CN115035112B - Preparation process control method of environment-friendly electrochemical aluminum laser colorant - Google Patents
Preparation process control method of environment-friendly electrochemical aluminum laser colorant Download PDFInfo
- Publication number
- CN115035112B CN115035112B CN202210957988.5A CN202210957988A CN115035112B CN 115035112 B CN115035112 B CN 115035112B CN 202210957988 A CN202210957988 A CN 202210957988A CN 115035112 B CN115035112 B CN 115035112B
- Authority
- CN
- China
- Prior art keywords
- ridge line
- line segment
- value
- obtaining
- image
- 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 42
- 238000002360 preparation method Methods 0.000 title claims abstract description 33
- 239000003086 colorant Substances 0.000 title claims abstract description 31
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 title claims abstract description 24
- 229910052782 aluminium Inorganic materials 0.000 title claims abstract description 24
- 239000002245 particle Substances 0.000 claims abstract description 142
- 238000004090 dissolution Methods 0.000 claims abstract description 116
- 238000006243 chemical reaction Methods 0.000 claims abstract description 84
- 238000003756 stirring Methods 0.000 claims abstract description 23
- 238000000605 extraction Methods 0.000 claims abstract description 8
- 238000001816 cooling Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 8
- 239000003153 chemical reaction reagent Substances 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims 1
- 230000035484 reaction time Effects 0.000 abstract description 11
- 238000009501 film coating Methods 0.000 abstract description 2
- 239000010409 thin film Substances 0.000 abstract description 2
- 239000002699 waste material Substances 0.000 abstract 1
- 229920005989 resin Polymers 0.000 description 85
- 239000011347 resin Substances 0.000 description 85
- 230000008569 process Effects 0.000 description 12
- XEKOWRVHYACXOJ-UHFFFAOYSA-N Ethyl acetate Chemical compound CCOC(C)=O XEKOWRVHYACXOJ-UHFFFAOYSA-N 0.000 description 9
- 238000004519 manufacturing process Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 8
- 238000010438 heat treatment Methods 0.000 description 7
- 230000011218 segmentation Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 6
- YKYONYBAUNKHLG-UHFFFAOYSA-N propyl acetate Chemical compound CCCOC(C)=O YKYONYBAUNKHLG-UHFFFAOYSA-N 0.000 description 6
- 239000002994 raw material Substances 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 239000000047 product Substances 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- DKPFZGUDAPQIHT-UHFFFAOYSA-N Butyl acetate Natural products CCCCOC(C)=O DKPFZGUDAPQIHT-UHFFFAOYSA-N 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 239000008187 granular material Substances 0.000 description 3
- FUZZWVXGSFPDMH-UHFFFAOYSA-N hexanoic acid Chemical compound CCCCCC(O)=O FUZZWVXGSFPDMH-UHFFFAOYSA-N 0.000 description 3
- 230000001788 irregular Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000000877 morphologic effect Effects 0.000 description 3
- 238000004806 packaging method and process Methods 0.000 description 3
- 239000004640 Melamine resin Substances 0.000 description 2
- 229920000877 Melamine resin Polymers 0.000 description 2
- 239000004411 aluminium Substances 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 239000003822 epoxy resin Substances 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 229920000647 polyepoxide Polymers 0.000 description 2
- 229920005749 polyurethane resin Polymers 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 235000019504 cigarettes Nutrition 0.000 description 1
- 239000002537 cosmetic Substances 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000006740 morphological transformation Effects 0.000 description 1
- 229920006389 polyphenyl polymer Polymers 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002562 thickening agent Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
-
- G06T5/70—
-
- G06T5/90—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- G06T2207/20036—Morphological image processing
Abstract
The invention relates to the technical field of thin film coatings, in particular to a method for controlling the preparation process of an environment-friendly electrochemical aluminum laser colorant, which comprises the following steps: acquiring a solution image after the first stage of the preparation process is finished, and acquiring a connected domain in the image; performing skeleton extraction on the connected domain to obtain a ridge line, acquiring the tangential direction of each pixel point on the ridge line, and clustering the pixel points to obtain a plurality of categories; obtaining the ridge line segment with the largest number of pixel points in each category, recording the ridge line segment as a first-level ridge line segment, obtaining a second-level ridge line segment, and calculating the particle dissolution difficulty according to the ridge line segments of different levels; fitting a curve of the particle dissolution difficulty and time, obtaining a weight based on a peak value of the curve, correcting the particle dissolution difficulty by using the weight, further obtaining time required by reaction according to the corrected curve, and completing stirring in the second stage; and cooling after the stirring of the third stage is finished, so that the preparation is finished. The invention can adaptively set the fixed reaction time of the reaction kettle and avoid resource waste.
Description
Technical Field
The invention relates to the technical field of thin film coatings, in particular to a preparation process control method of an environment-friendly electrochemical aluminum laser colorant.
Background
The environment-friendly electrochemical aluminum colorant can be used for laser exquisite pattern decoration and laser anti-counterfeiting mark manufacture on packaging products such as food packaging, cigarette packet, wine box, cosmetic packaging and the like, and anti-counterfeiting of identity cards, various certificates and various paper currencies.
