CN112776304A

CN112776304A - Wood-grain-like profile extrusion method and extruder

Info

Publication number: CN112776304A
Application number: CN202110136979.5A
Authority: CN
Inventors: 王晓燕; 王智遵; 王礼木
Original assignee: Foshan Zhongkejigang Technology Co ltd
Current assignee: Foshan Zhongkejigang Technology Co ltd
Priority date: 2021-02-01
Filing date: 2021-02-01
Publication date: 2021-05-11
Anticipated expiration: 2041-02-01
Also published as: CN112776304B

Abstract

The invention relates to the field of profile molding, in particular to a wood grain-like profile extrusion method, which comprises the steps of adjusting extrusion parameters of an extruder by acquiring evaluation conditions of profile scoring, scoring the wood grain effect of the extruded profile by forming a uniform evaluation standard, and adjusting the extrusion parameters of the extruder according to the scoring to ensure that the wood grain effect of the extruded profile is uniform; the invention also provides an extruder to realize the wood grain-like profile extrusion method.

Description

Wood-grain-like profile extrusion method and extruder

Technical Field

The invention relates to the field of profile molding, in particular to a wood-grain-like profile extrusion method and an extruder.

Background

At present, the extrusion process of the wood-like profile comprises the following steps: heating the base material, adding the color master batch and extruding the profile. The wood grain forming effect on the general section is related to the proficiency of personnel operating the extruder, on one hand, the wood grain effect on the same batch of sections is uneven due to different individual operating habits and cognition; on the other hand, the operator skilled in cultivation takes a lot of time, and a lot of resources are also consumed in cultivation.

Meanwhile, in a society developing increasingly, people have higher and higher requirements for home decoration, and particularly reflect the requirements of sectional materials. The demand for wood grain on profiles is increasing, and the current technology has not made much progress in creating profiles of uniform style, mainly in relation to the proficiency of the operator, which results in an imbalance in the supply and demand of profiles of uniform style.

Disclosure of Invention

The present invention is directed to solving at least one of the problems of the prior art or the related art.

In view of the above, an object of the present invention is to provide a method for extruding a wood-like profile.

In view of the above, it is a further object of the present invention to provide an extruder.

In order to achieve the above object, the present invention provides an extrusion method of a wood-like profile, comprising: controlling the extruder to heat the base material; controlling the color master batch to be put into the base material to form a melt, and heating the melt to a preset temperature; extruding a profile; calculating a profile score from the profile; adjusting extrusion parameters of the extruder according to the profile score.

The wood grain-like profile extrusion method provides a profile wood grain adjustment strategy, namely, a uniform evaluation standard is formed, the extruded profile is evaluated, and extrusion parameters of an extruder are correspondingly adjusted according to the evaluation condition, so that a uniform wood grain effect is formed.

In the above technical solution, the calculating the section score according to the section includes: obtaining a reverse color picture of the profile shapeThe three-channel matrix M of the reverse color picture comprises a red channel matrix M_RGreen channel matrix M_GAnd a blue channel matrix M_B(ii) a Respectively calculating the area score A of the reverse color picture according to the three-channel matrix M_pColor score C_pAnd a shape score S_p(ii) a According to the area score A_pThe color score C_pAnd a shape score S_pCalculating the profile score.

According to the technical scheme, the wood grain area, the color depth and the shape of the profile are evaluated through the area score, the color score and the shape score of the reverse color picture, so that the extrusion parameters of the extruder are adjusted according to the evaluation result, and a uniform wood grain effect is formed.

In the above technical solution, the calculating the area score a_pColor score C_pAnd a shape score S_pThe method comprises the following steps: according to the formula

Acquiring a channel matrix M' with the maximum sum of elements in the three-channel matrix; counting the distribution A of all elements in the matrix M'; according to empirical formula

Calculating an area score A_pWhere x is the number of elements larger than the distribution A, μ is the offset coefficient, and σ is the correction coefficient.

The technical scheme provides an evaluation standard of the wood grain area, and the standard is combined with other standards, so that a uniform and effective wood grain evaluation standard is formed.

In the above technical solution, the calculating the area score a_pColor score C_pAnd a shape score S_pThe method comprises the following steps: taking the RGB color value of the complementary color of the color master batch, and selecting a color value C corresponding to a channel matrix M'; computingThe average value A of the elements of the channel matrix M' greater than the distribution A₂(ii) a According to empirical formula

Calculating a color score C_p。

The technical scheme provides an evaluation standard of wood grain color, combines the standard with other standards, and is favorable for forming a uniform and effective wood grain evaluation standard.

