CN114913248B - Self-adaptive control method of corona machine in film production process - Google Patents
Self-adaptive control method of corona machine in film production process Download PDFInfo
- Publication number
- CN114913248B CN114913248B CN202210838471.4A CN202210838471A CN114913248B CN 114913248 B CN114913248 B CN 114913248B CN 202210838471 A CN202210838471 A CN 202210838471A CN 114913248 B CN114913248 B CN 114913248B
- Authority
- CN
- China
- Prior art keywords
- level
- corona
- calculating
- coefficient
- pixel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 31
- 239000011159 matrix material Substances 0.000 claims abstract description 28
- 230000001105 regulatory effect Effects 0.000 claims abstract description 8
- 238000011144 upstream manufacturing Methods 0.000 claims description 19
- 230000007935 neutral effect Effects 0.000 claims description 12
- 230000001276 controlling effect Effects 0.000 claims description 11
- 239000010408 film Substances 0.000 claims 8
- 239000010409 thin film Substances 0.000 claims 2
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 abstract 1
- 238000003851 corona treatment Methods 0.000 description 7
- 239000000654 additive Substances 0.000 description 5
- 230000007547 defect Effects 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 230000015556 catabolic process Effects 0.000 description 3
- 238000012512 characterization method Methods 0.000 description 3
- 238000004806 packaging method and process Methods 0.000 description 3
- 239000002985 plastic film Substances 0.000 description 3
- 229920006255 plastic film Polymers 0.000 description 3
- 239000000853 adhesive Substances 0.000 description 2
- 230000001070 adhesive effect Effects 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 2
- 238000001556 precipitation Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000010410 layer Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- QVRVXSZKCXFBTE-UHFFFAOYSA-N n-[4-(6,7-dimethoxy-3,4-dihydro-1h-isoquinolin-2-yl)butyl]-2-(2-fluoroethoxy)-5-methylbenzamide Chemical compound C1C=2C=C(OC)C(OC)=CC=2CCN1CCCCNC(=O)C1=CC(C)=CC=C1OCCF QVRVXSZKCXFBTE-UHFFFAOYSA-N 0.000 description 1
- 239000005022 packaging material Substances 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0205—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric not using a model or a simulator of the controlled system
- G05B13/024—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric not using a model or a simulator of the controlled system in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention relates to the field of artificial intelligence, in particular to a self-adaptive control method of a corona machine in a film production process. Comprising the following steps: collecting a film gray level image, and calculating a neighborhood difference coefficient of each pixel point; dividing all pixel points into a plurality of levels to establish a neighborhood difference run matrix, and calculating the run Cheng Ji neutrality of each level; calculating the limit trend value of each level and calculating the limit trend duty ratio of each level; calculating a centralized offset coefficient of each level, and calculating the credibility of each level; calculating a corona error coefficient and adjusting the power of the corona machine according to the corona error coefficient value. According to the technical means provided by the invention, the pixel points are classified, so that the corona power can be regulated and controlled according to different characteristics of the film, the accurate corona effect can be obtained, and the corona power can be regulated and controlled accurately.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a self-adaptive control method of a corona machine in a film production process.
Background
With the increasing requirements of human health and environmental protection, the requirements of end consumers on product packaging are also higher and higher, the packaging is required to have better transparent visibility, and meanwhile, the requirements on barrier property, and the like of packaging materials are higher and higher due to the quality guarantee and safety of packages. At present, various plastic films are used as the most important products in the packaging industry, corona treatment is needed in the film production process in order to meet the requirements of printing, adhesiveness and the like, and various quality indexes of the products are influenced under the condition that the degree of the corona treatment is great, so that the degree of the corona is needed to be controlled in the production process to ensure the quality of the products.
