Method for detecting spraying quality of porous oil injector of diesel engine

Abstract

The invention discloses a diesel engine porous oil injector spraying quality detection method, which comprises three steps of spraying image standardization processing, spraying quality index parameter detection and spraying quality index parameter comparison evaluation. The spray image standardization processing comprises image background removal, image cutting, image graying, image denoising, image binaryzation and oil beam segmentation; the spraying quality index parameter detection comprises the subtle uniformity, penetration distance and spraying taper angle of spraying; the parameter comparison evaluation of the spraying quality comprises evaluation of spraying subtle uniformity, penetration distance and spraying cone angle. The problem that detection indexes are not comprehensive is solved, parameter changes of the spraying quality can be evaluated more accurately by comparing with a standard spraying image, a reference basis is provided for evaluation of the technical condition of the oil sprayer, and therefore detection and evaluation of the spraying quality of the porous oil sprayer of the diesel engine are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and more specifically, to a method for detecting spray quality of a diesel engine multi-hole fuel injector. Background Art

[0002] Diesel engines are widely used in gravity operations due to their high power and torque. They are currently the most widely used type of power machinery. The injector is an important component in the diesel engine fuel supply system to achieve diesel atomization. The quality of diesel atomization directly determines the quality of combustion in the cylinder. Heavy-duty diesel engines often face high-load operating conditions. Under long-term use in complex working conditions, carbon deposits may appear on the injector's spray holes, resulting in a decrease in the quality of diesel atomization, worsening combustion in the cylinder, a decrease in power, and even a hidden danger to the safety and stability of the diesel engine. Therefore, it is necessary to detect the injector spray characteristic parameters and evaluate the injector's atomization performance status.

[0003] The spray characteristic parameter indicators of the injector include penetration distance, spray cone angle and fine uniformity. The current spray processing method has two shortcomings: first, the detection indicators are not comprehensive, only penetration distance and spray cone angle are included, and fine uniformity is not taken into account; second, there is no comparison with the standard spray image of the injector in good technical condition, and there is no evaluation reference standard. These two shortcomings make it impossible to fully detect the spray characteristic parameter parameters of the injector and effectively evaluate the performance status of the injector spray quality. Therefore, it is necessary to make improvements to improve the accuracy of detection and evaluation. Summary of the invention

[0004] The purpose of the present invention is to design and develop a method for detecting the spray quality of a diesel engine multi-hole fuel injector, which can comprehensively detect the index parameters of the spray quality and improve the detection accuracy.

[0005] The technical solution provided by the present invention is:

[0006] A method for detecting the spray quality of a diesel engine multi-hole injector comprises the following steps:

[0007] Step 1, collecting the spray image of the multi-hole injector to be tested;

[0008] Step 2: performing standardization processing on the spray image of the multi-hole injector to be detected to obtain a segmented sub-image;

[0009] Step 3: perform index parameter detection on the segmented sub-images in order to obtain index parameter values ​​of all oil beams;

[0010] The index parameter detection includes the fine uniformity, penetration distance and spray cone angle of the spray;

[0011] Step 4: Compare the index parameter values ​​of all the oil beams with the index parameter values ​​of all the oil beams of the new injector, and calculate the change value of each oil beam.

[0012] Preferably, the step 1 specifically includes:

[0013] Step 1, collecting images of the multi-hole injector before spraying and during spraying;

[0014] Step 2: Subtract the two images to eliminate the background and obtain the spray image of the multi-hole injector to be tested.

[0015] Preferably, the standardization process includes:

[0016] Image cropping, image grayscale, image denoising, image binarization, oil beam segmentation, image rectification and image sorting.

[0017] Preferably, the image is cropped to obtain a circular image with the nozzle of the diesel engine multi-hole injector as the origin and the maximum oil beam length as the radius.

[0018] Preferably, the image denoising is to remove salt and pepper noise by using a median filter function.

[0019] Preferably, the image binarization is to binarize the image by using a large inter-class variance method with an adaptive threshold.

[0020] Preferably, the oil beam is divided into:

[0021] A rectangular coordinate system is established with the nozzle center in the binary image as the origin, the horizontal direction as the x-axis, and the vertical direction as the y-axis. The binary image is divided into corresponding sub-images at equal angles according to the number of oil beams. In each sub-image, the oil beam is located at the center of the sub-image.

[0022] Preferably, the image correction is to perform rotation correction on the multiple sub-images so that the starting end of the oil beam is at the origin of the coordinate system and the center line of the oil beam coincides with the y-axis.

[0023] Preferably, the image sorting is to calculate the oil beam grayscale values ​​of all sub-images and sort all sub-images in descending order.

