CN116993717B - Visual detection method for production quality of heating wire of electronic cigarette - Google Patents

Visual detection method for production quality of heating wire of electronic cigarette Download PDF

Info

Publication number
CN116993717B
CN116993717B CN202311234497.9A CN202311234497A CN116993717B CN 116993717 B CN116993717 B CN 116993717B CN 202311234497 A CN202311234497 A CN 202311234497A CN 116993717 B CN116993717 B CN 116993717B
Authority
CN
China
Prior art keywords
metal wire
coil
metal
wire
electronic cigarette
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
Application number
CN202311234497.9A
Other languages
Chinese (zh)
Other versions
CN116993717A (en
Inventor
钟鸣
郭如云
郭小平
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Wulun Technology Co ltd
Original Assignee
Shenzhen Wulun Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Wulun Technology Co ltd filed Critical Shenzhen Wulun Technology Co ltd
Priority to CN202311234497.9A priority Critical patent/CN116993717B/en
Publication of CN116993717A publication Critical patent/CN116993717A/en
Application granted granted Critical
Publication of CN116993717B publication Critical patent/CN116993717B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/14—Measuring arrangements characterised by the use of optical techniques for measuring distance or clearance between spaced objects or spaced apertures
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge 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
    • G06T7/168—Segmentation; Edge detection involving transform domain methods
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20048—Transform domain processing
    • G06T2207/20061—Hough transform

Abstract

The invention relates to the technical field of image processing, and provides a visual detection method for production quality of an electronic cigarette heating wire, which comprises the following steps: acquiring an electronic cigarette heating wire image; acquiring an edge image of a heating wire of the electronic cigarette; acquiring the gradient direction of the pixel points of the edge image; acquiring a forward coil metal wire region and a reverse coil metal wire region of an image according to the distribution characteristics of metal wires in each region in the heating wire of the electronic cigarette; acquiring the overlapping degree of the metal wire edge and the profile difference degree of the metal wire between the coil metal wire areas; obtaining the metal wire regularity in the heating wire of the electronic cigarette; obtaining the winding distance and the winding quality of the coil metal wire; acquiring a quality detection index of an electronic cigarette heating wire; and finishing visual detection of the production quality of the heating wire of the electronic cigarette according to the quality detection index. The invention aims to solve the problem of precision reduction in the winding quality detection process of the heating wire coil of the electronic cigarette, so as to finely classify the quality of the heating wire of the electronic cigarette.