Corona treatment of plastic film is an important means for ensuring good printing and adhesion, and the corona treatment can ensure that the film surface has good tension, polar groups can be generated on the film surface layer, intermolecular acting force is enhanced, and the adhesive force of ink and aluminum layers is improved. If the corona treatment is insufficient, the surface tension of the film is insufficient and the precipitation of additives in the film further causes the adhesive force of the combination such as ink to be reduced, but if the corona treatment is too high, the sealing performance of the film is damaged, the barrier property of the film is reduced, the film is aged and crisp, brittle microcracks are generated, corona breakdown is possibly generated, and continuous micropores are formed on the surface of the film.
The existing control of the corona degree of the film generally depends on manual detection, a worker detects the surface tension of the film by using a dyne pen, and then calculates the corona degree, or performs film corona detection by using professional corona value detection equipment, but the subjective and error-prone defects exist in manual surface tension detection, and the professional equipment is time-consuming and labor-consuming to detect, so that the requirement of mass production cannot be met, and therefore, a method for performing corona value regulation and control according to the surface characteristics of a product after corona identification is needed to improve the production efficiency and the product quality of the film product.
Disclosure of Invention
The invention provides a self-adaptive control method of a corona machine in a film production process, which aims to solve the existing problems and comprises the following steps: collecting a film gray level image, and calculating a neighborhood difference coefficient of each pixel point; dividing all pixel points into a plurality of levels to establish a neighborhood difference run matrix, and calculating the run Cheng Ji neutrality of each level; calculating the limit trend value of each level and calculating the limit trend duty ratio of each level; calculating a centralized offset coefficient of each level, and calculating the credibility of each level; and calculating a corona error coefficient, and adjusting the power of the corona machine according to the corona error coefficient value.
According to the technical means provided by the invention, the pixel points are classified, and then the neighborhood difference run matrix is established according to the neighborhood difference coefficient of each pixel point to obtain the gray scale characteristics of each level, so that the corona error coefficient is calculated, the defect influence of the film can be effectively eliminated, the accurate regulation and control of the corona machine power can be performed according to the different characteristics of the pixel points of each level after corona, the production efficiency is ensured, and the production quality is improved.
The invention adopts the following technical scheme that the self-adaptive control method of the corona machine in the film production process comprises the following steps:
and acquiring a film gray level image, and calculating a neighborhood difference coefficient of each pixel point according to the gray level value of each pixel point in the film gray level image.
Dividing all pixel points in the film gray level image into a plurality of levels, establishing a neighborhood difference run matrix according to the neighborhood difference coefficient of the pixel points of each level, and calculating the neutrality of the run Cheng Ji of each level.
And calculating a limit trend value of each level according to the neighborhood difference coefficient of each level pixel point, and calculating a limit trend duty ratio of each level according to the trend value.
The centralized offset coefficient of each level is calculated according to the run centralization of the level, and the credibility of the corresponding level is calculated according to the limit trend duty ratio and the centralized offset coefficient of each level.
And calculating corona error coefficients according to the number of all pixel points in each level and the credibility of each level.
And adjusting the power of the corona machine according to the corona error coefficient value.
Further, the self-adaptive control method of the corona machine in the film production process is characterized in that all pixel points are equally divided into K grades from-1 to 1 according to the values of the neighborhood difference coefficients of all the pixel points.
Further, the self-adaptive control method of the corona machine in the film production process comprises four statistical directions, wherein the four statistical directions comprise four directions with the horizontal direction as a reference direction, and the included angles between the anticlockwise direction and the horizontal direction are respectively 0 degree, 45 degree, 90 degree and 135 degree.
