CN116402827B - Image processing-based cable clamp plate defect detection method and device for coal mining machine - Google Patents
Image processing-based cable clamp plate defect detection method and device for coal mining machine Download PDFInfo
- Publication number
- CN116402827B CN116402827B CN202310679518.1A CN202310679518A CN116402827B CN 116402827 B CN116402827 B CN 116402827B CN 202310679518 A CN202310679518 A CN 202310679518A CN 116402827 B CN116402827 B CN 116402827B
- Authority
- CN
- China
- Prior art keywords
- value
- line segment
- point
- pixel
- gate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000007547 defect Effects 0.000 title claims abstract description 61
- 239000003245 coal Substances 0.000 title claims abstract description 39
- 238000005065 mining Methods 0.000 title claims abstract description 39
- 238000001514 detection method Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 17
- 238000003709 image segmentation Methods 0.000 claims abstract description 14
- 230000004927 fusion Effects 0.000 claims description 42
- 238000005336 cracking Methods 0.000 claims description 36
- 238000003466 welding Methods 0.000 claims description 22
- 238000002844 melting Methods 0.000 claims description 13
- 230000008018 melting Effects 0.000 claims description 13
- 230000000694 effects Effects 0.000 abstract description 7
- 238000002347 injection Methods 0.000 description 6
- 239000007924 injection Substances 0.000 description 6
- 238000005266 casting Methods 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000012768 molten material Substances 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000001746 injection moulding Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a cable clamp plate defect detection method and device for a coal mining machine based on image processing. The invention is applied to the field of image processing, and the method comprises the following steps: acquiring a gray image of the surface of the cable clamp plate; performing image segmentation processing on the gray level image to determine all gate areas forming the cable clamp plate; and determining the defect of each gate area according to the gray level change from the gate point of each gate area to the line segment on the edge of the gate area and the gray level difference of different line segments in the gate area. Therefore, the defects of the cable clamp plate for the coal mining machine can be accurately detected, and the defect detection effect is improved.
Description
Technical Field
The invention relates to the field of image processing, in particular to a cable clamp plate defect detection method and device for a coal mining machine based on image processing.
Background
The cable clamping plate for the coal mining machine is equipment for protecting cables and water pipes in the coal mining machine, namely, a protection channel is formed by connecting a pin shaft or a bolt according to the working face of the coal mining machine so as to protect the cables or the water pipes from external force.
The cable clamp plate used for the coal mining machine is an injection molding product, and the molten material is injected from a gate through a mold casting system for casting during production, and when the injection pressure is unreasonable, cracks such as cracks and the like are easy to appear on the surface of the cable clamp plate, so that the protection force of the cable clamp plate on a cable and a water pipe is affected.
Therefore, when the production of the cable clamp plate is finished, defect detection is often needed to screen out the cable clamp plate with defects, so that the damage caused by poor protection of the subsequent cable clamp plate is prevented. However, since the cracks are unevenly distributed on the image, the cracks are extremely easily disturbed by the uneven gray scale phenomenon on the surface of the injection molding caused by uneven melting stock and the like when the cracks are detected, and the defect detection effect is poor.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a cable clamping plate defect detection method and device for a coal mining machine based on image processing.
The invention is realized by the following technical scheme:
the invention provides a cable clamp plate defect detection method for a coal mining machine based on image processing, which comprises the following steps:
acquiring a gray image of the surface of the cable clamp plate;
performing image segmentation processing on the gray level image to determine all gate areas forming the cable clamp plate;
and determining the defect of each gate area according to the gray level change from the gate point of each gate area to the line segment on the edge of the gate area and the gray level difference of different line segments in the gate area.
Further, the image segmentation processing is performed on the gray level image, and each gate area forming the cable clamp plate is determined, including:
subtracting the gray value of a first pixel with the gray value of a second pixel from the gray value of a third pixel to obtain a first subtraction result, wherein the first pixel is adjacent to the second pixel and the third pixel respectively, the first pixel comprises a pixel point far away from the gate point when the difference of the gray values of two adjacent pixels is larger than the preset gray difference on a ray taking the gate point as a starting point;
negative absolute value of the first subtraction result is calculated, and a second subtraction result is determined;
performing exp index processing on the second subtraction result to determine gray difference values of the first pixel, the second pixel and the third pixel;
and if the gray level difference value is larger than a first preset value, the first pixel is a fusion point of the gate area.
Further, the image segmentation processing is performed on the gray level image, and each gate area forming the cable clamp plate is determined, including:
determining a line segment difference value of the length between a first line segment and the rest line segments according to the length of the first line segment, the length of the rest line segments, the length of the longest line segment and the number of line segments, wherein the number of line segments comprises the number of rest line segments plus 1, the first line segment comprises a line segment between the gate point as a starting point and a first pixel, the longest line segment comprises the line segment with the longest length in the first line segment and the rest line segments, the first pixel comprises a pixel point far away from the gate point when the difference of gray values of two adjacent pixels is larger than a preset gray difference on a ray with the gate point as the starting point;
subtracting the segment difference value from 1, and multiplying the obtained result by the fusion point probability to obtain a product value;
if the product value is greater than a preset product value threshold, the end point of the first line segment is a first fusion point of the gate area.
Further, the step of multiplying the obtained result by the fusion point probability by subtracting the segment difference value from 1 to obtain a product value further includes:
if the product value is smaller than or equal to a preset product value, the end point of the first line segment is not a welding point of the gate area;
on the first line segment, taking a second pixel as a starting point, acquiring a gray difference value of two adjacent pixels, and if the gray difference value is larger than a preset gray difference value, determining a pixel point far away from the second pixel as a second welding point;
and processing the first welding point and the second welding point by a least square method, wherein the obtained fitting curve is the gate area.
