CN115222729A - Injection molding silver thread defect detection method and system based on gray level run matrix - Google Patents
Injection molding silver thread defect detection method and system based on gray level run matrix Download PDFInfo
- Publication number
- CN115222729A CN115222729A CN202211005960.8A CN202211005960A CN115222729A CN 115222729 A CN115222729 A CN 115222729A CN 202211005960 A CN202211005960 A CN 202211005960A CN 115222729 A CN115222729 A CN 115222729A
- Authority
- CN
- China
- Prior art keywords
- gray
- injection molding
- image
- value
- molding part
- 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.)
- Pending
Links
Images
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
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30116—Casting
-
- 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)
- Injection Moulding Of Plastics Or The Like (AREA)
Abstract
The invention discloses a method and a system for detecting silver thread defects of injection molding parts based on a gray level run matrix, and relates to the field of image processing. The method mainly comprises the following steps: comparing the gray value distribution in the gray level image of the injection molding part with the normal gray value distribution to judge whether the injection molding part has defects or not, obtaining skewness according to the degree that the gray value distribution is in positive skewness distribution to judge whether the defects are silver thread defects or not, if so, determining a gray threshold value according to the skewness and the gray mean value and the gray variance of the normal injection molding part, filling the gray level image by using the pixel value of the normal injection molding part to obtain a minimum circumcircle image, and radially expanding the minimum circumcircle image to obtain an expanded image; and setting the pixel points with the gray values smaller than the gray threshold value in the expanded image to be 0 to obtain a segmented image, and obtaining a long-run high-gray advantage metric value and a short-run low-gray advantage metric value of a gray run matrix in the vertical direction of the segmented image so as to judge the cause of the silver streak defect.
Description
Technical Field
The application relates to the field of image processing, in particular to a method and a system for detecting silver thread defects of injection molding parts based on a gray level run matrix.
Background
The injection molding piece has defects after being molded, the defective finished product can affect the assembly efficiency or the performance of the whole machine, and the product has certain difference with the preset quality standard and even cannot be used. The reason for forming the defects needs to be determined to fundamentally solve the defects of the injection molding piece, so that the production flow is correspondingly controlled, and the reject ratio of products in the subsequent new production process is reduced.
Silver silk thread is a defect that is comparatively common in the injection molding, is usually because different influence factors lead to when the pouring, according to influence factor, the cause of silver silk thread defect mainly divide into following three kinds: insufficient drying, gas mixing, and thermal decomposition. Different factors of influence lead to different silver striae. Therefore, the specific cause of the silver silking needs to be determined, so that the influence factors are determined, and the production flow is controlled.
Disclosure of Invention
In view of the above technical problems, embodiments of the present invention provide a method and a system for detecting a silver streak defect of an injection molding part based on a gray level run-length matrix, which can determine whether an injection molding part has a defect by analyzing a gray level value distribution in a gray level image of the injection molding part to be detected, determine whether the defect is the silver streak defect, and determine a cause of the silver streak defect under the condition that the silver streak defect exists, so that an implementer can conveniently take corresponding measures to control a subsequent production process, thereby improving a qualification rate of the injection molding part in the subsequent production process.
In a first aspect, an embodiment of the present disclosure provides a method for detecting a silver streak defect of an injection molded part based on a gray scale run matrix, including:
and obtaining a surface image of the injection molding to be detected and carrying out graying to obtain a gray image.
And comparing the gray value distribution in the gray image with the gray value distribution in the gray image of the normal injection molding part, judging whether the injection molding part has defects, if so, executing the subsequent steps, otherwise, not executing the subsequent steps.
And obtaining skewness by utilizing the degree of the gray value distribution in the gray image of the injection molding part judged to be in a positive skewness distribution, when the skewness is larger than 0, judging that the defect in the injection molding part judged to be the defect is a silver wire defect, determining a gray threshold value according to the skewness and the gray mean value and the gray variance of the normal injection molding part, and executing subsequent steps, otherwise, not executing the subsequent steps.
And filling the gray level image judged as the silver silk thread defect to obtain a minimum circumcircle image of the gray level image, wherein the pixel value of the filling part is the pixel value of a normal injection molding part, and radially expanding the minimum circumcircle image to obtain an expanded image.
Setting the pixel value of the pixel point with the gray value smaller than the gray threshold value in the expanded image to 0 to obtain a segmented image, obtaining a gray run matrix of the segmented image in the vertical direction, and calculating a long-run high-gray dominance metric value and a short-run low-gray dominance metric value of the gray run matrix.
When the long-run high-gray dominance measure value is larger than a preset first threshold value and the short-run low-gray dominance measure value is smaller than a preset second threshold value, the silver streaks are caused by insufficient drying. And when the short-run low-gray dominance measure value is larger than a preset first threshold value and the long-run high-gray dominance measure value is smaller than a preset second threshold value, the silver wire texture is caused by thermal decomposition. Otherwise, silver streaks are caused by gas incorporation.
In one possible embodiment, calculating the long-run high-gray dominance metric value and the short-run low-gray dominance metric value of the gray-run matrix includes:
wherein G is 1 For long-run high-gray dominance measure, G 2 For short runs of the low gray dominance measure, w st Representing the frequency of t consecutive occurrences of a pixel with a gray level s,
and the integer of 255-Y after being rounded downwards is represented, wherein M is the length of the grayscale image, N is the width of the grayscale image, Y is a grayscale threshold value, and e is a natural constant.
In one possible embodiment, the skewness is obtained according to the degree of the gray value distribution in the gray image in a positive skewness distribution, including
Wherein i max 、i min Maximum and minimum gray values on the gray histogram, respectively, h (i) is the frequency of the gray value i, μ 3 Is the mean value of the frequency of grey values, σ 3 The standard deviation of the frequency of the gray values.
In a possible embodiment, comparing the distribution of gray values in the gray image with the distribution of gray values in the gray image of the normal injection molded part to determine whether the injection molded part has defects includes:
calculating a matching coefficient after the gray image is compared with the gray image of the normal injection molding part:
wherein, mu 1 And σ 1 Mean and variance, mu, of the grey values in the grey scale image of the injection-molded part 2 And σ 2 The mean value and the variance of the surface gray value of the normal injection molding part are respectively, when the matching coefficient Q is smaller than a preset third threshold value, the injection molding part has defects, otherwise, the injection molding part has no defects.
In one possible embodiment, the grayscale threshold is:
wherein, mu 2 And σ 2 The mean and variance of the gray values in the gray image of the normal injection molding part are respectively, and S is skewness.
In one possible embodiment, the method further comprises:
and (4) sampling and inspecting injection molded parts to be detected, judging whether the injection molded parts have the silver thread defects or not respectively, and judging the reasons of the silver thread defects in the injection molded parts with the silver thread defects respectively.
When the proportion of the injection molded part in the injection molded part to be inspected is greater than a preset fourth threshold value due to insufficient drying of the silver threads, the drying condition needs to be changed.
And when the proportion of the injection molded part in the injection molded part which is checked out due to the fact that the silver threads are mixed by the gas is larger than a preset fourth threshold value, the forming condition of the injection molded part is reset or the material used for production is changed.
And when the proportion of the injection molding part in the injection molding part subjected to the sampling inspection, which is caused by thermal decomposition of the silver threads, is greater than a preset fourth threshold value, checking the heating strip, and adjusting the position of the injection nozzle while adjusting the temperature in the mold cavity.
In one possible embodiment, graying a surface image of an injection molded part to obtain a grayscale image comprises:
and taking the maximum value of pixel values of pixel points in the surface image of the injection molding part in three channels of RGB as the gray value of the pixel points in the gray image.
In a second aspect, an embodiment of the present invention provides a system for detecting a silver streak defect of an injection molded part based on a gray level run matrix, including: the injection molding part silver streak defect detection method based on the gray level run matrix is realized by executing a computer program stored in the memory by the processor.
Compared with the prior art, the embodiment of the invention provides a method and a system for detecting the silver thread defect of an injection molding part based on a gray level run matrix, and has the beneficial effects that: whether the injection molding part has defects or not can be determined and judged by analyzing the gray value distribution in the gray image of the injection molding part to be detected, whether the defects are silver thread defects or not can be judged, the cause of the silver thread defects can be judged under the condition that the silver thread defects exist, and an implementer can conveniently take corresponding measures to control the subsequent production process, so that the yield of the injection molding part in the subsequent production process is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for detecting a silver streak defect of an injection molding part based on a gray level run matrix according to an embodiment of the present invention.