Further, a method for adaptively controlling a corona machine in a film production process, which calculates the neutrality of each level of the upstream Cheng Ji, comprises the following steps:
the run concentration of each level comprises four directions, the run Cheng Ji neutrality of each level in each direction is calculated according to the element value of the corresponding level in the neighborhood difference run matrix of each level in each direction, and the expression is as follows:
wherein ,the position in the neighborhood difference run matrix representing the direction of 0 DEG isThe value of the element at the point is,representing the number of columns of the neighborhood difference run matrix,the neighborhood difference coefficient representing the kth level pixel point is the kth row in the field run matrix, D represents that the neighborhood difference run matrix shares D columns,the upstream Cheng Ji of the kth-stage pixel point in the 0-degree direction is shown;
similarly, run-length concentration in 45 °, 90 °, and 135 ° directions for each level is calculated、And。
further, a method for adaptively controlling a corona machine in a film production process, the method for calculating the limit trend value of each level comprises the following steps:
the limit trend for each level is: the neighborhood difference coefficient of each level pixel point tends to be-1, 0 and a limit trend value when 1, and the expression is:
wherein ,a limit trend value indicating that the pixel point of the kth level tends to be-1,representing a neighborhood difference coefficient of a kth level pixel point;
similarly, the limit trend value of 0 and 1 trend of each level is calculatedAnd。
further, the limit trend ratio of each level is the ratio of each limit trend value of each level to the sum of all limit trend values of the level.
Further, a method for adaptively controlling a corona machine in a film production process, the method for calculating the centralized offset coefficient of each level comprises the following steps:
the concentrated offset coefficient for each level was calculated from the difference in the upstream Cheng Jizhong property of each level in the 45 ° direction and 135 ° direction from the upstream Cheng Ji neutrality of each level in the 0 ° direction, expressed as:
wherein ,represents the concentrated offset coefficient of the kth level pixel,indicating that the kth level pixel is neutral upstream Cheng Ji in the 0 direction,indicating that the kth level pixel is neutral in the 45 deg. direction upstream Cheng Ji,indicating that the kth level pixel is neutral at the run Cheng Ji in the 135 deg. direction.
Further, a method for adaptively controlling a corona machine in a film production process comprises the following steps of:
calculating the credibility of the pixel points of the corresponding level according to the concentrated offset coefficient and the limit trend duty ratio of each level and the run concentration of the level in the 0 DEG direction, wherein the expression is as follows:
wherein ,representing the trustworthiness of the kth level pixel,a limit trend duty cycle representing the limit trend-1 of the kth level pixel,a limit trend duty cycle indicating that the limit of the kth level pixel point tends to be 0,indicating that the kth level pixel point limit tends toThe limit trend of 1 is to the ratio,represents the concentrated offset coefficient of the kth level pixel,indicating that the kth level pixel is neutral upstream Cheng Ji in the 0 deg. direction.
Further, an adaptive control method of a corona machine in a film production process calculates an expression of a corona error coefficient as follows:
wherein ,as a function of the corona error coefficient,representing the number of pixels in the kth level,representing the trustworthiness of the kth level pixel,the neighborhood difference coefficient of the kth level pixel point is represented, K represents the number of all levels of the pixel points in the film gray scale image, and N represents the number of all the pixel points in the film gray scale image.
Further, a method for adaptively controlling the corona machine in the film production process comprises the following steps of:
setting corona error coefficientTolerance range of (2),Corona error coefficient at initial power of corona machineLess thanWhen the corona machine is started, the power of the corona machine is reduced; corona error coefficient at initial power of corona machineGreater thanWhen the corona machine is started, the power of the corona machine is increased; and calculating a corona error coefficient after the power is regulated down or regulated up, judging whether the corona error coefficient after the power is regulated is within a tolerance range, if not, continuing regulation, and if so, stopping regulation within the tolerance range.
The beneficial effects of the invention are as follows: according to the technical means provided by the invention, the pixel points are classified, and then the neighborhood difference run matrix is established according to the neighborhood difference coefficient of each pixel point to obtain the gray scale characteristics of each level, so that the corona error coefficient is calculated, the defect influence of the film can be effectively eliminated, the accurate regulation and control of the corona machine power can be performed according to the different characteristics of the pixel points of each level after corona, the production efficiency is ensured, and the production quality is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a schematic structural diagram of a method for adaptively controlling a corona machine in a film production process according to 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.