Further, the determining the defect of each gate area according to the gray level change from each gate point to the line segment on the edge of the gate area and the gray level difference of different line segments in the gate area includes:
determining a cracking value of each gate area according to a first gray level entropy value, a second gray level entropy value, a first average gray level entropy value, a second average gray level entropy value and a length accumulated value of U gap line segments, wherein the first gray level entropy value comprises a gray level entropy value of a j-th corresponding normal line segment of an i-th gap line segment, the second gray level entropy value comprises a gray level entropy value of the i-th gap line segment, the first average gray level entropy value comprises an average gray level value of the j-th normal line segment corresponding to the i-th gap line segment, the second average gray level entropy value comprises an average gray level value of the i-th gap line segment, the gap line segment is a line segment from a gate point to a second melting point in the gate area, and the gap line segment comprises a line segment from the gate point to the second melting point;
and if the cracking value is larger than a preset cracking value, determining that the cracking property exists in the gate area.
Further, when the crack value is greater than the preset crack value, determining that the gate area has the crack, further includes:
determining a line segment uniformity value from a gate P point to a gate area edge point according to a first average gray value, a second average gray value, a distance value, a gray variance and a minimum positive number, wherein the first average gray value comprises an average gray value of pixel points on a first line segment in a gate area, the second average gray value comprises an average gray value of pixel points on a second line segment in the gate area, the distance value comprises a distance between the first line segment and the second line segment, and the gray variance comprises a gray variance of pixel points on the first line segment;
summing all line segment uniformity values in the gate area to determine the uniformity value of the gate area;
normalizing the uniform value and the cracking value to obtain a corrected uniform value;
if the uniformity value is smaller than a preset uniformity value, the uniformity of the gate area is poor.
The invention also provides a cable clamp plate defect detection device for the coal mining machine based on image processing, which comprises the following steps:
the acquisition module is used for acquiring a gray image of the surface of the cable clamp plate;
the processing module is used for carrying out image segmentation processing on the gray level image and determining all gate areas forming the cable clamp plate;
and the determining module is used for determining the defect of each gate area according to the gray level change from the gate point of each gate area to the line segment on the edge of the gate area and the gray level difference of different line segments in the gate area.
Further, the processing module is configured to perform subtraction processing on a gray value of a first pixel that is 2 times of a gray value of a second pixel and a gray value of a third pixel, so as to obtain a first subtraction result, where the first pixel is adjacent to the second pixel and the third pixel, and the first pixel includes a pixel point far from the gate point when a difference between gray values of two adjacent pixels is greater than a preset gray difference on a ray that uses the gate point as a starting point; negative absolute value of the first subtraction result is calculated, and a second subtraction result is determined; performing exp index processing on the second subtraction result to determine gray difference values of the first pixel, the second pixel and the third pixel; and if the gray level difference value is larger than a first preset value, the first pixel is a fusion point of the gate area.
Further, the processing module is configured to determine a line segment difference value of a length between a first line segment and a remaining line segment according to the length of the first line segment, the length of the remaining line segment, the length of the longest line segment, and the number of line segments, where the number of line segments includes a number of remaining line segments added with 1, the first line segment includes a line segment between the gate point and a first pixel, the first line segment includes a line segment with the longest length between the first line segment and the remaining line segment, the first pixel includes a pixel point far from the gate point when a difference between gray values of two adjacent pixels is greater than a preset gray difference on a ray with the gate point as a start point; subtracting the segment difference value from 1, and multiplying the obtained result by the fusion point probability to obtain a product value; if the product value is greater than a preset product value threshold, the end point of the first line segment is a first fusion point of the gate area.
Further, the processing module is further configured to, if the product value is less than or equal to a preset product value, make an end point of the first line segment not be a melting point of the gate area; on the first line segment, taking a second pixel as a starting point, acquiring a gray difference value of two adjacent pixels, and if the gray difference value is larger than a preset gray difference value, determining a pixel point far away from the second pixel as a second welding point; and processing the first welding point and the second welding point by a least square method, wherein the obtained fitting curve is the gate area.
Further, the determining module is configured to determine a crack value of each gate area according to a first gray level entropy value, a second gray level entropy value, a first average gray level entropy value, a second average gray level entropy value and a length accumulated value of U gap line segments, where the first gray level entropy value includes a gray level entropy value of a j-th corresponding normal line segment of the i-th gap line segment, the second gray level entropy value includes a gray level entropy value of the j-th normal line segment corresponding to the i-th gap line segment, the first average gray level entropy value includes an average gray level value of the i-th gap line segment, the gap line segment is a line segment from a gate point in the gate area to the second melting point, and the gap line segment includes a line segment from the gate point to the second melting point; and if the cracking value is larger than a preset cracking value, determining that the cracking property exists in the gate area.
Further, the determining module is further configured to determine a line segment uniformity value from the gate P point to the gate area edge point according to a first average gray value, a second average gray value, a distance value, a gray variance, and a minimum positive number, where the first average gray value includes an average gray value of a pixel point on a first line segment in the gate area, the second average gray value includes an average gray value of a pixel point on a second line segment in the gate area, the distance value includes a distance between the first line segment and the second line segment, and the gray variance includes a gray variance of the pixel point on the first line segment; summing all line segment uniformity values in the gate area to determine the uniformity value of the gate area; normalizing the uniform value and the cracking value to obtain a corrected uniform value; if the uniformity value is smaller than a preset uniformity value, the uniformity of the gate area is poor.
Compared with the prior art, the invention has the following beneficial technical effects:
the invention provides a cable clamp plate defect detection method and device for a coal mining machine based on image processing, which are characterized in that a gray level image of the surface of a cable clamp plate is obtained; performing image segmentation processing on the gray level image to determine all gate areas forming the cable clamp plate; and determining the defect of each gate area according to the gray level change from the gate point of each gate area to the line segment on the edge of the gate area and the gray level difference of different line segments in the gate area. Therefore, the defects of the cable clamp plate for the coal mining machine can be accurately detected, and the defect detection effect is improved.
Drawings
FIG. 1 is a schematic flow chart of a cable clamp plate defect detection method for a coal mining machine based on image processing according to an embodiment of the invention;
FIG. 2 is a schematic view of a cable clamp plate for a coal mining machine based on image processing according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a cable clamping plate defect detection device for a coal mining machine based on image processing according to an embodiment of the invention.
Detailed Description
The invention will now be described in further detail with reference to specific examples, which are intended to illustrate, but not to limit, the invention.
The cable clamp plate defect detection method for the coal mining machine provided by the embodiment of the invention is suitable for detecting the defects of the cable clamp plates for the coal mining machine, and the cable clamp plate defect detection for the coal mining machine provided by the embodiment of the invention can be arranged on the coal mining machine or can be an independent device outside the coal mining machine, and is not limited.
FIG. 1 is a schematic flow chart of a cable clamp plate defect detection method for a coal mining machine based on image processing according to an embodiment of the invention; fig. 2 is a schematic structural diagram of a cable clamping plate for a coal mining machine based on image processing according to an embodiment of the present invention, and as shown in fig. 1 and fig. 2, the method for detecting a defect of a cable clamping plate for a coal mining machine based on image processing according to an embodiment of the present invention includes:
step 101, acquiring a gray level image of the surface of a cable clamping plate;
specifically, through an industrial camera, a fixed light source overlooks and collects the surface image of the produced cable clamp plate, the collected image is an RGB image, and the method of weighting graying is used for graying the surface image to obtain the surface gray image of the cable clamp plate, wherein the weighting graying is a known technology, and the description is omitted here.
And 102, performing image segmentation processing on the gray level image to determine each gate area forming the cable clamp plate.
Specifically, according to the steps, the gray level image of the surface of the cable clamp plate can be obtained, firstly, the gray level image of the surface of the cable clamp plate is obtained by using an Ojin threshold segmentation algorithm, wherein the cable clamp plate is used as a foreground, and the rest part is used as a background to segment the image, so that the cable clamp plate area image is obtained. The division algorithm of the Ojin threshold is a known technique, and will not be described herein.
For example, an analysis is performed on any gate, assuming that the gate is P point, and the molten material spreads from the gate into the cable clamping plate area due to the existence of injection pressure after entering from the gate, so that rays passing through the cable clamping plate area from the P point are assumed to be M rays, and M is set to 200 according to an empirical value, the embodiment of the invention does not limit the experimental value, analyzes the change of the pixel point on the ray, takes ray a as an example, takes the starting point of ray a as P point, analyzes the pixel point on the ray, acquires adjacent pixel points on ray a from the P point, and assumes a point a, and the gray difference between the point a and the point P point=|I judges whether the point a and the point P are similar pixel points, if soAnd if the gray level difference threshold value is smaller than the set gray level difference threshold value, setting according to an empirical value, wherein the point a and the point P are the same type of pixel points, otherwise, the points are different types of pixel points. If the pixel points are the same type of pixel points, the judgment is carried out on the adjacent pixel points on the ray for acquiring the point a until the pixel points of different types are acquired, and at the moment, the ray A is provided with the adjacent pixel pointsThe same type of pixel point forms a line segment, which is assumed to beThe endpoint at this time is a V point, and the P point is the same as the P point, and the corresponding line segment can be obtained for the rest rays. The determination of whether the segment end is a weld line edge can be accomplished based on the local gray scale difference at the segment end.
Further, subtracting the gray value of the first pixel with the gray value of the second pixel from the gray value of the third pixel to obtain a first subtraction result, wherein the first pixel is adjacent to the second pixel and the third pixel respectively, the first pixel comprises a pixel point far away from the gate point when the difference of the gray values of the two adjacent pixels is larger than the preset gray difference on a ray taking the gate point as a starting point;
negative absolute value of the first subtraction result is calculated, and a second subtraction result is determined;
performing exp index processing on the second subtraction result to determine gray difference values of the first pixel, the second pixel and the third pixel;
and if the gray level difference value is larger than a first preset value, the first pixel is a fusion point of the gate area.
For example, the possibility KN that the line end point is the fusion point is obtained:
in the formulaIs a line segmentGray value of the first pixel V point of (c),then divide intoThe gray values of the adjacent pixels, i.e., the gray values of the second pixel V1 and the third pixel V2, are respectively the end point V. The gray scale difference value B reflects the line segment at this timeThe larger the difference of the local gray scale at the V point of the first pixel, the description of the line segmentThe greater the likelihood that the upper V point is the point of fusion.
When judging the fusion points according to the steps, for a normal area, the gray values of the pixel points in the normal area are close, and the obtained fusion lines are accurate, however, when defects exist in the area, the defective pixel points and the pixel points in the normal area are often different pixel points, the obtained fusion points are very easy to be the defective pixel points, and are not actual fusion points, so that the obtained fusion lines are inaccurate, the segmentation is inaccurate, the influence on the uniformity and the cracking index of different areas is caused, and the follow-up regulation and control are not accurate enough.