FIG. 2 is a schematic representation of an image of the surface of a molded part of the present invention showing three different causes of silver striation defects.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
The terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature; in the description of the present embodiment, "a plurality" means two or more unless otherwise specified.
The embodiment of the invention provides a method for detecting silver thread defects of injection molding parts based on a gray level run matrix, which comprises the following steps of:
and S101, obtaining a surface image of the injection molding piece to be detected, and performing graying to obtain a gray image.
And S102, comparing the gray value distribution in the gray image with the gray value distribution in the gray image of the normal injection molding part, judging whether the injection molding part has defects, if so, executing the subsequent steps, otherwise, not executing the subsequent steps.
S103, obtaining skewness by utilizing the degree that the gray value distribution in the gray image of the injection molding part judged as the defect is in a positive skewness distribution, when the skewness is larger than 0, judging that the defect in the injection molding part judged as the defect is a silver thread defect, determining a gray threshold value according to the skewness and the gray mean value and the gray variance of the normal injection molding part, and executing subsequent steps, otherwise, not executing the subsequent steps.
And S104, filling the gray level image judged as the silver silk line defect to obtain a minimum circumcircle image of the gray level image, wherein the pixel value of the filled part is the pixel value of a normal injection molding part, and radially expanding the minimum circumcircle image to obtain an expanded image.
And S105, setting the pixel value of the pixel point with the gray value smaller than the gray threshold value in the expanded image to 0 to obtain a segmented image, obtaining a gray run matrix of the segmented image in the vertical direction, and calculating a long-run high-gray advantage metric value and a short-run low-gray advantage metric value of the gray run matrix.
And S106, judging the cause of the silver wire line defect according to the values of the long-run high-gray-scale advantage metric value and the short-run low-gray-scale advantage metric value.
Silver thread is a common defect of injection molding, generally caused by different influence factors during casting, and the cause of the silver thread defect is mainly divided into the following three according to the influence factors: insufficient drying, gas mixing, and thermal decomposition.
Fig. 2 shows a schematic view of a surface image of a molded part with three different causes of silver streak defects in an embodiment of the present invention, which will be briefly described below with reference to fig. 2.
It should be noted that the specific reasons for the silver streak defects caused by insufficient drying include: the drying equipment and the drying conditions are not suitable. The surface image is embodied as: the silver stripes are diffused towards the periphery and are linear, and meanwhile, the silver silk stripe part is long in length and bright in brightness.
Specific causes of the silver streak defects caused by the gas incorporation include: the molding conditions, mold conditions, or raw materials do not match. The surface image is embodied as: from the central sprue to the far part, the silver thread is in a continuous sheet shape and occurs randomly, and the brightness of the silver thread part is moderate.
Specific causes of silver streak defects due to thermal decomposition include: uneven heating results from heating the strip, adjusting nozzle, mold cavity temperature, etc. The surface image is embodied as: the silver wire grains are in dense and discrete punctiform shapes taking the central sprue as a circle center, and the brightness of the silver wire grain area is darker.
Further, step S101, obtaining a surface image of the injection molding piece to be detected, and performing graying to obtain a grayscale image. The method specifically comprises the following steps:
firstly, a surface image of an injection molding to be detected is obtained, the obtained surface image is in an RGB format, RGB is a color standard, various colors are obtained through the change of three color channels of red (R), green (G) and blue (B) and the superposition of the three color channels of red (R), green (G) and blue (B), and RGB is the color representing the three color channels of red, green and blue.
Secondly, graying the surface image of the injection molding part to obtain a grayscale image, wherein the grayscale process comprises the following steps: taking the maximum value of pixel values of pixel points in the surface image of the injection molding part in three channels of RGB as the gray value of the pixel points in the gray image
Further, step S102, comparing the gray value distribution in the gray image with the gray value distribution in the gray image of the normal injection molded part, determining whether the injection molded part has a defect, if so, executing the subsequent steps, otherwise, not executing the subsequent steps. The method specifically comprises the following steps:
whether this injection molding has silver silk line defect is judged through the matching degree of the grey value distribution of the injection molding image of collection and the grey value distribution of normal injection molding, at first calculates the matching coefficient between the surface image of injection molding and the surface image of the injection molding under the normal condition, and the concrete process of matching coefficient includes:
It should be noted that the matching coefficient obtained in this embodiment can reflect the matching degree between the injection molded part to be detected and the injection molded part in a normal condition, so that the greater the matching coefficient in this embodiment is, the greater the probability that the injection molded part to be detected is a normal injection molded part is, and when the matching coefficient Q is smaller than a preset third threshold, the injection molded part to be detected has defects, and further analysis is required. Otherwise, there are no defects in the injection molded part.
As an example, the third threshold is preset to be 0.9 in the embodiment of the present invention.
Firstly, collecting a plurality of normal injection molding part surface images, respectively obtaining a gray histogram of the surface image of each normal injection molding part, wherein the gray histogram represents the probability of each gray value appearing on the plurality of images, and calculating the mean value and the variance of sample data by taking all the gray values and the probabilities corresponding to the gray values as the sample data.
Further, step S103, obtaining a skewness by using a degree that the gray value distribution in the gray image of the injection molded part with the defect is judged to be in a positive skewness distribution, when the skewness is greater than 0, the defect in the injection molded part is a silver thread defect, determining a gray threshold value according to the skewness and a gray average value and a gray variance of the normal injection molded part, and executing subsequent steps, otherwise, not executing the subsequent steps. The method specifically comprises the following steps:
firstly, obtaining skewness according to the degree that the gray value distribution in the gray histogram of the gray image is in positive skewness distribution, wherein the calculation process of the skewness comprises the following steps:
The skewness S is used for measuring the asymmetry of the gray distribution in the gray histogram, when the skewness S =0, the data are relatively uniformly distributed on two sides of the average value in the gray histogram, and the distribution of the gray histogram is normal distribution; when the skewness S is less than 0, the distribution of the gray level histogram presents left skewness, and the distribution of the gray level histogram is negative-state distribution; when the skewness S is greater than 0, the distribution of the gray level histogram is rightwards skewed, and the distribution of the gray level histogram is in a positive skew state.
It should be noted that, because the normal injection molding part gray level histogram is normally distributed, the gray level distribution in the gray level histogram is right-biased and is in a normal biased distribution due to the existence of the silver streak defect, and then the bias S is greater than 0. Therefore, in this embodiment, whether the defect is a silver streak defect is determined by skewness. In particular, when the defects of the injection-molded part are silver thread defects, the specific reasons for the existence of the defects need to be further analyzed so as to take corresponding improvement measures.
Further, step S104, filling the gray level image determined as the silver wire streak defect to obtain a minimum circumscribed circle image of the gray level image, wherein a pixel value of the filled portion is a pixel value of a normal injection molding part, and radially expanding the minimum circumscribed circle image to obtain an expanded image. The method specifically comprises the following steps:
in the embodiment of the invention, the silver thread is diverged towards the periphery by taking a central sprue as a circle center, so that the condition of calculating the change of the gray value in the radial direction is obtained, and the calculation in the radial direction can not be directly carried out on a single pixel, so that the image is filled and radially expanded, and the method comprises the following specific steps:
the size of the gray image is M multiplied by N, and the image is filled to have a diameter with the center of the image as the center of a circle
The minimum circumscribed circle image is obtained, and the gray value of the filling part is the mean value of the gray values in the gray histogram of the normal injection molding part.
The obtained minimum circumcircle image is radially expanded, and the radial direction in the circle before expansion can be directly represented by the vertical direction obtained after expansion due to the fact that the radial gray scale condition is mainly calculated in the embodiment and the circular image is radially expanded. Meanwhile, the silver wire grains mainly appear at the pouring gate of the injection molding part, so that the position of the pouring gate approximately coincides with the circle center of the minimum circumscribed circle of the image.
Further, step S105, setting the pixel value of the pixel point with the gray value smaller than the gray threshold value in the expanded image to 0 to obtain a segmented image, obtaining a gray run matrix in the vertical direction of the segmented image, and calculating a long-run high-gray dominance metric value and a short-run low-gray dominance metric value of the gray run matrix. The method specifically comprises the following steps:
first, a simple description is given of a gray level run matrix, which is a matrix formed by lengths of gray level run lines. The specific definition is as follows: the gray level run matrix is recorded as D [ s, t, θ ], wherein s represents a pixel value in an original image, all values of s are gray level numbers of the original image, t represents a length traveled by the pixel value, i.e., t values are s continuously appeared, θ represents a calculated direction, generally 0 degree, 45 degrees, 90 degrees and 135 degrees, and 90 degrees can directly represent a radial direction in a circular image before radial expansion, so the 90 degree direction is adopted for calculation in the embodiment.
Exemplary for a matrix
Calculating a gray level run matrix with theta =0, namely calculating the gray level run matrix according to the horizontal direction, and expressing the gray level run matrix as D [ s, t, theta ]]And D is [3,4,1]Wherein 3 represents the gray scale number [0,1,2](ii) a 4 represents the longest data value, i.e. the diagonal length is 4;1 represents the number of θ, i.e., only θ =0. Counting the number of consecutive occurrences of pixel 0 in the horizontal direction, 0 consecutively occurring 4 times 0,0 and 3 consecutively occurring 0,0 and 2 consecutively occurring 4,0 and 1 consecutively occurring 0, so pixel 0 results in [0,4,0,0]. The result of calculating pixel 1 as above is [0,2,0,0 ]]Thus:
the result calculated as θ =0 degrees is:
the result calculated as θ =45 degrees is:
in the embodiment of the invention, the characteristics of the pixel points belonging to the silver threads need to be judged, so that the gray mean value mu of the normal injection molding part is obtained 2 And the gray-scale variance sigma of the normal injection-molded part 2 And determining the skewness S of the injection molding to be detected to determine the gray threshold value
And then setting the gray value of the pixel point with the gray value smaller than Y to be 0 so as to eliminate the interference of the part of pixel points on the subsequent calculation process.
It should be noted that the silver striations are linear, long in length and bright due to insufficient drying; silver silks caused by gas mixing occur randomly, are in a continuous sheet shape, and have moderate brightness; the silver silks caused by thermal decomposition are in dense and discrete points and are darker in brightness, in the embodiment, it is found by analyzing the expression forms of surface images of different silver silks, the silver silks in different forms can be well represented by using the run gray dominance measure value, and in the embodiment, the run Cheng Huidu dominance measure value comprises a long-run high-gray dominance measure value and a short-run low-gray dominance measure value.
Secondly, obtaining the run gray advantage according to the radial gray run matrix, wherein the calculation process of the run gray advantage metric value comprises the following steps:
G 1 Representing a long-run high-grey dominance measure, G 1 Middle w st s 2 t 2 Giving greater weight to the long-run high gray, as more of the long-run high gray, G 1 The larger the value. G 2 Indicating a short run length of low gray dominance measure, G 2 In
Giving greater weight to short runs of low gray, as more short runs of low gray, G 2 The larger the value.
Alternatively, it can be larger than
Is divided into one level for every 10 gray values, and the total is
The radial gray level run matrix is DS, t, theta]In (1)
θ =1, θ being the radial direction, i.e. the perpendicular direction of the cell. Calculating w in the vertical direction st And expressing the frequency of continuous t times of the pixel points with the gray level s to obtain a radial gray level run matrix. Therefore, the calculation amount can be reduced while the precision is ensured, and the processing efficiency is improved.
Further, step S106, determining the cause of the silver streak defect according to the values of the long-run high gray level dominance measure value and the short-run low gray level dominance measure value. The method specifically comprises the following steps:
the purpose of this step is: and determining the cause of the silver silk thread defect according to the texture run-length gray level advantages, and further controlling the production flow, so that the corresponding strategy is adopted to reduce the failure rate of the subsequent production process.
Specifically, when the long-run high-gray-level advantage metric value is greater than a preset first threshold value and the short-run low-gray-level advantage metric value is less than a preset second threshold value, the surface texture has a long-run high-gray-level advantage, and the silver lines caused by insufficient drying are linear, long in length and bright in brightness, so that the silver lines are caused by insufficient drying.
When the short-run low-gray dominance measure value is larger than a preset first threshold value and the long-run high-gray dominance measure value is smaller than a preset second threshold value, the surface texture of the injection molding part has the short-run low-gray dominance, and the silver wire textures caused by thermal decomposition are in dense and discrete punctiform shapes and are darker in brightness, so the silver wire textures are caused by thermal decomposition.
Otherwise, the surface texture has neither the advantage of long-run high-gray scale nor the advantage of short-run low-gray scale, the silver striae caused by gas mixing occur randomly and are continuous sheets, the brightness is moderate, and the silver striae in the injection molding part are caused by gas mixing.
As an example, in the present embodiment, the first threshold is preset to be 0.8, and the second threshold is preset to be 0.3.
It should be noted that the control of the production flow of injection-molded parts needs to be reflected according to the defect characteristics in a batch of products, when the defect rate exceeds the standard, it indicates that there is a problem in the production flow, and the production flow needs to be correspondingly improved according to the specific defect cause of the injection-molded parts.
Performing spot inspection on injection molded parts to be detected, respectively judging whether the injection molded parts have the silver streak defects, and respectively judging the reasons of the silver streak defects in the injection molded parts with the silver streak defects; when the proportion of the injection molded part in the injection molded part to be inspected is larger than a preset fourth threshold value due to insufficient drying of the silver threads, the drying condition needs to be changed; when the proportion of the injection molded part in the injection molded part to be inspected is larger than a preset fourth threshold value due to the fact that the silver threads are mixed by gas, the forming condition of the injection molded part is reset or materials used for production are changed; and when the proportion of the injection molding part in the injection molding part subjected to the sampling inspection, which is caused by thermal decomposition of the silver threads, is greater than a preset fourth threshold value, checking the heating strip, and adjusting the position of the injection nozzle while adjusting the temperature in the mold cavity.
Based on the same inventive concept as the method, the embodiment further provides a system for detecting the silver thread defects of the injection molding part based on the gray level run matrix, and the system for detecting the silver thread defects of the injection molding part based on the gray level run matrix in the embodiment comprises a memory and a processor, wherein the processor executes a computer program stored in the memory to detect the silver thread defects of the injection molding part as described in the embodiment of the method for detecting the silver thread defects of the injection molding part based on the gray level run matrix.
Because the method for detecting the silver thread defects in the injection molding part has been described in the embodiment of the injection molding part silver thread defect detection method based on the gray level run matrix, details are not repeated here.
In summary, the embodiment of the invention can determine whether the injection molding part has the defect by analyzing the gray value distribution in the gray image of the injection molding part to be detected, and determine whether the defect is the silver streak defect, and can determine the cause of the silver streak defect under the condition that the silver streak defect exists, so that an implementer can conveniently take corresponding measures to control the subsequent production process, thereby improving the qualification rate of the injection molding part in the subsequent production process.
The use of words such as "including," "comprising," "having," and the like in this disclosure is an open-ended term that means "including, but not limited to," and is used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
It should also be noted that the various components or steps may be broken down and/or re-combined in the methods and systems of the present invention. These decompositions and/or recombinations are to be considered equivalents of the present disclosure.
The above-mentioned embodiments are merely examples for clearly illustrating the present invention and do not limit the scope of the present invention. It will be apparent to those skilled in the art that other variations and modifications may be made in the foregoing description, and it is not necessary or necessary to exhaustively enumerate all embodiments herein. All designs identical or similar to the present invention are within the scope of the present invention.
Claims (8)
1. A method for detecting silver thread defects of injection molding parts based on gray level run matrix is characterized by comprising the following steps:
obtaining a surface image of an injection molding to be detected and carrying out graying to obtain a gray image;
comparing the gray value distribution in the gray image with the gray value distribution in the gray image of the normal injection molding part, judging whether the injection molding part has defects, if so, executing the subsequent steps, otherwise, not executing the subsequent steps;
obtaining skewness by utilizing the degree of gray value distribution in the gray image of the injection molding part judged to be in positive skewness distribution, when the skewness is larger than 0, judging that the defect in the injection molding part judged to be the silver wire defect, determining a gray threshold value according to the skewness and the gray mean value and the gray variance of the normal injection molding part, and executing subsequent steps, otherwise, not executing the subsequent steps;
filling the gray level image judged as the silver silk line defect to obtain a minimum circumscribed circle image of the gray level image, wherein the pixel value of the filled part is the pixel value of a normal injection molding part, and radially expanding the minimum circumscribed circle image to obtain an expanded image;
setting the pixel value of a pixel point with the gray value smaller than the gray threshold value in the expanded image to 0 to obtain a segmented image, obtaining a gray run matrix of the segmented image in the vertical direction, and calculating a long-run high-gray dominance metric value and a short-run low-gray dominance metric value of the gray run matrix;
when the long-run high-gray dominance metric value is larger than a preset first threshold value and the short-run low-gray dominance metric value is smaller than a preset second threshold value, the silver silking is caused by insufficient drying; when the short-run low-gray dominance measure value is larger than a preset first threshold value and the long-run high-gray dominance measure value is smaller than a preset second threshold value, the silver silks are caused by thermal decomposition; otherwise, silver streaks are caused by gas incorporation.
2. The injection molding silver thread defect detection method based on the gray run matrix according to claim 1, wherein calculating the long-run high gray dominance measure value and the short-run low gray dominance measure value of the gray run matrix comprises:
wherein G is 1 For long-run high-gray dominance measure, G 2 For short runs of the low gray dominance measure, w st Representing the frequency of t consecutive occurrences of a pixel with a gray level s,
representing integers rounded down to 255-Y, M being said grey scale imageLength, N being the width of the grayscale image, Y being the grayscale threshold, e being a natural constant.
3. The method for detecting the silver thread defect of the injection molding part based on the gray scale run-length matrix as claimed in claim 1, wherein the skewness is obtained according to the degree that the gray scale value distribution in the gray scale image is in a positive skewness distribution, comprising
Wherein i max 、i min Maximum and minimum gray values on the gray histogram, respectively, h (i) is the frequency of the gray value i, μ 3 Is the mean value of the frequency of grey values, σ 3 Is the standard deviation of the frequency of the gray values.
4. The injection molding part silver thread defect detection method based on the gray scale run matrix according to claim 1, wherein the step of comparing the gray value distribution in the gray scale image with the gray value distribution in the gray scale image of a normal injection molding part to judge whether the injection molding part has defects comprises the following steps:
calculating a matching coefficient after comparing the gray image with the gray image of the normal injection molding part:
wherein, mu 1 And σ 1 Mean and variance, mu, of the grey values in the grey scale image of the injection-molded part 2 And σ 2 The mean value and the variance of the surface gray value of the normal injection molding part are respectively, when the matching coefficient Q is smaller than a preset third threshold value, the injection molding part has defects, otherwise, the injection molding part has no defects.
5. The injection molding part silver thread defect detection method based on the gray scale run matrix according to claim 1,the gray level threshold is as follows:
wherein, mu 2 And σ 2 The mean and variance of the gray values in the gray image of the normal injection molding part are respectively, and S is skewness.
6. The injection molding silver streak defect detection method based on the gray scale run matrix according to claim 1, further comprising:
performing spot inspection on injection molded parts to be detected, respectively judging whether the injection molded parts have the silver streak defects, and respectively judging the reasons of the silver streak defects in the injection molded parts with the silver streak defects;
when the proportion of the injection molding part in the injection molding part subjected to the random inspection, which is caused by insufficient drying of the silver threads, is greater than a preset fourth threshold value, the drying condition needs to be changed;
when the proportion of the injection molded part in the injection molded part to be inspected is larger than a preset fourth threshold value due to the fact that the silver threads are mixed by gas, the forming condition of the injection molded part is reset or materials used for production are changed;
and when the proportion of the injection molding part in the injection molding part subjected to the sampling inspection, which is caused by thermal decomposition of the silver threads, is greater than a preset fourth threshold value, checking the heating strip, and adjusting the position of the injection nozzle while adjusting the temperature in the mold cavity.
7. The injection molding part silver thread defect detection method based on the gray scale run matrix as claimed in claim 1, wherein graying the surface image of the injection molding part to obtain a gray scale image comprises:
and taking the maximum value of pixel values of pixel points in the surface image of the injection molding part in three channels of RGB as the gray value of the pixel points in the gray image.
8. The utility model provides an injection molding silver silk thread defect detecting system based on grey scale run matrix, includes: memory and processor, characterized in that the processor executes the computer program stored in the memory to realize the injection molding silver streak defect detection method based on the gray scale run matrix according to any one of claims 1-7.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2022104334415 | 2022-04-24 | ||
| CN202210433441.5A CN114841940A (en) | 2022-04-24 | 2022-04-24 | Injection molding silver thread defect detection method and system based on gray level run matrix |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115222729A true CN115222729A (en) | 2022-10-21 |
Family
ID=82565152
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210433441.5A Withdrawn CN114841940A (en) | 2022-04-24 | 2022-04-24 | Injection molding silver thread defect detection method and system based on gray level run matrix |
| CN202211005960.8A Pending CN115222729A (en) | 2022-04-24 | 2022-08-22 | Injection molding silver thread defect detection method and system based on gray level run matrix |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210433441.5A Withdrawn CN114841940A (en) | 2022-04-24 | 2022-04-24 | Injection molding silver thread defect detection method and system based on gray level run matrix |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN114841940A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116993718A (en) * | 2023-09-25 | 2023-11-03 | 深圳市东陆科技有限公司 | TFT array substrate defect detection method based on machine vision |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN115019159B (en) * | 2022-08-09 | 2022-10-25 | 济宁安泰矿山设备制造有限公司 | Method for rapidly identifying pump bearing fault |
| CN115100608B (en) * | 2022-08-25 | 2022-11-11 | 南通佰瑞利电动工具有限公司 | Electric drill shell glass fiber exposure identification method and system |
| CN115294098B (en) * | 2022-09-26 | 2022-12-16 | 江苏诺阳家居科技有限公司 | Lung shadow degree evaluation system based on X-ray film |
| CN115330762B (en) * | 2022-10-12 | 2023-03-24 | 纵驰电子科技(南通)有限责任公司 | Fuse wire breakage detection method of X-ray image |
| CN115330782B (en) * | 2022-10-13 | 2023-08-08 | 山东仁鸿精密科技有限公司 | Morphology-based defect detection method for injection molding part of ice making box |
| CN115731239B (en) * | 2023-01-06 | 2023-04-11 | 山东建筑大学鉴定检测中心有限公司 | Steel quality detection method |
-
2022
- 2022-04-24 CN CN202210433441.5A patent/CN114841940A/en not_active Withdrawn
- 2022-08-22 CN CN202211005960.8A patent/CN115222729A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116993718A (en) * | 2023-09-25 | 2023-11-03 | 深圳市东陆科技有限公司 | TFT array substrate defect detection method based on machine vision |
| CN116993718B (en) * | 2023-09-25 | 2023-12-22 | 深圳市东陆科技有限公司 | TFT array substrate defect detection method based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114841940A (en) | 2022-08-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115222729A (en) | Injection molding silver thread defect detection method and system based on gray level run matrix | |
| CN115082467B (en) | Building material welding surface defect detection method based on computer vision | |
| CN115082418B (en) | Precise identification method for automobile parts | |
| CN115100221B (en) | Glass defect segmentation method | |
| CN115841493B (en) | Cable detection method based on image processing | |
| CN114998345A (en) | Injection molding silver thread defect detection method and system based on gray level run matrix | |
| CN115578389B (en) | Defect detection method of groove MOS device | |
| CN115375688A (en) | Automatic detection method for belt type conveying equipment | |
| CN110443278B (en) | Method, device and equipment for detecting thickness abnormality of grid line of solar cell | |
| CN115294140A (en) | Hardware part defect detection method and system | |
| CN115953398B (en) | Defect identification method for strip steel surface | |
| CN115272321A (en) | Textile defect detection method based on machine vision | |
| CN116843692B (en) | Regenerated active carbon state detection method based on artificial intelligence | |
| CN115797361B (en) | Aluminum template surface defect detection method | |
| CN115861310B (en) | Method for detecting textile defects on surface of bed sheet | |
| CN115294116A (en) | Method, device and system for evaluating dyeing quality of textile material based on artificial intelligence | |
| CN114140425A (en) | Detection method for wafer back defect | |
| CN115049736A (en) | Method for accurately positioning surface defects of cable | |
| CN115100208A (en) | Film surface defect evaluation method based on histogram and dynamic light source | |
| CN117670879B (en) | Method and system for detecting quality of multi-surface flowers pressed by Fuzhuan tea | |
| CN116168024B (en) | Corrugated paper production quality real-time detection method based on computer vision | |
| CN114972349B (en) | Carrier roller running state detection method and system based on image processing | |
| CN115115635A (en) | Bleaching quality identification method for textile bleaching process | |
| CN116091495A (en) | Accurate detection method for road diseases | |
| CN115880181A (en) | Method, device and terminal for enhancing image contrast |
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 |