As shown in fig. 1, a method for adaptively controlling a corona machine in a film production process according to an embodiment of the present invention is provided, including:
101. and acquiring a film gray level image, and calculating a neighborhood difference coefficient of each pixel point according to the gray level value of each pixel point in the film gray level image.
The invention sets an industrial camera above a conveying roller for discharging of a corona machine, and sets the direction of conveying a film by the conveying roller asThe direction of the contact line between the conveying roller and the film isAnd (3) in the direction, acquiring RGB images on the surface of the plastic film after corona treatment, wherein the RGB images are square images with equal length and width, and graying the square images to acquire film gray images.
The difference of corona degree is characterized in the gray level image of the film, if the corona degree is too large, the film surface can be aged and brittle, cracks can be generated, corona breakdown can also exist, continuous breakdown micropores are generated, the appearance of the corona degree is characterized by continuous near-black pixels, when the corona degree is insufficient, the film surface can also be separated out of internal additives, the appearance of the corona degree is characterized by single near-white pixels, namely, if one point is very different from the neighborhood pixel, and the pixel value of the neighborhood pixel is larger than the pixel value of the point, the pixel point can be a defect point formed by excessive corona. If a point is very different from its neighboring pixel and the pixel of the neighboring pixel is smaller than the pixel value of the point, the pixel may be a defective point due to insufficient corona, and if a point is not very different from its neighboring pixel. Then the pixel is likely to be a normal pixel
For a point on the film gray level image, calculating a neighborhood difference coefficient according to the difference between the gray level of the point and the neighborhood of the point, wherein the formula is as follows:
wherein ,on the film gray scale imageThe neighborhood pixel gray scale average of a point,on the film gray scale imageEvery point is [ ]) Is used for the gray-scale value of (c),is taken as a pointThe value range of the neighborhood difference coefficient is as followsThe closer it is to-1, the closer it is to 1, the more it is to a characterization point of corona shortage, the closer it is to 0, the more it is to a characterization point of normal corona degree.
And calculating the neighborhood difference coefficients of all pixel points on the film gray scale image in the above mode.
102. Dividing all pixel points in the film gray level image into a plurality of levels, establishing a neighborhood difference run matrix according to the neighborhood difference coefficient of the pixel points of each level, and calculating the neutrality of the run Cheng Ji of each level.
And equally dividing all the pixel points into K levels from-1 to 1 according to the values of the neighborhood difference coefficients of all the pixel points. In the invention, the value of K is 10.
The score value ranges are expressed as the respective average value from small to large as the respective level。
The characterization point of corona transition can form tiny cracks on the gray level image, the crack length is irregular, but the extending direction extends along the contact line direction of the film and the conveying roller, which leads to the fact that in the statistics neighborhood difference run matrix, when the statistics angle is 0 degree, the crack length is equal to the sum of the values of the differenceA neighborhood difference run matrix of direction) whose run length is not constant, i.e., run concentration is poor; however, when the statistical angle is the other three directions (45 degrees, 90 degrees and 135 degrees), the running range is very short, namely the running Cheng Ji is strong.
The characteristic points of the corona deficiency are caused by the precipitation of the additives, the distribution of the additives are not adjacent to each other, and the additives cannot be precipitated in a large amount at the same point, so that the running length of the neighborhood difference is concentrated in a shorter length no matter what angle is used for statistics.
The normal corona degree is that the points on the film are normal points, so that the 0-degree and 90-degree runlengths are concentrated at the longest length, and the 45-degree and 135-degree runlengths are uniformly distributed on each runlength.
The neighborhood difference run matrix comprises four statistical directions, wherein the four statistical directions take the horizontal direction as a reference direction, and the included angles between the anticlockwise direction and the horizontal direction are respectively 0 degree, 45 degrees, 90 degrees and 135 degrees.