The embodiment of the invention further provides a method for optimizing a fusion point, which comprises the steps of determining a line segment difference value of the length between a first line segment and the rest line segments according to the length of the first line segment, the length of the rest line segments, the length of the longest line segment and the number of line segments, wherein the number of line segments comprises the number of rest line segments plus 1, the first line segment comprises a line segment from a gate point to a first pixel, the longest line segment comprises the first line segment and the line segment with the longest length in the rest line segments, the first pixel comprises a pixel point far away from the gate point when the difference of gray values of two adjacent pixels is larger than a preset gray difference on a ray with the gate point as the starting point;
subtracting the segment difference value from 1, and multiplying the obtained result by the fusion point probability to obtain a product value;
if the product value is larger than a preset product value, the end point of the first line segment is a first welding point of the gate area.
For example, the fusion is performed by the following formulaThe possibility of the point is optimized, and the fusion point after optimization is marked as:
Length difference in the formulaFor the first line segment acquired at this timeThe difference in length from the remaining line segments acquired,in order to obtain the number of line segments,representing a first line segmentThe length of (2) is not described in detail herein.Representing the length of the ith segment of the remaining segments,the length of the line segment is obtained as a known technology, wherein the line segment represents the longest length of the first line segment and the rest of line segments. Difference in lengthThe larger the difference, the description of the first line segment at that timeThe more likely defects are at the end points of (c), the less likely the corresponding fusion points should be. Fusion point probabilityFor the first line sectionAt the end points of (a) are the possibilities of fusion points probability fusion points, preferably,can be according to the first line segmentEnd point of (c)Is calculated from the gray-scale difference value B of (c),or an empirical value, without limitation.
When the product valueWhen the value is larger than the preset product value threshold value, the first line segmentThe terminal points of (a) are fusion points, otherwise, are not fusion points.
Further, the step of multiplying the obtained result by the fusion point probability by subtracting the segment difference value from 1 to obtain a product value further includes:
if the product value is smaller than or equal to a preset product value, the end point of the first line segment is not a fusion point of the gate area;
on the first line segment, taking a second pixel as a starting point, acquiring a gray difference value of two adjacent pixels, and if the gray difference value is larger than a preset gray difference value, determining a pixel point far away from the second pixel as a second welding point;
and processing the first welding point and the second welding point by a least square method, wherein the obtained fitting curve is the gate area.
That is, for other than fusionA line segment of the point, here ray A, a first line segmentFor example, a point Z is selected on the ray, the Z point and the first line segmentThe average gray value difference of (c) is smallest, and if there are a plurality of points, the nearest point is selected. The steps may be repeated starting at point Z and then acquiring a new line segment until a fusion point is acquired. The difference is that if the end point of the line segment obtained by the Z point is the I point, when the steps are repeated to calculate the length of the line segment, the length of the line segment is the length from the P point to the I point.
According to the steps, the fusion point on each ray of the pouring gate P is obtained, a fitting curve is obtained through a least square method, the area formed by the boundary of the obtained curve and the cable clamping plate area is the pouring gate area, the steps of analysis are carried out on different pouring gates, the self-adaptive segmentation of the image can be completed, and the image is segmented into N pouring gate areas. The reason why the image is divided into different gate areas is that parameters set at different gate areas may be inconsistent, that is, injection pressure, injection speed, melt temperature, etc., if the image is directly detected later, defects may be detected by mistake due to different process parameter settings at different gate areas, and the gray values between the areas are also different.
Step 103, determining the defect of each gate area according to the gray level change from the gate point of each gate area to the line segment on the edge of the gate area and the gray level difference of different line segments in the gate area.
Specifically, a crack value of each gate area is determined according to a first gray level entropy value, a second gray level entropy value, a first average gray level entropy value, a second average gray level entropy value and a length accumulated value of a U gap line segment, wherein the first gray level entropy value comprises a gray level entropy value of a j-th corresponding normal line segment of an i-th gap line segment, the second gray level entropy value comprises a gray level entropy value of the i-th gap line segment, the first average gray level entropy value comprises an average gray level value of the j-th normal line segment corresponding to the i-th gap line segment, the second average gray level entropy value comprises an average gray level value of the i-th gap line segment, the gap line segment is a line segment from a gate point to a second melting point in the gate area, and the gap line segment comprises a line segment from the gate point to the second melting point;
and if the cracking value is larger than a preset cracking value, determining that the cracking property exists in the gate area.
For example, some of the segments obtained by the gate P are obtained after multiple times of obtaining the actual welding points, so that the regions between the different segments obtained multiple times on the same ray can be recorded as gap segments, if U gap segments exist, the crack performance index JL can be constructed by the difference between the gap segments and the corresponding normal segments, and if the two end points of the gap segment T are the point a and the point b, the normal segments can be intercepted from the ray starting from the point PNormal line segmentThe distance between the two end points and the P point is equal to the distance between the two end points and the P point of the gap line segment T. The corresponding normal line segment number of the gap line segment T is assumed to beJL may be obtained:
in the formulaThe gray entropy value of the normal line segment corresponding to the jth interval line segment is shown, and the gray entropy value obtaining means is a known technology and will not be described again.The gray entropy value of the ith gap line segment is represented,the average gray value of the j normal line segment corresponding to the i gap line segment,is the average gray value of the ith gap line segment.The accumulated values of the lengths of the U gap line segments are indicated, and the length of the line segments is obtained as a known technique, so that the description thereof is omitted.
The embodiment of the invention also comprises the following steps: and if the cracking value is greater than the preset cracking value, determining that the gate area has the cracking property, and then further comprising:
determining a line segment uniformity value from a gate P point to a gate area edge point according to a first average gray value, a second average gray value, a distance value, a gray variance and a minimum positive number, wherein the first average gray value comprises an average gray value of pixel points on a first line segment in a gate area, the second average gray value comprises an average gray value of pixel points on a second line segment in the gate area, the distance value comprises a distance between the first line segment and the second line segment, and the gray variance comprises a gray variance of pixel points on the first line segment;
summing all line segment uniformity values in the gate area to determine the uniformity value of the gate area;
normalizing the uniform value and the cracking value to obtain a corrected uniform value;
if the uniformity value is smaller than a preset uniformity value, the uniformity of the gate area is poor.
For example, when a gate region Q is further analyzed and the gate is P, the gray level change of the line segment from the P point of the gate to the edge of the Q region and the difference of different line segments can be obtained to obtain the uniformity JY of the gate region:
in the formulaAs the average gray value of the pixel points on the line segment S acquired in the gate region Q,the larger the difference is, the smaller the line segment uniformity R is for the average gray value of the pixel point on the ith line segment acquired in the gate area.Representing the distance between the ith line segment and the line segment S.The larger the value of the gray variance representing the pixel point on the line segment S, the smaller the line segment uniformity R,for a very small positive number, the denominator is prevented from being 0, with an example value of 0.001.For uniformity of the obtained ith line segment. JY is the uniformity of the gate area.
In the above steps, the uniformity index of the region is constructed by the gray level conversion of the pixel points in the region, however, when the cracking and cracking phenomenon exists in the region, the casting pressure is too large, however, the uniformity in the region corresponding to the casting pressure is also disturbed, so that the phenomenon of weaker uniformity occurs, and the surface non-uniformity defect is misdetected.
Preferably, if the JL is normalized, the uniformity index corresponding to the gate area may be corrected based on the crack index JL, and the corrected uniformity index is marked as:
In the formulaJL is the crack property of the gate area for uniformity of the gate area.For uniformity after correction.
And analyzing and processing different gate areas according to the steps to obtain the cracking property and uniformity of the gate areas.
Thus, the crazing property and uniformity corresponding to each gate area are obtained, and the acquisition of the injection pressure regulation parameters is completed.
In this embodiment, through collecting the surface image of the produced cable clamping plate, completing the self-adaptive segmentation of the cable clamping plate through the distribution characteristics of the molten material at the gate, obtaining the gate area, completing the acquisition of the uniformity and crack index of the gate area based on the similarity of different gate areas and the gray level change characteristics of the pixel points in the gate area, completing the injection defect detection of the cable clamping plate based on the uniformity and crack, and when a certain gate area has uniformity<0.2, the defect of poor surface smoothness and uneven surface appears in the gate area, and the crack JL of a certain gate area>And 0.8, indicating that a crack and a cracking defect appear at the gate area, wherein a closed area formed by adjacent gap line segments in the step is a defect area. When (when)<0.2, and JL>And 0.8, indicating that the surface non-uniformity defect, the cracking and the cracking defect exist at the gate area.
According to the embodiment of the invention, the gray level image of the surface of the cable clamping plate is obtained; performing image segmentation processing on the gray level image to determine all gate areas forming the cable clamp plate; and determining the defect of each gate area according to the gray level change from the gate point of each gate area to the line segment on the edge of the gate area and the gray level difference of different line segments in the gate area. Therefore, the defects of the cable clamp plate for the coal mining machine can be accurately detected, and the defect detection effect is improved.
FIG. 3 is a schematic structural diagram of a cable clamping plate defect detection device for a coal mining machine based on image processing according to an embodiment of the invention; as shown in fig. 3, the cable clamp plate defect detection device for a coal mining machine based on image processing provided by the embodiment of the invention includes: an acquisition module 31, a processing module 32 and a determination module 33, wherein:
an acquisition module 31 for acquiring a gray image of the cable clamp plate surface;
a processing module 32 for performing image segmentation processing on the gray level image to determine each gate region constituting the cable clamp plate;
a determining module 33, configured to determine a defect of each gate area according to a gray level change from a gate point of each gate area to a line segment on an edge of the gate area, and a gray level difference of different line segments in the gate area.
According to the embodiment of the invention, the gray level image of the surface of the cable clamping plate is obtained; performing image segmentation processing on the gray level image to determine all gate areas forming the cable clamp plate; and determining the defect of each gate area according to the gray level change from the gate point of each gate area to the line segment on the edge of the gate area and the gray level difference of different line segments in the gate area. Therefore, the defects of the cable clamp plate for the coal mining machine can be accurately detected, and the defect detection effect is improved.
On the basis of the above embodiment, the cable clamp plate defect detection device for the coal mining machine based on image processing according to the embodiment of the invention comprises: the processing module 32 is configured to perform subtraction processing on a gray value of a first pixel that is 2 times that of a gray value of a second pixel and that of a gray value of a third pixel, to obtain a first subtraction result, where the first pixel is adjacent to the second pixel and the third pixel, and the first pixel includes a pixel point far from the gate point when a difference between gray values of two adjacent pixels is greater than a preset gray difference on a ray that uses the gate point as a starting point; negative absolute value of the first subtraction result is calculated, and a second subtraction result is determined; performing exp index processing on the second subtraction result to determine gray difference values of the first pixel, the second pixel and the third pixel; and if the gray level difference value is larger than a first preset value, the first pixel is a fusion point of the gate area.
Further, the processing module is configured to determine a line segment difference value of a length between a first line segment and a remaining line segment according to the length of the first line segment, the length of the remaining line segment, the length of the longest line segment, and the number of line segments, where the number of line segments includes a number of remaining line segments added with 1, the first line segment includes a line segment between the gate point and a first pixel, the first line segment includes a line segment with the longest length between the first line segment and the remaining line segment, the first pixel includes a pixel point far from the gate point when a difference between gray values of two adjacent pixels is greater than a preset gray difference on a ray with the gate point as a start point; subtracting the segment difference value from 1, and multiplying the obtained result by the fusion point probability to obtain a product value; if the product value is greater than a preset product value threshold, the end point of the first line segment is a first fusion point of the gate area.