Description

Visual detection method for production quality of heating wire of electronic cigarette
Technical Field
The invention relates to the technical field of image processing, in particular to a visual detection method for production quality of an electronic cigarette heating wire.
Background
The heating wire is a core component of the electronic cigarette and is a coil made of metal materials, and is mainly used for generating smoke and adjusting the temperature and taste of the smoke. In the production process of the heating wire of the electronic cigarette, due to improper control of the manufacturing process and occurrence of problems of machine equipment, the problem of uneven winding of the coil winding of the heating wire of the electronic cigarette can be caused, and further the problems of unstable resistance value, poor heating effect and short service life of the heating wire of the electronic cigarette are caused, so that the use experience and safety of the electronic cigarette are greatly influenced. Therefore, the production quality of the heating wire of the electronic cigarette needs to be detected to discover and correct potential quality problems in time, and the normal use and the safety of the electronic cigarette are ensured.
The quality detection of the production of the heating wire of the electronic cigarette is generally divided into manual detection and machine vision detection, the machine vision detection is higher in efficiency relative to the manual detection, and the detection speed is faster, but when the computer is utilized for the vision detection, the winding quality precision of the winding wire of the electronic cigarette is reduced due to the staggered winding of the winding wire of the electronic cigarette, so that the quality classification error is caused.
Disclosure of Invention
In order to solve the technical problems, the invention provides a visual detection method for production quality of an electronic cigarette heating wire, which aims to solve the existing problems.
The visual detection method for the production quality of the heating wire of the electronic cigarette adopts the following technical scheme:
the embodiment of the invention provides a visual detection method for the production quality of an electronic cigarette heating wire, which comprises the following steps:
acquiring an electronic cigarette heating wire image;
acquiring an edge image of a heating wire of the electronic cigarette; acquiring the gradient direction of the edge pixel points; acquiring a straight line in an electronic cigarette heating wire edge image through a Hough detection algorithm; obtaining the membership degree of the metal wire according to the relation between the straight lines in the edge image; taking two straight lines with the membership degree higher than a threshold value of the metal wire as a pair of same membership straight lines;
obtaining a metal wire area according to the same membership straight line; counting the number of pixels in each metal line area, and taking the metal line area with the number of pixels smaller than the threshold value of the number of pixels as a coil metal line area; acquiring the overlapping degree of the metal wire edge according to the gradient direction of the pixel points at the edge of the metal wire area of the coil; acquiring a forward coil metal wire area and a reverse coil metal wire area according to the edge distribution characteristics of the coil metal wire area; taking the coil metal wire area with the same direction as the same-direction coil metal wire area; acquiring the metal wire contour difference degree between the metal wire areas of the same-direction coil according to the gradient direction of the pixel points at the edges of the metal wire areas of the same-direction coil; obtaining metal wire regularity according to the metal wire edge overlapping degree and the metal wire contour difference degree of the metal wire region of the homodromous coil;
obtaining the winding distance of the coil metal wires according to the distance between the coil metal wire areas; obtaining the winding quality of the metal wire according to the winding interval of the coil metal wire;
acquiring a quality detection index according to the regularity of the metal wire and the winding quality of the metal wire; and finishing visual detection of the production quality of the heating wire of the electronic cigarette according to the quality detection index.
Preferably, the method for obtaining the membership degree of the metal wire according to the relation between the straight lines in the edge image includes the following specific steps:
calculating the inclination difference according to the angle difference corresponding to the slopes of the two straight lines, wherein the specific expression is as follows:
in the method, in the process of the invention,indicate->Strip, th->Inclination difference of straight line, +.>、/>Indicate->Strip, th->Inclination angle corresponding to the slope of straight line, +.>Representing a preset standard tilt angle greater than zero;
setting a threshold value of inclination differenceThe inclination difference degree is satisfied->Is recorded as a parallel straight line, and the distance between the parallel straight lines is calculated +.>The specific expression is:
in the method, in the process of the invention,、/>respectively represent +.>Strip, th->Cross-sectional distance of straight line->Indicate->Strip and the firstThe average value of the slope of the straight line;
setting a standard distance, calculating a difference value between the distance of the parallel straight line and the standard distance, and forming a negative correlation between the membership degree of the metal wire and the difference value.
Preferably, the method for obtaining the metal wire area according to the same membership straight line comprises the following specific steps:
each pair of the same affiliated straight lines are respectively translated to two sides with the translation distance ofWherein->Is a preset distance; calculating the number of edge pixel points on each translation straight line, and when the number of the pixel points on the straight line is less than +.>Wherein->Stopping translation for the preset number of pixels; the straight line after the translation is stopped is taken as a boundary straight line, and the area surrounded by the two boundary straight lines is taken as a metal line area.
Preferably, the method for obtaining the overlapping degree of the edge of the metal wire according to the gradient direction of the pixel point at the edge of the metal wire area of the coil comprises the following steps:
each coil metal line area corresponds to two edge lines, gradient direction angles of pixel points on the two edge lines of the coil metal line area are respectively recorded as a first edge contour sequence and a second edge contour sequence, and the first edge contour sequence and the second edge contour sequence are calculatedDistance, said->The inverse of the distance is taken as the metal line edge overlap.
Preferably, the method for obtaining the forward and reverse coil metal wire areas according to the edge distribution characteristics of the coil metal wire areas comprises the following steps:
calculating the slope of the edge of the coil metal line area corresponding to the boundary line, if the slope is positive, marking as a positive coil metal line area, and if the slope is negative, marking as a reverse coil metal line area.
Preferably, the gradient direction of the edge pixel points of the metal wire area of the homodromous coil is used for obtaining the metal wire profile difference degree between the metal wire areas of the homodromous coil, and the expression is as follows:
in the method, in the process of the invention,indicate->And->Metal line profile variability between metal line regions of the plurality of coils; />、/>Respectively represent +.>Person, th->The first +.in the gradient direction histogram of the metal line region of the individual coils>Values corresponding to the gradient directions; />Representing the total number of gradient directions of the gradient direction histogram.
Preferably, the metal wire regularity is obtained according to the metal wire edge overlapping degree and the metal wire contour difference degree of the metal wire region of the homodromous coil, and the obtaining method comprises the following steps:
calculating the average value of the overlapping degree of the metal wire edges of all the coil metal wire areas; calculating the product of standard deviation of the profile difference of the metal wire areas of the forward coil and the reverse coil; taking the ratio of the product of the mean value and the standard deviation as the metal wire regularity.
Preferably, the winding pitch of the coil metal wire is obtained according to the distance between the coil metal wire areas, and the expression is:
in the method, in the process of the invention,indicate->Winding spacing of the metal wires of the coils in the same direction; />As a function of the minimum value;is->The corresponding boundary straight line at the left side of the metal line area of each homodromous coil is equal to the +.>The distance between the left boundary straight lines of the metal wire areas of the coils in the same direction; />Is->The corresponding boundary straight line at the left side of the metal line area of each homodromous coil is equal to the +.>The distance between right boundary straight lines of the metal wire areas of the coils in the same direction; />Is->The right corresponding boundary straight line of the metal line area of each homodromous coil is equal to the +.>The distance between the left boundary straight lines of the metal wire areas of the coils in the same direction; />Is->The right corresponding boundary straight line of the metal line area of each homodromous coil is equal to the +.>The distance between right border lines of the metal wire areas of the coils in the same direction.
Preferably, the method for obtaining the winding quality of the metal wire according to the winding interval of the metal wire of the coil specifically comprises the following steps:
and calculating the product of the winding interval variances of the forward coil metal wire and the reverse coil metal wire, and taking the reciprocal of the product as the winding quality of the metal wire.
Preferably, the quality detection index is a product of the wire regularity and the wire winding quality.
The invention has at least the following beneficial effects:
according to the method, the positions of the metal wire areas of the forward coil and the backward coil in the heating wire of the electronic cigarette are accurately positioned according to the edge parallel distribution characteristics of the metal wire areas in the image and the difference between the forward coil and the backward coil, whether the metal wires in the coils are slightly bent and damaged is reflected by means of the regularity and the winding quality of the metal wires of the forward coil and the backward coil, whether the winding interval between the metal wires of each coil is slightly deviated is further reflected, the influence of the alternate distribution of the metal wires of the forward coil and the backward coil on the detection of the slight quality problem of the heating wire of the electronic cigarette is effectively reduced, the production quality of the heating wire of the electronic cigarette is more accurately reflected, and the quality of the heating wire of the electronic cigarette is more finely graded.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a visual detection method for production quality of an electronic cigarette heating wire;
FIG. 2 is an image of a coil wire area provided in one embodiment of the present invention;
fig. 3 is an image of the area of the forward and reverse coil wires provided by an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flowchart of a method for visually detecting production quality of an electronic cigarette heating wire according to an embodiment of the invention is shown, and the method includes the following steps:
step S001: and acquiring an electronic cigarette heating wire image and preprocessing the image to obtain an electronic cigarette heating wire edge image.
The purpose of this embodiment is to perform visual detection on the quality of the heating wire according to the image of the heating wire of the electronic cigarette, so that the image of the heating wire of the electronic cigarette needs to be acquired first. It should be noted that, because the electronic cigarette heating wire is made of metal material, the light source can reflect light, so that the image shot under standard illumination can appear blurred in outline, and the visual detection of the quality of the electronic cigarette heating wire is affected. Therefore, in this embodiment, the parallel backlight source and the CCD camera with the telecentric lens are used to shoot the horizontally placed heating wire of the electronic cigarette, so as to obtain the RGB image of the heating wire of the electronic cigarette.
In the image shooting process, noise generated by factors such as a camera and environment can appear, in order to avoid the influence of the noise on subsequent image processing, median filtering is used for denoising the RGB image of the heating wire of the electronic cigarette, wherein the image denoising processing method is not limited, and an implementer can denoise the image through other methods. And converting the denoised image into a gray image, and recording the gray image as a heating wire gray image. And processing the heating wire gray level image to obtain a heating wire edge image, and obtaining the gradient direction of each pixel point in the heating wire edge image. It should be noted that, the heating wire edge image and the gradient direction of the pixel point of the heating wire edge image can be obtained by the prior art, which is not in the protection scope of the embodiment, and will not be described in detail.
Step S002: according to the edge parallel characteristics of the metal wires in the heating wires of the electronic cigarette, the membership degree of the metal wires is obtained, and the metal wire areas of the positive and negative coils in the image are screened out based on the membership degree of the metal wires.
In the embodiment, the outline of the central part of the coil metal wire is in a straight line shape in the gray level image, the outline of the pin metal wire is also in a straight line shape, and two edges of the metal wire in the electronic cigarette heating wire are provided with parallel characteristics, so that the metal wire area in the heating wire image is obtained.
Firstly, processing the edge image of the heating wire to obtain a straight line and a corresponding straight line equation in the edge image. It should be noted that, the straight line and the corresponding straight line equation in the obtained edge image may be obtained by the prior art, which is not in the protection scope of the present embodiment, and will not be described in detail. Calculating membership degree of metal wires between all straight lines:
wherein:indicate->Strip and->The membership degree of the metal wire between the straight lines; />Representing the degree of tilt difference between the two straight lines; />Representing the parallel distance between the two straight lines; />The standard parallel distance is indicated, i.e. the standard distance between two straight lines belonging to the same wire. />、/>Respectively representing the inclination angles corresponding to the slopes of the two straight lines; />A standard tilt angle greater than zero is indicated, and it should be noted that the value of the standard tilt angle may be implemented byAccording to the situation, in this embodiment +.>The value is +.>。/>、/>Respectively representing the cross-sectional distance of the two straight lines; />A mean value representing the slope of the two lines; />Represents a threshold value of inclination difference, and the inclination difference is +.>It should be noted that the inclination difference threshold value implementation can be set by the user according to the actual situation, in this embodiment +.>The empirical value was taken to be 0.01.
The closer the inclination angles of the two straight lines are, the inclination difference degreeThe smaller the value of (c) is, the greater the likelihood that the two lines are parallel to each other. Parallel distance between these two parallel straight lines +.>Distance parallel to standard->The closer the values of (c) are, the more likely the two lines are to be the lines where the edges of the same metal line are located. Therefore, the metal line membership between these two lines +.>The larger the value of (2) means that the two lines are more likely to be the lines where the two edges of the same wire are located, wherein the wire membership +.>Is 1. Setting a metal line membership threshold value +.>It should be noted that, the metal line membership threshold value implementer can choose according to the actual situation, in this embodiment +.>The empirical value was taken to be 0.9. If the membership threshold of the metal line between two straight lines is +.>The two straight lines are marked as a pair of same membership straight lines.
And obtaining the metal wire area according to the same membership straight line. Specifically, each pair of same membership straight lines are respectively translated to the horizontal directions of two sides, and the distance of each translation is thatWherein->Is a preset distance; after each translation, calculating the number of edge pixel points on the translation straight line, and when the number of pixel points on the translation straight line is less than +.>In the case of->For the preset number of pixel points, a linear translation stopping condition is reached, and the straight line after translation stopping is a boundary straight line; the area surrounded by the two boundary lines is referred to as a metal line area. It should be noted that the practitioner can implement the preset distance and the preset number of pixels according to the actual situationThe conditions are set by themselves, the preset distance chosen in this embodiment +.>1, preset number of pixels +.>3.
