image are determined. The edge target pixel is a target pixel located at the edge of the segmented image, and the non-edge target pixel is a target pixel not located at the edge of the segmented image.

[0078] A first target distance coefficient for a non-edge target pixel and a second target distance coefficient for an edge target pixel are obtained. Specifically, the first target distance coefficient for a non-edge target pixel and the second target distance coefficient for an edge target pixel are determined based on whether the corresponding target pixel is an edge point. In this embodiment, the first target distance coefficient for the non-edge target pixel is K, and the second target distance coefficient for the edge target pixel is 0. The value of K is determined based on experimental experience and is determined by the injector pressure.

[0079] The dilation matrix for the corresponding target pixel is calculated based on the first and second target distance coefficients, as well as the distance. The dilation matrix for non-edge target pixels is the value obtained by multiplying the first target distance coefficient by the distance, rounded up. For example, the dilation matrix for a non-edge target pixel is [Y × Y], where Y is the value obtained by multiplying the first target distance coefficient by the distance between the target pixel and the spray base, rounded up. This is K × D, rounded up, where K is the first target distance coefficient and D is the Euclidean distance between the target pixel and the spray base. The dilation matrix for edge target pixels is 0, indicating that no morphological dilation is performed on these edge target pixels.

[0080] In this embodiment, the first target distance coefficient of the non-edge target pixel point and the second target distance coefficient of the edge target pixel point are obtained respectively, and the corresponding target distance coefficient is multiplied by the distance of the corresponding target pixel point to determine the expansion matrix of the corresponding target pixel point. The expansion matrix of the corresponding non-edge target pixel point increases with the increase of the distance, which can better connect discontinuous target pixels and does not expand the edge target pixel points, thereby avoiding the error caused by the expansion of the edge target pixel points.

[0081] S203: Calculate the spray area, spray angle, and spray deflection angle of each target area.

[0082] In step S203 , the spray area is the size of each target area, the spray angle is the angle between the spray edge straight lines of the corresponding target areas, and the spray deflection angle is the deflection angle between adjacent target areas.

[0083] In this embodiment, the region after morphological dilation processing is a continuous region. When calculating the area of the target region, the number of target pixels contained in the target region can be calculated. When calculating the spray angle and spray deflection angle of the target region, it is necessary to perform edge detection on the target region and extract the edge lines of the target region. The angle between the edge lines of the target region is determined as the spray angle, i.e., the expansion angle of the spray after passing through the nozzle. The angle between the center lines of each spray angle is used as the spray deflection angle. If there is only one target region, i.e., the injector has only one nozzle, the spray deflection angle is 0. If there are multiple target regions, the spray area, spray angle, and spray deflection angle of each target region are calculated. If the injector has multiple nozzles, it is necessary to calculate the number of target pixels contained in each target region, i.e., the spray area of each target region; the angle between the edge lines of each target region, i.e., the spray angle of each target region; and the angle between the center lines of the spray angles of adjacent target regions, i.e., the deflection angle of each target region. The spray deflection angle is the angle between the center line of the spray angle in the target area adjacent to the target area after counterclockwise rotation and the center line of the spray angle in the target area.

[0084] It should be noted that when performing edge detection on each target region, the Canny operator edge detection method can be used to perform edge detection to obtain the edge of the target region. Based on the edge of the target region, the edge straight line of the target region is extracted. When extracting the edge straight line of the target region, a Hough transform algorithm can be used for line extraction. Other algorithms can also be used for edge detection and line extraction, and this embodiment does not limit this.

[0085] In this embodiment, the spray area, spray angle, and spray deflection angle of each target area are calculated to obtain quantitative values of the injector during the injection process, thereby performing quality inspection based on the multiple quantitative values during the injection process.

[0086] Optionally, the spray area, spray angle, and spray deflection angle of each target area are calculated, including:

[0087] Calculate the gradient magnitude and gradient direction of each target pixel in the target area;

[0088] Extract the spray edge of the target area based on the gradient amplitude and gradient direction of each target pixel;

[0089] According to the spray edge, the edge straight line of the target area is extracted, and the spray area, spray angle and spray deflection angle of each target area are calculated based on the edge straight line.

[0090] In this embodiment, when edge detection is performed on the target area, the gradient magnitude and gradient direction of each target pixel in the target area are calculated. The calculation formulas for the gradient magnitude and gradient direction of each target pixel are as follows:

[0091] ;

[0092] Among them, I(i, j) is the pixel value corresponding to the target pixel point (i, j), I(i, j+1) is the pixel value of the pixel point (i, j+1), I(i+1, j+1) is the pixel value of the pixel point (i+1, j+1), I(i+1, j) is the pixel value of the pixel point (i+1, j), fx(i, j) is the partial derivative of the pixel value in the x direction of the target pixel point (i, j), fy(i, j) is the partial derivative of the pixel value in the y direction of the target pixel point (i, j), M(i, j) is the gradient amplitude of the target pixel point (i, j), and H(i, j) is the gradient direction of the target pixel point (i, j).

[0093] In this embodiment, to balance the requirements of accurate edge positioning and noise suppression in gradient amplitude calculation, the gradient amplitude and gradient direction of the target pixel are determined by calculating the finite difference of the first-order partial derivatives in the x-direction, y-direction, 45° direction, and 135° direction within the 8-neighborhood of the target pixel.

[0094] According to the gradient direction of each target pixel point, the two adjacent pixels along the opposite direction of the target pixel point along the straight line where the gradient direction is located are calculated. According to the pixel values corresponding to the two adjacent pixels, the gradient amplitude of the two adjacent pixels is calculated to obtain the adjacent gradient amplitude. The magnitude of the gradient amplitude of the target pixel point and the corresponding adjacent gradient amplitude are judged. Based on the judgment result, it is determined whether the target pixel point is the edge of the spray.

[0095] It should be noted that, based on the gradient direction of each target pixel, when calculating the two adjacent pixels of the target pixel in the opposite direction along the straight line where the gradient direction lies, the calculation formula is as follows:

[0096] ;

[0097] Among them, i is the horizontal coordinate of the target pixel point, j is the vertical coordinate of the target pixel point, is the gradient direction of the target pixel (i, j), and are two pixels adjacent to the corresponding target pixel, where The coordinates are , The coordinates are .

[0098] When calculating the gradient magnitude of two adjacent pixels based on the pixel values corresponding to the two adjacent pixels, the interpolation method can be used to calculate the gradient magnitude of the two adjacent pixels. The calculation formula is as follows:

[0099] ;

[0100] Among them, M(i, j) is the gradient amplitude of the target pixel (i, j), M(i+1, j) is the gradient amplitude of the pixel (i+1, j), M(i, j+1) is the gradient amplitude of the pixel (i, j+1), and M(i+1, j+1) is the gradient amplitude of the pixel (i+1, j+1). is the gradient direction of the target pixel (i, j), For adjacent pixels The gradient amplitude of For adjacent pixels The gradient magnitude.

[0101] Determine the gradient amplitude of the target pixel and the corresponding adjacent gradient amplitude. If the gradient amplitude of the target pixel is smaller than that of the adjacent pixel, The gradient amplitude is smaller than that of the adjacent pixels. The gradient amplitude is , then it is determined that the target pixel is not the spray edge.

[0102] After determining the target pixel points that are not the spray edge, the remaining target pixel points are thresholded to obtain a preset high threshold and a preset low threshold, wherein the preset high threshold is a pixel value that can clearly distinguish a strong edge, and the preset low threshold is slightly lower than the preset high threshold.

[0103] Keep the pixels greater than the preset high threshold, and assign the pixel values of other pixels to 0 to obtain the high threshold image. Keep the pixels less than or equal to the preset low threshold, and assign the pixel values of other pixels to 0 to obtain the low threshold image. Connect the edge contours in the high threshold image to find all non-zero pixels as the starting point, track and connect adjacent edge pixels along the edge direction, and use the low threshold image to fill the edge gaps. For each endpoint, search for weak edge points in the neighborhood of the low threshold image, connect the weak edge points to form a complete edge contour, and obtain the final spray edge.

[0104] Linear detection is performed on the spray edge to obtain an edge line of the spray edge. In this embodiment, the Hough transform algorithm is used for line detection. Other algorithms can also be used for line detection, which is not limited in this embodiment.

[0105] After extracting the edge lines of the target area, determine the endpoint coordinates of the intersection of the lines in the target area. Based on these endpoint coordinates, calculate the area of the target area (i.e., the spray area). Also, calculate the angle between the edge lines at the root of the spray (i.e., the spray angle). Also, calculate the angle between the center lines of the spray angles of adjacent target areas (i.e., the deflection angle of each target area). The spray deflection angle is the angle between the center line of the spray angle in the target area adjacent to the target area, rotated counterclockwise, and the center line of the spray angle in the target area.

[0106] In this embodiment, the spray edge of the target area is extracted according to the gradient amplitude and gradient direction of each target pixel point, so as to improve the accuracy of extracting the spray edge.

[0107] S204: Determine the spray characteristics of the target spray image according to the spray quantity, the spray area of each target area, the spray angle of each target area, and the spray deflection angle of each target area, and classify the spray quality according to the spray characteristics to obtain a classification result.

[0108] In step S204, the spray quantity, the spray area of each target area, the spray angle of each target area, and the spray deflection angle of each target area are used as spray features of the target spray image. The spray quality is classified according to the spray features to obtain a classification result, wherein the classification result includes qualified quality and unqualified quality.

[0109] In this embodiment, when determining the spray characteristics of the target spray image based on the spray quantity, the spray area of each target area, the spray angle of each target area, and the spray deflection angle of each target area, the average value of the spray area of all target areas, the average value of the spray angle of all target areas, and the average value of the spray deflection angle of all target areas are calculated. The average value of the spray quantity, the average value of the spray area, the average value of the spray angle, and the average value of the spray deflection angle are determined as the spray characteristics of the target spray image.

[0110] When classifying spray quality based on spray characteristics, Boolean statistics are performed on the number of sprays, the average value of the spray area, the average value of the spray angle, and the average value of the spray deflection angle. For example, if the number of nozzle holes, the standard spray area, the standard spray angle, and the standard spray deflection angle are obtained, if the number of sprays is equal to the number of nozzle holes, the spray number is determined to be true; otherwise, it is determined to be false. If the difference between the average value of the spray area and the average value of the standard spray area is less than a preset area threshold, the average value of the spray area is determined to be true; otherwise, it is determined to be false. If the difference between the average value of the spray angle and the average value of the standard spray angle is less than a preset angle threshold, the average value of the spray angle is determined to be true; otherwise, it is determined to be false. If the difference between the average value of the spray deflection angle and the average value of the standard spray deflection angle is less than a preset deflection angle threshold, the average value of the spray deflection angle is determined to be true; otherwise, it is determined to be false. The preset area threshold, preset angle threshold, and preset deflection angle threshold are set according to actual conditions and are not limited in this embodiment.

[0111] The spray quality is classified according to the statistical results to obtain a classification result. For example, if all the statistical results are true values, the classification result is determined to be qualified quality; if there are false values in the statistical results, the classification result is determined to be unqualified quality.

[0112] In order to verify the accuracy and robustness of spray quality detection using corresponding spray features, spray quality detection was performed on 100 target spray images of injectors collected in practice. The quality detection results are shown in the following table:

[0113]

[0114] The spray area is the average of the spray areas of each target spray image, the spray angle is the average of the spray angles of each target spray image, and the spray deflection angle is the average of the spray deflection angles of each target spray image.

[0115] In this embodiment, multiple types of features are used to classify the spray quality, thereby improving the classification accuracy.

[0116] In another embodiment, when determining the spray characteristics of the target spray area, the characteristics of the corresponding target area can also be determined based on the spray area of the corresponding target area, the spray angle of the corresponding target area, and the spray deflection angle of the corresponding target area. That is, for any target area, the spray area, spray angle, and spray deflection angle of the target area are spliced to obtain the characteristics of the corresponding target area, and then the number of sprays is spliced with the characteristics of each target area to obtain the spray characteristics. The truth or falsehood of the number of sprays and the characteristics of each target area are counted. For example, the number of nozzles and the standard characteristics are obtained; if the number of sprays is equal to the number of nozzles, the number of sprays is determined to be true, otherwise, it is determined to be false; for any target area, if the similarity between the characteristics of the target area and the standard characteristics is greater than a preset similarity threshold, the characteristics of the target area are determined to be true, otherwise, it is determined to be false. Among them, different numbers of nozzles correspond to different standard characteristics, and the similarity threshold is set according to actual conditions, which is not limited in this embodiment.

[0117] The spray quality is classified according to the statistical results to obtain a classification result. For example, if all the statistical results are true values, the classification result is determined to be qualified quality; if there are false values in the statistical results, the classification result is determined to be unqualified quality.

[0118] Optionally, determining spray characteristics of the target spray image includes:

[0119] Determine the spray area characteristics based on the spray area of each target area;

[0120] Determine the spray angle characteristics based on the spray angle of each target area;

[0121] Determine the spray deflection angle characteristics according to the spray deflection angle of each target area;

[0122] The spray quantity, spray area characteristics, spray angle characteristics and spray deflection angle characteristics are spliced and fused to obtain the spray characteristics of the target spray image.

[0123] In this embodiment, the splicing order is marked for each target area, the spray area of each target area is spliced according to the splicing order to obtain the spray area feature, the spray angle of each target area is spliced according to the splicing order to obtain the spray angle feature; the spray deflection angle of each target area is spliced according to the splicing order to obtain the spray deflection angle feature; the spray quantity, spray area feature, spray angle feature and spray deflection angle feature are spliced and fused to obtain the spray feature of the target spray image.

[0124] In another embodiment, after determining the spray quantity, spray area characteristics, spray angle characteristics and spray deflection angle characteristics, when determining the spray characteristics of the target spray image, the structured characteristics and image characteristics of the target spray image can also be fused, wherein the structured characteristics of the target spray image include color characteristics, texture characteristics and shape characteristics, and the image characteristics of the target spray image are features extracted based on a convolutional neural network.

[0125] It should be noted that color features can include the frequency of each color, color mean, variance, skewness and other statistical quantities. Texture features can be the spatial relationship between pixel grayscale values. Shape features can be the edge coordinate sequence of the target area.

[0126] It should be noted that the convolutional neural network structure may include: a convolution layer, a pooling layer connected to the convolution layer, and a global average pooling layer connected to the pooling layer; wherein the convolution layer is used to extract the features of the target spray image; the pooling layer is used to reduce the feature dimension extracted by the convolution layer, so that the target in the target spray image remains unchanged during translation; global average pooling is used to take the average value of all pixels in the image after dimensionality reduction as the feature value, which can extract highly abstract features of the feature map.

[0127] The spray quantity, spray area, spray angle, spray deflection angle, structural features, and image features are fused to obtain the spray features of the target spray image. The feature fusion can be performed by splicing or other methods, which are not limited in this embodiment.

[0128] In this embodiment, the features are fused to integrate information from different dimensions, so that the spray feature can contain multiple types of data to provide rich image information, thereby improving the accuracy of the spray feature.

[0129] Optionally, the spray quality is classified according to the spray characteristics to obtain classification results, including:

[0130] Obtain the trained spray quality classification model;

[0131] The spray features are input into the trained spray quality classification model and the classification results are output.

[0132] In this embodiment, a trained spray quality classification model is obtained, wherein the spray quality classification model is a deep learning model, such as a logistic regression model, or other types of classification models may be used, which is not limited in this embodiment.

[0133] The training process of the trained spray quality classification model includes the following steps:

[0134] Obtain an initial spray quality classification model and training data, where the training data includes sample spray features from a sample spray image and the classification label of the sample spray image. Use the training data to perform supervised training on the initial spray quality classification model to obtain a trained spray quality classification model. The sample spray features are extracted using the method described above for determining the spray features of the target spray image.

[0135] The spray characteristics are input into the trained spray quality classification model, and the classification results are output, including qualified and unqualified quality.

[0136] In this embodiment, a trained spray quality classification model is used to classify the spray quality. The spray quality classification model automatically processes the spray characteristics, thereby improving processing efficiency. The spray quality classification model can also eliminate subjective bias and improve classification accuracy.

[0137] In the present application, the target spray image is segmented to determine the position of the spray root in the target spray image. Based on the position of the spray root, the distance between each target pixel in the segmented image and the spray root is calculated. Based on the distance, the expansion matrix corresponding to each target pixel is determined. The segmented image is morphologically expanded according to the expansion matrix to improve the adaptability of the expansion matrix so that when the segmented image is morphologically expanded according to the expansion matrix, the target pixels that are far away from the nozzle can be connected to ensure the integrity of the spray. The spray characteristics of the target spray image are determined based on the number of sprays, the spray area of each target area, the spray angle of each target area and the spray deflection angle of each target area. The spray quality is classified according to the spray characteristics, taking into account the weight and shape of the spray, thereby improving the accuracy of spray quality detection.

[0138] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0139] See also Figure 5 , Figure 5 This is a schematic diagram of the structure of a spray quality detection device for a fuel injector provided by one embodiment of the present invention. The spray quality detection device for a fuel injector corresponds to the system fault prediction method in the above embodiment. For details, please refer to Figure 2 For the convenience of explanation, only the parts related to this embodiment are shown. Figure 5 The spray quality detection device 50 includes: an acquisition module 51 , a processing module 52 , a calculation module 53 , and a classification module 54 .

[0140] The acquisition module 51 is used to acquire a target spray image for detecting spray quality, and perform segmentation processing on the target spray image to obtain a segmented image.

[0141] The processing module 52 is used to determine the position of the spray root in the target spray image based on the segmented image, calculate the distance between each target pixel point in the segmented image and the spray root based on the position of the spray root, determine the expansion matrix corresponding to each target pixel point based on the distance, and perform morphological expansion processing on the segmented image based on the expansion matrix to obtain the target area and spray quantity of the corresponding spray.

[0142] The calculation module 53 is used to calculate the spray area, spray angle and spray deflection angle of each target area.

[0143] The classification module 54 is used to determine the spray characteristics of the target spray image according to the spray quantity, the spray area of each target area, the spray angle of each target area and the spray deflection angle of each target area, and classify the spray quality according to the spray characteristics to obtain a classification result.

[0144] Optionally, the acquisition module 51 includes:

[0145] The acquisition unit is used to acquire a sequence of spray images of the spray sprayed by the injector, and extract the number of peaks in the waveform of the current spray image in the sequence of spray images.

[0146] The judging unit is used to obtain the number of nozzle holes in the sprayer and judge whether the number of nozzle holes is equal to the number of wave peaks.

[0147] The first determining unit is configured to determine the current spray image as the target spray image if the number of the spray holes is equal to the number of the wave peaks.

[0148] Optionally, the acquisition module 51 further includes:

[0149] The second determining unit is configured to determine a spray image preceding the target spray image in the sequence of spray images as a target sequence spray image.

[0150] The first calculation unit is used to obtain a background image, determine the first image in the target sequence spray image as the target image, and calculate the pixel difference between each pixel corresponding to the target image and the background image.

[0151] The third determining unit is configured to determine the background image as a target background image if there is a pixel point whose difference value is greater than a preset difference threshold.

[0152] The execution unit is configured to determine the target image as the background image if there is no pixel difference greater than a preset difference threshold, determine the first image of the remaining images in the target sequence spray image as the target image, and execute the step of calculating the pixel difference between the target image and the background image until the target background image is obtained.

[0153] The denoising unit is used to perform background denoising on the target spray image according to the target background image to obtain a denoised spray image.

[0154] The segmentation unit is used to perform segmentation processing on the denoised spray image to obtain a segmented image.

[0155] Optionally, the processing module 52 includes:

[0156] The fourth determining unit is used to determine edge target pixel points and non-edge target pixel points in the segmented image.

[0157] The second acquisition unit is configured to acquire a first target distance coefficient of a non-edge target pixel point and a second target distance coefficient of an edge target pixel point.

[0158] The second calculation unit is configured to calculate a dilation matrix for each target pixel point according to the first target distance coefficient, the second target distance coefficient, and the distance.

[0159] Optionally, the calculation module 53 includes:

[0160] The third calculation unit is used to calculate the gradient magnitude and gradient direction of each target pixel point in the target area.

[0161] The extraction unit is used to extract the spray edge of the target area according to the gradient amplitude and gradient direction of each target pixel point.

[0162] The fourth calculation unit is used to extract the edge straight line of the target area according to the spray edge, and calculate the spray area, spray angle and spray deflection angle of each target area according to the edge straight line.

[0163] Optionally, the classification module 54 includes:

[0164] The fifth determining unit is configured to determine a spray area characteristic according to the spray area of each target area.

[0165] The sixth determining unit is configured to determine a spray angle feature according to the spray angle of each target area.

[0166] The seventh determining unit is configured to determine a spray deflection angle feature according to the spray deflection angle of each target area.

[0167] The unit is obtained, which is used to splice and fuse the spray quantity, spray area characteristics, spray angle characteristics and spray deflection angle characteristics to obtain the spray characteristics of the target spray image.

[0168] Optionally, the classification module 54 further includes:

[0169] The second acquisition unit is used to acquire the trained spray quality classification model.

[0170] The output unit is used to input the spray characteristics into the trained spray quality classification model and output the classification results.

[0171] The specific definition of the injector spray quality detection device can be found in the definition of the injector spray quality detection method described above and will not be further elaborated here. Each module in the aforementioned injector spray quality detection device can be implemented in whole or in part via software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or stored in a computer device memory in software form, allowing the processor to call and execute the corresponding operations of each module.

[0172] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, a network interface, and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to provide a target spray image. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for detecting the spray quality of an injector is implemented.

[0173] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for detecting the spray quality of the fuel injector in the above embodiment is implemented. For example, Figure 2 Alternatively, when the processor executes the computer program, the functions of each module / unit in the embodiment of the spray quality detection device for the injector are realized, for example, Figure 5 The functions of the acquisition module, processing module, calculation module, and classification module shown are not described here in detail to avoid repetition.

[0174] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for detecting the spray quality of the fuel injector in the above embodiment is implemented. For example, Figure 2 S201-S204 are shown, and will not be described here in detail to avoid repetition. Alternatively, when the computer program is executed by the processor, the functions of each module / unit in the embodiment of the spray quality detection device for the injector are realized, for example Figure 5 The functions of the acquisition module, processing module, calculation module, and classification module shown are not described here in detail to avoid repetition.

[0175] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0176] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0177] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A method for detecting the spray quality of a fuel injector, characterized in that: The spray quality detection method comprises: Acquire a sequence of spray images of sprays ejected from the injector, and extract the number of peaks in a waveform of a current spray image in the sequence of spray images; acquire the number of nozzle holes in the sprayer, and determine whether the number of nozzle holes is equal to the number of peaks; if the number of nozzle holes is equal to the number of peaks, determine the current spray image as a target spray image, and segment the target spray image to obtain a segmented image; Determine the position of the spray root in the target spray image based on the segmented image, calculate the distance between each target pixel in the segmented image and the spray root based on the position of the spray root, determine the expansion matrix corresponding to each target pixel based on the distance, perform morphological expansion processing on the segmented image based on the expansion matrix, and obtain the target area and spray quantity of the corresponding spray; The spray area, spray angle and spray deflection angle of each target area are calculated; The spray characteristics of the target spray image are determined according to the spray quantity, the spray area of each target area, the spray angle of each target area, and the spray deflection angle of each target area. The spray quality is classified according to the spray characteristics to obtain a classification result.

2. The spray quality detection method according to claim 1, wherein: The step of segmenting the target spray image to obtain a segmented image includes: determining a spray image preceding the target spray image in the sequence of spray images as a target sequence spray image; Acquire a background image, determine the first image in the target sequence spray image as the target image, and calculate the pixel difference between each pixel corresponding to the target image and the background image; If there is a pixel point whose difference value is greater than a preset difference threshold, the background image is determined as a target background image; If there is no pixel point difference greater than the preset difference threshold, the target image is determined as the background image, the first image among the remaining images in the target sequence spray image is determined as the target image, and the step of calculating the pixel point difference between the target image and the background image is performed until the target background image is obtained; performing background denoising on the target spray image according to the target background image to obtain a denoised spray image; The denoised spray image is segmented to obtain a segmented image.

3. The spray quality detection method according to claim 1, wherein: Determining the expansion matrix corresponding to each target pixel point according to the distance includes: Determining edge target pixel points and non-edge target pixel points in the segmented image; Obtaining a first target distance coefficient of a non-edge target pixel point and a second target distance coefficient of an edge target pixel point; An expansion matrix for each target pixel is calculated based on the first target distance coefficient, the second target distance coefficient, and the distance.

4. The spray quality detection method according to claim 1, wherein: Calculating the spray area, spray angle, and spray deflection angle of the target area includes: Calculating the gradient magnitude and gradient direction of each target pixel in the target area; Extracting the spray edge of the target area according to the gradient amplitude and gradient direction of each target pixel point; According to the spray edge, the edge straight line of the target area is extracted, and according to the edge straight line, the spray area, spray angle and spray deflection angle of each target area are calculated.

5. The spray quality detection method according to claim 1, wherein: Determining the spray characteristics of the target spray image includes: Determine the spray area characteristics based on the spray area of each target area; Determine the spray angle characteristics based on the spray angle of each target area; Determine the spray deflection angle characteristics according to the spray deflection angle of each target area; The spray quantity, the spray area feature, the spray angle feature and the spray deflection angle feature are spliced and fused to obtain the spray feature of the target spray image.

6. The spray quality detection method according to claim 1, wherein: The classifying the spray quality according to the spray characteristics to obtain a classification result includes: Obtain the trained spray quality classification model; The spray characteristics are input into the trained spray quality classification model, and a classification result is output.

7. A spray quality detection device for a fuel injector, characterized in that: The spray quality detection device comprises: an acquisition module, configured to acquire a sequence of spray images of sprays ejected from the injector, extract the number of peaks in a waveform of a current spray image in the sequence of spray images, acquire the number of nozzle holes in the sprayer, and determine whether the number of nozzle holes is equal to the number of peaks; if the number of nozzle holes is equal to the number of peaks, determine the current spray image as a target spray image, and segment the target spray image to obtain a segmented image; a processing module, configured to determine, based on the segmented image, a position of a spray root in the target spray image; calculate, based on the position of the spray root, a distance between each target pixel in the segmented image and the spray root; determine, based on the distance, a dilation matrix corresponding to each target pixel; and perform morphological dilation processing on the segmented image based on the dilation matrix to obtain a target area and a spray quantity corresponding to the spray; A calculation module is used to calculate the spray area, spray angle and spray deflection angle of each target area; A classification module is used to determine the spray characteristics of the target spray image according to the spray quantity, the spray area of each target area, the spray angle of each target area and the spray deflection angle of each target area, and classify the spray quality according to the spray characteristics to obtain a classification result.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the spray quality detection method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the spray quality detection method according to any one of claims 1 to 6 is implemented.

Images