Preferably, on the basis of the foregoing embodiment, the processing module is further configured to, if the product value is less than or equal to a preset product value, make an end point of the first line segment not be a melting point of the gate area; on the first line segment, taking a second pixel as a starting point, acquiring a gray difference value of two adjacent pixels, and if the gray difference value is larger than a preset gray difference value, determining a pixel point far away from the second pixel as a second welding point; and processing the first welding point and the second welding point by a least square method, wherein the obtained fitting curve is the gate area.
Optionally, the determining module is configured to determine a crack value of each gate area according to a first gray level entropy value, a second gray level entropy value, a first average gray level entropy value, a second average gray level entropy value and a length accumulated value of U gap line segments, where the first gray level entropy value includes a gray level entropy value of a j-th corresponding normal line segment of the i-th gap line segment, the second gray level entropy value includes a gray level entropy value of the j-th normal line segment corresponding to the i-th gap line segment, the first average gray level entropy value includes an average gray level value of the i-th gap line segment, the gap line segment is a line segment from a gate point to the second melting point in the gate area, and the gap line segment includes a line segment from the gate point to the second melting point; and if the cracking value is larger than a preset cracking value, determining that the cracking property exists in the gate area.
Further, on the basis of the foregoing embodiment, the determining module is further configured to determine a line segment uniformity value from the gate P point to the gate edge point according to a first average gray value, a second average gray value, a distance value, a gray variance, and a minimum positive number, where the first average gray value includes an average gray value of pixel points on a first line segment in the gate area, the second average gray value includes an average gray value of pixel points on a second line segment in the gate area, the distance value includes a distance between the first line segment and the second line segment, and the gray variance includes a gray variance of pixel points on the first line segment; summing all line segment uniformity values in the gate area to determine the uniformity value of the gate area; normalizing the uniform value and the cracking value to obtain a corrected uniform value; if the uniformity value is smaller than a preset uniformity value, the uniformity of the gate area is poor.
The working principle and technical effects of the embodiment of the present invention are similar to those of the above embodiment, and are not described herein.
Claims (10)
1. The method for detecting the defects of the cable clamp plates for the coal mining machine based on image processing is characterized by comprising the following steps of:
acquiring a gray image of the surface of the cable clamp plate;
performing image segmentation processing on the gray level image to determine all gate areas forming the cable clamp plate;
determining defects of each gate region according to the gray level change from the gate point of each gate region to the line segment on the edge of the gate region and the gray level difference of different line segments in the gate region;
the determining the defect of each gate area according to the gray level change from the gate point of each gate area to the line segment on the edge of the gate area and the gray level difference of different line segments in the gate area comprises the following steps:
determining a cracking value of each gate area according to a first gray level entropy value, a second gray level entropy value, a first average gray level entropy value, a second average gray level entropy value and a length accumulated value of U gap line segments, wherein the first gray level entropy value comprises a gray level entropy value of a j-th corresponding normal line segment of an i-th gap line segment, the second gray level entropy value comprises a gray level entropy value of the j-th normal line segment corresponding to the i-th gap line segment, the second average gray level entropy value comprises an average gray level value of the i-th gap line segment, the gap line segment is a line segment from a gate point to a second fusion point in the gate area, and the gap line segment comprises a line segment from the gate point to the second fusion point;
and if the cracking value is larger than a preset cracking value, determining that the cracking property exists in the gate area.
2. The image processing-based cable cleat defect detection method for a coal mining machine according to claim 1, wherein the image segmentation processing of the grayscale image to determine each gate area constituting the cable cleat comprises:
subtracting the gray value of a first pixel with the gray value of a second pixel from the gray value of a third pixel to obtain a first subtraction result, wherein the first pixel is adjacent to the second pixel and the third pixel respectively, the first pixel comprises a pixel point far away from the gate point when the difference of the gray values of two adjacent pixels is larger than the preset gray difference on a ray taking the gate point as a starting point;
negative absolute value of the first subtraction result is calculated, and a second subtraction result is determined;
performing exp index processing on the second subtraction result to determine gray difference values of the first pixel, the second pixel and the third pixel;
and if the gray level difference value is larger than a first preset value, the first pixel is a fusion point of the gate area.
3. The image processing-based cable cleat defect detection method for a coal mining machine according to claim 1, wherein the image segmentation processing of the grayscale image to determine each gate area constituting the cable cleat comprises:
determining a line segment difference value of the length between a first line segment and the rest line segments according to the length of the first line segment, the length of the rest line segments, the length of the longest line segment and the number of line segments, wherein the number of line segments comprises the number of rest line segments plus 1, the first line segment comprises a line segment between the gate point as a starting point and a first pixel, the longest line segment comprises the line segment with the longest length in the first line segment and the rest line segments, the first pixel comprises a pixel point far away from the gate point when the difference of gray values of two adjacent pixels is larger than a preset gray difference on a ray with the gate point as the starting point;
subtracting the segment difference value from 1, and multiplying the obtained result by the fusion point probability to obtain a product value;
if the product value is greater than a preset product value threshold, the end point of the first line segment is a first fusion point of the gate area.
4. The method for detecting a cable clamp defect for a coal mining machine based on image processing according to claim 3, wherein the step of multiplying the obtained result by the fusion point probability by subtracting the segment difference value from 1 to obtain a product value further comprises:
if the product value is smaller than or equal to a preset product value, the end point of the first line segment is not a fusion point of the gate area;
on the first line segment, taking a second pixel as a starting point, acquiring a gray difference value of two adjacent pixels, and if the gray difference value is larger than a preset gray difference value, determining a pixel point far away from the second pixel as a second welding point;
and processing the first welding point and the second welding point by a least square method, wherein the obtained fitting curve is the gate area.
5. The method for detecting a cable clamp plate defect for a coal mining machine based on image processing according to claim 1, wherein after determining that the gate area has the crazing property if the crazing value is greater than a preset crazing value, further comprising:
determining a line segment uniformity value from a gate P point to a gate area edge point according to a first average gray value, a second average gray value, a distance value, a gray variance and a minimum positive number, wherein the first average gray value comprises an average gray value of pixel points on a first line segment in a gate area, the second average gray value comprises an average gray value of pixel points on a second line segment in the gate area, the distance value comprises a distance between the first line segment and the second line segment, and the gray variance comprises a gray variance of pixel points on the first line segment;
summing all line segment uniformity values in the gate area to determine the uniformity value of the gate area;
normalizing the uniform value and the cracking value to obtain a corrected uniform value;
if the uniformity value is smaller than a preset uniformity value, the uniformity of the gate area is poor.
6. The utility model provides a coal-winning machine cable splint defect detection device based on image processing which characterized in that includes:
the acquisition module is used for acquiring a gray image of the surface of the cable clamp plate;
the processing module is used for carrying out image segmentation processing on the gray level image and determining all gate areas forming the cable clamp plate;
the determining module is used for determining the defect of each gate area according to the gray level change from the gate point of each gate area to the line segment on the edge of the gate area and the gray level difference of different line segments in the gate area;
the determining module is configured to determine a crack value of each gate area according to a first gray level entropy value, a second gray level entropy value, a first average gray level entropy value, a second average gray level entropy value and a length accumulated value of U gap line segments, where the first gray level entropy value includes a gray level entropy value of a normal line segment corresponding to a j-th gap line segment, the second gray level entropy value includes a gray level entropy value of a j-th gap line segment corresponding to a i-th gap line segment, the first average gray level entropy value includes an average gray level value of a j-th normal line segment corresponding to a i-th gap line segment, the second average gray level entropy value includes an average gray level value of a i-th gap line segment, the gap line segment is a line segment from a gate point to a second melting point in a gate area, and the gap line segment includes a line segment from the gate point to the second melting point; and if the cracking value is larger than a preset cracking value, determining that the cracking property exists in the gate area.
7. The cable splint defect detection device for coal mining machine based on image processing according to claim 6, wherein the processing module is configured to perform subtraction processing on a gray value of a first pixel 2 times that of a second pixel and that of a third pixel to obtain a first subtraction result, where the first pixel is adjacent to the second pixel and the third pixel, and the first pixel includes a pixel point far from the gate point when a difference between gray values of two adjacent pixels is greater than a preset gray difference on a ray using the gate point as a starting point; negative absolute value of the first subtraction result is calculated, and a second subtraction result is determined; performing exp index processing on the second subtraction result to determine gray difference values of the first pixel, the second pixel and the third pixel; and if the gray level difference value is larger than a first preset value, the first pixel is a fusion point of the gate area.
8. The device for detecting a cable clamp defect for a coal mining machine based on image processing according to claim 6, wherein the processing module is configured to determine a line segment difference value of a length between a first line segment and a remaining line segment according to a length of the first line segment, a length of the remaining line segment, a length of a longest line segment, and a number of line segments, the number of line segments including a number of remaining line segments plus 1, the first line segment including a line segment between the gate point as a start point and a first pixel, the longest line segment including a line segment with a length longest between the first line segment and the remaining line segment, the first pixel including a pixel point far from the gate point determined when a difference in gray value between two adjacent pixels is greater than a preset gray difference on a ray with the gate point as a start point; subtracting the segment difference value from 1, and multiplying the obtained result by the fusion point probability to obtain a product value; if the product value is greater than a preset product value threshold, the end point of the first line segment is a first fusion point of the gate area.
9. The device for detecting a cable clamping plate defect for a coal mining machine based on image processing as claimed in claim 8, wherein the processing module is further configured to, if the product value is less than or equal to a preset product value, make an end point of the first line segment not be a welding point of the gate area; on the first line segment, taking a second pixel as a starting point, acquiring a gray difference value of two adjacent pixels, and if the gray difference value is larger than a preset gray difference value, determining a pixel point far away from the second pixel as a second welding point; and processing the first welding point and the second welding point by a least square method, wherein the obtained fitting curve is the gate area.