In practical situations, the metal wire of the heating wire of the electronic cigarette comprises a pin metal wire and a coil metal wire, and since the length of the pin metal wire in the metal wire area of the heating wire of the electronic cigarette is larger than that of the metal wire in the coil, the metal wire area can be divided into the pin metal wire area and the coil metal wire area according to the characteristic, therefore, the embodiment sets the pixel point number threshold value by acquiring the pixel point number of each metal wire area, takes the metal wire area with the pixel point number smaller than the pixel point number threshold value as the coil metal wire area, and the pixel point number threshold value implementer can set the pixel point number threshold value as 100 according to the practical situations. The method for dividing and extracting the coil metal wire region is not limited in this embodiment, and the practitioner may use other dividing methods to obtain the coil metal wire region. And obtaining a boundary linear equation corresponding to the coil metal line areas, marking the coil metal line areas with positive boundary linear slopes as positive coil metal line areas, and marking the coil metal line areas with negative boundary linear slopes as negative coil metal line areas.
The coil wire regions are shown with reference to fig. 2, and the forward and reverse coil wire regions are shown with reference to fig. 3.
Thus, the forward and reverse coil metal line regions can be obtained. And taking the coil metal wire area with the same direction as the homodromous coil metal wire area.
Step S003: and obtaining the regularity of the metal wire, the winding interval of the metal wire of the coil and the winding quality of the metal wire.
According to the embodiment, through edge line comparison in the coil metal wire area and contour comparison between the areas, regularity and winding quality between the coil metal wires are obtained, whether slight bending and defect of the metal wires in the coil and slight deviation of winding intervals between the metal wires in the coils are reflected, and the influence of alternate distribution of the positive and negative coil metal wires on the detection of the slight quality problem of heating wires of the electronic cigarette is reduced.
Specifically, each coil metal wire area corresponds to two edge wires, the overlapping degree of the metal wire edges is analyzed, and the calculation formula is as follows:
wherein:representing the overlapping degree of the edges of the metal lines; />Respectively representing a first edge profile sequence and a second edge profile sequence in the coil metal wire region; />Expression sequence->、/>Between->Distance. If the metal wire in the coil metal wire area is bent or damaged, the lower the similarity between the two edges of the coil metal wire area is, namely +.>The smaller the value of (2) is, the more the metal line edge overlap ratio is->The smaller the value of (2), wherein>Maximum of (2)The value is 1. It should be noted that->The distance may be obtained by the prior art, and is not within the scope of the present embodiment, and specific details are not described.
The method comprises the steps of obtaining the metal wire profile difference degree between coil metal wire areas, wherein the specific expression is as follows:
wherein:indicate->Person and->Metal line profile variability between metal line regions of the plurality of coils; />、/>Respectively represent +.>Person, th->The first +.in the gradient direction histogram of the metal line region of the individual coils>Values corresponding to the gradient directions; />Representing the total number of gradient directions of the gradient direction histogram. The smaller the difference between the two wire contour histograms, the more similar the contour of the wires representing the two forward coil wire regionsHigh metal line profile variability +.>The smaller the value of (2). It should be noted that, the gradient direction histogram may be obtained by the prior art, which is not in the scope of the present embodiment, and specific details are not described.
Further, in this embodiment, considering that quality problems such as bending and defect may occur on the metal wires of the forward and reverse coils, the metal wire regularity is analyzed, and the specific expression is:
wherein:representing the regularity of the metal wire; />All wire edge overlap representing coil wire areaIs the average value of (2); />All wire profile differences representing the wire region of the forward coil +.>Standard deviation of (2); />All metal line profile differences representing the reverse coil metal line region +.>Standard deviation of (2). />The greater the value of (2), the greater the metal line regularity +.>The larger the value of (2) is, the less the possibility that the metal wire on the heating wire coil of the electronic cigarette is bent and has a defect quality problem is; the closer the profile difference of each wire in the forward coil wire region and the reverse coil wire region is, i.e. +.>And->The smaller the value of (2), the metal line regularity +.>The larger the value of (c) is, the smaller the bending degree of each metal wire on the heating wire coil of the electronic cigarette is.
The present embodiment analyzes the winding pitch of the wire of the forward and reverse coils in consideration of deviation of the coils at the time of winding. Specifically, a pixel point is selected at will in each coil metal wire area, the coil metal wire area with the smallest abscissa of the selected pixel point in the forward and backward coil metal wire areas is respectively marked as a first forward and backward coil metal wire area, and a second forward and backward coil metal wire area, a third forward and backward coil metal wire area are sequentially obtained from small to large according to the value of the abscissa of the selected pixel point, and the forward and backward coil metal wire areas are respectively numbered according to the rule.
In the first placeFor example, the winding pitch +.>：
