CN117710901B - Cable manufacture abnormality detection system based on machine vision - Google Patents
Cable manufacture abnormality detection system based on machine vision Download PDFInfo
- Publication number
- CN117710901B CN117710901B CN202410145743.1A CN202410145743A CN117710901B CN 117710901 B CN117710901 B CN 117710901B CN 202410145743 A CN202410145743 A CN 202410145743A CN 117710901 B CN117710901 B CN 117710901B
- Authority
- CN
- China
- Prior art keywords
- cable
- image
- module
- abnormality
- coefficient
- 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
- 230000005856 abnormality Effects 0.000 title claims abstract description 93
- 238000001514 detection method Methods 0.000 title claims abstract description 73
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 38
- 230000002159 abnormal effect Effects 0.000 claims abstract description 30
- 238000007781 pre-processing Methods 0.000 claims abstract description 21
- 238000000605 extraction Methods 0.000 claims abstract description 16
- 238000013178 mathematical model Methods 0.000 claims description 24
- 238000004364 calculation method Methods 0.000 claims description 23
- 238000012937 correction Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 9
- 230000008030 elimination Effects 0.000 claims description 6
- 238000003379 elimination reaction Methods 0.000 claims description 6
- 230000001788 irregular Effects 0.000 claims description 6
- 230000002146 bilateral effect Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 238000009432 framing Methods 0.000 abstract 1
- 230000007547 defect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000004382 visual function Effects 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of automation, and discloses a cable manufacturing abnormality detection system based on machine vision, which comprises the following components: the system comprises a cable image acquisition module, an acquired image preprocessing module, a characteristic information extraction module, a surface abnormality judgment module, a shape abnormality detection module, a pixel difference comparison module, a system abnormality self-adjustment module, an adjusted detection model establishment module and a system abnormality early warning module, wherein the cable image is subjected to framing processing to obtain cable related data of each frame of image, the surface integrity coefficient, the shape matching coefficient and the pixel homogeneity coefficient of the cable are calculated, whether abnormality occurs or not is judged according to a preset threshold value, the abnormality module is automatically adjusted, the adjusted detection model establishment module calculates an image abnormality index, whether abnormal state occurs in cable manufacture is detected according to the image abnormality index, early warning prompt is carried out, and labor cost is reduced and production quality of the cable is improved through automatic detection.
Description
Technical Field
The invention relates to the technical field of automation, in particular to a cable manufacturing abnormality detection system based on machine vision.
Background
The machine vision is a branch of rapid development of artificial intelligence, mainly comprises simulating human visual functions by a computer, using a machine to replace human eyes for measurement and judgment, converting a shot object into an image signal by a machine vision product, transmitting the image signal to a special image processing system to obtain form information of the shot object, converting the form information into a digital signal according to information such as pixel distribution, brightness, color and the like, and performing various operations on the signals by the image system to extract characteristics of the object, and further controlling on-site equipment action according to a judging result.
In the cable manufacturing process, defects or anomalies may be caused in the produced cable due to various reasons, so that not only the quality of the cable is affected, but also safety accidents may be caused, therefore, the cable manufacturing anomaly detection becomes an important research direction, the cable manufacturing anomaly detection system based on machine vision is realized, the anomaly detection method in the cable manufacturing process is realized by using a computer vision technology, various anomalies in the cable manufacturing process can be quickly and accurately found through automatic detection of the cable, and a powerful guarantee is provided for improving the quality and the production efficiency of the cable.
Limitations of conventional detection methods: the traditional cable manufacturing abnormality detection method mainly depends on manual detection, is low in efficiency, is easily affected by human factors, is difficult to accurately judge for some tiny defects, and is lack of automatic adjustment for abnormal conditions due to the fact that early warning reminding is sent out through judgment, so that the working intensity of manual work is increased, and production efficiency of cable production is not improved.
Disclosure of Invention
In order to overcome the above-mentioned drawbacks of the prior art, the present invention provides a system for detecting abnormal manufacturing of a cable based on machine vision, so as to solve the above-mentioned problems in the prior art.
The invention provides the following technical scheme: a machine vision-based cable manufacturing anomaly detection system, comprising: the system comprises a cable image acquisition module, an acquired image preprocessing module, a characteristic information extraction module, a surface abnormality judging module, a shape abnormality detecting module, a pixel difference comparing module, a system abnormality self-adjusting module, an adjusted detection model building module and a system abnormality early warning module;
The cable image acquisition module adopts a high-resolution industrial camera to shoot the cable on a production line in real time, acquires primary image data, and transmits the acquired primary image data to the acquired image preprocessing module;
The collected image preprocessing module comprises a noise elimination unit, a geometric transformation unit and a color correction unit, receives primary image data transmitted by the cable image collecting module, acquires secondary image data through preprocessing operation, and transmits the secondary image data to the characteristic information extracting module;
The characteristic information extraction module is used for receiving the secondary image data transmitted by the collected image preprocessing module, extracting characteristic information of the secondary image data by utilizing an edge detection algorithm, wherein the characteristic information comprises cable surface information, cable shape information and cable pixel information;
The surface abnormality judging module is used for calculating a surface integrity coefficient through a cable surface detection mathematical model based on the cable surface information extracted by the characteristic information extracting module, and transmitting the calculated surface integrity coefficient to the system abnormality self-adjusting module and the post-adjustment detection model building module;
the shape anomaly detection module is used for calculating a shape matching degree coefficient through a cable shape detection mathematical model based on the cable shape information extracted by the characteristic information extraction module, and transmitting the calculated shape matching degree coefficient to the system anomaly self-adjustment module and the post-adjustment detection model establishment module;
The pixel difference comparison module is used for calculating a pixel homogeneity coefficient through a cable pixel detection mathematical model based on the cable pixel information extracted by the characteristic information extraction module, and transmitting the calculated pixel homogeneity coefficient to the system abnormity self-adjustment module;
The system abnormality self-adjusting module is used for receiving the surface integrity coefficient, the shape matching degree coefficient and the pixel homogeneity coefficient transmitted by the surface abnormality judging module, the shape abnormality detecting module and the pixel difference comparing module, judging whether abnormality occurs according to a preset threshold value, and automatically adjusting the abnormality module;
The post-adjustment detection model building module is used for building a mathematical model to calculate an image abnormality index based on the surface integrity coefficient, the shape matching coefficient and the pixel homogeneity coefficient obtained after adjustment of the system abnormality self-adjustment module, and transmitting a calculation result to the system abnormality early warning module;
the system abnormality early warning module is used for receiving the image abnormality index transmitted by the adjusted detection model building module, detecting whether the abnormal state occurs in the cable manufacture or not, and carrying out early warning prompt.
Preferably, the primary image data acquired in the cable image acquisition module includes n frames of images, denoted as i=1, 2, 3.
Preferably, the noise elimination unit in the collected image preprocessing module reduces noise through bilateral filtering, the geometric transformation unit realizes geometric transformation of the image through matrix operation and interpolation algorithm, and the color correction unit performs color correction on the image through color space conversion, color balance and color mapping.
Preferably, the feature information extracting module extracts feature information of the secondary image data, including extracting image feature information of n frames of images;
The cable surface information comprises the circularity of the cable edge line of each frame of gray level image, the gray level area of each frame of gray level image, the perimeter of the cable edge line of each frame of gray level image, the irregular length of the cable edge line of each frame of gray level image, the standard circularity of the cable edge line and the image frame number, which are respectively used 、/>、/>、/>、/>/>A representation;
The cable shape information includes the abscissa of each intersection point in each frame image and the ordinate of each intersection point in each frame image, respectively And/>A representation;
the cable pixel information includes coordinates of pixels in each frame image, pixel gap values in each frame image, average pixels in each frame image, and standard deviations of pixel gap values in each frame image, respectively 、/>、/>/>And (3) representing.
Preferably, the surface integrity coefficient calculation step of the surface anomaly determination module by using the cable surface detection mathematical model is as follows:
step S01: carrying out gray scale treatment on the n frames of images to obtain gray scale images of the cable surface;
Step S02: calculating the circularity of the cable edge line of each frame gray image, wherein the calculation formula is as follows: wherein/> Representing the circularity of the cable edge line of each frame gray level image,/>Representing the gray scale area of each frame gray scale image,/>Perimeter of cable edge line representing gray level image of each frame,/>The irregular length of the cable edge line of each frame gray level image is represented;
step S03: calculating the surface integrity coefficient of the cable, wherein the calculation formula is as follows: wherein/> Representing the surface integrity factor,/>Representing the circularity of the cable edge line of each frame gray level image,/>Representing the standard circularity of the cable edge line,/>Representing the number of image frames.
Preferably, the calculating step of calculating the shape matching degree coefficient by the cable shape detection mathematical model in the shape anomaly detection module is as follows:
step S01: the intersection point in the n frames of images is expressed by coordinates, and the coordinates of each intersection point at the midpoint of the ith frame of image are expressed as ；
Step S02: calculating the shape matching degree coefficient of the cable, wherein the calculation formula is as follows: wherein/> Representing shape matching degree coefficient,/>Representing the coordinates of each intersection point in each frame of image,/>Representing the abscissa of each intersection in each frame of image,/>The ordinate of each intersection point in each frame image is indicated.
Preferably, the step of calculating the pixel homogeneity coefficient by using a cable pixel detection mathematical model in the pixel difference comparison module is as follows:
step S01: the pixels in the n-frame image are represented by coordinates, and the coordinates of the pixels in the i-th frame image are represented as ；
Step S02: calculating pixel homogeneity coefficient of the cable, wherein the calculation formula isWhereinRepresenting the pixel homogeneity coefficient,/>Representing coordinates of pixels in each frame of image,/>Representing the pixel gap value in each frame of image,/>Representing the average pixel in each frame of image,/>Representing the standard deviation of the pixel gap values in each frame of image.
Preferably, the system anomaly self-adjusting module receives the surface integrity coefficient transmitted by the surface anomaly judging module and sends the surface integrity coefficient to the system anomaly self-adjusting moduleAnd a preset first judgment threshold/>For comparison, if the surface integrity coefficient/>Greater than or equal to a preset first judgment threshold/>Judging whether the surface of the cable is abnormal, if the surface integrity coefficient/>Less than a preset first judgment threshold/>Judging that the surface of the cable is abnormal, and starting a system abnormal self-adjusting module;
Matching the shape to the coefficient of degree And a preset second judgment threshold/>Comparing, if the shape matching degree coefficientGreater than or equal to a preset second judgment threshold/>Judging whether the cable shape is abnormal, and if the shape matching degree coefficient/>Less than a preset second judgment threshold/>Judging that the cable shape is abnormal, and starting a system abnormality self-adjusting module;
Pixel homogeneity coefficient And a preset third judgment threshold/>Comparing, if the pixel homogeneity coefficientGreater than or equal to a preset third judgment threshold/>Judging whether the cable is abnormal, if the pixel homogeneity coefficient/>Less than a preset third judgment threshold/>And judging the abnormality in the cable, and starting the system abnormality self-adjusting module.
Preferably, the post-adjustment detection model building module builds a mathematical model to calculate an image anomaly index, and a calculation formula of the image anomaly index is as follows: wherein/> Representing an image anomaly index, n representing the number of image frames,/>Representing the surface integrity factor,/>Representing shape matching degree coefficient,/>Representing the pixel homogeneity coefficient,、/>And/>Representing a constant.
Preferably, the system abnormality early warning module receives the image abnormality index transmitted by the adjusted detection model building moduleIndex of image abnormality/>Judging threshold value/>, with preset cable imageComparing, if the image abnormality index/>Greater than a preset cable image judgment threshold/>Judging that the cable is abnormal in manufacture, transmitting early warning prompt to a system terminal, and if the image abnormality index/>Less than or equal to a preset cable image judgment threshold/>And judging that the cable is manufactured abnormally.
The invention has the technical effects and advantages that:
The invention processes the cable image frame by frame to obtain the cable related data of each frame image, calculates the surface integrity coefficient, shape matching coefficient and pixel homogeneity coefficient of the cable, judges whether the abnormality occurs according to the preset threshold value, automatically adjusts the abnormality module, and the post-adjustment detection model building module calculates the image abnormality index, detects whether the abnormal state occurs in the cable manufacture according to the image abnormality index, and carries out early warning prompt.
Drawings
Fig. 1 is a flow chart of a machine vision based cable manufacturing anomaly detection system.
Fig. 2 is a flow chart of an acquired image preprocessing module.
Fig. 3 is a block diagram of the feature information extraction module.
Detailed Description
The embodiments of the present invention will be clearly and completely described below with reference to the drawings in the present invention, and the configurations of the structures described in the following embodiments are merely examples, and the system for detecting abnormal manufacturing of a cable according to the present invention is not limited to the structures described in the following embodiments, and all other embodiments obtained by a person having ordinary skill in the art without making any creative effort are within the scope of the present invention.
The invention provides a cable manufacture abnormality detection system based on machine vision, which comprises: the system comprises a cable image acquisition module, an acquired image preprocessing module, a characteristic information extraction module, a surface abnormality judging module, a shape abnormality detecting module, a pixel difference comparing module, a system abnormality self-adjusting module, an adjusted detection model building module and a system abnormality early warning module;
The cable image acquisition module adopts a high-resolution industrial camera to shoot the cable on a production line in real time, acquires primary image data, and transmits the acquired primary image data to the acquired image preprocessing module;
The collected image preprocessing module comprises a noise elimination unit, a geometric transformation unit and a color correction unit, receives primary image data transmitted by the cable image collecting module, acquires secondary image data through preprocessing operation, and transmits the secondary image data to the characteristic information extracting module;
The characteristic information extraction module is used for receiving the secondary image data transmitted by the collected image preprocessing module, extracting characteristic information of the secondary image data by utilizing an edge detection algorithm, wherein the characteristic information comprises cable surface information, cable shape information and cable pixel information;
The surface abnormality judging module is used for calculating a surface integrity coefficient through a cable surface detection mathematical model based on the cable surface information extracted by the characteristic information extracting module, and transmitting the calculated surface integrity coefficient to the system abnormality self-adjusting module and the post-adjustment detection model building module;
the shape anomaly detection module is used for calculating a shape matching degree coefficient through a cable shape detection mathematical model based on the cable shape information extracted by the characteristic information extraction module, and transmitting the calculated shape matching degree coefficient to the system anomaly self-adjustment module and the post-adjustment detection model establishment module;
The pixel difference comparison module is used for calculating a pixel homogeneity coefficient through a cable pixel detection mathematical model based on the cable pixel information extracted by the characteristic information extraction module, and transmitting the calculated pixel homogeneity coefficient to the system abnormity self-adjustment module;
The system abnormality self-adjusting module is used for receiving the surface integrity coefficient, the shape matching degree coefficient and the pixel homogeneity coefficient transmitted by the surface abnormality judging module, the shape abnormality detecting module and the pixel difference comparing module, judging whether abnormality occurs according to a preset threshold value, and automatically adjusting the abnormality module;
The post-adjustment detection model building module is used for building a mathematical model to calculate an image abnormality index based on the surface integrity coefficient, the shape matching coefficient and the pixel homogeneity coefficient obtained after adjustment of the system abnormality self-adjustment module, and transmitting a calculation result to the system abnormality early warning module;
the system abnormality early warning module is used for receiving the image abnormality index transmitted by the adjusted detection model building module, detecting whether the abnormal state occurs in the cable manufacture or not, and carrying out early warning prompt.
In this embodiment, it should be specifically described that the primary image data acquired in the cable image acquisition module includes n frames of images, which are denoted as i=1, 2, 3.
In this embodiment, it should be specifically described that, in the collected image preprocessing module, the noise elimination unit reduces noise through bilateral filtering, the geometric transformation unit implements geometric transformation of an image through matrix operation and interpolation algorithm, and the color correction unit performs color correction on the image through color space conversion, color balance and color mapping.
In this embodiment, it should be specifically described that, extracting feature information of the secondary image data in the feature information extracting module includes extracting image feature information of n frames of images;
The cable surface information comprises the circularity of the cable edge line of each frame of gray level image, the gray level area of each frame of gray level image, the perimeter of the cable edge line of each frame of gray level image, the irregular length of the cable edge line of each frame of gray level image, the standard circularity of the cable edge line and the image frame number, which are respectively used 、/>、/>、/>、/>/>A representation;
The cable shape information includes the abscissa of each intersection point in each frame image and the ordinate of each intersection point in each frame image, respectively And/>A representation;
the cable pixel information includes coordinates of pixels in each frame image, pixel gap values in each frame image, average pixels in each frame image, and standard deviations of pixel gap values in each frame image, respectively 、/>、/>/>And (3) representing.
In this embodiment, it should be specifically described that the surface integrity coefficient is calculated by the cable surface detection mathematical model in the surface anomaly determination module according to the following calculation steps:
step S01: carrying out gray scale treatment on the n frames of images to obtain gray scale images of the cable surface;
Step S02: calculating the circularity of the cable edge line of each frame gray image, wherein the calculation formula is as follows: wherein/> Representing the circularity of the cable edge line of each frame gray level image,/>Representing the gray scale area of each frame gray scale image,/>Perimeter of cable edge line representing gray level image of each frame,/>The irregular length of the cable edge line of each frame gray level image is represented;
step S03: calculating the surface integrity coefficient of the cable, wherein the calculation formula is as follows: wherein/> Representing the surface integrity factor,/>Representing the circularity of the cable edge line of each frame gray level image,/>Representing the standard circularity of the cable edge line,/>Representing the number of image frames.
In this embodiment, it should be specifically described that the calculation step of calculating the shape matching degree coefficient by the cable shape detection mathematical model in the shape anomaly detection module is as follows:
step S01: the intersection point in the n frames of images is expressed by coordinates, and the coordinates of each intersection point at the midpoint of the ith frame of image are expressed as ；
Step S02: calculating the shape matching degree coefficient of the cable, wherein the calculation formula is as follows: wherein/> Representing shape matching degree coefficient,/>Representing the coordinates of each intersection point in each frame of image,/>Representing the abscissa of each intersection in each frame of image,/>The ordinate of each intersection point in each frame image is indicated.
In this embodiment, it should be specifically described that the step of calculating the pixel homogeneity coefficient by using the cable pixel detection mathematical model in the pixel difference comparison module is as follows:
step S01: the pixels in the n-frame image are represented by coordinates, and the coordinates of the pixels in the i-th frame image are represented as ；
Step S02: calculating pixel homogeneity coefficient of the cable, wherein the calculation formula isWhereinRepresenting the pixel homogeneity coefficient,/>Representing coordinates of pixels in each frame of image,/>Representing the pixel gap value in each frame of image,/>Representing the average pixel in each frame of image,/>Representing the standard deviation of the pixel gap values in each frame of image.
In this embodiment, it should be specifically described that the system anomaly self-adjustment module receives the surface integrity coefficient transmitted by the surface anomaly determination module and sends the surface integrity coefficient to the system anomaly self-adjustment moduleAnd a preset first judgment threshold/>For comparison, if the surface integrity coefficient/>Greater than or equal to a preset first judgment threshold/>Judging whether the surface of the cable is abnormal, if the surface integrity coefficient/>Less than a preset first judgment threshold/>Judging that the surface of the cable is abnormal, and starting a system abnormal self-adjusting module;
Matching the shape to the coefficient of degree And a preset second judgment threshold/>Comparing, if the shape matching degree coefficientGreater than or equal to a preset second judgment threshold/>Judging whether the cable shape is abnormal, and if the shape matching degree coefficient/>Less than a preset second judgment threshold/>Judging that the cable shape is abnormal, and starting a system abnormality self-adjusting module;
Pixel homogeneity coefficient And a preset third judgment threshold/>Comparing, if the pixel homogeneity coefficientGreater than or equal to a preset third judgment threshold/>Judging whether the cable is abnormal, if the pixel homogeneity coefficient/>Less than a preset third judgment threshold/>And judging the abnormality in the cable, and starting the system abnormality self-adjusting module.
In this embodiment, it needs to be specifically described that the adjusted detection model building module builds a mathematical model to calculate an image anomaly index, where a calculation formula of the image anomaly index is: Wherein Representing an image anomaly index, n representing the number of image frames,/>Representing the surface integrity factor,/>Representing the coefficient of the degree of matching of the shape,Representing the pixel homogeneity coefficient,/>、/>And/>Representing a constant.
In this embodiment, it should be specifically described that the system anomaly early-warning module receives the image anomaly index transmitted by the post-adjustment detection model building moduleIndex of image abnormality/>Judging threshold value/>, with preset cable imageComparing, if the image abnormality index/>Greater than a preset cable image judgment threshold/>Judging that the cable is abnormal in manufacture, transmitting early warning prompt to a system terminal, and if the image abnormality index/>Less than or equal to a preset cable image judgment threshold/>And judging that the cable is manufactured abnormally.
In this embodiment, it needs to be specifically explained that the difference between the implementation and the prior art is mainly that, by providing a cable image acquisition module, an acquired image preprocessing module, a feature information extraction module, a surface anomaly judging module, a shape anomaly detecting module, a pixel difference comparing module, a system anomaly self-adjusting module, an adjusted detection model building module, and a system anomaly early warning module, the cable image is processed in frames to obtain cable related data of each frame image, a surface integrity coefficient, a shape matching coefficient and a pixel homogeneity coefficient of the cable are calculated, whether anomalies occur is judged according to a preset threshold value, the anomaly module is automatically adjusted, an image anomaly index is calculated by the adjusted detection model building module, whether the abnormal state occurs in cable manufacture is detected according to the image anomaly index, and early warning prompt is performed.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (7)
1. The utility model provides a cable manufacture anomaly detection system based on machine vision which characterized in that: comprising the following steps: the system comprises a cable image acquisition module, an acquired image preprocessing module, a characteristic information extraction module, a surface abnormality judging module, a shape abnormality detecting module, a pixel difference comparing module, a system abnormality self-adjusting module, an adjusted detection model building module and a system abnormality early warning module;
The cable image acquisition module adopts a high-resolution industrial camera to shoot the cable on a production line in real time, acquires primary image data, and transmits the acquired primary image data to the acquired image preprocessing module;
The collected image preprocessing module comprises a noise elimination unit, a geometric transformation unit and a color correction unit, receives primary image data transmitted by the cable image collecting module, acquires secondary image data through preprocessing operation, and transmits the secondary image data to the characteristic information extracting module;
The characteristic information extraction module is used for receiving the secondary image data transmitted by the collected image preprocessing module, extracting characteristic information of the secondary image data by utilizing an edge detection algorithm, wherein the characteristic information comprises cable surface information, cable shape information and cable pixel information;
The surface abnormality judging module is used for calculating a surface integrity coefficient through a cable surface detection mathematical model based on the cable surface information extracted by the characteristic information extracting module, and transmitting the calculated surface integrity coefficient to the system abnormality self-adjusting module and the post-adjustment detection model building module;
The surface integrity coefficient is calculated by the cable surface detection mathematical model in the surface anomaly judgment module, and the calculation steps are as follows:
step S01: carrying out gray scale treatment on the n frames of images to obtain gray scale images of the cable surface;
Step S02: calculating the circularity of the cable edge line of each frame gray image, wherein the calculation formula is as follows: Wherein Representing the circularity of the cable edge line of each frame gray level image,/>Representing the gray scale area of each frame gray scale image,/>Perimeter of cable edge line representing gray level image of each frame,/>The irregular length of the cable edge line of each frame gray level image is represented;
step S03: calculating the surface integrity coefficient of the cable, wherein the calculation formula is as follows: wherein/> Representing the surface integrity factor,/>Representing the circularity of the cable edge line of each frame gray level image,/>Representing the standard circularity of the cable edge line,/>Representing the number of image frames;
the shape anomaly detection module is used for calculating a shape matching degree coefficient through a cable shape detection mathematical model based on the cable shape information extracted by the characteristic information extraction module, and transmitting the calculated shape matching degree coefficient to the system anomaly self-adjustment module and the post-adjustment detection model establishment module;
the calculation step of calculating the shape matching degree coefficient through the cable shape detection mathematical model in the shape anomaly detection module is as follows:
step S01: the intersection point in the n frames of images is expressed by coordinates, and the coordinates of each intersection point at the midpoint of the ith frame of image are expressed as ；
Step S02: calculating the shape matching degree coefficient of the cable, wherein the calculation formula is as follows: wherein/> Representing shape matching degree coefficient,/>Representing the coordinates of each intersection point in each frame of image,/>Representing the abscissa of each intersection in each frame of image,/>An ordinate representing each intersection point in each frame image;
The pixel difference comparison module is used for calculating a pixel homogeneity coefficient through a cable pixel detection mathematical model based on the cable pixel information extracted by the characteristic information extraction module, and transmitting the calculated pixel homogeneity coefficient to the system abnormity self-adjustment module;
the pixel homogeneity coefficient is calculated by a cable pixel detection mathematical model in the pixel difference comparison module, and the pixel homogeneity coefficient is calculated by the following steps:
step S01: the pixels in the n-frame image are represented by coordinates, and the coordinates of the pixels in the i-th frame image are represented as ；
Step S02: calculating pixel homogeneity coefficient of the cable, wherein the calculation formula isWherein/>Representing the pixel homogeneity coefficient,/>Representing coordinates of pixels in each frame of image,/>Representing the pixel gap value in each frame of image,/>Representing the average pixel in each frame of image,/>Representing standard deviation of pixel gap values in each frame of image;
The system abnormality self-adjusting module is used for receiving the surface integrity coefficient, the shape matching degree coefficient and the pixel homogeneity coefficient transmitted by the surface abnormality judging module, the shape abnormality detecting module and the pixel difference comparing module, judging whether abnormality occurs according to a preset threshold value, and automatically adjusting the abnormality module;
The post-adjustment detection model building module is used for building a mathematical model to calculate an image abnormality index based on the surface integrity coefficient, the shape matching coefficient and the pixel homogeneity coefficient obtained after adjustment of the system abnormality self-adjustment module, and transmitting a calculation result to the system abnormality early warning module;
the system abnormality early warning module is used for receiving the image abnormality index transmitted by the adjusted detection model building module, detecting whether the abnormal state occurs in the cable manufacture or not, and carrying out early warning prompt.
2. The machine vision-based cable manufacturing anomaly detection system of claim 1, wherein: the primary image data acquired in the cable image acquisition module includes n frames of images, denoted as i=1, 2, 3.
3. The machine vision-based cable manufacturing anomaly detection system of claim 1, wherein: the noise elimination unit in the collected image preprocessing module reduces noise through bilateral filtering, the geometric transformation unit realizes geometric transformation of the image through matrix operation and interpolation algorithm, and the color correction unit performs color correction on the image through color space conversion, color balance and color mapping.
4. The machine vision-based cable manufacturing anomaly detection system of claim 1, wherein: extracting the characteristic information of the secondary image data in the characteristic information extraction module comprises extracting the image characteristic information of n frames of images;
The cable surface information comprises the circularity of the cable edge line of each frame of gray level image, the gray level area of each frame of gray level image, the perimeter of the cable edge line of each frame of gray level image, the irregular length of the cable edge line of each frame of gray level image, the standard circularity of the cable edge line and the image frame number, which are respectively used 、/>、/>、/>、/>/>A representation;
The cable shape information includes the abscissa of each intersection point in each frame image and the ordinate of each intersection point in each frame image, respectively And/>A representation;
the cable pixel information includes coordinates of pixels in each frame image, pixel gap values in each frame image, average pixels in each frame image, and standard deviations of pixel gap values in each frame image, respectively 、/>、/>/>And (3) representing.
5. The machine vision-based cable manufacturing anomaly detection system of claim 1, wherein: the system abnormality self-adjusting module receives the surface integrity coefficient transmitted by the surface abnormality judging module and sends the surface integrity coefficient to the system abnormality self-adjusting moduleAnd a preset first judgment threshold/>For comparison, if the surface integrity coefficient/>Greater than or equal to a preset first judgment threshold/>Judging whether the surface of the cable is abnormal, if the surface integrity coefficient/>Less than a preset first judgment threshold/>Judging that the surface of the cable is abnormal, and starting a system abnormal self-adjusting module;
Matching the shape to the coefficient of degree And a preset second judgment threshold/>Comparing, if the shape matching degree coefficient/>Greater than or equal to a preset second judgment threshold/>Judging whether the cable shape is abnormal, and if the shape matching degree coefficient/>Less than a preset second judgment threshold/>Judging that the cable shape is abnormal, and starting a system abnormality self-adjusting module;
Pixel homogeneity coefficient And a preset third judgment threshold/>Comparing, if the pixel homogeneity coefficient/>Greater than or equal to a preset third judgment threshold/>Judging whether the cable is abnormal, if the pixel homogeneity coefficient/>Less than a preset third judgment threshold/>And judging the abnormality in the cable, and starting the system abnormality self-adjusting module.
6. The machine vision-based cable manufacturing anomaly detection system of claim 1, wherein: the adjusted detection model building module builds a mathematical model to calculate an image abnormality index, and a calculation formula of the image abnormality index is as follows: wherein/> Representing an image anomaly index, n representing the number of image frames,/>Representing the surface integrity factor,/>Representing shape matching degree coefficient,/>Representing the pixel homogeneity coefficient,/>、/>And/>Representing a constant.
7. The machine vision-based cable manufacturing anomaly detection system of claim 1, wherein: the system abnormality early warning module receives the image abnormality index transmitted by the detection model building module after adjustmentIndex of image abnormality/>Judging threshold value/>, with preset cable imageComparing, if the image abnormality index/>Greater than a preset cable image judgment threshold/>Judging that the cable is abnormal in manufacture, transmitting early warning prompt to a system terminal, and if the image abnormality index/>Less than or equal to a preset cable image judgment threshold/>And judging that the cable is manufactured abnormally.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410145743.1A CN117710901B (en) | 2024-02-02 | 2024-02-02 | Cable manufacture abnormality detection system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410145743.1A CN117710901B (en) | 2024-02-02 | 2024-02-02 | Cable manufacture abnormality detection system based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117710901A CN117710901A (en) | 2024-03-15 |
| CN117710901B true CN117710901B (en) | 2024-04-26 |
Family
ID=90162712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410145743.1A Active CN117710901B (en) | 2024-02-02 | 2024-02-02 | Cable manufacture abnormality detection system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117710901B (en) |
Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102692216A (en) * | 2012-06-08 | 2012-09-26 | 中北大学 | Real-time optical fiber winding defect detection method based on machine vision technology |
| CN107703148A (en) * | 2017-10-10 | 2018-02-16 | 贵州大学 | A kind of cable strand quality detecting system and its detection method based on machine vision |
| CN108918542A (en) * | 2018-08-29 | 2018-11-30 | 成都理工大学 | A kind of cable surface defect detecting device and method |
| CN109692820A (en) * | 2018-12-19 | 2019-04-30 | 河南大学 | Optical fiber metalwork surface defect on-line measuring device and method based on image procossing |
| CN110297476A (en) * | 2019-07-24 | 2019-10-01 | 天长市海纳电气有限公司 | A kind of intelligent PI C control system based on cable production control |
| CN111539935A (en) * | 2020-04-24 | 2020-08-14 | 江苏大学 | Online cable surface defect detection method based on machine vision |
| CN112697814A (en) * | 2020-12-15 | 2021-04-23 | 电子科技大学 | Cable surface defect detection system and method based on machine vision |
| CN113161067A (en) * | 2021-04-16 | 2021-07-23 | 鲁能泰山曲阜电缆有限公司 | Intelligent mineral insulated cable |
| EP3855359A1 (en) * | 2020-01-23 | 2021-07-28 | Schleuniger AG | Cable processing station, cable machine with cable processing stations and computer implemented method |
| CN113256570A (en) * | 2021-05-10 | 2021-08-13 | 郑州轻工业大学 | Visual information processing method, device, equipment and medium based on artificial intelligence |
| CN113427731A (en) * | 2021-06-24 | 2021-09-24 | 广州中和互联网技术有限公司 | Injection molding machine mold detection system and method based on machine vision |
| WO2022065621A1 (en) * | 2020-09-28 | 2022-03-31 | (주)미래융합정보기술 | Vision inspection system using distance learning of product defect image |
| CN114757939A (en) * | 2022-05-16 | 2022-07-15 | 安徽天凯光通信技术有限公司 | Optical cable production detection supervisory systems based on machine vision |
| KR20220147911A (en) * | 2021-04-28 | 2022-11-04 | 주식회사 파인브이티 | Process monitoring apparatus for judging the defectiveness of cables produced through harness cable production process, and the operating method thereof |
| CN115761405A (en) * | 2022-11-21 | 2023-03-07 | 国网山东省电力公司临沂供电公司 | Method for determining running state of high-voltage cable |
| CN116721107A (en) * | 2023-08-11 | 2023-09-08 | 青岛胶州电缆有限公司 | Intelligent monitoring system for cable production quality |
| CN117029703A (en) * | 2023-10-09 | 2023-11-10 | 广东欢联电子科技有限公司 | Communication cable field production data real-time management monitoring system |
| CN117030721A (en) * | 2023-08-14 | 2023-11-10 | 梅州达士通精密工业有限公司 | Cable quality inspection system based on machine vision recognition |
| CN117078005A (en) * | 2023-08-01 | 2023-11-17 | 安徽远征电缆科技有限公司 | Cable assembly production line operation risk assessment system based on data analysis |
| CN117250206A (en) * | 2023-09-24 | 2023-12-19 | 南京理工大学 | Conductive wire abnormality detection method and device based on visible light and infrared light fusion |
| CN117392123A (en) * | 2023-12-07 | 2024-01-12 | 广东新亚光电缆股份有限公司 | Wire and cable sign mistake proofing system based on image recognition |
| CN117455843A (en) * | 2023-09-28 | 2024-01-26 | 上海东捷建设(集团)有限公司 | Intelligent cable head defect detection system |
-
2024
- 2024-02-02 CN CN202410145743.1A patent/CN117710901B/en active Active
Patent Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102692216A (en) * | 2012-06-08 | 2012-09-26 | 中北大学 | Real-time optical fiber winding defect detection method based on machine vision technology |
| CN107703148A (en) * | 2017-10-10 | 2018-02-16 | 贵州大学 | A kind of cable strand quality detecting system and its detection method based on machine vision |
| CN108918542A (en) * | 2018-08-29 | 2018-11-30 | 成都理工大学 | A kind of cable surface defect detecting device and method |
| CN109692820A (en) * | 2018-12-19 | 2019-04-30 | 河南大学 | Optical fiber metalwork surface defect on-line measuring device and method based on image procossing |
| CN110297476A (en) * | 2019-07-24 | 2019-10-01 | 天长市海纳电气有限公司 | A kind of intelligent PI C control system based on cable production control |
| EP3855359A1 (en) * | 2020-01-23 | 2021-07-28 | Schleuniger AG | Cable processing station, cable machine with cable processing stations and computer implemented method |
| CN111539935A (en) * | 2020-04-24 | 2020-08-14 | 江苏大学 | Online cable surface defect detection method based on machine vision |
| WO2022065621A1 (en) * | 2020-09-28 | 2022-03-31 | (주)미래융합정보기술 | Vision inspection system using distance learning of product defect image |
| CN112697814A (en) * | 2020-12-15 | 2021-04-23 | 电子科技大学 | Cable surface defect detection system and method based on machine vision |
| CN113161067A (en) * | 2021-04-16 | 2021-07-23 | 鲁能泰山曲阜电缆有限公司 | Intelligent mineral insulated cable |
| KR20220147911A (en) * | 2021-04-28 | 2022-11-04 | 주식회사 파인브이티 | Process monitoring apparatus for judging the defectiveness of cables produced through harness cable production process, and the operating method thereof |
| CN113256570A (en) * | 2021-05-10 | 2021-08-13 | 郑州轻工业大学 | Visual information processing method, device, equipment and medium based on artificial intelligence |
| CN113427731A (en) * | 2021-06-24 | 2021-09-24 | 广州中和互联网技术有限公司 | Injection molding machine mold detection system and method based on machine vision |
| CN114757939A (en) * | 2022-05-16 | 2022-07-15 | 安徽天凯光通信技术有限公司 | Optical cable production detection supervisory systems based on machine vision |
| CN115761405A (en) * | 2022-11-21 | 2023-03-07 | 国网山东省电力公司临沂供电公司 | Method for determining running state of high-voltage cable |
| CN117078005A (en) * | 2023-08-01 | 2023-11-17 | 安徽远征电缆科技有限公司 | Cable assembly production line operation risk assessment system based on data analysis |
| CN116721107A (en) * | 2023-08-11 | 2023-09-08 | 青岛胶州电缆有限公司 | Intelligent monitoring system for cable production quality |
| CN117030721A (en) * | 2023-08-14 | 2023-11-10 | 梅州达士通精密工业有限公司 | Cable quality inspection system based on machine vision recognition |
| CN117250206A (en) * | 2023-09-24 | 2023-12-19 | 南京理工大学 | Conductive wire abnormality detection method and device based on visible light and infrared light fusion |
| CN117455843A (en) * | 2023-09-28 | 2024-01-26 | 上海东捷建设(集团)有限公司 | Intelligent cable head defect detection system |
| CN117029703A (en) * | 2023-10-09 | 2023-11-10 | 广东欢联电子科技有限公司 | Communication cable field production data real-time management monitoring system |
| CN117392123A (en) * | 2023-12-07 | 2024-01-12 | 广东新亚光电缆股份有限公司 | Wire and cable sign mistake proofing system based on image recognition |
Non-Patent Citations (1)
| Title |
|---|
| 基于机器视觉的线缆表面缺陷检测系统设计与算法研究;乔湘洋;王海芳;祁超飞;李新庆;;机床与液压;20200315(第05期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117710901A (en) | 2024-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111539935B (en) | Online cable surface defect detection method based on machine vision | |
| CN110458157B (en) | Intelligent monitoring system for power cable production process | |
| CN116934740B (en) | Plastic mold surface defect analysis and detection method based on image processing | |
| CN110021133B (en) | All-weather fire-fighting fire patrol early-warning monitoring system and fire image detection method | |
| CN114881915A (en) | Symmetry-based mobile phone glass cover plate window area defect detection method | |
| CN109781737B (en) | Detection method and detection system for surface defects of hose | |
| CN116188468B (en) | HDMI cable transmission letter sorting intelligent control system | |
| CN112258444A (en) | Elevator steel wire rope detection method | |
| CN116630321A (en) | Intelligent bridge health monitoring system based on artificial intelligence | |
| CN114212452B (en) | Coal flow detection method based on laser assistance and image processing and energy-saving control system | |
| CN113808087A (en) | Defect management and control method and device for surface of steel plate and computer readable storage medium | |
| CN116229668A (en) | Fire disaster positioning system based on infrared video monitoring | |
| CN117710901B (en) | Cable manufacture abnormality detection system based on machine vision | |
| CN113411510B (en) | Camera automatic exposure algorithm based on image quality evaluation and red hot forging | |
| CN114257736A (en) | Self-adaptive shooting method for workpieces | |
| CN113091915A (en) | Automatic body temperature information acquisition system based on face recognition | |
| CN111402158A (en) | Method for clearing low-illumination fog dust image of fully mechanized coal mining face | |
| CN113870220A (en) | Conductor galloping on-line monitoring method and device based on rectangular image detection | |
| CN113810555A (en) | Video quality evaluation method based on just noticeable difference and blocking effect | |
| CN111017728A (en) | Crane brake health state assessment method based on machine vision | |
| CN110717899A (en) | Online visual detection method for bead explosion defects of transparent filter rod | |
| CN116805405B (en) | Intelligent protection method and system for milling machine equipment | |
| CN112468697B (en) | Visual acquisition method and device with intelligent position adjustment function | |
| CN115294749B (en) | Multi-position monitoring system based on metal protective net | |
| CN117351433B (en) | Computer vision-based glue-cured mortar plumpness monitoring system |
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 |