In the above technical solution, the distribution is an average value or a median value.

In the technical scheme, the evaluation of the element distribution condition of the matrix M' is formed by selecting the average value or the median value according to the actual condition, and the evaluation standard of effective area score and color score is favorably formed.

In the above technical solution, the calculating the area score a_pColor score C_pAnd a shape score S_pThe method comprises the following steps: constructing a convolutional neural network model, taking a reverse color picture of the shape of the profile as a sample, taking the number of wood grains on the profile as a label, and training the convolutional neural network model; inputting the reverse color picture of the section into the convolutional neural network model, and outputting the convolutional neural network model to obtain a shape score S_p。

The technical scheme provides an evaluation standard of the wood grain shape, and the standard is combined with other standards, so that a uniform and effective wood grain evaluation standard is formed.

In the above technical solution, the calculating the section score according to the area score, the color score, and the shape score specifically includes: the profile score P ═ k₁×A_p+k₂×C_p+k₃×S_pWherein k is₁、k₂And k₃Are all weight coefficients.

The technical scheme provides an evaluation standard combining the area score, the color score and the shape score, and is beneficial to forming a uniform and effective wood grain evaluation standard.

In the above technical solution, the adjusting the extrusion parameters of the extruder according to the profile score includes: computing

And

wherein P is₁As a proportion of the area score, P₂Is the ratio of the color scores, P₃Is the ratio of the shape scores, A_pl is the total score of the area score, C_pl is the total score of the color score, S_pl is the total score of the shape score; when the profile score P is less than a first threshold value, comparing P₁、P₂And P₃If P is the size of₁At minimum, the input speed of the color master batch is increased, if P is₂At a minimum, decreasing the preset temperature if P₃At a minimum, the extrusion rate of the profile is increased, if P₁、P₂If all the color master batches are minimum, the input speed of the color master batch is increased, and if P is minimum₁、P₃If all the color master batches are minimum, the input speed of the color master batch is increased, and if P is minimum₂、P₃If both are minimum, the preset temperature is reduced, if P is₁、P₂And P₃If the color master batch is equal to the color master batch, the input speed of the color master batch is increased; when the profile score P is greater than or equal to a first threshold value and less than a second threshold value, if P₁Greater than P₂Then the current extrusion parameters are maintained, if P is₁Less than or equal to P₂The input speed of the color master batch is increased; comparing P when the profile score P is greater than or equal to a second threshold value₁、P₂And P₃If P is the size of₁At maximum, the input speed of the color master batch is reduced, and if P is higher than P, the color master batch is added₂At maximum, increase the preset temperature, if P₃At maximum, the extrusion speed of the profile is reduced, if P is₁、P₂If the color master batch is maximum, the input speed of the color master batch is reduced, and if P is maximum₁、P₃If the color master batch is maximum, the input speed of the color master batch is reduced, and if P is maximum₂、P₃At maximum, increasing the preset temperature, if P₁、 P₂And P₃And if the color master batch is equal, the input speed of the color master batch is reduced.

In the technical scheme, the extrusion parameters of the extruder are adjusted according to the condition of the evaluation standard, so that the wood grain effect is uniform.

Another aspect of the present invention provides an extruder comprising: the color masterbatch feeding device comprises a bracket, a feeding device and a feeding device, wherein the bracket is provided with a spiral conveyer, the spiral conveyer is provided with a first feeding port, and the first feeding port is used for feeding color masterbatch; a barrel provided with a second input port and a third input port; one end of the spiral conveyer is arranged above the second input port, and the second input port is used for receiving the color master batches conveyed by the spiral conveyer; the third input port is used for inputting the base material; a screw is arranged in the machine barrel and is used for stirring; the extruder further comprises a control module for performing the method of wood grain profile extrusion as claimed in any one of claims 1 to 8.

The extruder can realize the extrusion method in the technical scheme through the matching of all the parts and the control module.

The invention provides a wood grain-like profile extrusion method, which comprises the steps of adjusting the extrusion parameters of an extruder by obtaining the evaluation condition of profile score, scoring the wood grain effect of the extruded profile by forming a uniform evaluation standard, and adjusting the extrusion parameters of the extruder according to the score to ensure that the wood grain effect of the extruded profile is uniform; the invention also provides an extruder to realize the wood grain-like profile extrusion method.

Drawings

FIG. 1 illustrates a flow diagram of a simulated wood grain profile extrusion method according to one embodiment of the present invention;

FIG. 2 illustrates a flow chart for profile score calculation for a simulated wood grain profile extrusion method according to one embodiment of the present invention;

FIG. 3 illustrates a flow chart of area score calculation for a simulated wood grain profile extrusion method according to one embodiment of the present invention;

FIG. 4 illustrates a flow chart of color score calculation for a simulated wood grain profile extrusion method according to one embodiment of the present invention;

FIG. 5 illustrates a flow chart of a shape score calculation for a simulated wood grain profile extrusion method according to one embodiment of the present invention;

FIG. 6 illustrates a flow diagram of a profile score analysis of a simulated wood grain profile extrusion method according to one embodiment of the present invention;

FIG. 7 shows a schematic structural view of an extruder according to one embodiment of the present invention;

the relationship between the reference numbers and the names of the components is shown in the following table:

reference numerals	Name of component	Reference numerals	Name of component
				1	Support frame	4	Barrel
2	Screw conveyer	5	Second inlet
				3	The first inlet	6	Third inlet

Detailed Description

So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments thereof which are illustrated in the appended drawings. It should be noted that, in the present application, the embodiments and features of the embodiments may be combined with each other without conflict.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.

Before describing the related embodiments of the present invention, it is necessary to describe the present invention that the formation of uniform wood grains does not mean the formation of the same wood grains, which is impractical due to the characteristics of an extruder itself, in order to adjust the area, color and shape of profiles to make the wood grain styles of different profiles uniform, as well as to form new images by inheriting the styles of existing images, as the effect of style migration algorithms in deep learning, and in order to form more various profiles according to the simulated wood grain extrusion method.

The reverse color picture is a picture in which the sum of the RGB color value of a point on the picture and the RGB color value of the corresponding point on the original picture is (255, 255, 255).

Some embodiments according to the invention are described below with reference to fig. 1 to 7.

The invention provides a wood-like profile extrusion method, as shown in figure 1, comprising the following steps: s1, controlling the extruder to heat the base material; s2, controlling the color master batch to be put into the base material to form a melt, and heating the melt to a preset temperature; s3, extruding the section bar; s4, calculating the section bar score according to the section bar; and S5, adjusting the extrusion parameters of the extruder according to the section score.

Specifically, the extruder heats the base material to soften the base material, the masterbatch is added to form a melt, the masterbatch and the base material in the melt flow to form wood grains on the base material, and the melt is heated to a preset temperature and then extruded to form the wood grain profile. And grading the section bar, adjusting the extrusion parameters of the extruder according to the grading condition, and correspondingly adjusting the extrusion parameters of the extruder according to the evaluation condition so as to form a uniform wood grain effect.

It will be appreciated that calculating the profile score P may form a uniform scoring criterion. The profile score P may include: area score A_pColor score C_pAnd a shape score S_p. And (3) correlating the three scores to form a profile score, and adjusting the extrusion parameters of the extruder according to the score to complete the unification of the wood grain effect on the profile.

Specifically, as shown in fig. 2, the method for calculating the profile score includes: and acquiring a reverse color picture of the profile shape, and acquiring a three-channel matrix of the reverse color picture. Wherein, the profile shape refers to one side of the profile. Through statistics, the positions of the section bar which are not colored by the color master batch are mostly in a light color state, namely, in a three-channel matrix on the section bar, the elements in at least two color channels are close to the maximum value of 255, the positions colored by the color master batch are in a darker color state, namely, the elements in each color matrix in the three-channel matrix on the section bar are far less than 255, a reverse color picture of the section bar is obtained, the positions colored by the color master batch on the section bar are extracted, the positions which are not colored are eliminated, and the three-channel matrix M is obtained from the reverse color picture, wherein the size of the three-channel matrix M is (3, a, b), and a and b are the width and the height of the picture. The reverse color picture is selected to be beneficial to extracting the area parameter, the color parameter and the shape parameter of the wood grain, and to the subsequent relevant statistics and calculation.

Optionally, an original image of the profile shape can be obtained, after the original image is sharpened, a part of the original image is weakly colored, namely, the point with low coloring degree is eliminated, and then the reverse image is obtained, so that interference caused when the extracted point is counted subsequently is avoided. The sharpening process is within the scope of the prior art and will not be described further herein.

Specifically, the calculation flow of the area score is shown in fig. 3, and the area score can be calculated to evaluate the profileArea of wood grain. The area condition of the wood grain refers to the area of the wood grain formed in the profile, and under the condition that the original appearance and color of the profile are not affected, the larger the area of the wood grain is, the better the coloring effect of the color master batch is, and the calculation of the area score comprises the following steps: according to the formula

In particular, according to the formula

Obtaining the sum of all elements in each color channel matrix, and then taking the channel matrix M' with the maximum sum of elements, wherein C represents the color of the channel matrix, such as M_RRepresenting a red channel matrix, M_BRepresenting a blue channel matrix. The RGB value of the wood grain corresponding point in the image after the reverse color processing is larger than that of the corresponding point of the section bar, if more elements with the numerical value of 0 are selected in the three-channel matrix M, the subsequent operation is not facilitated, and in order to make the elements participating in the operation as more as possible, the matrix M' with the largest sum of the elements is selected. It will be appreciated that M 'is the matrix with the largest sum of elements in each color channel matrix, and that M' belongs to the red channel matrix M_RBlue channel matrix M_BAnd green channel matrix M_GOne of (1).

Specifically, the distribution A of all elements in the matrix M' is calculated. The distribution A can be used to pick the elements actually used for the area score calculation, i.e. to pick the elements identified as wood grain, so that the area score result reflects the wood grain area of the profile as much as possible. The distribution a may be: the average value or the median value of the channel matrix M' may also be obtained by selecting a larger number from the obtained average value and median value, which may be: the larger one of the mean, median, mean and median of the uncolored portions of the channel matrix M' is selected. The method for acquiring the average value and the median value of the uncolored part comprises the following steps: and (3) obtaining a profile extruded without adding color master batches, and calculating the average value or the median value in the channel matrix of the color corresponding to the matrix M' in the profile picture, namely the average value and the median value at the moment are constants. The selection method is determined according to actual conditions.

In particular, according to empirical formulas

Calculating an area score A_p. It can be understood that, when the color master batch is used for completely coloring the profile or is not used for completely coloring the profile, all elements of the channel matrix in the picture corresponding to the profile are the same, which may cause the situation of high score in a false manner, and is not beneficial to adjusting the extrusion parameters to form uniform wood grains, so the area score should not have a simple linear relationship with the wood grain area. By the following equation:

in the formula, x is the number of elements larger than the distribution A, namely the number of elements identified as wood grains, and μ is a deviation coefficient, namely the number of elements identified as wood grains in the profile when the highest score of 100 is obtained, the value is determined according to the actual situation, and the function image corresponding to the formula is in a shape which is symmetrical left and right by taking μ as the center, so that the adjustment result of the extrusion parameters of the extruder tends to μ, and the accurate area score is favorably obtained.

Specifically, the color score calculation process is shown in fig. 4, the color depth of the profile can be obtained by calculating the color score, a coloring master batch is used as a coloring material, the wood grain color of the profile is close to the color of the master batch, and the color score calculation includes: taking the complementary RGB color value of the color master batch, and selecting a color value C corresponding to the channel matrix M'; calculating the average value A of the elements in the channel matrix M' larger than the distribution A₂(ii) a According to empirical formula

Calculating a color score C_p。

Specifically, the RGB color value of the complementary color of the color master batch is taken, and the color value C belonging to the channel matrix M' is selected. The color of the color master batch is taken as a reference, so that the color value of a corresponding channel matrix M ' representing the original color master batch needs to be obtained firstly, if the channel matrix M ' is selected as a blue channel matrix, the color master batch should correspondingly select a blue value B, and if the channel matrix M ' is green, the color master batch should select a green value G. Generally, a reverse color picture of the color master batch is obtained, and then the element value of the corresponding channel is taken.

Specifically, the average value A of the elements in the channel matrix M' larger than the distribution A is calculated₂. It will be appreciated that the elements to be compared with the masterbatch should be elements representing wood grain, so the average value A of the elements in the calculated channel matrix M' that are larger than the distribution A is calculated₂And then taking the average value to participate in the subsequent calculation.

In particular, according to empirical formulas

Calculating a color score C_p. Taking the average value A of the elements larger than the distribution A as the matrix composed of the elements representing the wood grain₂The color depth of the wood grain in the section bar can be reflected, and an empirical formula can be utilized

The understanding of the formula is that when the wood grain color in the section material is close to or has too large difference with the color of the master batch, the wood grain color should be carefully graded, and when the wood grain color in the section material is moderate with the color difference of the master batch, the wood grain color and the color grading should be in a linear relation as much as possible.

Specifically, the calculation flow of the shape score is as shown in fig. 5, the shape score is an important parameter for evaluating the wood grain shape, and since the wood grain shape is complicated and various, but all wood grains cannot be completely included by a formula, the wood grain shape can be evaluated by constructing a convolutional neural network model, training the convolutional neural network model, and using the trained model. The convolutional neural network model can be a Fast-R CNN model, existing section bar pictures are classified, classification can be formed in a numerical value mode according to the number of wood grains of the section bar, exemplarily, the section bar without wood grains is classified as 0 type, the section bar with 1 wood grain is classified as 1 type, and the like, the larger the number of the wood grains is, the larger the numerical value of the type is, 101 types can be set, 0-100 points are correspondingly formed, labels of a training set are formed, the pictures are used as input samples, the number of the wood grains on the pictures is counted, and the shapes are classified into the most posterior type when the number of the wood grains is set to be a specific value. And modifying the classifier of the model according to the labels of the training set, so that the labels of the training set correspond to the classes of the classifier one by one, training, and completing the construction of the convolutional neural network model.

Specifically, after the evaluation of the area score, the color score and the shape score is completed, the three are integrated to form a complete evaluation standard for the wood grain of the profile. Section bar score P ═ k₁×A_p+k₂×C_p+k₃×S_pAccording to actual situation, the k is modified₁、k₂And k₃Optionally, k₁、k₂And k₃The ratio of (5): 3: 1, from which a complete evaluation of the wood grain of the profile is formed.

Specifically, the flow of adjusting the extrusion parameters is shown in fig. 6, and after a complete evaluation criterion is formed, the extrusion parameters need to be adjusted according to the evaluation criterion. Computing

And

wherein P is₁As a proportion of the area score, P₂Is the ratio of the color scores, P₃Is the ratio of the shape scores, A_pl is the total score of the area score, C_pl is the total score of the color score, S_pl is the total score of the shape score; when the profile score P is less than a first threshold value, P is compared₁、P₂And P₃The size of (d);if P₁The minimum, the input speed of the color master batch is increased; if P₂If the temperature is minimum, reducing the preset temperature; if P₃If the minimum, the extrusion speed of the profile is increased; if P₁、 P₂Are all smallest (i.e. P)₁、P₂Equal), the input speed of the color master batch is increased; if P₁、P₃Are all smallest (i.e. P)₁、P₃Equal), the input speed of the color master batch is increased; if P₂、P₃Are all smallest (i.e. P)₂、P₃Equal), then the preset temperature is reduced; if P₁、P₂And P₃And if the color master batch is equal, the input speed of the color master batch is increased. When the profile score P is greater than or equal to the first threshold value and less than the second threshold value, if P₁Greater than P₂Then the current extrusion parameters are maintained, if P is₁Less than or equal to P₂The input speed of the color master batch is increased. When the profile score P is greater than or equal to a second threshold value, compare P₁、P₂And P₃The size of (d); if P₁Maximally reducing the input speed of the color master batch; if P₂The maximum temperature is increased; if P₃At the maximum, the extrusion speed of the profile is reduced; if P₁、P₂Are all maximum (i.e. P)₁、P₂Equal), the input speed of the color master batch is reduced; if P₁、P₃Are all maximum (i.e. P)₁、P₃Equal), the input speed of the color master batch is reduced; if P₂、P₃Is at maximum (i.e. P)₂、 P₃Equal), the preset temperature is increased; if P₁、P₂And P₃And if the color master batch is equal, the input speed of the color master batch is reduced.

It will be appreciated that when the grain evaluation is more off-set from the expectation, the extrusion parameters need to be adjusted to change the score that needs to be changed, so P is introduced₁、P₂And P₃These three parameters may represent the scoring of the wood grain, its area, color and shape of the profile, when the profile score is low, i.e. when the profile score is less than a first threshold, the wood grain style deviates from the expected style type, when there must be a minimum score ratio, by adjusting the extrusionParameters are used for improving the minimum score ratio, so that the wood grain effect of the profile extruded next time is correspondingly changed, the wood grain style of the profile is approached, and the formation of a uniform style is facilitated; when the section bar score is higher, namely when the section bar score is larger than a second threshold value, the wood grain style deviates from the expected style type, the maximum score ratio is always existed, the extrusion parameters are adjusted to reduce the maximum score ratio, so that the wood grain effect of the next extruded section bar is correspondingly changed, the wood grain style of the section bar is approached, and the uniform style is favorably formed. When the profile score is between the first threshold and the second threshold, it is then possible to compare the ratio P of the area scores₁Ratio of color score P₂The ratio P of the area score is considered as₁Should be greater than the color score₂So when P is₁Greater than P₂Keeping the existing extrusion parameters, otherwise increasing the input speed of the color master batch to ensure that P is added₁And is increased. P₁、P₂And P₃In, P₁Of highest priority, P₃Is lowest, i.e. when the scores are the same, the extrusion parameters are preferentially adjusted to P₁Is increased or decreased, and the extrusion parameters are adjusted to P₂Is increased or decreased, and finally the extrusion parameters are adjusted to P₃The score of (a) is increased or decreased.

Specifically, each score has a corresponding adjustment measure. Wherein the means for changing the area score comprises: the feeding speed of the color master batch is changed, and the color master batch is generally considered to be added when other conditions are not changed: the faster the addition speed of the color master batch is, the more the color master batch is added in a unit time, the easier the color master batch forms wood grains on the profile, and the higher the area score is. The means for changing the color score includes: changing the preset temperature of the extruder, wherein the preset temperature of the extruder generally, particularly the temperature at an extrusion port, is kept at about 179 ℃, and the dispersion speed of the color master batch is high at high temperature, so that the color is light, when the color score needs to be improved, the preset temperature of the extruder is reduced, and when the color score needs to be reduced, the preset temperature of the extruder is improved; the means for changing the shape score includes: the speed of the extrusion profile is varied, wherein the speed of the extrusion profile can be determined by the rotation speed of the extrusion screw, and whether the color master batch can form wood grains on the profile is related to the rotation speed of the extrusion screw, namely the speed of stirring the melt. Generally, the peak value of the color master batch input speed is 76 color master batches input per minute, the peak value of the screw extrusion speed is 10.8 revolutions per minute, the peak value of the preset temperature of the extruder is 189 ℃, when the input speed of the color master batches, the extrusion speed of the screw or the preset temperature of the extruder exceeds the peak value, the parameters are locked at the peak value, and the parameters are not reduced until the score corresponding to the adjustment measure needs to be reduced.

Optionally, the adjustment amount of each extrusion parameter is 2.8% of the current parameter value, and if the current temperature of the extrusion port is 180 ℃, the preset temperature is increased by 5.04 ℃.

Optionally, the wood grain-like profile extrusion method is performed every 1 time interval, so that the wood grains on the profile can form a uniform style.

In one embodiment, the simulated wood grain profile extrusion method is performed as follows: when the extruder reaches 180 ℃, extruding the profile to obtain a three-channel matrix of a reversed-color picture of the profile, wherein in the embodiment, the size of the three-channel matrix is (3, 218, 361), wherein 3 denotes that the three-channel matrix has a red channel matrix, a green channel matrix and a blue channel matrix, and 218 and 361 mean that the size of each color channel matrix is (218, 361), that is, the width is 218 elements, and the height is 361 elements. The color of the color master batch is selected to be brown, the RGB value of the color master batch is (150, 75, 0), namely the R value is 150, the G value is 75, the B value is 0, the reverse RGB value is (105, 180, 255), the average value of each color channel matrix of the three-channel matrix of the section bar is respectively close to (188, 174, 165), namely the red channel matrix M_RThe average value of all elements in is close to 188, and the green channel matrix M_GAverage value of all elements in (B) is close to 174, and blue channel matrix M_BThe average value of all elements in the three-channel matrix is close to 165, and the average value of the reverse color of each color channel matrix of the three-channel matrix is respectively close to (67, 81, 90), namely the red channel matrix M_RIs close to the average value of all elements in the inverse matrixAt 67, the green channel matrix M_GHas an average value of all elements close to 81, and a blue channel matrix M_BThe average value of all elements in the inverse matrix of (2) is close to 90, so the blue channel matrix is taken as M'. In the formula

In the above formula, when μ is 47000, i.e., 47000 elements in M' are larger than the average value of 90, the area score is 100, i.e., the highest score, σ²Is taken to be 2.58 multiplied by 10⁸Counting that 38654 elements are larger than the average value 90, and calculating according to the result that the area score is 76.34; the average value of the 38654 elements is 153.03, the color value of the selected color master batch is 255, and the color master batch is obtained according to a formula

Calculating to obtain a color score of 88.10 points; inputting the reverse color picture of the profile shape into a convolutional neural network model to obtain that the profile belongs to 53 classes, namely the profile has a shape score of 53.00, the highest score is 100, and the weight ratio of the area score to the color score to the shape score is 5: 3: 1, according to the formula P-5A_p+3C_p+S_pThe obtained section bar has a score of 69.90, a first threshold value of 40, a second threshold value of 70 and an area score ratio P₁0.76, color score ratio P₂0.88, shape score ratio P₃Is 0.53, greater than or equal to the first threshold value and less than the second threshold value, and P, since the profile score is 69.90 points₁Less than P₂Therefore, the input speed of the color master batch should be increased.

Another aspect of the present invention provides an extruder comprising: the support 1 is provided with a spiral conveyer 2, and the spiral conveyer 2 is provided with a first input port 3; the machine barrel 4 is provided with a second input port 5 and a third input port 6, the second input port 5 is used for inputting color master batches, the third input port 6 is used for inputting base materials, and a screw is arranged in the machine barrel 4; wherein, one end of the spiral conveyer 2 is arranged above the second input port 5; the control module is used for executing the wood-grain-like profile extrusion method.

It will be appreciated that in a first aspect, as shown in fig. 7, the control module is configured to control the extruder to perform an extrusion process, including heating the base material, feeding the color masterbatch through the screw conveyor 2, heating the color masterbatch to a predetermined temperature, and extruding the profile. In the second aspect, the control module can obtain the appearance pictures of the section bar and the color master batch to complete the selection of corresponding wood grain elements and complete the corresponding calculation of area score, color score, shape score and section bar score so as to complete the complete evaluation of the section bar, and in the third aspect, the control module adjusts the extrusion parameters according to the result of the section bar score, wherein the feeding speed of the color master batch refers to the feeding amount of the color master batch in unit time, namely the amount of the color master batch entering the machine barrel 4 through the second feeding port 5, and the third feeding port 6 is used for feeding the base stock, and the base stock is stirred by the screw rod and reaches the preset temperature. The feeding speed of the color master batches can be adjusted by adjusting the rotating speed of the spiral conveyer 2, so that the feeding amount of the color master batches in unit time is changed. The preset temperature can be realized by adjusting the temperature in the machine barrel 4, and the speed of extruding the section bar is realized by adjusting the rotating speed of the screw in the machine barrel 4, so that the method for extruding the wood grain-like section bar is realized, and the section bar with uniform style is formed.

In this embodiment, the first input port 3 is used for inputting color master batches, and the color master batches fall into the second input port 5 through one end of the screw conveyor 2 under the driving of the screw conveyor 2, enter the machine barrel 4 through the second input port 5, are mixed with the base material in the machine barrel 4 and are extruded to form the profile.

In the present invention, the terms "first", "second", and "third" are used for descriptive purposes only and are not to be construed as indicating or implying importance; the term "plurality" means two or more unless expressly limited otherwise. The terms "mounted," "connected," "fixed," and the like are to be construed broadly, and for example, "connected" may be a fixed connection, a removable connection, or an integral connection; "coupled" may be direct or indirect through an intermediary. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.

In the description of the present invention, it is to be understood that the terms "upper", "lower", "left", "right", "front", "rear", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplification of description, but do not indicate or imply that the referred device or unit must have a specific direction, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention.

In the description herein, the description of the terms "one embodiment," "some embodiments," "specific embodiments," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method of extruding a wood grain-like profile, comprising:

controlling the extruder to heat the base material;

controlling the color master batch to be put into the base material to form a melt, and heating the melt to a preset temperature;

extruding a profile;

calculating a profile score from the profile;

adjusting extrusion parameters of the extruder according to the profile score.

2. The method of wood-like grain profile extrusion as set forth in claim 1, wherein said calculating the profile score from the profile comprises:

obtaining a reverse color picture of the profile shape, and obtaining a three-channel matrix M of the reverse color picture, wherein the three-channel matrix M comprises a red channel matrix M_RGreen channel matrix M_GAnd a blue channel matrix M_B；

Respectively calculating the area score A of the reverse color picture according to the three-channel matrix M_pColor score C_pAnd a shape score S_p；

According to the area score A_pThe color score C_pAnd a shape score S_pCalculating the profile score.

3. The method of extruding a wood-like grain profile as recited in claim 2, wherein said calculating said area score a_pColor score C_pAnd a shape score S_pThe method comprises the following steps:

according to the formula

Acquiring a channel matrix M' with the maximum sum of elements in the three-channel matrix;

calculating the distribution condition A of all elements in the matrix M';

according to empirical formula

4. The method of extruding a wood-like grain profile as recited in claim 3, wherein said calculating said area score A_pColor score C_pAnd a shape score S_pThe method comprises the following steps:

selecting a color value C corresponding to a channel matrix M' from the reversed RGB color values of the color master batch;

calculating elements of the channel matrix M' larger than the distribution AAverage value of A₂；

According to empirical formula

Calculating a color score C_p。

5. Process for the extrusion of a simulated wood grain profile as claimed in claim 3 or 4, characterized in that the profile A is an average or median value.

6. The method of extruding a wood-like grain profile as recited in claim 5, wherein said calculating said area score A_pColor score C_pAnd a shape score S_pThe method comprises the following steps:

constructing a convolutional neural network model, taking the shape picture of the section as a sample, taking the number of wood grains on the section as a label, and training the convolutional neural network model;

inputting the reverse color picture of the section into the convolutional neural network model, and outputting the convolutional neural network model to obtain a shape score S_p。

7. The method of extruding a wood-like grain profile as recited in claim 6, wherein said scoring A is based on said area_pThe color score C_pAnd a shape score S_pCalculating the section bar score, which specifically comprises the following steps: the profile score P ═ k₁×A_p+k₂×C_p+k₃×S_pWherein k is₁、k₂And k₃Are weight coefficients.

8. The method of wood grain-like profile extrusion according to claim 7, wherein said adjusting extrusion parameters of said extruder based on said profile score comprises:

computing

And

wherein P is₁As a proportion of the area score, P₂Is the ratio of the color scores, P₃Is the ratio of the shape scores, A_plAs a total score of the area score, C_plIs the total score of the color score, S_plIs the total score of the shape score;

when the profile score P is less than a first threshold value, comparing P₁、P₂And P₃The size of (a) is (b),

if P₁The minimum, the input speed of the color master batch is increased,

if P₂And if the temperature is minimum, reducing the preset temperature,

if P₃And at the minimum, the extrusion speed of the profile is improved,

if P₁、P₂The addition speed of the color master batch is increased if the addition amount is minimum,

if P₁、P₃The addition speed of the color master batch is increased if the addition amount is minimum,

if P₂、P₃If both are minimum, the preset temperature is reduced,

if P₁、P₂And P₃If the color master batch is equal to the color master batch, the input speed of the color master batch is increased;

when the profile score P is greater than or equal to a first threshold value and less than a second threshold value, if P₁Greater than P₂Then the current extrusion parameters are maintained, if P is₁Less than or equal to P₂The input speed of the color master batch is increased;

comparing P when the profile score P is greater than or equal to a second threshold value₁、P₂And P₃The size of (a) is (b),

if P₁Maximally, the input speed of the color master batch is reduced,

if P₂And at the maximum, the preset temperature is increased,

if P₃And maximally, the extrusion speed of the profile is reduced,

if P₁、P₂Are all maximumThe input speed of the color master batch is reduced,

if P₁、P₃The feeding speed of the color master batch is reduced if the color master batch is the maximum,

if P₂、P₃If the temperature is the maximum, the preset temperature is increased,

if P₁、P₂And P₃And if the color master batch is equal, the input speed of the color master batch is reduced.

9. An extruder, comprising:

the color masterbatch feeding device comprises a bracket, a feeding device and a feeding device, wherein the bracket is provided with a spiral conveyer, the spiral conveyer is provided with a first feeding port, and the first feeding port is used for feeding color masterbatch;

a barrel provided with a second input port and a third input port;

one end of the spiral conveyer is arranged above the second input port, and the second input port is used for receiving the color master batches conveyed by the spiral conveyer; the third input port is used for inputting the base material;

a screw is arranged in the machine barrel and is used for stirring;

the extruder further comprises a control module for carrying out the method of wood grain profile extrusion as set forth in any one of claims 1 to 8.