Wherein:indicate->Winding spacing of the metal wires of the coils in the same direction; />As a function of the minimum value;is->The corresponding boundary straight line at the left side of the metal line area of each homodromous coil is equal to the +.>The distance between the left boundary straight lines of the metal wire areas of the coils in the same direction; />Is->The corresponding boundary straight line at the left side of the metal line area of each homodromous coil is equal to the +.>The distance between right boundary straight lines of the metal wire areas of the coils in the same direction; />Is->The right corresponding boundary straight line of the metal line area of each homodromous coil is equal to the +.>The distance between the left boundary straight lines of the metal wire areas of the coils in the same direction; />Is->The right corresponding boundary straight line of the metal line area of each homodromous coil is equal to the +.>The distance between right border lines of the metal wire areas of the coils in the same direction.
And evaluating the discrete degree of the winding interval by using a quality detection index, wherein the specific expression is as follows:
wherein:the winding quality index of the metal wire of the forward coil in the heating wire coil of the electronic cigarette; />The number of the metal wire areas of the forward coil is represented; />Representation->Winding pitch of the positive coil metal wires; />Indicating this->The average of the individual winding intervals. The smaller the difference between winding pitches of the forward coil metal wires is, the winding quality index +.>The smaller the value of (c) is, the better the winding quality of the metal wire of the forward coil in the coil of the heating wire of the electronic cigarette is.
Calculating the winding quality index of the reverse coil wire using the same method。
Further, in this embodiment, considering that the wires of the forward and reverse coils are wound in a staggered distribution, and the winding quality index of the wires of the forward and reverse coils is combined, the winding quality of the wires is analyzed, and the specific expression is as follows:
wherein:indicating the wire winding quality, < > and->Indicating the winding quality index of the forward coil wire, < >>Indicating the winding quality index of the reverse coil wire. Winding quality index of the forward coil wire>Winding quality index with reverse coil wire>The smaller the value of (2) is, the better the winding quality thereof, i.e., the winding quality of the metal wire +.>The greater the value of (2), wherein>Is 1.
Thus, the coil metal wire regularity and winding quality are obtained.
Step S004: acquiring a quality detection index of an electronic cigarette heating wire; and finishing visual detection of the production quality of the heating wire of the electronic cigarette according to the quality detection index.
Specifically, according to the metal wire regularity of the heating wire coil of the electronic cigaretteAnd wire winding quality->Obtaining the quality detection index of the heating wire of the electronic cigarette>：
Wherein:for normalization function, represent pair->The values in are normalized. Metal wire regularity->Wire winding quality->The larger the value of (2) is, the better the coil quality of the heating wire of the electronic cigarette is, namely the quality detection index of the heating wire of the electronic cigarette is +.>The greater the value of (2).
Dividing the high-quality products, the secondary products and the unqualified products by a plurality of manually detected heating wires of the electronic cigarettes, analyzing according to the process, and calculating quality detection indexes corresponding to images of the divided heating wires of the electronic cigarettesThe quality detection index of the quality product and the secondary product is corresponding to each other>Minimum value +.>、/>As a threshold for dividing these three grades: will->The heating wire of the electronic cigarette is marked as a high-quality product, andthe heating wire of the electronic cigarette is marked as a secondary product, and +.>The electronic cigarette heating wire is marked as an unqualified product, and visual detection of the production quality of the electronic cigarette heating wire is completed. It should be noted that, the threshold value of the quality product, the secondary product and the unqualified product is divided, and the practitioner can combine the quality detection index according to the actual situation>Self-setting, in this embodiment +.>、/>。
In summary, according to the embodiment of the invention, the positions of the metal wire areas of the forward coil and the backward coil in the heating wire of the electronic cigarette are accurately positioned according to the parallel distribution characteristics of the edges of the metal wire areas in the image and the difference between the forward coil and the backward coil, whether the metal wires in the coils are slightly bent and defective is reflected by means of the regularity and winding quality of the metal wires of the forward coil and the backward coil, whether the winding interval between the metal wires of each coil is slightly deviated is further reflected, the influence of the alternate distribution of the metal wires of the forward coil and the backward coil on the detection of the slight quality problem of the heating wire of the electronic cigarette is effectively reduced, the production quality of the heating wire of the electronic cigarette is more accurately reflected, and the quality of the heating wire of the electronic cigarette is more finely graded.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and the same or similar parts of each embodiment are referred to each other, and each embodiment mainly describes differences from other embodiments.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting; the technical solutions described in the foregoing embodiments are modified or some of the technical features are replaced equivalently, so that the essence of the corresponding technical solutions does not deviate from the scope of the technical solutions of the embodiments of the present application, and all the technical solutions are included in the protection scope of the present application.

Claims (6)

1. The visual detection method for the production quality of the heating wire of the electronic cigarette is characterized by comprising the following steps of:
acquiring an electronic cigarette heating wire image;
acquiring an edge image of a heating wire of the electronic cigarette; acquiring the gradient direction of the edge pixel points; acquiring a straight line in an electronic cigarette heating wire edge image through a Hough detection algorithm; obtaining the membership degree of the metal wire according to the relation between the straight lines in the edge image; taking two straight lines with the membership degree higher than a threshold value of the metal wire as a pair of same membership straight lines;
obtaining a metal wire area according to the same membership straight line; counting the number of pixels in each metal line area, and taking the metal line area with the number of pixels smaller than the threshold value of the number of pixels as a coil metal line area; acquiring the overlapping degree of the metal wire edge according to the gradient direction of the pixel points at the edge of the metal wire area of the coil; acquiring a forward coil metal wire area and a reverse coil metal wire area according to the edge distribution characteristics of the coil metal wire area; taking the coil metal wire area with the same direction as the same-direction coil metal wire area; acquiring the metal wire contour difference degree between the metal wire areas of the same-direction coil according to the gradient direction of the pixel points at the edges of the metal wire areas of the same-direction coil; obtaining metal wire regularity according to the metal wire edge overlapping degree and the metal wire contour difference degree of the metal wire region of the homodromous coil;
obtaining the winding distance of the coil metal wires according to the distance between the coil metal wire areas; obtaining the winding quality of the metal wire according to the winding interval of the coil metal wire;
acquiring a quality detection index according to the regularity of the metal wire and the winding quality of the metal wire; completing visual detection of the production quality of the heating wire of the electronic cigarette according to the quality detection index;
the metal line membership degree is obtained according to the relation between all straight lines in the edge image, and the specific method comprises the following steps:
calculating the inclination difference according to the angle difference corresponding to the slopes of the two straight lines, wherein the specific expression is as follows:
in the method, in the process of the invention,indicate->Strip, th->Inclination difference of straight line, +.>、/>Indicate->Strip, firstInclination angle corresponding to the slope of straight line, +.>Representing a preset standard tilt angle greater than zero;
setting a threshold value of inclination differenceThe inclination difference degree is satisfied->Is recorded as a parallel straight line, and the distance between the parallel straight lines is calculated +.>The specific expression is:
in the method, in the process of the invention,、/>respectively represent +.>Strip, th->Cross-sectional distance of straight line->Indicate->Strip and->The average value of the slope of the straight line;
setting a standard distance, and calculating a difference value between the distance of the parallel straight line and the standard distance, wherein the membership degree of the metal wire and the difference value form a negative correlation;
the method for acquiring the overlapping degree of the metal wire edge according to the gradient direction of the pixel point at the edge of the metal wire area of the coil comprises the following steps:
each coil metal line area corresponds to two edge lines, gradient direction angles of pixel points on the two edge lines of the coil metal line area are respectively recorded as a first edge contour sequence and a second edge contour sequence, and the first edge contour sequence and the second edge contour sequence are calculatedDistance, said->The inverse of the distance is used as the overlapping degree of the metal wire edge;
the metal wire contour difference degree between the metal wire areas of the same-direction coil is obtained according to the gradient direction of the pixel points at the edges of the metal wire areas of the same-direction coil, and the expression is as follows:
in the method, in the process of the invention,indicate->And->Metal wire between metal wire regions of the coils in the same directionProfile variability; />、/>Respectively represent +.>Person, th->The first +.in the gradient direction histogram of the metal line region of the individual coils>Values corresponding to the gradient directions; />Representing the total number of gradient directions of the gradient direction histogram;
the metal wire regularity is obtained according to the metal wire edge overlapping degree and the metal wire contour difference degree of the metal wire region of the homodromous coil, and the obtaining method comprises the following steps:
calculating the average value of the overlapping degree of the metal wire edges of all the coil metal wire areas; calculating the product of standard deviation of the profile difference of the metal wire areas of the forward coil and the reverse coil; taking the ratio of the product of the mean value and the standard deviation as the metal wire regularity.
2. The visual inspection method for the production quality of the heating wire of the electronic cigarette according to claim 1, wherein the method for obtaining the metal wire area according to the same membership straight line comprises the following specific steps:
each pair of the same affiliated straight lines are respectively translated to two sides with the translation distance ofWherein->Is a preset distance; calculating the number of edge pixel points on each translation straight line, and when the number of the pixel points on the straight line is less than +.>Wherein->Stopping translation for the preset number of pixels; the straight line after the translation is stopped is taken as a boundary straight line, and the area surrounded by the two boundary straight lines is taken as a metal line area.
3. The visual inspection method for the production quality of the heating wire of the electronic cigarette according to claim 2, wherein the method is characterized in that the forward and reverse coil metal wire areas are obtained according to the edge distribution characteristics of the coil metal wire areas, and comprises the following specific steps:
calculating the slope of the edge of the coil metal line area corresponding to the boundary line, if the slope is positive, marking as a positive coil metal line area, and if the slope is negative, marking as a reverse coil metal line area.
4. The visual inspection method for the production quality of heating wires of an electronic cigarette according to claim 1, wherein the winding interval of the coil metal wires is obtained according to the distance between the coil metal wire areas, and the expression is as follows:
in the method, in the process of the invention,indicate->Winding spacing of the metal wires of the coils in the same direction; />As a function of the minimum value; />Is->The corresponding boundary straight line at the left side of the metal line area of each homodromous coil is equal to the +.>The distance between the left boundary straight lines of the metal wire areas of the coils in the same direction; />Is->The corresponding boundary straight line at the left side of the metal line area of each homodromous coil is equal to the +.>The distance between right boundary straight lines of the metal wire areas of the coils in the same direction; />Is->The right corresponding boundary straight line of the metal line area of each homodromous coil is equal to the +.>The distance between the left boundary straight lines of the metal wire areas of the coils in the same direction; />Is->The right corresponding boundary straight line of the metal line area of each homodromous coil is equal to the +.>The distance between right border lines of the metal wire areas of the coils in the same direction.
5. The visual inspection method for production quality of heating wires of electronic cigarettes according to claim 1, wherein the method is characterized in that the winding quality of the wires is obtained according to the winding interval of the coil wires, and specifically comprises the following steps:
and calculating the product of the winding interval variances of the forward coil metal wire and the reverse coil metal wire, and taking the reciprocal of the product as the winding quality of the metal wire.
6. The visual inspection method for the production quality of heating wires of an electronic cigarette according to claim 1, wherein the quality inspection index is a product of metal wire regularity and metal wire winding quality.
CN202311234497.9A 2023-09-25 2023-09-25 Visual detection method for production quality of heating wire of electronic cigarette Active CN116993717B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311234497.9A CN116993717B (en) 2023-09-25 2023-09-25 Visual detection method for production quality of heating wire of electronic cigarette

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311234497.9A CN116993717B (en) 2023-09-25 2023-09-25 Visual detection method for production quality of heating wire of electronic cigarette

Publications (2)

Publication Number Publication Date
CN116993717A CN116993717A (en) 2023-11-03
CN116993717B true CN116993717B (en) 2024-02-13

Family

ID=88532389

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311234497.9A Active CN116993717B (en) 2023-09-25 2023-09-25 Visual detection method for production quality of heating wire of electronic cigarette

Country Status (1)

Country Link
CN (1) CN116993717B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111489341A (en) * 2020-04-09 2020-08-04 长沙琢冶信息技术有限公司 Method, device, equipment and storage medium for detecting random filament of filament coiling filament
WO2022016328A1 (en) * 2020-07-20 2022-01-27 深圳大学 Metal foreign body detection method and apparatus, and terminal device
CN114926463A (en) * 2022-07-20 2022-08-19 深圳市尹泰明电子有限公司 Production quality detection method suitable for chip circuit board
CN115496753A (en) * 2022-11-16 2022-12-20 山东中烟工业有限责任公司青州卷烟厂 Tobacco shred structure detection method based on machine vision
CN115601364A (en) * 2022-12-14 2023-01-13 惠州威尔高电子有限公司（Cn） Golden finger circuit board detection method based on image analysis

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111489341A (en) * 2020-04-09 2020-08-04 长沙琢冶信息技术有限公司 Method, device, equipment and storage medium for detecting random filament of filament coiling filament
WO2022016328A1 (en) * 2020-07-20 2022-01-27 深圳大学 Metal foreign body detection method and apparatus, and terminal device
CN114926463A (en) * 2022-07-20 2022-08-19 深圳市尹泰明电子有限公司 Production quality detection method suitable for chip circuit board
CN115496753A (en) * 2022-11-16 2022-12-20 山东中烟工业有限责任公司青州卷烟厂 Tobacco shred structure detection method based on machine vision
CN115601364A (en) * 2022-12-14 2023-01-13 惠州威尔高电子有限公司（Cn） Golden finger circuit board detection method based on image analysis

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
分水岭分割的方向迭代后处理算法;杨明辉 等;计算机工程;第32卷(第12期);第8-10页 *
应用多尺度纹理边缘的居民地轮廓提取;王华 等;计算机工程与应用;第45卷(第25期);第157-159页 *

Also Published As

Publication number Publication date
CN116993717A (en) 2023-11-03

Similar Documents

Publication Publication Date Title
CN115222741B (en) Cable surface defect detection method
CN116030060B (en) Plastic particle quality detection method
CN114972343A (en) Method for detecting production abnormity of laser welding product
CN114998341B (en) Gear defect detection method and system based on template matching
CN111062961A (en) Contact lens edge defect detection method based on deep learning
JP2013238449A (en) Crack detection method
CN116843692B (en) Regenerated active carbon state detection method based on artificial intelligence
CN116934763B (en) Medical rubber plug defect detection method based on visual characteristics
CN117237646B (en) PET high-temperature flame-retardant adhesive tape flaw extraction method and system based on image segmentation
CN115115641A (en) Pupil image segmentation method
CN117095004A (en) Excavator walking frame main body welding deformation detection method based on computer vision
CN113012105A (en) Yarn hairiness detection and rating method based on image processing
CN115330796A (en) Copper wire tinning defect identification method
CN116993717B (en) Visual detection method for production quality of heating wire of electronic cigarette
CN117315289B (en) Aeroengine blade contour edge detection method based on image processing
CN116612125B (en) Artificial intelligence-based food and drug capsule quality detection method
CN116630312B (en) Visual detection method for polishing quality of constant-force floating polishing head
CN116721096B (en) New energy harness quality online detection method based on artificial intelligence
CN117808799B (en) Chamfering equipment processing quality detection method based on artificial intelligence
CN117764989B (en) Visual-aided display screen defect detection method
CN117745723B (en) Chip wire bonding quality detection method, system and storage medium
CN117274405B (en) LED lamp working color detection method based on machine vision
CN117495829B (en) Intelligent watch hardware quality detection method
CN117788300B (en) Image enhancement optimization method for ureteroscope lithotripsy
CN115953384B (en) Online detection and prediction method for morphological parameters of tobacco leaves

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