10. The device for detecting the cable clamp defect for the coal mining machine based on the image processing according to claim 6, wherein the determining module is further configured to determine a line segment uniformity value from the point of the gate P to the edge point of the gate area according to a first average gray value, a second average gray value, a distance value, a gray variance and a minimum positive number, wherein the first average gray value comprises an average gray value of pixel points on a first line segment in the gate area, the second average gray value comprises an average gray value of pixel points on a second line segment in the gate area, the distance value comprises a distance between the first line segment and the second line segment, and the gray variance comprises a gray variance of pixel points on the first line segment; summing all line segment uniformity values in the gate area to determine the uniformity value of the gate area; normalizing the uniform value and the cracking value to obtain a corrected uniform value; if the uniformity value is smaller than a preset uniformity value, the uniformity of the gate area is poor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310679518.1A CN116402827B (en) | 2023-06-09 | 2023-06-09 | Image processing-based cable clamp plate defect detection method and device for coal mining machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310679518.1A CN116402827B (en) | 2023-06-09 | 2023-06-09 | Image processing-based cable clamp plate defect detection method and device for coal mining machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116402827A CN116402827A (en) | 2023-07-07 |
| CN116402827B true CN116402827B (en) | 2023-08-11 |
Family
ID=87014688
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310679518.1A Active CN116402827B (en) | 2023-06-09 | 2023-06-09 | Image processing-based cable clamp plate defect detection method and device for coal mining machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116402827B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116500048B (en) * | 2023-06-28 | 2023-09-15 | 四川联畅信通科技有限公司 | Cable clamp defect detection method, device, equipment and medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101730133B1 (en) * | 2015-12-28 | 2017-04-27 | 동명대학교산학협력단 | Method of inspection for injection molding plastic |
| WO2022042579A1 (en) * | 2020-08-28 | 2022-03-03 | 歌尔股份有限公司 | Lcd screen defect detection method and apparatus |
| CN114565614A (en) * | 2022-05-02 | 2022-05-31 | 武汉华塑亿美工贸有限公司 | Injection molding surface defect analysis method and system based on machine vision |
| CN114998345A (en) * | 2022-08-04 | 2022-09-02 | 南通金丝楠膜材料有限公司 | Injection molding silver thread defect detection method and system based on gray level run matrix |
| CN115294410A (en) * | 2022-10-08 | 2022-11-04 | 加乐新材料(南通)有限公司 | Plastic product molding control method based on pattern recognition |
| CN115861317A (en) * | 2023-02-27 | 2023-03-28 | 深圳市伟利达精密塑胶模具有限公司 | Plastic mold production defect detection method based on machine vision |
| WO2023077404A1 (en) * | 2021-11-05 | 2023-05-11 | 宁德时代新能源科技股份有限公司 | Defect detection method, apparatus and system |
| CN116168003A (en) * | 2023-02-28 | 2023-05-26 | 北京三度镜界科技有限公司 | Artificial intelligence-based injection molding silver streak defect detection method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108387587B (en) * | 2018-01-22 | 2020-07-31 | 京东方科技集团股份有限公司 | Defect detection method and defect detection equipment |
-
2023
- 2023-06-09 CN CN202310679518.1A patent/CN116402827B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101730133B1 (en) * | 2015-12-28 | 2017-04-27 | 동명대학교산학협력단 | Method of inspection for injection molding plastic |
| WO2022042579A1 (en) * | 2020-08-28 | 2022-03-03 | 歌尔股份有限公司 | Lcd screen defect detection method and apparatus |
| WO2023077404A1 (en) * | 2021-11-05 | 2023-05-11 | 宁德时代新能源科技股份有限公司 | Defect detection method, apparatus and system |
| CN114565614A (en) * | 2022-05-02 | 2022-05-31 | 武汉华塑亿美工贸有限公司 | Injection molding surface defect analysis method and system based on machine vision |
| CN114998345A (en) * | 2022-08-04 | 2022-09-02 | 南通金丝楠膜材料有限公司 | Injection molding silver thread defect detection method and system based on gray level run matrix |
| CN115294410A (en) * | 2022-10-08 | 2022-11-04 | 加乐新材料(南通)有限公司 | Plastic product molding control method based on pattern recognition |
| CN115861317A (en) * | 2023-02-27 | 2023-03-28 | 深圳市伟利达精密塑胶模具有限公司 | Plastic mold production defect detection method based on machine vision |
| CN116168003A (en) * | 2023-02-28 | 2023-05-26 | 北京三度镜界科技有限公司 | Artificial intelligence-based injection molding silver streak defect detection method and system |
Non-Patent Citations (1)
| Title |
|---|
| 钢轨表面缺陷图像自适应分割算法;闵永智;岳彪;马宏锋;程天栋;肖本郁;;北京工业大学学报(10);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116402827A (en) | 2023-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116402827B (en) | Image processing-based cable clamp plate defect detection method and device for coal mining machine | |
| CN115082485B (en) | Method and system for detecting bubble defects on surface of injection molding product | |
| CN114972203A (en) | Mechanical part rolling abnormity detection method based on watershed segmentation | |
| CN115131354B (en) | Laboratory plastic film defect detection method based on optical means | |
| CN101224472A (en) | Plate head bending shape detection device based on nearing fared image and method thereof | |
| CN111815555A (en) | Metal additive manufacturing image detection method and device combining anti-neural network with local binary | |
| KR101730133B1 (en) | Method of inspection for injection molding plastic | |
| CN116934740B (en) | Plastic mold surface defect analysis and detection method based on image processing | |
| CN116136393B (en) | Bearing ring inner ring detection system and method | |
| CN113470005A (en) | Welding spot detection device and welding spot detection method for cylindrical battery cap | |
| CN117173632A (en) | Surface bubble evaluation method and system for aluminum template concrete | |
| CN115424008A (en) | Method and system for detecting light modulation and focusing of laser projector production line | |
| CN115880296A (en) | Machine vision-based prefabricated part quality detection method and device | |
| CN115535525A (en) | Conveyor belt longitudinal tearing detection system and method based on image matching | |
| CN109767426B (en) | Shield tunnel water leakage detection method based on image feature recognition | |
| CN117252878B (en) | Image defect detection method of nano-imprint mold | |
| CN114359251A (en) | Automatic identification method for concrete surface damage | |
| CN112837287B (en) | Method and device for extracting defect area of board surface | |
| CN111626104B (en) | Cable hidden trouble point detection method and device based on unmanned aerial vehicle infrared thermal image | |
| CN109389616A (en) | A kind of silk cocoon image background segment method | |
| CN115625317B (en) | Surface water wave optimization processing method and system for die casting regulation and control | |
| CN116228798A (en) | Intelligent iron tower cutting detection method based on machine vision | |
| CN113936291A (en) | Aluminum template quality inspection and recovery method based on machine vision | |
| CN110728679A (en) | Intelligent monitoring method for water leakage of pipe joint | |
| TW201621856A (en) | A method for measuring display module gap width |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |