CN116485790B - Intelligent detection system for personal protective clothing production abnormality for epidemic prevention - Google Patents
Intelligent detection system for personal protective clothing production abnormality for epidemic prevention Download PDFInfo
- Publication number
- CN116485790B CN116485790B CN202310715645.2A CN202310715645A CN116485790B CN 116485790 B CN116485790 B CN 116485790B CN 202310715645 A CN202310715645 A CN 202310715645A CN 116485790 B CN116485790 B CN 116485790B
- Authority
- CN
- China
- Prior art keywords
- run
- gray
- degree
- positions
- uniformity
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 97
- 230000005856 abnormality Effects 0.000 title claims abstract description 50
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 30
- 230000001681 protective effect Effects 0.000 title claims abstract description 23
- 230000002265 prevention Effects 0.000 title claims abstract description 15
- 238000009826 distribution Methods 0.000 claims abstract description 71
- 239000000835 fiber Substances 0.000 claims abstract description 65
- 239000004744 fabric Substances 0.000 claims abstract description 30
- 230000002159 abnormal effect Effects 0.000 claims abstract description 19
- 239000011159 matrix material Substances 0.000 claims description 38
- 238000000034 method Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 6
- 241001270131 Agaricus moelleri Species 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims 1
- 230000007547 defect Effects 0.000 abstract description 32
- 238000009987 spinning Methods 0.000 description 9
- 239000004750 melt-blown nonwoven Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/30—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/956—Inspecting patterns on the surface of objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention relates to the technical field of image data processing, and provides an intelligent detection system for personal protective clothing production abnormality for epidemic prevention, which comprises the following components: collecting a melt-blown cloth surface image to obtain a gray image, and obtaining an abnormality detection kernel of each position for the gray image; obtaining fiber uniformity of each position according to gray value distribution in the anomaly detection core of each position, and constructing gray scale run matrixes of the anomaly detection core of each position in four directions; acquiring the run distribution difference of the two positions in the same direction, acquiring the distribution difference degree of the two positions according to the run distribution difference of all directions, and acquiring the flying abnormal degree of each position according to the distribution difference degree and the fiber uniformity; and obtaining an abnormality detection result of each position on the surface of the melt-blown fabric according to the uniformity of the fiber and the degree of the abnormal fly-away, and finishing the production abnormality detection. The invention aims to solve the problem that the production quality is affected by inaccurate detection of local defects on the surface of melt-blown cloth.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to an intelligent detection system for personal protective clothing production abnormality for epidemic prevention.
Background
The epidemic prevention personnel of each medical institution are growing in demand for personal medical protective clothing, so that personal protective clothing manufacturers are required to strictly control the quality of the personal protective clothing while ensuring the production efficiency, and the normal production of the personal protective clothing can be effectively ensured by detecting the abnormal production quality of the melt-blown non-woven fabric, wherein the main fabric of the personal protective clothing is the melt-blown non-woven fabric.
Various defects exist in the production process of the melt-blown non-woven fabric, wherein uneven spinning and surface flying are main two defects, and if the defects occur in the production process, the quality of the melt-blown fabric is influenced, so that the protection effect of the personal protective clothing cannot be ensured; the uneven spinning is caused by uneven distribution of fiber filaments forming the melt-blown cloth, the surface flying is the phenomenon that the fiber filaments are only partially attached to a receiving net due to the small spraying wind speed in the melt-blown process, and the rest part is agglomerated into flocculus on the surface of the melt-blown cloth, so that the two phenomena are different in generation reason and different in solving mode; however, in the prior art, defects are generally identified directly according to the distribution difference of different gray scales, and the defects are easily confused by the existing visual detection technology because the defects are unevenly distributed on the gray scale distribution, so that the defect detection result is inaccurate and the defect removal efficiency is affected; therefore, a detection method capable of effectively distinguishing uneven spinning and surface flying defects is needed, so that the accuracy of the detection result of the surface defects of the melt-blown non-woven fabric is ensured, and the production quality and the production efficiency of the personal protective clothing are improved.
Disclosure of Invention
The invention provides an intelligent detection system for production abnormality of personal protective clothing for epidemic prevention, which aims to solve the problem that the production quality is affected by inaccurate detection of local defects on the surface of the existing melt-blown cloth, and adopts the following technical scheme:
one embodiment of the present invention provides an intelligent detection system for personal protective clothing production anomalies for epidemic prevention, the system comprising:
the surface image acquisition module acquires a melt-blown cloth surface image to obtain a gray image, and acquires an abnormality detection kernel of each position for the gray image;
an image processing analysis module: grading gray values of pixel points in the anomaly detection cores at each position, acquiring fiber uniformity of each position according to gray level distribution in the anomaly detection cores at each position, and constructing gray scale run matrixes of the anomaly detection cores at each position in four directions;
acquiring run distribution differences of two positions in the same direction according to the gray scale run matrixes of any two positions in the same direction, acquiring the distribution difference degree of the two positions according to the run distribution differences of all directions, and acquiring the flying abnormal degree of each position according to the distribution difference degree and the fiber uniformity;
and the surface abnormality detection module is used for acquiring an abnormality detection result of each position of the surface of the melt-blown fabric according to the uniformity of the fiber and the degree of the flying abnormality, and finishing production abnormality detection.
Optionally, the method for obtaining the uniformity of the fiber at each position includes the following specific steps:
wherein ,representation of the position->Uniformity coefficient of>Representing the number of gray levels +.>Representation of the position->The gray level of the pixel point in the anomaly detection kernel is +.>And the neighborhood gray level mean value is +.>Is added to the gray level combination of the pixel points in the kernel according to the ratio of the gray level combination of the pixel points in the kernel>Represent the logarithm of the base natural constant;
and obtaining the uniformity coefficient of each position in the gray level image, normalizing all the uniformity coefficients, and recording the obtained result as the fiber uniformity of each position.
Optionally, the constructing the gray scale run matrix of the anomaly detection kernel at each position in four directions includes the following specific methods:
in position ofFor the target position, constructing gray scale run matrixes for pixel points in anomaly detection cores of the target position according to gray scales, wherein the number of lines of each gray scale run matrix is +.>Column number is->, wherein />Representing the number of gray levels +.>The side length of the abnormality detection core is represented, and the four directions are +.>、/>、/> and />For position->Four gray scale run matrices are obtained, respectively denoted +.>、/>、/> and />；
Four gray scale run matrices of the anomaly detection kernel for each position are acquired.
Optionally, the acquiring the run distribution difference of the two positions in the same direction includes the following specific steps:
in position ofFor the target position, any one of the other positions is marked as +.>Then for both positions +.>Gray scale run matrix->Is->Run distribution difference->The calculation method of (1) is as follows:
wherein ,representing the number of columns of the gray scale run matrix, i.e. the number of runs, +.>Representation of the position->At->The run length in the gray scale run matrix of (2) is +.>The sum of the matrix element values of (2), i.e. the run length in the matrix is +.>The total number of occurrences of the run of (c) is,representation of the position->At->The run length in the gray scale run matrix of (2) is +.>Sum of matrix element values of>Representing absolute value;
acquisition positionAnd position->At->、/> and />A run distribution difference on a gray scale run matrix; and acquiring the run distribution difference of any two positions in each direction.
Optionally, the obtaining the distribution difference degree of the two positions according to the run distribution differences in all directions includes the following specific methods:
taking the average value of the run distribution differences of any two positions in four directions as the distribution difference degree of the two positions.
Optionally, the method for obtaining the fly waste abnormal degree of each position according to the distribution difference degree and the fiber uniformity includes the following specific steps:
wherein ,representation of the position->Degree of flight abnormality of->Representing a set of positions corresponding to all abnormality detection cores, +.>Representing the total number of positions corresponding to all abnormality detection cores, < >>Representation of the position->Is used for the fiber uniformity of the fiber,representation of the position->Fiber uniformity of->Representation of the position->And position->Distribution difference degree of (3);
and acquiring the degree of the flying abnormal of each position.
The beneficial effects of the invention are as follows: according to the invention, an anomaly detection core is constructed for each position in a gray level image of a melt-blown fabric surface image, firstly, fiber uniformity of each position is quantified according to gray level distribution in the anomaly detection core, the fiber uniformity reflects the degree of fiber density and the degree of anomaly aggregation of each position, the smaller the fiber uniformity is, the uneven fiber distribution in the anomaly detection core is indicated, and the defect detection can be carried out as a parameter of uneven spinning defect; the distribution difference of short runs is constructed and considered through a gray run matrix, so that the distribution difference degree is obtained quantitatively, the flying abnormal degree is obtained by combining the fiber uniformity difference of each position, the short runs have larger difference, the fiber distribution is uneven, the fibers at the target positions float on the surface for a large number, and flying defects are more likely to occur; and the defects are detected, and meanwhile, different defects are distinguished, so that the accuracy of an abnormal detection result of the melt-blown fabric is improved, and the working efficiency of production of the personal protective clothing is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a block diagram of an intelligent detection system for personal protective clothing production anomalies for epidemic prevention according to one embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a block diagram of a personal protective garment production anomaly intelligent detection system for epidemic prevention according to an embodiment of the present invention is shown, the system includes:
and a surface image acquisition module S101 for acquiring a melt-blown cloth surface image to obtain a gray image, and acquiring an abnormality detection kernel of each position for the gray image.
The object of this embodiment is to accurately detect defects on the surface of the meltblown fabric, so that the image of the surface of the meltblown fabric needs to be acquired first; in the embodiment, a light source is arranged at a discharge hole of a melt-blown fabric production, the light source is arranged below the melt-blown fabric, an industrial camera is arranged above the melt-blown fabric, an image of the surface of the melt-blown fabric is acquired through the industrial camera, and a gray image is acquired through gray processing; it should be noted that, the collected surface images and gray level images are square images, i.e. the length and the width of the surface images and the gray level images are equal in number; setting a plurality of anomaly detection kernels according to the resolution of the camera, wherein the anomaly detection kernels are a smaller anomaly detection range, traversing on the gray level image, and the anomaly detection kernels are still square, and the embodiment adopts 1/100 of the length of the gray level image as the side length of the anomaly detection kernels, namely the number of pixels of the side length of the anomaly detection kernels is 1/100 of the number of pixels of the gray level image; the anomaly detection kernels at each position can be obtained by traversing the anomaly detection kernels on the gray level image, and it should be noted that some positions cannot obtain complete anomaly detection kernels in the gray level image, i.e., the anomaly detection kernels at the positions exceed the gray level image range, and the anomaly detection kernels are not obtained for the positions in this embodiment.
Thus, a gray image of the meltblown surface image was obtained, and an abnormality detection kernel for each position was set on the gray image.
The image processing analysis module S102:
(1) And obtaining the fiber uniformity of each position according to the gray value distribution in the anomaly detection core of each position, and constructing a gray scale run matrix of the anomaly detection core of each position in four directions.
It should be noted that, for a gray image of a surface image of a melt-blown fabric, the lower the light source is, the lower the transmittance is, the lower the gray value is, which means that the more dense the fibers are, whereas the more sparse the gray level is, the uniformity of the distribution of gray levels of pixel points at different positions on the image is utilized to calculate the uniformity of the fibers.
Specifically, taking an abnormality detection core at any one position as an example, the position is expressed asThe abnormality detection core size is expressed as +.>Gradation values of each pixel point in the abnormality detection kernel are classified, the present embodiment classifies the gradation values into 26 levels, and if 10 gradation values are one level, level 1 is +.>Level 2 +.>,., grade 25Level 26 +.>The method comprises the steps of carrying out a first treatment on the surface of the Acquiring the level of the gray value of each pixel point in the anomaly detection kernel according to the gray value, and marking the level as the gray level of each pixel point; the gray level of any pixel point in the abnormality detection kernel is recorded asThe neighborhood gray level mean value is marked as +.>Wherein the neighborhood gray level mean is rounded down to +.>Counting the duty ratio of the gray level combination corresponding to all pixel points in the anomaly detection core, and marking the duty ratio as +.>Location->Is of the fiber uniformity of (a)The calculation method of (1) is as follows:
wherein ,representation of the position->Uniformity coefficient of>Representing the number of gray levels +.>Representation of the position->The gray level of the pixel point in the anomaly detection kernel is +.>And the neighborhood gray level mean value is +.>Is added to the gray level combination of the pixel points in the kernel according to the ratio of the gray level combination of the pixel points in the kernel>Represent the logarithm of the base natural constant; obtaining uniform coefficients by a calculation method similar to entropy values, and entropyThe larger the value is, the more uneven the gray level distribution is, the smaller the uniformity coefficient is, the entropy value is calculated as the opposite number of the uniformity coefficient, so that the more uniform the gray level distribution is, the larger the uniformity coefficient is, and the uniformity coefficient is negative; according to the method, the uniformity coefficient of each position in the gray level image is obtained, all the uniformity coefficients are subjected to linear normalization, the obtained result is recorded as the fiber uniformity of each position, the fiber uniformity represents the uniformity degree of gray level distribution in the anomaly detection core of each position, and the larger the uniformity degree of gray level distribution is, the more uniform the fiber distribution in the anomaly detection core is.
Further, taking any position and an anomaly detection kernel thereof as an example, a gray level run matrix is constructed according to gray levels for pixel points in the anomaly detection kernel, and because the anomaly detection kernel is square, the embodiment constructs four gray level run matrices in four directions altogether, rows in the gray level run matrix represent different gray levels, columns represent run lengths, and the number of rows of each gray level run matrix is the same as that of the rows of the other gray level run matrixColumn number is->, wherein />Representing the number of gray levels +.in this embodiment>，/>The side length of the abnormality detection core is represented, and the four directions are +.>、/>、/> and />Then ∈>Four gray scale run-length matrixes are obtained in total and respectively marked as、/>、/> and />In this embodiment, the right horizontal direction is +.>Rotating clockwise by an increasing angle; and acquiring four gray scale run matrixes of the anomaly detection core at each position according to the method.
Thus, the fiber uniformity of each position and four gray scale run-length matrixes of each position are obtained.
(2) According to the gray scale run matrix of any two positions in the same direction, the run distribution difference of the two positions in the direction is obtained, the distribution difference degree of the two positions is obtained according to the run distribution difference of all directions, and the flying abnormal degree of each position is obtained according to the distribution difference degree and the fiber uniformity.
The fiber uniformity corresponding to any one position is taken as a target position, the fiber uniformity characteristic in the abnormality detection core is represented, and the gray scale run matrix in the corresponding four directions is represented by the fiber extending direction and the length characteristic in the abnormality detection core; the difference of the distribution of different run lengths in the gray scale run matrix at the target position and other positions represents the abnormal degree of the fiber extension and length, and the shorter runs in the gray scale run matrix at the target position are compared with the runs Cheng Yue in the gray scale run matrix at other positions, so that the shorter the fiber extension at the target position is; that is, under the same conditions, only a short portion of the filaments on the surface of the meltblown web adhere to the receiving web, a portion of the fibers float on the surface of the meltblown web, indicating that fly may occur at the target location, while the difference between the uniformity of the fibers indicates a reference level of the gray scale run matrix feature at the other location relative to the target location, and if the uniformity of the fibers at the other location is greater than the target location, indicating that the gray scale run matrix feature at the other location indicates a fiber feature of normal fiber distribution, the reference level is greater, otherwise, the reference level is smaller.
In particular, in terms of positionFor the target position, any one of the other positions is marked as +.>Then for both positions +.>Gray scale run matrix->Is->The run distribution is different->The calculation method of (1) is as follows:
wherein ,representing the number of columns of the gray scale run matrix, i.e. the number of runs, +.>Representation of the position->At->The run length in the gray scale run matrix of (2) is +.>The sum of the matrix element values of (2), i.e. the run length in the matrix is +.>The total number of occurrences of the run of (c) is,representation of the position->At->The run length in the gray scale run matrix of (2) is +.>Sum of matrix element values of>Representing absolute value; at this time->Smaller (less)>The larger, i.e. the greater the interest in short runs, the more critical the +.>The greater the degree of interest; in the gray scale run matrixes with the same positions and the same direction, the larger the total number difference of the same run length is, the larger the run distribution difference is; and run distribution difference->For normalized values, i.e. the value range is +.>The more towards 1, the two positions are +.>The larger the run distribution difference in the gray scale run matrix; acquiring the run distribution differences of two positions in the other three directions according to the method, taking the mean value of the run distribution differences in four directions as the distribution difference degree of the two positions, and marking the mean value as +.>The method comprises the steps of carrying out a first treatment on the surface of the Obtaining the target position according to the above method>The degree of difference from the distribution of each of the other locations.
Further, the degree of fly-away anomaly is calculated according to the degree of distribution difference and the uniformity of fibers, and the position is calculatedDegree of fly abnormality->The calculation method of (1) is as follows:
wherein ,representing a set of positions corresponding to all abnormality detection cores, +.>Representing the total number of positions corresponding to all abnormality detection cores, < >>Representation of the position->Fiber uniformity of->Representation of the position->Is used for the fiber uniformity of the fiber,representation of the position->And position->Distribution difference degree of (3); the more the fiber uniformity of other positions is greater than that of the target position, the more normal the fiber distribution of the position is, the greater the reference degree of the distribution difference degree between the position and the target position is, and the greater the distribution difference degree is, the greater the possibility of abnormality is; the smaller the fiber uniformity of the target position is, the larger the degree of the distribution difference is, the uneven fiber distribution is, the larger the difference between the fiber length and other positions is, the larger the possibility of the occurrence of the flying defect is, and the larger the degree of the flying abnormality is; />For the normalized value, the closer to 1, the more likely the target position is to have fly-over defects; and acquiring the degree of the flying abnormal at each position according to the method.
The flying abnormal degree of each position is obtained so as to reflect the possibility of flying defect of each position.
And the surface abnormality detection module S103 acquires an abnormality detection result of each position of the surface of the melt-blown fabric according to the uniformity of the fiber and the degree of the flying abnormality, and completes production abnormality detection.
After obtaining the fiber uniformity and the flying degree of abnormality of each position, the fiber uniformity mainly reflects the uneven spinning defect, so that uneven spinning judgment is carried out according to the fiber uniformity of each position, a preset first threshold value is given for judging the uneven spinning defect, the preset first threshold value in the embodiment is calculated by 0.4, and for any position, if the fiber uniformity of the position is smaller than the preset first threshold value, the uneven spinning defect exists in the position; meanwhile, judging the surface flying defect according to the flying abnormal degree, and giving a preset second threshold value for judging the surface flying defect, wherein the preset second threshold value is calculated by 0.4, and if the flying abnormal degree of any position is larger than the preset second threshold value, the position is indicated to have the surface flying defect; it should be noted that, firstly, judging the surface flying defect of each position, if the degree of the flying abnormality is greater than a preset second threshold value, the surface flying defect exists, if the degree of the flying abnormality is less than or equal to the preset second threshold value, and meanwhile, if the degree of the fiber uniformity is less than a preset first threshold value, the defect of uneven spinning exists, if the degree of the flying abnormality is less than or equal to the preset second threshold value, and if the degree of the fiber uniformity is greater than or equal to the preset first threshold value, the defect does not exist at the position; and performing defect detection on each position of the surface of the melt-blown cloth according to the method, and finishing the abnormal detection of the surface of the melt-blown cloth.
By detecting the abnormality of the surface of the melt-blown cloth, intelligent abnormality detection in the production process of the personal protective clothing is realized.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (6)
1. An intelligent detection system for personal protective clothing production anomalies for epidemic prevention, characterized in that the system comprises:
the surface image acquisition module acquires a melt-blown cloth surface image to obtain a gray image, and acquires an abnormality detection kernel of each position for the gray image;
an image processing analysis module: grading gray values of pixel points in the anomaly detection cores at each position, acquiring fiber uniformity of each position according to gray level distribution in the anomaly detection cores at each position, and constructing gray scale run matrixes of the anomaly detection cores at each position in four directions;
acquiring run distribution differences of two positions in the same direction according to the gray scale run matrixes of any two positions in the same direction, acquiring the distribution difference degree of the two positions according to the run distribution differences of all directions, and acquiring the flying abnormal degree of each position according to the distribution difference degree and the fiber uniformity;
and the surface abnormality detection module is used for acquiring an abnormality detection result of each position of the surface of the melt-blown fabric according to the uniformity of the fiber and the degree of the flying abnormality, and finishing production abnormality detection.
2. The intelligent detection system for abnormal production of personal protective clothing for epidemic prevention according to claim 1, wherein the method for obtaining the uniformity of the fiber at each position comprises the following specific steps:
wherein ,representation of the position->Uniformity coefficient of>Representing the number of gray levels +.>Representation of the position->The gray level of the pixel point in the anomaly detection kernel is +.>And the neighborhood gray level mean value is +.>Is added to the gray level combination of the pixel points in the kernel according to the ratio of the gray level combination of the pixel points in the kernel>Represent the logarithm of the base natural constant;
and obtaining the uniformity coefficient of each position in the gray level image, normalizing all the uniformity coefficients, and recording the obtained result as the fiber uniformity of each position.
3. The intelligent detection system for personal protective clothing production anomalies for epidemic prevention according to claim 1, wherein the construction of the gray scale run matrix of anomaly detection cores at each position in four directions comprises the following specific steps:
in position ofFor the target position, constructing gray scale run matrixes for pixel points in anomaly detection cores of the target position according to gray scales, wherein the number of lines of each gray scale run matrix is +.>Column number is->, wherein />Representing the number of gray levels +.>The side length of the abnormality detection core is represented, and the four directions are +.>、/>、/> and />For position->Four gray scale run matrices are obtained, respectively denoted +.>、/>、/> and />；
Four gray scale run matrices of the anomaly detection kernel for each position are acquired.
4. The intelligent detection system for personal protective clothing production anomalies for epidemic prevention according to claim 1, wherein the method for acquiring the run distribution difference of two positions in the same direction comprises the following specific steps:
in position ofFor the target position, any one of the other positions is marked as +.>Then for both positions +.>Gray scale run matrix->Is->Run distribution difference->The calculation method of (1) is as follows:
wherein ,representing the number of columns of the gray scale run matrix, i.e. the number of runs, +.>Representation of the position->At->The run length in the gray scale run matrix of (2) is +.>The sum of the matrix element values of (2), i.e. the run length in the matrix is +.>The total number of occurrences of the run of (c) is,representation of the position->At->The run length in the gray scale run matrix of (2) is +.>Sum of matrix element values of>Representing absolute value;
acquisition positionAnd position->At->、/> and />A run distribution difference on a gray scale run matrix; and acquiring the run distribution difference of any two positions in each direction.
5. The intelligent detection system for personal protective clothing production abnormality for epidemic prevention according to claim 1, wherein the method for obtaining the distribution difference degree of two positions according to the run distribution difference in all directions comprises the following specific steps:
taking the average value of the run distribution differences of any two positions in four directions as the distribution difference degree of the two positions.
6. The intelligent detection system for personal protective clothing production abnormality for epidemic prevention according to claim 1, wherein the method for obtaining the flying abnormal degree of each position according to the distribution difference degree and the fiber uniformity comprises the following specific steps:
wherein ,representation of the position->Degree of flight abnormality of->Representing a set of locations corresponding to all anomaly detection cores,representing the total number of positions corresponding to all abnormality detection cores, < >>Representation of the position->Fiber uniformity of->Representation of the position->Fiber uniformity of->Representation of the position->And position->Distribution difference degree of (3);
and acquiring the degree of the flying abnormal of each position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310715645.2A CN116485790B (en) | 2023-06-16 | 2023-06-16 | Intelligent detection system for personal protective clothing production abnormality for epidemic prevention |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310715645.2A CN116485790B (en) | 2023-06-16 | 2023-06-16 | Intelligent detection system for personal protective clothing production abnormality for epidemic prevention |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116485790A CN116485790A (en) | 2023-07-25 |
| CN116485790B true CN116485790B (en) | 2023-08-22 |
Family
ID=87223478
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310715645.2A Active CN116485790B (en) | 2023-06-16 | 2023-06-16 | Intelligent detection system for personal protective clothing production abnormality for epidemic prevention |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116485790B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109684875A (en) * | 2018-11-30 | 2019-04-26 | 深圳灵图慧视科技有限公司 | Cloth detects recording method, device, equipment and storage medium |
| CN113610848A (en) * | 2021-10-09 | 2021-11-05 | 阿里巴巴（中国）有限公司 | Digital cloth processing system, cloth flaw detection method, device and medium |
| CN114913178A (en) * | 2022-07-19 | 2022-08-16 | 山东天宸塑业有限公司 | Melt-blown fabric defect detection method and system |
| CN114998206A (en) * | 2022-04-24 | 2022-09-02 | 江苏莎数自动化设备有限公司 | Intelligent control method and system for melt-blown process parameters |
| CN115719344A (en) * | 2022-11-24 | 2023-02-28 | 南通世森布业有限公司 | Fabric defect analysis and identification method for textile fabric quality inspection |
-
2023
- 2023-06-16 CN CN202310715645.2A patent/CN116485790B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109684875A (en) * | 2018-11-30 | 2019-04-26 | 深圳灵图慧视科技有限公司 | Cloth detects recording method, device, equipment and storage medium |
| CN113610848A (en) * | 2021-10-09 | 2021-11-05 | 阿里巴巴（中国）有限公司 | Digital cloth processing system, cloth flaw detection method, device and medium |
| CN114998206A (en) * | 2022-04-24 | 2022-09-02 | 江苏莎数自动化设备有限公司 | Intelligent control method and system for melt-blown process parameters |
| CN114913178A (en) * | 2022-07-19 | 2022-08-16 | 山东天宸塑业有限公司 | Melt-blown fabric defect detection method and system |
| CN115719344A (en) * | 2022-11-24 | 2023-02-28 | 南通世森布业有限公司 | Fabric defect analysis and identification method for textile fabric quality inspection |
Non-Patent Citations (1)
| Title |
|---|
| "SVM 在无纺布质量检测方面的应用";陈先 等;《实验研究》;第90-94页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116485790A (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108037133B (en) | Intelligent electric power equipment defect identification method and system based on unmanned aerial vehicle inspection image | |
| CN106326808B (en) | Method for detecting bird nest on power transmission line tower based on unmanned aerial vehicle image | |
| CN104408473B (en) | Cotton grade sorting technique and device based on learning distance metric | |
| CN112418128B (en) | Surface water monitoring and management system and method | |
| CN103927553B (en) | Coal and rock recognition method based on multi-scale micro-lamination and contrast ratio joint distribution | |
| CN112740267A (en) | Learning data collection device, learning data collection method, and program | |
| CN104700395A (en) | Method and system for detecting appearance crack of structure | |
| Haidari et al. | Deep learning-based model for fault classification in solar modules using infrared images | |
| CN115311284B (en) | Production quality detection method for glass fiber mat | |
| CN114881960A (en) | Feature enhancement-based cloth linear defect detection method and system | |
| CN116012701A (en) | Water treatment dosing control method and device based on alum blossom detection | |
| CN116485790B (en) | Intelligent detection system for personal protective clothing production abnormality for epidemic prevention | |
| CN114972339A (en) | Data enhancement system for bulldozer structural member production abnormity detection | |
| CN112616425B (en) | On-line detection method, system and device for operation performance of grain combine harvester | |
| JPH05263411A (en) | Object observation method and device | |
| CN113469974A (en) | Method and system for monitoring grate plate state of pellet chain grate | |
| CN107977531A (en) | A kind of method that ground resistance hard measurement is carried out based on image procossing and field mathematical model | |
| CN116152220A (en) | Seed counting and size measuring method based on machine vision | |
| CN115423807A (en) | Cloth defect detection method based on outlier detection | |
| CN114399669A (en) | Target detection method and device | |
| CN107909555A (en) | A kind of gridding noise elimination method for keeping acutance | |
| CN113091699A (en) | Micro-displacement amplification method based on video image | |
| JP2012234245A (en) | Method for inspecting edible fruit, inspection device, and program | |
| CN113538489B (en) | Method for measuring fiber diameter of non-woven fabric | |
| CN110533644A (en) | A kind of isolator detecting method based on image recognition |
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 |