Constructing a neighborhood difference run matrix under four statistical directions, which are sharedRow of lines'Liu' ofAs the number of levels of the neighborhood difference levels,is the maximum length of the run, which is determined by the specifications of the camera acquisition image. I.e. the acquired image specification isOf (b) a first orderLine 1The element value of the column is neighborhood difference levelRun length ofThe number of times the run of (c) appears on the image.
The run instance means that the points with the same neighborhood difference level continuously appear in the current statistical direction, so that the pixel points with the same neighborhood difference level form a run in the current statistical direction, and the run length is the number of the points.
The method of calculating the per-level run Cheng Ji neutrality is:
the run concentration of each level comprises four directions, the run Cheng Ji neutrality of each level in each direction is calculated according to the element value of the corresponding level in the neighborhood difference run matrix of each level in each direction, and the expression is as follows:
wherein ,the position in the neighborhood difference run matrix representing the direction of 0 DEG isThe value of the element at the point is,representing the number of columns of the neighborhood difference run matrix,the neighborhood difference coefficient representing the kth level pixel point is the kth row in the field run matrix, D represents that the neighborhood difference run matrix shares D columns,the upstream Cheng Ji of the kth-stage pixel point in the 0-degree direction is shown;
similarly, run-length concentration in 45 °, 90 °, and 135 ° directions for each level is calculated、And。
the run concentration、、、All are normalized values.
103. And calculating a limit trend value of each level according to the neighborhood difference coefficient of each level pixel point, and calculating a limit trend duty ratio of each level according to the trend value.
The method for calculating the limit trend value of each level is as follows:
the limit trend for each level is: the neighborhood difference coefficient of each level pixel point tends to be-1, 0 and a limit trend value when 1, and the expression is:
wherein ,a limit trend value indicating that the pixel point of the kth level tends to be-1,representing a neighborhood difference coefficient of a kth level pixel point;
similarly, the limit trend value of 0 and 1 trend of each level is calculatedAnd。
the limit trend ratio of each level is the ratio of each limit trend value of each level to the sum of all limit trend values of the level.
The calculated trend ratio is as follows:
、、respectively representThe trend ratio of the three limit values is 1.
104. And calculating a concentrated offset coefficient of each level according to the run concentration of the level, and calculating the credibility of the pixel points of the corresponding level according to the limit trend duty ratio and the concentrated offset coefficient of each level.
The method for calculating the centralized offset coefficient of each level comprises the following steps:
the concentrated offset coefficient for each level was calculated from the difference in the upstream Cheng Jizhong property of each level in the 45 ° direction and 135 ° direction from the upstream Cheng Ji neutrality of each level in the 0 ° direction, expressed as:
wherein ,represents the concentrated offset coefficient of the kth level pixel,indicating that the kth level pixel is neutral upstream Cheng Ji in the 0 direction,indicating that the kth level pixel is neutral in the 45 deg. direction upstream Cheng Ji,indicating that the kth level pixel is neutral at the run Cheng Ji in the 135 deg. direction.
The method for calculating the credibility of each level comprises the following steps:
calculating the credibility of the pixel points of the corresponding level according to the concentrated offset coefficient and the limit trend duty ratio of each level and the run concentration of the level in the 0 DEG direction, wherein the expression is as follows:
wherein ,representing the trustworthiness of the kth level pixel,a limit trend duty cycle representing the limit trend-1 of the kth level pixel,a limit trend duty cycle indicating that the limit of the kth level pixel point tends to be 0,a limit trend duty cycle representing the limit trend of 1 for the kth level pixel point,represents the concentrated offset coefficient of the kth level pixel,indicating that the kth level pixel is neutral upstream Cheng Ji in the 0 deg. direction.
105. And calculating corona error coefficients according to the number of all pixel points in the film gray level image and the credibility of each level of pixel points.
The expression for calculating the corona error coefficient is:
wherein ,as a function of the corona error coefficient,representing the number of pixels in the kth level,representing the trustworthiness of the kth level pixel,the neighborhood difference coefficient of the kth level pixel point is represented, K represents the number of all levels of the pixel points in the film gray scale image, and N represents the number of all the pixel points in the film gray scale image.
To this end, for a film gray scale image, the corona error coefficient thereof is obtainedThe closer it is to-1 the more corona is presented, and the more corona is presented, if it is to-0 the corona degree is appropriate.
106. And adjusting the power of the corona machine according to the corona error coefficient value.
For the calculated corona error coefficientThe closer it is to-1 the more corona is presented, and if it is to-0 the corona degree is proper, so the corona motor corona power parameter is adjusted as follows:
setting corona error coefficientTolerance range of (2),Obtaining corona error coefficient under initial powerIf (if)Less thanThe corona power is adjusted to be small, ifGreater thanThe corona power is adjusted greatly; if it isCorona errors are considered suitable.
According to the technical means provided by the invention, the pixel points are classified, and then the neighborhood difference run matrix is established according to the neighborhood difference coefficient of each pixel point to obtain the gray scale characteristics of each level, so that the corona error coefficient is calculated, the defect influence of the film can be effectively eliminated, the accurate regulation and control of the corona machine power can be performed according to the different characteristics of the pixel points of each level after corona, the production efficiency is ensured, and the production quality is improved.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (8)
1. The self-adaptive control method of the corona machine in the film production process is characterized by comprising the following steps of:
collecting a film gray level image, and calculating a neighborhood difference coefficient of each pixel point according to the gray level value of each pixel point in the film gray level image;
dividing all pixel points in the film gray level image into a plurality of levels, establishing a neighborhood difference run matrix according to the neighborhood difference coefficient of each level pixel point, and calculating the run Cheng Ji neutrality of each level; wherein, the neighborhood difference run matrix has K rows and D columns, K is the number of the levels of the neighborhood difference levels, and D is the maximum length of the run; the method of calculating the per-level run Cheng Ji neutrality is: the run concentration of each level comprises four directions, the run Cheng Ji neutrality of each level in each direction is calculated according to the element value of the corresponding level in the neighborhood difference run matrix of each level in each direction, and the expression is as follows:
wherein ,the position in the neighborhood difference run matrix representing the direction of 0 DEG isThe value of the element at the point is,representing the number of columns of the neighborhood difference run matrix,neighborhood difference coefficient representing kth level pixel in field run lengthThe kth row in the matrix, D represents the D columns shared by the neighborhood difference run matrices,the upstream Cheng Ji of the kth-stage pixel point in the 0-degree direction is shown; similarly, run-length concentration in 45 °, 90 °, and 135 ° directions for each level is calculated、And;
calculating a limit trend value of each level according to the neighborhood difference coefficient of each level pixel point, and calculating a limit trend duty ratio of each level according to the trend value;
calculating a concentrated offset coefficient of each level according to the run concentration of the level, and calculating the credibility of the corresponding level according to the limit trend occupation ratio and the concentrated offset coefficient of each level;
the concentrated offset coefficient for each level was calculated from the difference in the upstream Cheng Jizhong property of each level in the 45 ° direction and 135 ° direction from the upstream Cheng Ji neutrality of each level in the 0 ° direction, expressed as:
wherein ,represents the concentrated offset coefficient of the kth level pixel,indicating that the kth level pixel is neutral upstream Cheng Ji in the 0 direction,indicating that the kth level pixel is neutral in the 45 deg. direction upstream Cheng Ji,the stream Cheng Ji representing the kth level pixel point in the 135 deg. direction is neutral;
calculating corona error coefficients according to the number of all pixel points in each level and the credibility of each level;
and adjusting the power of the corona machine according to the corona error coefficient value.
2. The method according to claim 1, wherein the number of the pixels is equally divided into K levels from-1 to 1 according to the value of the neighborhood difference coefficient of the pixels.
3. The method according to claim 1, wherein the neighborhood difference run matrix comprises four statistical directions including four directions with horizontal direction as reference direction, and angles between counter-clockwise direction and horizontal direction are respectively 0 °,45 °, 90 ° and 135 °.
4. The method for adaptively controlling a corona machine in a thin film manufacturing process according to claim 1, wherein the method for calculating the limit trend value of each level is as follows:
the limit trend for each level is: the neighborhood difference coefficient of each level pixel point tends to be-1, 0 and a limit trend value when 1, and the expression is:
wherein ,a limit trend value indicating that the pixel point of the kth level tends to be-1,representing a neighborhood difference coefficient of a kth level pixel point;
similarly, the limit trend value of 0 and 1 trend of each level is calculatedAnd。
5. the method of claim 4, wherein the limiting trend ratio of each level is a ratio of each limiting trend value of each level to a sum of all limiting trend values of the level.
6. The method for adaptively controlling a corona machine in a thin film manufacturing process according to claim 1, wherein the method for calculating the reliability of each level is as follows:
calculating the credibility of the pixel points of the corresponding level according to the concentrated offset coefficient and the limit trend duty ratio of each level and the run concentration of the level in the 0 DEG direction, wherein the expression is as follows:
wherein ,representing the trustworthiness of the kth level pixel,a limit trend duty cycle representing the limit trend-1 of the kth level pixel,a limit trend duty cycle indicating that the limit of the kth level pixel point tends to be 0,a limit trend duty cycle representing the limit trend of 1 for the kth level pixel point,represents the concentrated offset coefficient of the kth level pixel,indicating that the kth level pixel is neutral upstream Cheng Ji in the 0 deg. direction.
7. The method for adaptively controlling a corona machine in a film production process according to claim 1, wherein the expression for calculating the corona error coefficient is:
wherein ,as a function of the corona error coefficient,representing the number of pixels in the kth level,representing the trustworthiness of the kth level pixel,the neighborhood difference coefficient of the kth level pixel point is represented, K represents the number of all levels of the pixel points in the film gray scale image, and N represents the number of all the pixel points in the film gray scale image.
8. The method for adaptively controlling a corona machine in a film production process according to claim 1, wherein the method for adjusting the power of the corona machine according to the corona error coefficient value comprises the steps of:
setting corona error coefficientTolerance range of (2),Corona error coefficient at initial power of corona machineLess thanWhen the corona machine is started, the power of the corona machine is reduced; corona error coefficient at initial power of corona machineGreater thanWhen the corona machine is started, the power of the corona machine is increased; and calculating a corona error coefficient after the power is regulated down or regulated up, judging whether the corona error coefficient after the power is regulated is within a tolerance range, if not, continuing regulation, and if so, stopping regulation within the tolerance range.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210838471.4A CN114913248B (en) | 2022-07-18 | 2022-07-18 | Self-adaptive control method of corona machine in film production process |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210838471.4A CN114913248B (en) | 2022-07-18 | 2022-07-18 | Self-adaptive control method of corona machine in film production process |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114913248A CN114913248A (en) | 2022-08-16 |
CN114913248B true CN114913248B (en) | 2023-08-22 |
Family
ID=82771753
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210838471.4A Active CN114913248B (en) | 2022-07-18 | 2022-07-18 | Self-adaptive control method of corona machine in film production process |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114913248B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115131352B (en) * | 2022-08-30 | 2022-11-18 | 南通佰瑞利电动工具有限公司 | Corona effect evaluation method for corona machine |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101615286A (en) * | 2008-06-25 | 2009-12-30 | 中国科学院自动化研究所 | A kind of blind hidden information detection method based on analysis of image gray run-length histogram |
CN113934190A (en) * | 2021-12-17 | 2022-01-14 | 武汉春田纸品包装有限公司 | Corrugated board production quality regulation and control method based on machine vision |
CN114663435A (en) * | 2022-05-25 | 2022-06-24 | 启东新朋莱纺织科技有限公司 | Automatic monitoring method for tension abnormity of textile fabric |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AUPP702498A0 (en) * | 1998-11-09 | 1998-12-03 | Silverbrook Research Pty Ltd | Image creation method and apparatus (ART77) |
CN1312625C (en) * | 2004-07-02 | 2007-04-25 | 清华大学 | Character extracting method from complecate background color image based on run-length adjacent map |
CN101259771A (en) * | 2008-04-17 | 2008-09-10 | 富维薄膜(山东)有限公司 | Single-face matt polyester film and preparation method thereof |
CN102156970B (en) * | 2011-04-14 | 2013-04-10 | 复旦大学 | Fisheye image correction method based on distorted straight slope calculation |
-
2022
- 2022-07-18 CN CN202210838471.4A patent/CN114913248B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101615286A (en) * | 2008-06-25 | 2009-12-30 | 中国科学院自动化研究所 | A kind of blind hidden information detection method based on analysis of image gray run-length histogram |
CN113934190A (en) * | 2021-12-17 | 2022-01-14 | 武汉春田纸品包装有限公司 | Corrugated board production quality regulation and control method based on machine vision |
CN114663435A (en) * | 2022-05-25 | 2022-06-24 | 启东新朋莱纺织科技有限公司 | Automatic monitoring method for tension abnormity of textile fabric |
Also Published As
Publication number | Publication date |
---|---|
CN114913248A (en) | 2022-08-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113934190B (en) | Corrugated board production quality regulation and control method based on machine vision | |
CN114913248B (en) | Self-adaptive control method of corona machine in film production process | |
CN107704801B (en) | Curve lane line detection method based on segmented straight line and segmented Bezier curve | |
CN114757949A (en) | Wire and cable defect detection method and system based on computer vision | |
CN112686890B (en) | Artificial board surface defect detection method based on singular value decomposition | |
CN109035195B (en) | Fabric defect detection method | |
CN107749057B (en) | Method for detecting appearance slurry leakage defect of solar cell | |
CN105046700A (en) | Brightness correction and color classification-based fruit surface defect detection method and system | |
CN115375588B (en) | Power grid transformer fault identification method based on infrared imaging | |
CN114708325A (en) | Method for quickly positioning rubber production problem based on rubber blooming defect | |
CN107103600A (en) | A kind of defects of insulator automatic testing method based on machine learning | |
CN114387274A (en) | Carton defect detection method based on artificial intelligence | |
CN115115625A (en) | Cable production abnormity detection method based on image processing | |
CN113298792A (en) | Belt deviation monitoring and speed regulating control device and method based on AI vision | |
CN110853089A (en) | Multi-factor-based simulation wire icing thickness algorithm | |
CN115330646A (en) | Metal component inspection method for fitness equipment paint spraying process | |
CN111882549B (en) | Automatic detection and identification method and detection and identification system for grayish green tiny foreign fibers | |
CN105208362B (en) | Image colour cast auto-correction method based on gray balance principle | |
CN115256900B (en) | Plastic protection film production parameter control method based on image processing | |
CN115817039B (en) | Gravure printing method based on flying ink inhibition | |
CN109389579A (en) | A kind of combination is entropy constrained anti-light according to interference method with the textile acetes chinensis of standard deviation weighting | |
CN114212452B (en) | Coal flow detection method based on laser assistance and image processing and energy-saving control system | |
CN111079598B (en) | Lane line detection method based on image texture and machine learning | |
CN104729413B (en) | One kind is puted the palms together before one product width online automatic detection and adjusting means and method | |
CN114199127A (en) | Automobile part size detection system and method based on machine vision |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20230718 Address after: 528135 No.1, Row 3, No. 7, No. 105, east side of Industrial Avenue, Leping Town, Sanshui District, Foshan City, Guangdong Province (residence declaration) Applicant after: Foshan Pinte plastic color new material Co.,Ltd. Address before: No. 16, Shidi Avenue, lvsigang Economic Development Zone, Qidong City, Nantong City, Jiangsu Province, 226000 Applicant before: Nantong jinsinan membrane material Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |