CN114789927B - Artificial intelligent control method and system for textile fabric gray cloth winding machine - Google Patents
Artificial intelligent control method and system for textile fabric gray cloth winding machine Download PDFInfo
- Publication number
- CN114789927B CN114789927B CN202210697774.9A CN202210697774A CN114789927B CN 114789927 B CN114789927 B CN 114789927B CN 202210697774 A CN202210697774 A CN 202210697774A CN 114789927 B CN114789927 B CN 114789927B
- Authority
- CN
- China
- Prior art keywords
- concave
- area
- convex
- fabric
- gray
- 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
- 239000004744 fabric Substances 0.000 title claims abstract description 217
- 238000004804 winding Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 33
- 239000004753 textile Substances 0.000 title claims abstract description 30
- 230000037303 wrinkles Effects 0.000 claims description 35
- 238000013473 artificial intelligence Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000005096 rolling process Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 6
- 238000003708 edge detection Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 abstract description 7
- 239000000463 material Substances 0.000 abstract description 3
- 238000012360 testing method Methods 0.000 abstract description 3
- 238000004154 testing of material Methods 0.000 abstract description 2
- 230000008859 change Effects 0.000 description 10
- 238000012545 processing Methods 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005056 compaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000002657 fibrous material Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 210000001161 mammalian embryo Anatomy 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000009941 weaving Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65H—HANDLING THIN OR FILAMENTARY MATERIAL, e.g. SHEETS, WEBS, CABLES
- B65H18/00—Winding webs
- B65H18/08—Web-winding mechanisms
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65H—HANDLING THIN OR FILAMENTARY MATERIAL, e.g. SHEETS, WEBS, CABLES
- B65H26/00—Warning or safety devices, e.g. automatic fault detectors, stop-motions, for web-advancing mechanisms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0014—Image feed-back for automatic industrial control, e.g. robot with camera
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/64—Analysis of geometric attributes of convexity or concavity
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65H—HANDLING THIN OR FILAMENTARY MATERIAL, e.g. SHEETS, WEBS, CABLES
- B65H2701/00—Handled material; Storage means
- B65H2701/10—Handled articles or webs
- B65H2701/17—Nature of material
- B65H2701/174—Textile; fibres
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30124—Fabrics; Textile; Paper
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Robotics (AREA)
- Treatment Of Fiber Materials (AREA)
Abstract
The invention relates to the technical field of material testing and analysis, in particular to an artificial intelligent control method and system for a textile fabric gray fabric winding machine. By utilizing the material analysis and test means, the invention can accurately determine the flatness of the fabric, and finally realizes the reliable adjustment of the extension tension of the fabric.
Description
Technical Field
The invention relates to the technical field of material testing and analysis, in particular to an artificial intelligent control method and system for a textile fabric gray cloth winding machine.
Background
Textile production is an important industry in development and construction of China, textile fabric gray cloth is used for manufacturing molded clothes, and in a production process program of the textile fabric gray cloth, the textile fabric gray cloth needs to be rolled by a fabric rolling machine to be bundled, so that the situation that the fabric gray cloth is stacked disorderly is avoided, and the situation that the fabric is attached with dirt, folded and the like is avoided.
Because the weaving surface fabric embryo cloth is many by fibrous material composition, in the rolling operation in-process, but crease-resistant rolling machine need extend the surface fabric earlier, have certain power of dragging to the surface fabric, when because roll up core winding speed is unchangeable, when extension tension is not enough, the position of surface fabric than the fold need consume the longer time just can transport to rolling up the core under the conveying of compaction roller, can come too late to transport because of the compaction roller and pile up to some extent, the tension of extension has made the condition that the too big degree of dragging of fibre appears in some surface fabric positions easily and has played the batting. The existing method for adjusting the extension tension applied to the fabric needs manual adjustment according to experience, and has strong subjectivity and poor adjustment reliability.
Disclosure of Invention
The invention aims to provide an artificial intelligent control method and system for a textile fabric gray cloth rolling machine, which are used for solving the problem that the existing fabric extension tension is unreliable to adjust.
In order to solve the technical problem, the invention provides an artificial intelligent control method of a textile fabric gray cloth winding machine, which comprises the following steps of:
acquiring a fabric operation image of a winding machine, acquiring a fabric gray fabric image according to the fabric operation image, and further acquiring a fabric gray fabric image;
performing wrinkle identification according to the gray level image of the fabric gray fabric to obtain each convex area and each concave area, and further determining the area of each convex area and each concave area;
determining the overall concave-convex degree of the fabric according to the gray level image of the fabric gray fabric, the gray level values of all pixel points in all convex areas and concave areas and the areas of all convex areas and concave areas;
performing skeletonization treatment on each convex area and each concave area to obtain ridge lines of each convex area and each concave area;
determining the tortuosity of the ridge line of each convex area and each concave area according to the pixel value of each pixel point on the ridge line of each convex area and each concave area;
determining slope lines of the ridge lines of the convex areas and the concave areas according to the ridge lines of the convex areas and the concave areas and pixel values of pixel points on the ridge lines;
determining the kurtosis of the ridge line of each convex area and each concave area according to the gray value of each pixel point on the slope line of the ridge line of each convex area and each concave area;
determining the sharpness of each convex area and each concave area according to the tortuosity and the kurtosis of the ridge line of each convex area and each concave area, and further determining the comprehensive sharpness of the fabric;
and determining the flatness of the fabric according to the overall concave-convex degree and the comprehensive sharp degree of the fabric, and controlling the extension tension of the fabric of the winding machine according to the flatness of the fabric.
Further, the performing wrinkle identification to obtain each of the convex area and the concave area includes:
performing edge detection on the gray level image of the fabric gray cloth to obtain each convex area and each initial concave area;
determining a gray variance value corresponding to each initial concave area according to the gray value of each pixel point in each initial concave area;
and screening each initial concave area according to the gray scale variance value corresponding to each initial concave area, thereby obtaining each concave area.
Further, the determining of the overall concave-convex degree of the fabric comprises:
determining a flat area on the gray level image of the fabric gray level cloth according to the gray level image of the fabric gray level cloth, each convex area and each initial concave area;
determining a gray mean value of the flat area according to the gray values of all pixel points in the flat area on the gray image of the fabric gray grey cloth;
calculating a sum of gray values of all pixel points in each convex area minus a gray average value of the flat area, thereby obtaining the height of each convex area;
calculating a sum of gray values of all pixel points in all concave areas minus a gray average of the flat areas so as to obtain depths of all concave areas;
and calculating the overall concave-convex degree of the fabric according to the height of each convex region, the depth of each concave region and the area of each convex region and each concave region.
Further, a calculation formula corresponding to the overall concave-convex degree of the fabric is as follows:
wherein,
the degree of the overall concave-convex of the fabric,
is a firstiThe area of each of the convex regions is,
is as followsiThe height of the individual convex regions is such that,
is the area of the jth concave region,
is the depth of the jth concave region,
is the total number of the convex regions,
the total number of concave regions.
Further, a calculation formula for determining the degree of curvature of the ridge line of each convex region and each concave region is as follows:
wherein,
the degree of meandering of the ridge lines of the respective convex or concave regions,
on the ridgeline of each convex or concave regioniThe gray value of +1 pixel point,
on the ridgeline of each convex or concave regioniThe gray value m of each pixel point is the total number of the pixel points on the ridge line of each convex area or concave area.
Further, the step of determining a slope line of the ridge line of each of the convex region and the concave region includes:
determining a maximum pixel value pixel point on the ridge line of each convex area and a minimum pixel value pixel point on the ridge line of each concave area according to the pixel values of the pixel points on the ridge lines of each convex area and each concave area;
and determining the perpendicular line of the tangent line of the ridge line of each convex region at the maximum pixel value pixel point corresponding to the ridge line of each convex region and the perpendicular line of the tangent line of the ridge line of each concave region at the minimum pixel value pixel point corresponding to the ridge line of each concave region according to the ridge line of each convex region and each concave region, the maximum pixel value pixel point on the ridge line of each convex region and the minimum pixel value pixel point on the ridge line of each concave region, so as to obtain the slope line of the ridge line of each convex region and each concave region.
Further, the determining the kurtosis of the ridge line of each of the convex region and the concave region includes:
determining the mean value of pixel values on the slope lines of the ridge lines of the convex areas and the concave areas according to the pixel values of the pixel points on the slope lines of the ridge lines of the convex areas and the concave areas;
calculating the difference value between the pixel value of each pixel point on the slope line of the ridge line of each convex area and each concave area and the mean value of the pixel values on the corresponding slope line, thereby obtaining the fourth-order central moment and the second-order central moment of the ridge line of each convex area and each concave area;
and calculating the ratio of the fourth-order central moment of the ridge line of each convex area and each concave area to the square of the corresponding second-order central moment, thereby obtaining the kurtosis of the ridge line of each convex area and each concave area.
Further, the corresponding calculation formula of the kurtosis of the ridge line of each convex area and each concave area is as follows:
wherein,
the kurtosis of the ridge line of each convex region or concave region,
for the ith pixel point on the slope line of the ridge line of each convex region or concave regionThe value of the pixel is determined by the pixel value,
the value is the mean value of pixel values on the slope line of the ridge line of each convex region or each concave region, and t is the total number of pixel points on the slope line of the ridge line of each convex region or each concave region.
Further, the calculation formula for determining the flatness of the fabric is as follows:
wherein,
the smoothness of the fabric is the degree of smoothness of the fabric,
the degree of the overall concave-convex of the fabric,
the comprehensive sharpness degree of the fabric is shown.
The invention also provides an artificial intelligence control system of the textile fabric gray cloth winding machine, which comprises a processor and a memory, wherein the processor is used for processing the instructions stored in the memory so as to realize the artificial intelligence control method of the textile fabric gray cloth winding machine.
The invention has the following beneficial effects: the fabric gray image processing method comprises the steps of obtaining a fabric gray image through a winding machine, carrying out material analysis and test on the fabric gray image, determining each convex area and each concave area, further determining the overall concave-convex degree of the fabric, obtaining the ridge line of each convex area and each concave area and the slope line of the ridge line, further determining the tortuosity and the kurtosis of the ridge line of each convex area and each concave area, combining the tortuosity and the kurtosis of the ridge line of each convex area and each concave area, determining the comprehensive sharp degree of the fabric, combining the overall concave-convex degree and the comprehensive sharp degree of the fabric, further determining the flatness of the fabric, and finally realizing the control of the extension tension of the fabric to the winding machine. According to the invention, by acquiring the fabric operation image of the winding machine and utilizing material analysis and test means, the flatness of the fabric can be accurately determined, and finally the reliable adjustment of the extension tension of the fabric is realized.
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 an artificial intelligence control method of a textile fabric gray cloth winding machine of the invention;
figure 2 is a schematic view of a fabric pleat in an embodiment of the invention.
Detailed Description
To further explain the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the embodiments, structures, features and effects of the technical solutions according to the present invention will be given with reference to the accompanying drawings and preferred embodiments. 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 tensile regulation of extension of textile fabric crease-resistance rolling machine influences surface fabric gray cloth quality and operating efficiency, and this embodiment utilizes computer vision technique, through handling the surface fabric image of shooting, according to the characteristic analysis of image, calculates the roughness of surface fabric, and then obtains the required best extension tension of extending the surface fabric, adjusts the extension power of rolling machine, makes the surface fabric extend to optimum, avoids the surface fabric to pile up or tear the surface fabric.
Specifically, the embodiment provides an artificial intelligence control method for a textile fabric gray cloth winding machine, and a corresponding flowchart is shown in fig. 1, and the method includes the following steps:
acquiring a fabric operation image of a winding machine, acquiring a fabric gray fabric image according to the fabric operation image, and further acquiring a fabric gray image;
performing wrinkle identification according to the gray level image of the fabric gray fabric to obtain each convex area and each concave area, and further determining the area of each convex area and each concave area;
determining the overall concave-convex degree of the fabric according to the gray level image of the fabric gray fabric, the gray level values of all pixel points in all the convex areas and the concave areas and the areas of all the convex areas and all the concave areas;
performing skeletonization treatment on each convex area and each concave area to obtain ridge lines of each convex area and each concave area;
determining the tortuosity of the ridge line of each convex area and each concave area according to the pixel value of each pixel point on the ridge line of each convex area and each concave area;
determining slope lines of the ridge lines of the convex areas and the concave areas according to the ridge lines of the convex areas and the concave areas and pixel values of pixel points on the ridge lines;
determining the kurtosis of the ridge line of each convex area and each concave area according to the gray value of each pixel point on the slope line of the ridge line of each convex area and each concave area;
determining the sharpness of each convex area and each concave area according to the tortuosity and the kurtosis of ridge lines of each convex area and each concave area, and further determining the comprehensive sharpness of the fabric;
and determining the flatness of the fabric according to the overall concave-convex degree and the comprehensive sharp degree of the fabric, and controlling the extension tension of the fabric of the winding machine according to the flatness of the fabric.
The artificial intelligent control method of the textile fabric gray cloth winding machine is described in detail below with reference to specific embodiments.
The method comprises the following steps: and acquiring an image shot by a camera above the winding machine, and performing semantic segmentation to identify the fabric image.
The embodiment needs clear fabric surface images, and according to the fabric surface image characteristics, the flatness of the fabric is calculated, and the extension force of the winding machine is adjusted. All the surface images of the fabric on the winding machine need to be collected, and the characteristic information of the fabric surface in the images is identified.
In order to clearly display the wrinkles on the surface of the fabric, the single-side LED lamp is used as a light source for lighting, and due to the existence of the wrinkles, light and shade change can be formed at the wrinkles by light, the sharper the wrinkles are, the more intense the light and shade change is, so that the wrinkle characteristics of an image can be described based on the phenomenon, and the wrinkle characteristics can be used for distinguishing the fabrics with different flatness.
The present embodiment adopts a DNN semantic segmentation manner to identify the target in the segmented image, and the relevant content of the DNN network is as follows:
a. the used data set is a fabric image data set on the winding machine acquired in a overlooking mode.
b. The pixels to be segmented are divided into 2 types, namely the labeling process of the training set corresponding to the labels is as follows: and in the single-channel semantic label, the label of the pixel at the corresponding position belonging to the background class is 0, and the label of the pixel belonging to the fabric is 1.
c. The role of the network is classification, so the loss function used is the cross entropy loss function.
Therefore, the processing of the fabric image on the winding machine is realized through the DNN, and the connected domain information of the fabric surface in the image is obtained.
Step two: and judging the flatness of the fabric according to the characteristic analysis of the fabric image.
And calculating a convex area and a concave area of each wrinkle according to the difference between the flat area and the wrinkle area of the surface of the fabric, analyzing the change characteristics of the gray value in each wrinkle area, and calculating the severity of each single wrinkle. And comprehensively obtaining the flatness of the current fabric.
The process of obtaining the fabric flatness in this embodiment is as follows: a) The masked area in the folds of the fabric was calculated according to Canny edge detection.
b) And distinguishing a real wrinkle concave area according to the characteristics of the wrinkle concave area of the fabric.
c) And calculating the flatness of the fabric according to the gray level change of each wrinkle area.
The following are specific developments:
a) the masked area in the folds of the fabric was calculated according to Canny edge detection.
When the fabric is wrinkled, the gray level of the presented image is unstable. The gray values of the areas where the wrinkles are recessed are small, and the gray values of the areas where the wrinkles are protruding are large, as shown in fig. 2.
Therefore, the surface image of the fabric is subjected to gray processing, then noise and miscellaneous points in the image are removed by using median filtering, and then convex areas and concave areas of folds are identified and segmented by using Canny edge detection, wherein the number of the convex areas and the number of the concave areas are respectively
And
。
calculating the area of each fold convex area, namely the number of pixel points, and obtaining a convex surface area set
Then calculating the area of each fold concave area to obtain a concave area set
. And finally, calculating gray values of all pixel points in the flat area on the fabric, summing the gray values, and taking the average value as R.
Due to the use of a single-sided light source for illumination, the convex area of the fold can generate shadows, which can be in the flat area of the fabric. When the segmentation is identified, the segmentation may be judged as a wrinkle concave area, which affects the calculation of the flatness of the fabric, so that the wrinkle concave area needs to be further analyzed.
b) And distinguishing a real wrinkle concave area according to the characteristics of the wrinkle concave area of the fabric.
When the flat area of the fabric is influenced by the shadow, the numerical difference of the gray value of each pixel point in the area is not obvious, and the gray value of each pixel point in the fold concave area gradually becomes smaller along with the downward depth of the concave pit. Therefore, the shaded flat area and the wrinkle concave area can be analyzed according to the change of the gray value in the wrinkle concave area.
Firstly, gray values of all pixel points in a fold concave area are calculated to obtain a set
And n is the number of pixel points in the region. Recalculating sets
Of the mean value C, thereby obtaining a set
Standard deviation of (2)
The calculation formula is as follows:
wherein, aggregate
Standard deviation of (2)
The smaller the value of (A), the smaller the change of the gray value in the description area is, and the flatter the fabric is.
Taking a plurality of flat areas on the current fabric, and calculating the standard deviation of each position
Obtaining a set, and calculating the mean value of the set
This is used as a threshold. When here the concave region is wrinkled
Value less than
Then, this region is a flat region. When here the concave region is wrinkled
Is greater than
This region is a true recessed region. From this, the true fold concave area has
A is prepared from
. I.e. the area of the fold concave region is integrated into
。
c) And calculating the flatness of the fabric according to the gray level change of each wrinkle area.
In conclusion, all the wrinkle convex areas and concave areas on the fabric are obtained, and the influence on the flatness is different due to different shape characteristics of the concave-convex areas. The effect of each fold on the overall flatness needs to be analyzed.
Firstly, a convex region is taken, the sum of the gray value of each pixel point in the region minus R is calculated, and a set is obtained
Wherein
For the number of convex regions of the current fabric, the data in the set can represent the height of each point protrusion. Then a concave area is taken, the sum of the gray value of each pixel point in the area after being subtracted by R is calculated, and a set is obtained
Wherein
The data in the set may represent the depth of each point depression, which is the number of concave regions on the current fabric.
Thus, the overall concave-convex degree F of the current fabric can be obtained:
the former term is the sum of products of the areas of the corrugated convex regions and the convex heights of the corrugated convex regions, the latter term is the sum of products of the areas of the corrugated concave regions and the concave depths of the corrugated concave regions, and the sum of the areas and the concave depths represents the overall concave-convex degree F of the current fabric.
And then calculating the sharpness degree of the whole wrinkle according to the height change of the convex area and the depth change of the concave area. The process of refining the wrinkle region, i.e. reducing the lines of the image from a multi-pixel width to a unit pixel width, is also called skeletonization. Thereby obtaining the peak ridge lines of the corrugated convex regions and the valley ridge lines of the concave regions.
Then analyzing the gray value change of the thinned ridge line, and firstly calculating a gray value set from one end to the other end of the ridge line of a fold area
And m represents the length of the ridge line, namely the number of pixel points of the ridge line.
Then in the collection
The former value is used to subtract the latter value to obtain the ridge fluctuation, which is summed to take the average G. The degree of tortuosity of the ridge line is expressed by G, and the calculation formula is as follows：
Wherein,
and the gray scale difference from one point to the next point on the ridge line is represented, m is the number of pixel points on the ridge line, and G is the average value of the gray scale difference on the ridge line and represents the tortuosity of the ridge line. The larger the value of G, the more meandering the peak ridge line or the valley ridge line of the wrinkle and the larger the degree of the wrinkle.
If the ridge line is the corrugated convex area, taking the maximum gray value point on the ridge line. If the ridge line is the fold concave area, taking the minimum gray value point on the ridge line. And a straight line perpendicular to the tangent line of the ridge line at the point is made in the fold area, and the straight line can represent slopes on the left and right sides of the highest part of the ridge line of the peak of the fold or the lowest part of the ridge line of the valley. Counting the gray value set from one end to the other end of the straight line
WhereintIndicating the length of the two ramps.
It is known that kurtosis is the degree of steepness of the distribution of the measurement data, and the larger the kurtosis value is, the higher the distribution is, and the shorter the distribution is, the smaller the kurtosis value is. Thus can be assembled by calculation
The steepness of the slope is judged according to the kurtosis H of the slope. First computing a set of distances
Average value of (2)
Obtaining a set
Central moment of
The calculation formula is as follows:
and the kurtosis is the ratio of the fourth-order central moment to the square of the second-order central moment, and the calculation formula is as follows:
wherein,
representation collection
The fourth-order central moment of (a) of (b),
representation collection
The second-order central moment of (a) is,
representation collection
The value of the (i) th value,
is a set
Average value of (a). The larger the kurtosis H is, the steeper the slopes of the left and right sides of the highest position of the ridge line of the fold peak or the lowest position of the valley ridge line are.
Thus, the sharpness degree R of the whole wrinkle is obtained, and the calculation formula is as follows:
g is the tortuosity of the crest line or the valley line of the fold, H is the steepness of the slopes on the left side and the right side of the highest position of the crest line or the lowest position of the valley line of the fold, and the sum value R of the G and the H represents the integral sharpness of a single fold.
Calculating the overall sharpness of each fold to obtain a set
Wherein
All wrinkles are indicated. Summing the obtained results, and calculating the comprehensive sharpness degree Q of the current fabric as follows:
to sum up, the obtained flatness W of the current fabric is as follows:
wherein F represents the overall concave-convex degree of the current fabric, Q represents the comprehensive sharp degree of the current fabric, and the larger the sum of the F and Q is, the more and more serious the wrinkles in the fabric are, so the inverse ratio W thereof is used for representing the flatness degree of the current fabric.
Step three: and adjusting the extension tension of the winding machine to the fabric according to the flatness of the fabric to enable the fabric to be extended to the optimal state.
Obtaining the flatness W of the current fabric according to the second step, and automatically setting a threshold value according to different requirements of implementers
When the value of the flatness degree W is notGreater than a threshold value
In the process, the extension tension of the winding machine on the fabric is increased until the value of the flatness degree W is greater than the threshold value
And when the tension is not enough, the winding machine keeps the extension tension at the moment.
The embodiment also provides an artificial intelligence control system of the textile fabric gray cloth winding machine, which comprises a processor and a memory, wherein the processor is used for processing the instructions stored in the memory so as to realize the artificial intelligence control method of the textile fabric gray cloth winding machine. Since the artificial intelligence control method of the textile fabric gray cloth winding machine is described in detail in the above, the details are not repeated herein.
It should be noted that: the above-mentioned embodiments are only used to illustrate the technical solutions of the present application, and not to limit 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; such modifications and substitutions do not depart from the spirit and scope of the embodiments of the present application, and they should be construed as being included in the present application.
Claims (10)
1. An artificial intelligence control method for a textile fabric gray cloth winding machine is characterized by comprising the following steps:
acquiring a fabric operation image of a winding machine, acquiring a fabric gray fabric image according to the fabric operation image, and further acquiring a fabric gray image;
performing wrinkle identification according to the gray level image of the fabric gray fabric to obtain each convex area and each concave area, and further determining the area of each convex area and each concave area;
determining the overall concave-convex degree of the fabric according to the gray level image of the fabric gray fabric, the gray level values of all pixel points in all convex areas and concave areas and the areas of all convex areas and concave areas;
performing skeletonization treatment on each convex area and each concave area to obtain ridge lines of each convex area and each concave area;
determining the tortuosity of the ridge line of each convex area and each concave area according to the pixel value of each pixel point on the ridge line of each convex area and each concave area;
determining slope lines of the ridge lines of the convex areas and the concave areas according to the ridge lines of the convex areas and the concave areas and pixel values of pixel points on the ridge lines;
determining the kurtosis of the ridge line of each convex area and each concave area according to the gray value of each pixel point on the slope line of the ridge line of each convex area and each concave area;
determining the sharpness of each convex area and each concave area according to the tortuosity and the kurtosis of the ridge line of each convex area and each concave area, and further determining the comprehensive sharpness of the fabric;
determining the flatness of the fabric according to the overall concave-convex degree and the comprehensive sharp degree of the fabric, and controlling the extension tension of the winding machine on the fabric according to the flatness of the fabric; when the value of the flatness degree is not more than the threshold value
In the process, the extension tension of the winding machine on the fabric is increased until the value of the flatness degree is greater than the threshold value
And when the tension is not enough, the winding machine keeps the extension tension at the moment.
2. The artificial intelligence control method of the textile fabric greige cloth rolling machine according to claim 1, wherein the step of performing wrinkle identification to obtain each convex area and each concave area comprises the following steps:
performing edge detection on the gray level image of the fabric gray cloth to obtain each convex area and each initial concave area;
determining a gray variance value corresponding to each initial concave area according to the gray value of each pixel point in each initial concave area;
and screening each initial concave area according to the gray scale variance value corresponding to each initial concave area, thereby obtaining each concave area.
3. The artificial intelligence control method of the textile fabric gray cloth winding machine according to claim 2, wherein the determining of the overall concave-convex degree of the fabric comprises:
determining a flat area on the gray level image of the fabric gray level cloth according to the gray level image of the fabric gray level cloth, each convex area and each initial concave area;
determining the gray average value of the flat area according to the gray value of each pixel point in the flat area on the gray image of the fabric gray grey cloth;
calculating a sum of gray values of all pixel points in each convex area minus a gray average value of the flat area, thereby obtaining the height of each convex area;
calculating a sum of the gray value of each pixel point in each concave area minus the gray average value of the flat area, thereby obtaining the depth of each concave area;
and calculating the overall concave-convex degree of the fabric according to the height of each convex region, the depth of each concave region and the area of each convex region and each concave region.
4. The artificial intelligence control method of the textile fabric gray cloth winding machine according to claim 3, characterized in that the calculation formula corresponding to the overall concave-convex degree of the fabric is as follows:
wherein,
the degree of the overall concave-convex of the fabric,
is as followsiThe area of each of the convex regions is,
is as followsiThe height of the individual convex regions is such that,
is the area of the jth concave region,
is the depth of the jth concave region,
is the total number of the convex regions,
the total number of concave regions.
5. The artificial intelligence control method of the textile fabric greige cloth rolling machine according to claim 1, characterized in that the calculation formula for determining the corresponding degree of tortuosity of ridge lines of each convex area and each concave area is as follows:
wherein,
the degree of meandering of the ridge line of each convex region or concave region,
on the ridge line of each convex or concave regioniThe gray value of +1 pixel points,
on the ridge line of each convex or concave regioniThe gray value m of each pixel point is the total number of the pixel points on the ridge line of each convex area or concave area.
6. The artificial intelligence control method of the textile fabric greige cloth rolling machine according to claim 1, wherein the step of determining the slope line of the ridge line of each of the convex area and the concave area comprises the following steps:
determining a maximum pixel value pixel point on the ridge line of each convex region and a minimum pixel value pixel point on the ridge line of each concave region according to the pixel values of the pixel points on the ridge lines of each convex region and each concave region;
and determining the perpendicular line of the tangent line of the ridge line of each convex region at the maximum pixel value pixel point corresponding to the ridge line of each convex region and the perpendicular line of the tangent line of the ridge line of each concave region at the minimum pixel value pixel point corresponding to the ridge line of each concave region according to the ridge line of each convex region and each concave region, the maximum pixel value pixel point on the ridge line of each convex region and the minimum pixel value pixel point on the ridge line of each concave region, so as to obtain the slope line of the ridge line of each convex region and each concave region.
7. The artificial intelligence control method of the textile fabric greige cloth rolling machine according to claim 6, wherein the determining the kurtosis of the ridge line of each of the convex area and the concave area comprises:
determining the mean value of pixel values on the slope lines of the ridge lines of the convex areas and the concave areas according to the pixel values of the pixel points on the slope lines of the ridge lines of the convex areas and the concave areas;
calculating the difference value between the pixel value of each pixel point on the slope line of the ridge line of each convex area and each concave area and the mean value of the pixel values on the corresponding slope line, thereby obtaining the fourth-order central moment and the second-order central moment of the ridge line of each convex area and each concave area;
and calculating the ratio of the fourth-order central moment of the ridge line of each convex area and each concave area to the square of the corresponding second-order central moment, thereby obtaining the kurtosis of the ridge line of each convex area and each concave area.
8. The artificial intelligence control method of the textile fabric gray cloth winding machine according to claim 7, characterized in that the corresponding calculation formula of the kurtosis of the ridge line of each convex area and each concave area is as follows:
wherein,
the kurtosis of the ridge line of each convex region or concave region,
the pixel value of the ith pixel point on the slope line of the ridge line of each convex region or each concave region,
the value is the mean value of pixel values on the slope line of the ridge line of each convex region or each concave region, and t is the total number of pixel points on the slope line of the ridge line of each convex region or each concave region.
9. The artificial intelligence control method of textile fabric gray cloth winding machine according to claim 1,
the calculation formula for determining the flatness of the fabric is as follows:
wherein,
the smoothness of the fabric is the degree of smoothness of the fabric,
the degree of the overall concave-convex of the fabric,
is the comprehensive sharpness of the fabric.
10. An artificial intelligence control system for a textile fabric blank winder, comprising a processor and a memory, wherein the processor is configured to process instructions stored in the memory to implement the artificial intelligence control method for a textile fabric blank winder according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210697774.9A CN114789927B (en) | 2022-06-20 | 2022-06-20 | Artificial intelligent control method and system for textile fabric gray cloth winding machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210697774.9A CN114789927B (en) | 2022-06-20 | 2022-06-20 | Artificial intelligent control method and system for textile fabric gray cloth winding machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114789927A CN114789927A (en) | 2022-07-26 |
| CN114789927B true CN114789927B (en) | 2022-09-23 |
Family
ID=82463569
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210697774.9A Active CN114789927B (en) | 2022-06-20 | 2022-06-20 | Artificial intelligent control method and system for textile fabric gray cloth winding machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114789927B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117163730B (en) * | 2023-11-02 | 2024-03-12 | 南通明富纺织品有限公司 | Production cloth rolling system based on internet of things |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1099031C (en) * | 1995-10-27 | 2003-01-15 | 日本钢管株式会社 | Method for detecting surface defects and apparatus thereof |
| CN104766329B (en) * | 2013-01-28 | 2018-04-27 | 海信集团有限公司 | A kind of image processing method and electronic equipment |
| JP6131928B2 (en) * | 2014-10-20 | 2017-05-24 | コニカミノルタ株式会社 | Image forming apparatus and image forming system |
| CN205652888U (en) * | 2016-05-31 | 2016-10-19 | 马春阳 | A receive unwinding device for rolling up type product processing |
| CN112224868A (en) * | 2020-10-17 | 2021-01-15 | 东莞科卓机器人有限公司 | FPC (Flexible printed Circuit) light bar feeding method based on CCD (Charge coupled device) |
-
2022
- 2022-06-20 CN CN202210697774.9A patent/CN114789927B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114789927A (en) | 2022-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113934190B (en) | Corrugated board production quality regulation and control method based on machine vision | |
| CA3053219C (en) | Real-time, full web image processing method and system for web manufacturing supervision | |
| CN109035195B (en) | Fabric defect detection method | |
| CN116977358B (en) | Visual auxiliary detection method for corrugated paper production quality | |
| Çelik et al. | Development of a machine vision system: real-time fabric defect detection and classification with neural networks | |
| CN114842007B (en) | Textile wear defect detection method based on image processing | |
| CN114789927B (en) | Artificial intelligent control method and system for textile fabric gray cloth winding machine | |
| CN101598677B (en) | Online three-dimensional recognition method of fabric defects | |
| JP2007132757A (en) | Visual examination method and device | |
| CN111861996A (en) | Printed fabric defect detection method | |
| CN115311267B (en) | Method for detecting abnormity of check fabric | |
| CN114862855B (en) | Textile defect detection method and system based on template matching | |
| CN114998321B (en) | Textile material surface hairiness degree identification method based on optical means | |
| CN115063424B (en) | Textile bobbin yarn detection method based on computer vision | |
| CN116363140B (en) | Method, system and device for detecting defects of medium borosilicate glass and storage medium | |
| CN115359053A (en) | Intelligent detection method and system for defects of metal plate | |
| CN115294116A (en) | Method, device and system for evaluating dyeing quality of textile material based on artificial intelligence | |
| CN118097305B (en) | Method and system for detecting quality of semiconductor light-emitting element | |
| CN112767384A (en) | Compensation method and device of elastic cloth gram weight online detection system | |
| CN114581428A (en) | Powder coating adhesion degree detection method based on optical means | |
| CN116563276A (en) | Chemical fiber filament online defect detection method and detection system | |
| CN118229688B (en) | Corrugated paper fold defect detection method and system | |
| CN118379301B (en) | Hydration degree appearance detection method for regenerated granule | |
| JP2004125629A (en) | Defect detection apparatus | |
| CN112735021B (en) | Banknote zebra crossing identification and counterfeit detection method |
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 |