[0024] Preferably, the fine uniformity of the spray is determined according to the grayscale average value and the standard deviation value. If the grayscale average value is larger, the amount of spray oil of the diesel engine multi-hole fuel injector is more and more concentrated; if the standard deviation value is smaller, the spray distribution of the diesel engine multi-hole fuel injector is more uniform;

[0025] The penetration distance is the oil beam length;

[0026] The spray cone angle is obtained by identifying an edge map from a sub-image, connecting the far end of the oil beam in the edge map with the coordinate origin, selecting the midpoint of the connection, and drawing horizontal lines to the left and right sides with the midpoint of the connection as the starting point. The horizontal line has an intersection with each side edge of the oil beam. Polynomials are fitted according to the coordinates of the two side edges of the oil beam using the intersection points on both sides and the coordinate origin, and the angle between the two polynomials after drawing lines.

[0027] The beneficial effects of the present invention are:

[0028] A diesel engine multi-hole fuel injector spray quality detection method designed and developed by the present invention solves the problem of incomplete detection indicators, and by comparing with a standard spray image, can more accurately evaluate the parameter changes of the spray quality, provide a reference basis for the evaluation of the technical condition of the injector, thereby realizing the detection of the diesel engine multi-hole fuel injector spray quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 The figure is a schematic flow chart of the method for detecting the spray quality of a multi-hole fuel injector of a diesel engine according to the present invention.

[0030] Figure 2 It is a grayscale schematic diagram of the spray image of the multi-hole injector to be tested according to the present invention.

[0031] Figure 3 This is a schematic diagram of the binarization of the spray image of the diesel engine multi-hole injector according to the present invention.

[0032] Figure 4 It is a schematic diagram of the oil beam segmentation of the spray image of the diesel engine multi-hole injector according to the present invention.

[0033] Figure 5 Schematic diagram of the edge of the sub-image described in the present invention. DETAILED DESCRIPTION

[0034] The present invention is further described in detail below so that those skilled in the art can implement it according to the description.

[0035] like Figure 1 As shown, the present invention provides a method for detecting the spray quality of a diesel engine multi-hole injector, which specifically comprises the following steps:

[0036] Step 1: Collect the spray image of the multi-hole injector to be tested. Specifically:

[0037] Step 1, collecting images of the multi-hole injector before spraying and during spraying;

[0038] Step 2, subtracting the two images to eliminate the background and obtain the spray image of the multi-hole injector to be tested;

[0039] Step 2: standardizing the spray image of the multi-hole injector to be tested;

[0040] The standardization process includes image cropping, image graying, image denoising, image binarization, oil beam segmentation, image correction and image sorting. Specifically:

[0041] The image clipping is to clip the spray image of the multi-hole injector to be tested into a circle with the nozzle as the origin and the maximum oil beam length as the radius.

[0042] like Figure 2 As shown, the image grayscale is to grayscale the cropped image.

[0043] The image denoising is to remove salt and pepper noise using a median filter function.

[0044] like Figure 3 As shown, in this embodiment, the image binarization uses a large inter-class variance method with an adaptive threshold to binarize the image.

[0045] like Figure 4 As shown, the oil beam segmentation is specifically as follows:

[0046] According to the coordinates in the acquired binary image, the grayscale image is segmented into oil beams. The nozzle center in the binary image is taken as the coordinate origin, the horizontal direction is the x-axis, and the vertical direction is the y-axis. A rectangular coordinate system is established as the coordinates for segmenting the image. The pixel coordinates of the starting center of the oil beam are selected using an interactive method, that is, the pixel coordinates of the nozzle center are selected, and the segmentation angle is determined according to the number of oil beams. The binary image is segmented into corresponding sub-images at equal angles according to the number of oil beams.

[0047] In this embodiment, the number of the oil beams is 10, and any one of the oil beams is used as the starting line, and 18° is taken on both sides of the starting line as the segmentation range, that is, the circular image is divided into 10 36° sub-images, and in each sub-image the oil beam is at the center of the sub-image.

[0048] The image correction is to perform rotation correction on the multiple sub-images to ensure that the starting end of the oil beam is at the origin of the coordinate system and the center line of the oil beam coincides with the y-axis.

[0049] The image sorting is to calculate the oil beam grayscale values ​​of all sub-images and sort all the sub-images in descending order.

[0050] Step 3: perform index parameter detection on the image to obtain the index parameter value of each individual oil beam corresponding to the spray image of the multi-hole injector to be detected;

[0051] The index parameters include the fine uniformity, penetration distance and spray cone angle of the spray;

[0052] The fine uniformity of the spray is determined based on the calculated grayscale mean and standard deviation. The grayscale mean reflects the overall state of the oil beam. A small grayscale mean indicates a small and dispersed amount of oil, while a large grayscale mean indicates a large and concentrated amount of oil. The grayscale standard deviation reflects the spray distribution state. A small standard deviation indicates a uniform spray distribution, while a large standard deviation indicates an uneven spray distribution.

[0053] The penetration distance is the oil beam length;

[0054] like Figure 5 As shown, the edge map is identified from the sub-image, the far end of the oil beam in the edge map and the coordinate origin are connected, the midpoint of the connection line is selected, and a horizontal line is drawn to the left and right sides with the midpoint of the connection line as the starting point. The horizontal line has an intersection with the edges of the two sides of the oil beam respectively. Two polynomials are fitted according to the coordinates of the edges of the two sides of the oil beam based on the intersection points on both sides and the coordinate origin. The angle between the two polynomials after drawing the lines is the spray cone angle.

[0055] Step 4: Use the same method to test the index parameters of the newly manufactured injectors to obtain the index parameter value of each individual oil beam, and compare it with the index parameter value of each individual oil beam corresponding to the spray image of the multi-hole injector to be tested in sequence, and calculate the change value of each individual oil beam.

[0056] In this embodiment, the step one is obtained by photographing with an industrial camera.

[0057] A diesel engine multi-hole fuel injector spray quality detection method designed and developed by the present invention solves the problem of incomplete detection indicators, and by comparing with a standard spray image, can more accurately evaluate the parameter changes of the spray quality, provide a reference basis for the evaluation of the technical condition of the injector, thereby realizing the detection of the diesel engine multi-hole fuel injector spray quality.

[0058] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the implementation modes. They can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the embodiments shown and described herein.

Claims

1. A method for detecting the spray quality of a diesel engine multi-hole injector, characterized in that: The steps include: Step 1, collecting the spray image of the multi-hole injector to be tested; Step 2: performing standardization processing on the spray image of the multi-hole injector to be detected to obtain a segmented sub-image; Step 3: perform index parameter detection on the segmented sub-images in order to obtain index parameter values ​​of all oil beams; The index parameter detection includes the fine uniformity, penetration distance and spray cone angle of the spray; Step 4: Compare the index parameter values ​​of all the oil beams with the index parameter values ​​of all the oil beams of the new injector, and calculate the change value of each oil beam.

2. The diesel engine multi-hole injector spray quality detection method according to claim 1, characterized in that: The step 1 specifically includes: Step 1, collecting images of the multi-hole injector before spraying and during spraying; Step 2: Subtract the two images to eliminate the background and obtain the spray image of the multi-hole injector to be tested.

3. The diesel engine multi-hole injector spray quality detection method according to claim 2, characterized in that: The standardization process includes: Image cropping, image grayscale, image denoising, image binarization, oil beam segmentation, image rectification and image sorting.

4. The diesel engine multi-hole injector spray quality detection method as claimed in claim 3, characterized in that: The image is cropped to obtain a circular image with the nozzle of the diesel engine multi-hole injector as the origin and the maximum oil beam length as the radius.

5. The diesel engine multi-hole injector spray quality detection method according to claim 4, characterized in that: The image denoising is to remove salt and pepper noise by using a median filter function.

6. The diesel engine multi-hole injector spray quality detection method according to claim 5, characterized in that: The image binarization is to binarize the image by using a large inter-class variance method with an adaptive threshold.

7. The diesel engine multi-hole injector spray quality detection method according to claim 6, characterized in that: The oil beam is divided into: A rectangular coordinate system is established with the nozzle center in the binary image as the origin, the horizontal direction as the x-axis, and the vertical direction as the y-axis. The binary image is divided into corresponding sub-images at equal angles according to the number of oil beams. In each sub-image, the oil beam is located at the center of the sub-image.

8. The diesel engine multi-hole injector spray quality detection method according to claim 7, characterized in that: The image correction is to perform rotation correction on the multiple sub-images so that the starting end of the oil beam is at the origin of the coordinate system and the center line of the oil beam coincides with the y-axis.

9. The diesel engine multi-hole injector spray quality detection method according to claim 8, characterized in that: The image sorting is to calculate the oil beam grayscale values ​​of all sub-images and sort all the sub-images in descending order.

10. The diesel engine multi-hole injector spray quality detection method according to claim 9, characterized in that: The fine uniformity of the spray is determined according to the grayscale average value and the standard deviation value. If the grayscale average value is larger, the amount of spray oil of the diesel engine multi-hole fuel injector is larger and more concentrated; if the standard deviation value is smaller, the spray distribution of the diesel engine multi-hole fuel injector is more uniform; The penetration distance is the oil beam length; The spray cone angle is obtained by identifying an edge map from a sub-image, connecting the far end of the oil beam in the edge map with the coordinate origin, selecting the midpoint of the connection, and drawing horizontal lines to the left and right sides with the midpoint of the connection as the starting point. The horizontal line has an intersection with each side edge of the oil beam. Polynomials are fitted according to the coordinates of the two side edges of the oil beam using the intersection points on both sides and the coordinate origin, and the angle between the two polynomials after drawing lines.

Images