And in the production preparation process of environment-friendly electrochemical aluminium colorant, mix the stirring reaction preparation through the heating in reation kettle, current reation kettle adopts fixed reaction time parameter control mostly, if the fixed reaction time parameter setting of reation kettle corresponds the production demand reasonable, then can obtain qualified product, but if the fixed reaction time parameter setting of reation kettle is unreasonable for the production demand, then gained colorant goods may not conform to the production requirement. In addition, in the production, if the prepared colorant does not meet the expected production requirement, the fixed reaction time parameters of the reaction kettle need to be adjusted, and a great deal of energy and material resources are consumed at the moment.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a preparation process control method of an environment-friendly electrochemical aluminum laser colorant, which adopts the following technical scheme:
obtaining an internal image of the reaction kettle after the first stage in the preparation process of the environment-friendly type alumite laser colorant, segmenting the image to obtain a solution image, and performing graying processing on the solution image to obtain a solution gray image; acquiring a plurality of connected domains in a solution gray level image;
performing skeleton extraction on the connected domain to obtain a ridge line corresponding to the connected domain, and acquiring the tangential direction of each pixel point on the ridge line; clustering according to the pixel coordinates and the tangential direction of the pixel points to obtain a plurality of categories;
acquiring the ridge line segment with the largest number of pixel points in each category, marking as a first-level ridge line segment, acquiring the minimum distance value between other ridge line segments and the first-level ridge line segment in each category, and marking the ridge line segment with the smallest number of pixel points as a second-level ridge line segment, wherein the minimum distance value is a set numerical value; and so on, stopping until no next level ridge line segment exists; calculating the particle dissolution difficulty according to the grade of the ridge line segment contained in the connected domain, the length of each grade of ridge line segment and the area of the connected domain;
performing curve fitting according to the maximum particle dissolution difficulty and the corresponding time of the solution images at different moments in a set time period, obtaining a weight by using a peak value on a curve obtained by fitting, and correcting the particle dissolution difficulty corresponding to each point on the curve by using the weight; obtaining the time corresponding to the corrected particle dissolution difficulty as a set numerical value, and adjusting the reaction kettle according to the time so as to complete the stirring of the solution in the reaction kettle in the second stage;
adding a reagent into the reaction kettle, and judging according to the viscosity until the third stirring stage of the solution in the reaction kettle is finished; and (3) cooling the reaction kettle until the temperature meets the expected requirement, and finishing the preparation of the environment-friendly electrochemical aluminum laser colorant.
Preferably, the method for obtaining the tangential direction of the pixel point specifically comprises the following steps:
calculating a Hessian matrix of each pixel point on the ridge line image, acquiring a characteristic vector corresponding to the minimum characteristic value in the Hessian matrix, and recording the direction corresponding to the characteristic vector as the tangential direction of the pixel point.
Preferably, the method for obtaining the minimum distance value between the other ridge line segments and the first-level ridge line segment specifically comprises:
and calculating the distance from each pixel point on other ridge line segments to each pixel point on the first-level ridge line segment, and recording the minimum value of the distances as the minimum distance value between other ridge line segments and the first-level ridge line segment.
Preferably, the method for obtaining the dissolution difficulty of the particles specifically comprises the following steps:
wherein, the first and the second end of the pipe are connected with each other,
indicating the dissolution difficulty of the particles corresponding to the connected domain i,
indicates the area of the connected component i,
indicating the length of the mth level ridge line segment in the connected component i,
the number of the indicated levels is the mth level, and M indicates the total number of the levels contained in the connected domain i.
Preferably, the curve fitting according to the maximum particle solubility corresponding to the solution image at different times within the set time period and the corresponding time specifically comprises:
obtaining the maximum particle dissolution difficulty and the corresponding time corresponding to the solution image at the current moment, and further obtaining the maximum particle dissolution difficulty and the corresponding time corresponding to the solution image at different moments in a set time period; and taking the maximum particle solubility as an ordinate value and the time as an abscissa value, and performing curve fitting.
Preferably, the obtaining of the weight by using the peak value on the fitted curve specifically includes:
obtaining the mean value of the dissolution difficulty of all the maximum particles between the f-th peak value and the adjacent peak value, obtaining the dissolution difficulty difference according to the difference value between the maximum dissolution difficulty corresponding to the f-th peak value and the mean value, obtaining the ratio of the dissolution difficulty difference to the mean value, and recording the sum of the numerical value 1 and the ratio as a weight.
The embodiment of the invention at least has the following beneficial effects:
the invention realizes the automatic control of the preparation process of the environment-friendly electrochemical aluminum laser colorant by using the reaction kettle, wherein the dissolving time of the second stage is optimized and adjusted. Specifically, when the second stage begins, carry out morphological analysis to the solution image in the reation kettle, according to the distribution condition of granule in the solution and the length morphological characteristic of granule, the granule that corresponds solution image at different moments dissolves the degree of difficulty and analyzes, concrete condition in the reation kettle has fully been considered, in order to predict the required concrete time of reaction completion, and adjust reation kettle's reaction time, can adjust reation kettle's reaction time in real time according to concrete condition in the reation kettle in the stirring process, the robustness is good, the adaptation scene is more, avoided because unreasonable production substandard product of reation kettle's reaction time setting, cause the problem of wasting of resources. Meanwhile, because fixed dissolving time is not adopted, the dissolving quality is ensured, and the dissolving efficiency is improved. When data prediction is carried out, the sinking and floating conditions of particles are considered, the particle dissolution difficulty is weighted to different degrees, the obtained data prediction result is more accurate, and the accuracy rate of automatically controlling the dissolution time of the reaction kettle is ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flow chart of a method for controlling a preparation process of an environment-friendly alumite laser colorant according to the present invention.
Detailed Description
In order to further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the method for controlling the preparation process of the environment-friendly electrochemical aluminum laser colorant according to the present invention, with reference to the accompanying drawings and preferred embodiments, the specific implementation, structure, characteristics and effects thereof are described in detail. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The specific scheme of the preparation process control method of the environment-friendly electrochemical aluminum laser colorant provided by the invention is specifically described below with reference to the accompanying drawings.
Example (b):
the specific scenes aimed by the invention are as follows: utilize reation kettle to prepare the radium-shine colorant of environment-friendly electrochemical aluminium, wherein, visual reation kettle is chooseed for use to reation kettle, and has agitating unit, heating device and temperature monitoring device in the visual reation kettle.
Referring to fig. 1, a flowchart of steps of a method for controlling a manufacturing process of an environment-friendly electrochemical aluminum laser colorant according to an embodiment of the present invention is shown, wherein the method comprises the following steps:
step one, obtaining an image in a reaction kettle after the first stage in the preparation process of the environment-friendly electrochemical aluminum laser colorant is finished, segmenting the image to obtain a solution image, and performing graying treatment on the solution image to obtain a solution gray image; and acquiring a plurality of connected domains in the solution gray level image.
Firstly, in the first stage of the preparation process of the environment-friendly electrochemical aluminum laser colorant, ethyl acetate, n-propyl acetate and butyl acetate raw materials are required to be added into a reaction kettle, although the addition amounts and the proportion of the ethyl acetate, the n-propyl acetate and the butyl acetate required in different processes are different, the temperature required when the three are stirred and mixed is not changed, namely the temperature is a certain value, and the empirical value is 50 ℃, which represents the optimal temperature required when the three are stirred and mixed. It should be noted that, since it is a known technique to produce a colorant using ethyl acetate, n-propyl acetate, and butyl acetate as raw materials, in this example, the amounts and the ratios of these three components are not studied, and therefore, they will not be described in detail herein, and the practitioner can set them according to the actual conditions and, at the same time, the practitioner can adjust the optimum temperature for the three components when they are stirred and mixed according to the specific circumstances.
Wherein, detect the temperature value of liquid in the reation kettle through temperature sensor, when the temperature value reached 50 degrees centigrade, can reduce heating temperature to 50 degrees centigrade. In addition, in order to raise the temperature rapidly in the temperature raising stage, the heating temperature needs to be set to a temperature value greater than 50 degrees celsius, the heating temperature in the preset temperature raising stage in this embodiment is 65 degrees celsius, and the implementer can adjust the temperature according to the specific implementation scenario. When the temperature value in the reaction kettle reaches 50 ℃, the heating temperature is reduced to 50 ℃ for constant temperature maintenance and post reaction operation.
When the temperature value of the liquid in the reaction kettle reaches the expected heating temperature, the first stage of the preparation process of the environment-friendly electrochemical aluminum laser colorant is completed, and the reaction kettle is controlled to enter the second stage.
Then, it should be noted that, after the temperature value in the reaction kettle reaches the constant temperature, the second stage of the preparation process is entered, the modified polyurethane resin, the epoxy resin and the melamine resin are sequentially added into the reaction kettle, and then the mixture is stirred at constant temperature until the resin is completely dissolved, and then the second stage is shifted to the third stage.
When the solution reaches the standard in the second-stage constant-temperature stirring, the image in the reaction kettle is shot by the camera through the visible window of the visible reaction kettle, and the estimated value of the time required for dissolving in the current second stage can be obtained through the form change of the resin particles. Whether the resin particles can be shot to judge whether the second stage is finished or not is not directly adopted, because the solution color tends to the resin color along with the dissolution of the resin particles, the visual effect of the resin particles in the solution is poor so that the resin particles cannot be accurately identified, the detection effect is poor, the judgment condition for the completion of the dissolution of the resin particles in the reaction kettle cannot be used, and the control of the reaction kettle is finished by estimating the time required by the dissolution.
Because the reaction kettle is a visible reaction kettle, images in the reaction kettle can be obtained through shooting through the observation window, wherein raw materials required by the second stage of the preparation process are added into the reaction kettle from the feeding hole, and the raw materials are modified polyurethane resin, epoxy resin and melamine resin in the embodiment. In this embodiment, only the dissolution time required for the second stage of the preparation process is analyzed, so the addition amount and the ratio of the raw materials used in the preparation process in this embodiment are not described in detail, and the practitioner can set the dissolution time according to a specific scenario.
And finally, fixing a camera on one side of the observation window of the reaction kettle for acquiring images inside the reaction kettle. After the camera acquires the internal image of the reaction kettle, the acquired internal image of the reaction kettle is sent to a data processing center in a wireless or wired mode, and the size of the resin particles in the internal image of the reaction kettle at the current moment is judged by the data processing center.
And after the data processing center obtains the image of the inside of the reaction kettle at the current moment, color segmentation is carried out on the image of the inside of the reaction kettle by utilizing color two classification to obtain a solution part and a reaction kettle part. After color segmentation is calculated, the category with the largest difference value between the two color categories and the color category of the reaction kettle is the category corresponding to the solution, so that a solution part in the image in the reaction kettle is obtained, and the image is segmented to obtain a solution image corresponding to the solution part. The color two classification is a well-known technique, and will not be described herein too much, and the implementer may select other suitable algorithms to perform segmentation processing on the image according to the actual situation, for example, algorithms such as threshold segmentation.
Carrying out graying processing on the solution image, then denoising by adopting Gaussian filtering to obtain a denoised image, and carrying out contrast enhancement on the denoised image by adopting a gray histogram equalization algorithm to obtain a solution gray image. And carrying out gray threshold segmentation processing on the solution gray image by using an Otsu threshold segmentation algorithm, and processing a segmentation result by using a morphological processing means to obtain a binary image of the resin particles in the solution image at the current moment in the reaction kettle. And then, the connected domain analysis is carried out on the binary image, so that the connected domain corresponding to each resin particle in the image can be obtained.
Secondly, skeleton extraction is carried out on the connected domain to obtain a ridge line corresponding to the connected domain, and the tangential direction of each pixel point on the ridge line is obtained; and clustering according to the pixel coordinates and the tangential direction of the pixel points to obtain a plurality of categories.
Specifically, in the stirring and dissolving process of the resin particles in the second stage of the preparation process, if the volume of one resin particle is larger, it indicates that the dissolving effect of the resin particle is not good at the present time, and the longer the dissolving time is required. And the shape of the resin particles has a large influence on the dissolution speed during the dissolution of the resin particles. If the distribution number of the resin particles is large and the resin particles are dispersed, it means that the dissolution rate of the resin particles in the solution is low at that time, and the dissolution time required for the dissolution is longer.
Meanwhile, in the dissolving process of stirring the resin particles, the dissolving time of single particles determines the finally needed dissolving time in the whole reaction kettle. The larger the volume of the resin particles, the longer the time required for dissolution, and the larger the contact area between the resin particles and the solution, the faster the dissolution rate, and the shorter the dissolution time required.
In the preparation process, the volumes of the adopted resin particle raw materials are all relatively close under the common condition, and the condition that the volumes of the resin particles are too large or too small cannot occur. Therefore, in the process of stirring and dissolving the resin particles, the larger the contact area between the resin particles and the solution, the shorter the dissolution time is required. Since some resin particles are partially dissolved with the passage of time, the shape of the resin particles is changed, and the shape of a resin particle may be irregular, have more branches, and be dispersed as a whole, so that the contact area between the resin particle and the solution is still large, the dissolution speed is high, and the required dissolution time is short. If there is a possibility that some resin particles are partially dissolved and still have a regular and aggregated shape, such as a spherical shape or an ellipsoidal shape, the contact area between the resin particles and the solution is small, the dissolution speed is slow, and the dissolution time is long.
The area of each connected domain is obtained, that is, the area of each connected domain is obtained according to the number of the pixel points in the connected domain, and an implementer can also select other methods to calculate the area of the connected domain. And then performing skeleton extraction on each connected domain to obtain a ridge line corresponding to the connected domain, wherein the ridge line can reflect the shape characteristics of the connected domain, and an image formed by the extracted ridge lines is recorded as a ridge line image. The skeleton extraction algorithm is a known technique, and will not be described herein in detail, but only be briefly introduced. Namely, the skeleton extraction is to extract a single-pixel representation form similar to the outline of each connected region according to each connected region so as to facilitate subsequent processing of visual observation images. It can therefore be considered as a pre-processing in image processing, the operation of which is based on a binary map. For better extraction of image skeleton, corresponding preprocessing such as denoising, filtering, morphological transformation, etc. is required to be performed on the image if necessary.
It should be noted that, in this embodiment, it is necessary to acquire a portion where the direction of each ridge line in the ridge line image changes greatly in different positions, and further analyze the shape characteristics of the resin particles. Because the part with the larger direction change of the ridge line means that the shape change of the resin particles is large, the more irregular the resin particles are, the larger the contact area with the solution when the particles are dissolved in the same volume, so that the resin particles have a faster dissolving speed, and the dissolving time of the reaction kettle can be reduced when the dissolution control is carried out.
Calculating a Hessian matrix corresponding to each pixel point in the ridge line image, wherein the Hessian matrix is a two-dimensional matrix, acquiring a minimum characteristic value of the Hessian matrix corresponding to each pixel point, and recording the direction of a characteristic vector corresponding to the minimum characteristic value as the tangential direction of the pixel point. The feature vector corresponding to the minimum feature value is a two-dimensional vector and is used for representing the direction in which the gray gradient of the pixel point on the image is minimum.
The shape characteristics of each resin particle need to be analyzed, and one polyphenyl particle corresponds to one connected domain, so that the ridge lines corresponding to the connected domains are classified by using a DBSCAN clustering algorithm. Specifically, for a ridge line in a connected domain, clustering is performed according to the pixel coordinates of pixel points on each ridge line and the tangential direction of the pixel points, so as to obtain a plurality of categories. The pixel points in one category form a ridge line segment, the positions of the pixel points in each category are close to each other, the tangential directions of the pixel points are approximately the same, the position difference of the pixel coordinates of the pixel points in different categories is large, and the change of the tangential directions is also large.
The direction and the position of each pixel point on the ridge line are clustered to obtain line segments formed by the pixel points in the same direction or in the direction similar to the same direction, and the largest difference between the line segments in different categories except for the position difference is the direction difference. If the number of corresponding connected domain categories in one resin particle is large, the shape of the resin particle is changed greatly, and the resin particle has many direction changes, and the shape may be irregular. Therefore, it is necessary to approximately fit the clustered pixels in each category to a line segment to form a ridge segment, and then analyze the shape characteristics of the resin particles according to the ridge segment.
It should be noted that, in this embodiment, a DBSCAN clustering algorithm is used to cluster the pixel points on the ridge line in the connected domain, where the minimum number of the pixel points is 5, and the neighborhood radius is 3. The minimum number of points and the neighborhood radius are hyper-parameters that need to be set when the DBSCAN algorithm performs clustering, and the above are the empirical values given in this embodiment, and the implementer can adjust the parameters according to specific implementation conditions.
Thirdly, obtaining the ridge line segment with the largest number of pixel points in each category, recording the ridge line segment with the largest number of pixel points as a first-level ridge line segment, obtaining the minimum distance value between other ridge line segments and the first-level ridge line segment in each category, and recording the ridge line segment with the minimum distance value as a set numerical value and the largest number of pixel points as a second-level ridge line segment; and so on until there is no next level ridge line segment, stop; and calculating the particle dissolution difficulty according to the grade of the ridge line segment contained in the connected domain, the length of each grade of ridge line segment and the area of the connected domain.
First, if the shape of one resin particle has many changes in direction or many branches, it is less concentrated, which means that the contact area of the resin particle and the solution is large, the dissolution rate is high, and the dissolution time required is short. If the shape distribution of one resin particle is concentrated and the shape of the resin particle is more regular, it indicates that the contact area of the resin particle and the solution is smaller, the dissolution speed is slower, and the required dissolution time is longer, then the longest ridge line segment in the ridge line segment of the connected domain corresponding to the resin particle is also shorter. Meanwhile, the ridge line segment with the longest length in each direction in each communicating domain needs to be selected for research, because whether the dissolution is finished is judged according to the fact that the largest and longest particles in the solution are completely dissolved.
In the following description, one connected domain corresponds to one resin particle, and the connected domain includes a plurality of classes, and the length of each ridge line segment is calculated in each class, and the ridge line segment having the longest length is referred to as a first-stage ridge line segment. The length of the ridge line segment is represented by counting the number of pixel points contained in the ridge line segment.
And acquiring the minimum distance values between other ridge line segments and the first-level ridge line segment in each category, and recording the ridge line segment with the minimum distance value as a set numerical value and the largest number of pixel points as a second-level ridge line segment. Specifically, the minimum distance value between the other ridge line segments and the first-level ridge line segment is calculated in each category, and the calculation method of the minimum distance value is as follows: for two line segments, the distances from each point on any line segment to each point on the other line segment are respectively calculated, and the minimum value of the distances of the points is recorded as the minimum distance value of the two line segments. And marking the ridge line segment with the minimum distance value of 0 between the other ridge line segments and the first-level ridge line segment as a second-level candidate ridge line segment, and selecting the ridge line segment with the longest length from the second-level candidate ridge line segments as the second-level ridge line segment. The method for obtaining the ridge line segments of the first level is characterized in that the ridge line segments of the second level are connected with the ridge line segments of the first level, the ridge line segments of the third level are connected with the ridge line segments of the second level, and the method for obtaining the ridge line segments of the other levels is analogized until the ridge line segments of the next level are not obtained.
And then, calculating the particle dissolution difficulty according to the grade of the ridge line segment contained in the connected domain, the length of each grade of ridge line segment and the area of the connected domain. In this embodiment, different connected domains are approximately characterized as different resin particles, and the size of the resin particle portion observed by the camera function is characterized by the area of the connected domains, and the larger the size, the greater the difficulty of dissolution of the resin particle, and the longer the dissolution time is required. Based on the above, the area of the connected domain is used as an influence index of the particle dissolution difficulty, and the relationship between the area of the connected domain and the particle dissolution difficulty is in a positive correlation relationship, but the relationship between the area of the connected domain and the particle dissolution difficulty is not a linear relationship.
For any connected domain, the connected domain corresponds to one resin particle and may contain a plurality of categories, and since one ridge line segment is formed by fitting all pixel points in one category, ridge line segments of different levels may belong to different categories. Meanwhile, the directions of the ridge line segments corresponding to different classes are different, so that the directions of the ridge line segments of different classes are different. If the number of the ridge line segments of different levels contained in one connected domain is large, the number of times of change of the direction of the ridge line of the whole connected domain is large, the shapes of the resin particles corresponding to the connected domain are branched more and are less concentrated, the contact area of the resin particles and the solution is large, the dissolving speed is high, the required dissolving time is short, and the difficulty in dissolving the particles corresponding to the resin particles is small. Based on this, the level of the ridge line segment included in the connected domain is used as one of the influence indexes of the particle dissolution difficulty, and the relationship between the level of the ridge line segment included in the connected domain and the particle dissolution difficulty is in a negative correlation relationship.
For a connected domain, the lengths of the ridge line segments in different levels are different, so that the lengths of the ridge line segments extending in different directions are different. The longer the length of the ridge line segment at each level, the less the length of the shape of the resin particle corresponding to the connected domain on the branch is, the more the shape is not concentrated, the larger the contact area with the solution is, the higher the dissolution speed is, and the shorter the dissolution time is, the less difficult the dissolution of the particle corresponding to the resin particle is. Based on the above, the lengths of the ridge line segments of each stage are used as an influence index of the particle dissolution difficulty, and the relationship between the lengths of the ridge line segments of each stage and the particle dissolution difficulty is in a negative correlation relationship, although the relationship between the lengths of the ridge line segments of each stage and the particle dissolution difficulty is in a negative correlation relationship, the relationship is not a linear relationship.
Finally, calculating the particle dissolution difficulty according to the functional relation, and expressing the particle dissolution difficulty as follows by a formula:
wherein, the first and the second end of the pipe are connected with each other,
indicating the particle dissolution difficulty of the resin particles corresponding to the connected domain i,
which represents the area of the connected component i,
indicating the length of the mth level ridge line segment in the connected component i,
the number of the indicated levels is the mth level, and M indicates the total number of the levels contained in the connected domain i.
Performing curve fitting according to the maximum particle dissolution difficulty and the corresponding time of the solution images at different moments in a set time period, obtaining a weight by using a peak value on a curve obtained by fitting, and correcting the particle dissolution difficulty corresponding to each point on the curve by using the weight; and obtaining the time corresponding to the corrected particle dissolution difficulty as a set value, and adjusting the reaction kettle according to the time so as to complete the stirring of the solution in the second-stage reaction kettle.
Firstly, in the above steps, analysis and calculation are performed according to the image inside the reaction kettle at the current moment, the particle dissolution difficulty corresponding to each connected domain on the solution image at the current moment is obtained, and the maximum value of the particle dissolution difficulty is taken as the dissolution difficulty at the current moment. According to the same method, the solution images at different moments in a set time period are obtained for analysis and calculation, and then the dissolving difficulty corresponding to the different moments is obtained. When the time required by the process of stirring and dissolving in the reaction kettle is estimated, the analysis needs to be carried out according to the shape characteristics of the resin particles in a period of stirring and dissolving, and then the time length required by the whole stirring and dissolving process is estimated, so that an implementer needs to set the value of the length of the set time period according to the specific reaction condition.
When the solution in the second stage is stirred, a reaction time is preset in the reaction kettle, but the reaction time may be inaccurate, so that the particle state in the solution needs to be analyzed and judged while the solution is stirred for reaction, the final required specific time is predicted, and then the reaction time of the reaction kettle is adjusted.
And then, acquiring time corresponding to each moment, taking the time as an abscissa value, taking the dissolution difficulty corresponding to each moment as an ordinate value, and performing curve fitting to obtain a dissolution difficulty-time curve. Curve fitting based on coordinate values is a well-known technique and will not be described in greater detail herein. Due to the sinking and floating of the resin particles, a dissolution difficulty-time curve is unstable, and if the dissolution time is directly predicted by polynomial fitting, the obtained dissolution time of the reaction kettle has a large error.
It should be noted that after the particle dissolution difficulty of each resin particle corresponding to each connected domain is obtained, in the stirring and dissolving process of the resin particles, due to the stirring effect of the reaction kettle, some resin particles may be at an upper position in the solution or a lower position in the solution, and the resin particles may not be detected by the camera vision, so that the maximum particle dissolution difficulty corresponding to the solution image at that time is changed, and thus the dissolution difficulty corresponding to different times needs to be corrected.
Finally, although the resin particles have a phenomenon of sinking and floating when dissolved by stirring in the reaction vessel, the dissolution rate of the resin particles corresponding to the maximum particle dissolution difficulty should be kept uniform. Namely, a peak value of the local dissolving difficulty is obtained in the floating process at a certain moment, and after the resin particles are settled, a peak value of the local dissolving difficulty is obtained when the resin particles float. If the resin particle corresponding to the maximum particle dissolution difficulty is broken, so that the particle dissolution difficulty of the resin particle is no longer the dissolution difficulty at the corresponding moment, other resin particles corresponding to the maximum value in comparison with the whole resin particle still have a peak value of local dissolution difficulty in sinking and floating. The local dissolution difficulty can be understood as that the value of a certain section of dissolution difficulty on a curve is large.
And in a set time period after the second stage starts, smoothing and denoising the corresponding dissolution difficulty-time curve, and further adopting a peak point detection algorithm for the smoothed data to obtain the peak value and the peak value coordinates of the dissolution difficulty-time curve. And acquiring the average value of all longitudinal coordinate values between the f-th peak and the adjacent peak, namely the average value of the dissolution difficulty corresponding to all moments. And obtaining the dissolution difficulty difference according to the difference value between the maximum dissolution difficulty corresponding to the f-th peak value and the mean value, wherein the larger the dissolution difficulty difference is, the larger the weight value needing to be adjusted is. And acquiring the ratio of the dissolution difficulty difference to the mean value, and recording the sum of the numerical value 1 and the ratio as a weight.
In this embodiment, the interval between the adjacent peaks around the f-th peak is obtained for calculation, and if the f-th peak is on the boundary, the interval between the single-sided adjacent peaks is taken for analysis and calculation.
And then weighting the dissolution difficulty corresponding to each moment by adopting a least square method according to the weight, carrying out polynomial fitting on the weighted dissolution difficulty-time curve, obtaining a function curve according to the fitting, obtaining a time value t corresponding to the dissolution difficulty of 0, adjusting the dissolution completion time of the reaction kettle to be consistent with the time value t corresponding to the dissolution difficulty of 0, and further completing the stirring of the reaction kettle in the second stage. When the dissolving difficulty is 0, the current solution reaches a complete dissolving state, and the reaction kettle is set in time through the time obtained through fitting. I.e. the set value is 0 in this embodiment.
Adding a reagent into the reaction kettle, and judging according to the viscosity until the third stirring stage of the solution in the reaction kettle is finished; and (4) cooling the reaction kettle until the temperature meets the expected requirement, and finishing the preparation of the environment-friendly electrochemical aluminum laser colorant.
Specifically, after the second stage in the reaction kettle is completed, a thickening agent and a leveling agent are added into the reaction kettle. And then in the process of stirring and mixing, obtaining the current viscosity measurement value in the reaction kettle through an online reaction kettle viscometer, and if the current viscosity measurement value in the reaction kettle is larger than the viscosity measurement result expected to be required by the product, indicating the completion of the third stage in the reaction kettle.
After the third stage is completed in the reaction kettle, the temperature of the reaction kettle needs to be reduced to obtain a final product, the temperature in the reaction kettle is detected by a temperature detector in the reaction kettle, and when the temperature value in the reaction kettle is lower than the expected cooling requirement of the reaction kettle, the current reaction kettle is cooled. Thereby removing the colorant from the reaction kettle and completing the preparation of the environment-friendly electrochemical aluminum laser colorant.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; the modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present application, and are included in the protection scope of the present application.
Claims (5)
1. A preparation process control method of an environment-friendly electrochemical aluminum laser colorant is characterized by comprising the following steps:
obtaining an image of the interior of the reaction kettle after the first stage in the preparation process of the environment-friendly electrochemical aluminum laser colorant is finished, segmenting the image to obtain a solution image, and performing graying processing on the solution image to obtain a solution gray image; acquiring a plurality of connected domains in a solution gray level image; performing skeleton extraction on the connected domain to obtain a ridge line corresponding to the connected domain, and acquiring the tangential direction of each pixel point on the ridge line; clustering according to the pixel coordinates and the tangential direction of the pixel points to obtain a plurality of categories; acquiring the ridge line segment with the largest number of pixel points in each category, marking as a first-level ridge line segment, acquiring the minimum distance value between other ridge line segments and the first-level ridge line segment in each category, and marking the ridge line segment with the smallest number of pixel points as a second-level ridge line segment, wherein the minimum distance value is a set numerical value; and so on, stopping until no next level ridge line segment exists; calculating the particle dissolution difficulty according to the grade of the ridge line segment contained in the connected domain, the length of each grade of ridge line segment and the area of the connected domain; the method for acquiring the particle dissolution difficulty specifically comprises the following steps:
wherein the content of the first and second substances,
indicating the dissolution difficulty of the particles corresponding to the connected domain i,
indicates the area of the connected component i,
representing the length of the M-th level ridge line segment in the connected domain i, wherein M represents the level number as the M-th level, and M represents the total number of levels contained in the connected domain i; according to the maximum particle dissolution difficulty corresponding to the solution images at different moments in a set time periodCarrying out curve fitting with corresponding time, obtaining a weight by utilizing a peak value on a curve obtained by fitting, and correcting the particle dissolution difficulty corresponding to each point on the curve by utilizing the weight; obtaining the time corresponding to the corrected particle dissolution difficulty as a set value, and adjusting the reaction kettle according to the time so as to complete the stirring of the solution in the second-stage reaction kettle; adding a reagent into the reaction kettle, and judging according to the viscosity until the third stirring stage of the solution in the reaction kettle is finished; and (3) cooling the reaction kettle until the temperature meets the expected requirement, and finishing the preparation of the environment-friendly electrochemical aluminum laser colorant.
2. The method for controlling the preparation process of the environment-friendly electrochemical aluminum laser colorant according to claim 1, wherein the method for obtaining the tangential direction of the pixel points comprises: and calculating a Hessian matrix of each pixel point on the ridge line image, acquiring a characteristic vector corresponding to the minimum characteristic value in the Hessian matrix, and recording the direction corresponding to the characteristic vector as the tangential direction of the pixel point.
3. The method for controlling the preparation process of the environment-friendly electrochemical aluminum laser colorant according to claim 1, wherein the method for obtaining the minimum distance value between the other ridge line segments and the first-level ridge line segment specifically comprises: and calculating the distance from each pixel point on other ridge line segments to each pixel point on the first-level ridge line segment, and recording the minimum value of the distances as the minimum distance value between the other ridge line segments and the first-level ridge line segment.
4. The method for controlling the preparation process of the environment-friendly electrochemical aluminum laser colorant according to claim 1, wherein the curve fitting according to the maximum particle solubility and the corresponding time of the solution image at different moments in the set time period specifically comprises: obtaining the maximum particle dissolution difficulty and the corresponding time corresponding to the solution image at the current moment, and further obtaining the maximum particle dissolution difficulty and the corresponding time corresponding to the solution image at different moments in a set time period; and taking the maximum particle solubility as an ordinate value and the time as an abscissa value, and performing curve fitting.
5. The method for controlling the preparation process of the environment-friendly electrochemical aluminum laser colorant according to claim 1, wherein the peak value obtaining weight on the curve obtained by fitting is specifically as follows: obtaining the mean value of the dissolution difficulty of all the maximum particles between the f-th peak value and the adjacent peak value, obtaining the dissolution difficulty difference according to the difference value between the maximum dissolution difficulty corresponding to the f-th peak value and the mean value, obtaining the ratio of the dissolution difficulty difference to the mean value, and recording the sum of the numerical value 1 and the ratio as a weight.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210957988.5A CN115035112B (en) | 2022-08-11 | 2022-08-11 | Preparation process control method of environment-friendly electrochemical aluminum laser colorant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210957988.5A CN115035112B (en) | 2022-08-11 | 2022-08-11 | Preparation process control method of environment-friendly electrochemical aluminum laser colorant |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115035112A CN115035112A (en) | 2022-09-09 |
| CN115035112B true CN115035112B (en) | 2022-11-01 |
Family
ID=83130228
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210957988.5A Active CN115035112B (en) | 2022-08-11 | 2022-08-11 | Preparation process control method of environment-friendly electrochemical aluminum laser colorant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115035112B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115218967B (en) * | 2022-09-21 | 2022-12-13 | 深圳市森盈智能科技有限公司 | Intelligent temperature and moisture control method and intelligent temperature and moisture control device for reagent reaction |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100432789C (en) * | 2004-04-26 | 2008-11-12 | 三菱化学株式会社 | Blue composition for color filter, color filter, and color image display device |
| CN108898080B (en) * | 2018-06-19 | 2022-03-11 | 广西大学 | Ridge line neighborhood evaluation model-based crack connection method |
| CN109269993A (en) * | 2018-10-15 | 2019-01-25 | 广州地理研究所 | A kind of recognition methods of dissolved oxygen, device, storage medium and equipment |
-
2022
- 2022-08-11 CN CN202210957988.5A patent/CN115035112B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115035112A (en) | 2022-09-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106651872B (en) | Pavement crack identification method and system based on Prewitt operator | |
| CN109377485B (en) | Machine vision detection method for instant noodle packaging defects | |
| CN106056118B (en) | A kind of identification method of counting for cell | |
| CN107610114B (en) | optical satellite remote sensing image cloud and snow fog detection method based on support vector machine | |
| CN106875395B (en) | Super-pixel-level SAR image change detection method based on deep neural network | |
| CN104036239B (en) | Fast high-resolution SAR (synthetic aperture radar) image ship detection method based on feature fusion and clustering | |
| CN113538433A (en) | Mechanical casting defect detection method and system based on artificial intelligence | |
| Lin et al. | Bubble size estimation for flotation processes | |
| CN110230978A (en) | A kind of refractory brick geometric dimension measurement method | |
| CN113362306B (en) | Packaged chip defect detection method based on deep learning | |
| CN115035112B (en) | Preparation process control method of environment-friendly electrochemical aluminum laser colorant | |
| CN113554629A (en) | Strip steel red rust defect detection method based on artificial intelligence | |
| CN109242870A (en) | A kind of sea horizon detection method divided based on image with textural characteristics | |
| CN109584253B (en) | Oil abrasive particle image segmentation method | |
| CN107945200A (en) | Image binaryzation dividing method | |
| CN116310845B (en) | Intelligent monitoring system for sewage treatment | |
| CN115049657A (en) | Glass defect detection method | |
| CN115880299A (en) | Quality detection system of lightweight concrete composite self-insulation external wall panel | |
| CN114694144B (en) | Intelligent identification and rating method for non-metallic inclusions in steel based on deep learning | |
| CN109341524A (en) | A kind of optical fiber geometric parameter detection method based on machine vision | |
| CN116524196A (en) | Intelligent power transmission line detection system based on image recognition technology | |
| CN114494318B (en) | Cornea contour extraction method based on cornea dynamic deformation video of Ojin algorithm | |
| CN117253024B (en) | Industrial salt quality inspection control method and system based on machine vision | |
| CN108629776B (en) | Mineral rock granularity detecting system | |
| CN116485801B (en) | Rubber tube quality online detection method and system based on computer 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |