CN115338091B - High-speed image transmission and analysis system under 5G application - Google Patents
High-speed image transmission and analysis system under 5G application Download PDFInfo
- Publication number
- CN115338091B CN115338091B CN202210931999.6A CN202210931999A CN115338091B CN 115338091 B CN115338091 B CN 115338091B CN 202210931999 A CN202210931999 A CN 202210931999A CN 115338091 B CN115338091 B CN 115338091B
- Authority
- CN
- China
- Prior art keywords
- gluing
- image
- module
- end cover
- glued
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 42
- 238000004026 adhesive bonding Methods 0.000 claims abstract description 176
- 238000001514 detection method Methods 0.000 claims abstract description 57
- 238000012545 processing Methods 0.000 claims abstract description 37
- 238000001125 extrusion Methods 0.000 claims abstract description 35
- 238000000034 method Methods 0.000 claims abstract description 26
- 238000005286 illumination Methods 0.000 claims abstract description 20
- 239000003638 chemical reducing agent Substances 0.000 claims description 44
- 239000003292 glue Substances 0.000 claims description 30
- 238000004891 communication Methods 0.000 claims description 16
- 230000007547 defect Effects 0.000 claims description 12
- 230000000007 visual effect Effects 0.000 claims description 5
- 230000006835 compression Effects 0.000 abstract description 2
- 238000007906 compression Methods 0.000 abstract description 2
- 230000011218 segmentation Effects 0.000 abstract description 2
- 239000011248 coating agent Substances 0.000 description 5
- 238000000576 coating method Methods 0.000 description 5
- 229910000831 Steel Inorganic materials 0.000 description 2
- 238000007789 sealing Methods 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05C—APPARATUS FOR APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05C11/00—Component parts, details or accessories not specifically provided for in groups B05C1/00 - B05C9/00
- B05C11/10—Storage, supply or control of liquid or other fluent material; Recovery of excess liquid or other fluent material
- B05C11/1002—Means for controlling supply, i.e. flow or pressure, of liquid or other fluent material to the applying apparatus, e.g. valves
- B05C11/1005—Means for controlling supply, i.e. flow or pressure, of liquid or other fluent material to the applying apparatus, e.g. valves responsive to condition of liquid or other fluent material already applied to the surface, e.g. coating thickness, weight or pattern
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05C—APPARATUS FOR APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05C11/00—Component parts, details or accessories not specifically provided for in groups B05C1/00 - B05C9/00
- B05C11/10—Storage, supply or control of liquid or other fluent material; Recovery of excess liquid or other fluent material
- B05C11/1002—Means for controlling supply, i.e. flow or pressure, of liquid or other fluent material to the applying apparatus, e.g. valves
- B05C11/1015—Means for controlling supply, i.e. flow or pressure, of liquid or other fluent material to the applying apparatus, e.g. valves responsive to a conditions of ambient medium or target, e.g. humidity, temperature ; responsive to position or movement of the coating head relative to the target
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to a high-speed image transmission and analysis system under 5G application. The 5G transmission protocol is used for transmitting images before and during the gluing, so that on one hand, a large number of cables can be prevented from being carried by a gluing extrusion head in the shooting process, the workload is high, on the other hand, the 5G transmission speed is high, the system response delay is reduced, the images can be rapidly processed, and the instant control is realized; the invention processes the image on the basis of 5G transmission, and the processed image data packet is smaller and is more suitable for a wireless transmission system; the image processed by gray scale, segmentation, binarization and the like is reduced by more than 1000 times compared with the original image, so that the transmission delay can be ensured to be within 15ms even if the image is transmitted for hundreds of times per second, and the time accuracy of detection is greatly improved. The annular light source matched with the detection is arranged for illumination, and the corresponding illumination mode is adopted under the corresponding detection mode, so that the transmission, the processing and the compression of the image can be matched, and the detection speed is greatly improved.
Description
Technical Field
The invention relates to the field of speed reducer gluing detection, in particular to a speed reducer gluing high-speed image transmission and analysis system under 5G application.
Background
The gluing process is very important for the sealing performance of the end cover of the speed reducer or the motor, and oil leakage faults are caused by the fact that the sealing performance is not up to standard due to uneven gluing, so that the gluing process is a core process flow and 100% online detection is needed. At present, the quality of the gluing process is mostly dependent on manual judgment, and the gluing process is low in efficiency and poor in accuracy.
The application number CN202110201620.1 discloses a method for automatically adjusting the glue coating amount, wherein a vision system monitors the glue coating shade value of the opening of a battery steel shell in real time and sends the glue coating shade value to a PLC (programmable logic controller); the PLC controller obtains the gluing time after operation according to the received shade value; and the PLC controls the gluing pump to glue the opening of the battery steel shell according to the gluing time. The glue coating amount is not required to be manually modified, the workload of workers is reduced, and the defective rate of glue coating is reduced. However, the current image shooting generally needs to be connected with a large number of data lines, so that the load of the glue spreading head is increased when the glue spreading head moves, and meanwhile, the actual detection is delayed due to the slow data processing speed, so that the glue spreading is difficult to control in real time.
Disclosure of Invention
Aiming at the above, in order to solve the problems, a high-speed image transmission and analysis system under 5G application is provided, which is applied to gluing detection of a speed reducer or a motor end cover, and comprises a gluing part and an upper computer, wherein the gluing part comprises a gluing control module, a gluing module, an image acquisition module, an image processing module, an image transmission module and an illumination module; the upper computer comprises a wireless communication module, a detection host, an analysis module and a sample database;
the gluing module is used for gluing the speed reducer or the motor end cover and comprises a gluing extrusion head; the image acquisition module is arranged on the gluing module, and moves along with the gluing module and acquires images of the speed reducer or the motor end cover; the end cover image is processed by the image processing module and then is sent to the wireless communication module of the upper computer through the image transmission module; the detection host acquires the end cover image from the wireless communication module and stores the end cover image in the sample database.
The analysis module is connected with the sample database and the detection host, and the analysis module analyzes the end cover image to determine whether the end cover has defects, and whether the end cover gluing has break points or path errors.
The analysis module analyzes the end cover image and also identifies the end cover model, and the detection host determines a gluing path and gluing control parameters according to the end cover model.
The image transmission module and the wireless communication module of the upper computer adopt a 5G communication protocol for transmission.
The image acquisition module is arranged on a gluing extrusion head of the gluing module, moves along with the gluing extrusion head, shoots a speed reducer or a motor end cover which is not glued, and takes a live non-glued image;
the un-glued image is sent to an image processing module; the image processing module carries out gray level processing on the non-glued image, and processes the color image into a gray level image to obtain the non-glued gray level image;
the non-glued gray level image is further thresholded by N sections; dividing the gray value of the non-glued gray image into N sections uniformly from the lowest to the highest, and extracting the pixel areas in the range of the gray value belonging to the corresponding sections, wherein N is more than or equal to 2; then binarizing the extracted area image, assigning 0 to the blank area and 255 to the non-blank area; n binarized images are obtained;
n pieces of binarized images are transmitted to a detection host through wireless transmission; the analysis module analyzes the N binarized images and calculates the number of connected domains and the area of the smallest connected domain, wherein the area of the connected domains is smaller than a threshold value, in the N binarized images; when the number of the communicating domains smaller than the threshold exceeds the threshold or the area of the smallest communicating domain is smaller than the threshold, judging that the un-glued speed reducer or the motor end cover has defects and cannot glue; otherwise, judging that the un-glued speed reducer or the motor end cover is qualified, and gluing the motor end cover.
The sample database is pre-stored with workpiece standard images of various models, and the workpiece standard images are subjected to gray level processing and N-segment thresholding;
if the non-glued speed reducer or the motor end cover is qualified, the analysis module compares the largest connected domain image in the N binarized images with images shot by various types of workpieces stored in a sample database in advance, calculates the similarity, and screens out the workpiece type with the highest similarity from the sample database, so as to determine the model of the non-glued speed reducer or the motor end cover;
the analysis module sends the model of the non-glued speed reducer or the motor end cover to the detection host; the detection host determines the shape of a gluing path and the extrusion speed of gluing according to the model of the un-glued speed reducer or the motor end cover;
the analysis module further transmits the coordinates of the central point of the maximum connected domain in the N non-glued binarized images to the detection host, and the detection host plans a gluing path according to the coordinates of the central point and the shape of the gluing path;
the detection host sends a gluing path and gluing extrusion speed to a gluing control module; and the gluing control module controls the gluing module to glue according to the gluing path and the gluing extrusion speed.
The gluing module is also connected with an illumination module; the lighting module is an annular light source consisting of two semicircular arc light sources; one of the two semicircular arc light sources is arranged on the same side of the image acquisition module, and the other semicircular arc light source is arranged on the opposite side of the image acquisition module; when the glue is not applied, the two semicircular arc light sources provide illumination at the same time; when the glue is applied, the semicircular light sources on the same side of the image acquisition module are closed, and the semicircular light sources on the opposite side of the image acquisition module are used for independently providing illumination;
when the glue is not applied, the annular light source is adopted to irradiate, so that a clear image can be shot when the end face is shot, and defects, unevenness and the like of the end face can be displayed; when the glue spreading operation is carried out, only illumination in a single direction is adopted, shadows are generated when opposite-side light irradiates the extruded glue, and the shape of the extruded glue can be rapidly judged by utilizing the shape of the shadows, so that analysis and judgment are rapidly carried out.
When the gluing extrusion head performs gluing operation, the image acquisition module continuously shoots gluing positions and obtains images of a plurality of gluing positions, namely gluing images; in the whole process of gluing, the image acquisition module shoots 20-50 images per second;
the image processing module processes the gluing image, firstly, reserving pixels with N pixels at intervals at the position of an extrusion outlet of the gluing extrusion head, and deleting pixels at other positions to obtain a segmented gluing image; then the image processing module carries out grey-scale treatment on the divided gluing image and then carries out binarization treatment to obtain a binarized gluing image;
in the whole gluing process, the image processing module sends the binarized gluing image to the detection host through wireless transmission; the analysis module analyzes the binarized gummed image to obtain a cut-off line in the binarized gummed image, compares the cut-off line of the latest photographed binarized gummed image with the cut-off lines of the photographed previous M binarized gummed images, analyzes the similarity between the cut-off line and the cut-off line in the previous M images, and judges that the gummed image has no break point or path error if the similarity between all the comparison results is greater than a threshold value; and if 1 or more of the similarity of all the comparison results is smaller than the threshold value, judging that the gluing has a breakpoint or a path error.
100≥N≥50,20≥M≥10。
And if the un-glued speed reducer or the motor end cover has defects or the glued end cover has break points or paths are wrong, an audible and visual warning is sent out.
The invention uses the 5G transmission protocol to transmit the images before and during the gluing, on one hand, the gluing extrusion head can be prevented from carrying a large number of cables in the shooting process, the workload is high, on the other hand, the 5G transmission speed is high, the system response delay is reduced, the images can be rapidly processed, and the instant control is realized;
the invention processes the image in gray scale, binarization and the like on the basis of 5G transmission, and the processed image data packet is smaller and is more suitable for a wireless transmission system; the image processed by gray scale, segmentation, binarization and the like is reduced by more than 1000 times compared with the original image, so that the transmission delay can be ensured to be within 15ms even if the image is transmitted for hundreds of times per second, and the time accuracy of detection is greatly improved.
The annular light source matched with the detection is arranged for illumination, and the corresponding illumination mode is adopted under the corresponding detection mode, so that the transmission, the processing and the compression of the image can be matched, and the detection speed is greatly improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosed subject matter, are incorporated in and constitute a part of this specification. The drawings also set forth implementations of the disclosed subject matter and, together with the detailed description, serve to explain the principles of the implementations of the disclosed subject matter. No attempt is made to show structural details of the disclosed subject matter in more detail than is necessary for a fundamental understanding of the disclosed subject matter and its various ways of practice.
Fig. 1 is a schematic diagram of the overall architecture of the present invention.
Detailed Description
The advantages, features and manner of attaining the stated objects of the invention will become apparent from the description to follow, and from the drawings.
Example 1:
the high-speed image transmission and analysis system applied to 5G is applied to gluing detection of a speed reducer or a motor end cover, and comprises a gluing part and an upper computer, wherein the gluing part comprises a gluing control module, a gluing module, an image acquisition module, an image processing module, an image transmission module and an illumination module; the upper computer comprises a wireless communication module, a detection host, an analysis module and a sample database;
the gluing module is used for gluing the speed reducer or the motor end cover and comprises a gluing extrusion head; the image acquisition module is arranged on the gluing module, and moves along with the gluing module and acquires images of the speed reducer or the motor end cover; the end cover image is processed by the image processing module and then is sent to the wireless communication module of the upper computer through the image transmission module; the detection host acquires the end cover image from the wireless communication module and stores the end cover image in the sample database.
The analysis module is connected with the sample database and the detection host, and the analysis module analyzes the end cover image to determine whether the end cover has defects, and whether the end cover gluing has break points or path errors.
The analysis module analyzes the end cover image and also identifies the end cover model, and the detection host determines a gluing path and gluing control parameters according to the end cover model.
The image transmission module and the wireless communication module of the upper computer adopt a 5G communication protocol for transmission.
The image acquisition module is arranged on a gluing extrusion head of the gluing module, moves along with the gluing extrusion head, shoots a speed reducer or a motor end cover which is not glued, and takes a live non-glued image;
the un-glued image is sent to an image processing module; the image processing module carries out gray level processing on the non-glued image, and processes the color image into a gray level image to obtain the non-glued gray level image;
the non-glued gray level image is further thresholded by N sections; dividing the gray value of the non-glued gray image into N sections uniformly from the lowest to the highest, and extracting the pixel areas in the range of the gray value belonging to the corresponding sections, wherein N is more than or equal to 2; then binarizing the extracted area image, assigning 0 to the blank area and 255 to the non-blank area; n binarized images are obtained;
n pieces of binarized images are transmitted to a detection host through wireless transmission; the analysis module analyzes the N binarized images and calculates the number of connected domains and the area of the smallest connected domain, wherein the area of the connected domains is smaller than a threshold value, in the N binarized images; when the number of the communicating domains smaller than the threshold exceeds the threshold or the area of the smallest communicating domain is smaller than the threshold, judging that the un-glued speed reducer or the motor end cover has defects and cannot glue; otherwise, judging that the un-glued speed reducer or the motor end cover is qualified, and gluing the motor end cover.
The sample database is pre-stored with workpiece standard images of various models, and the workpiece standard images are subjected to gray level processing and N-segment thresholding;
if the non-glued speed reducer or the motor end cover is qualified, the analysis module compares the largest connected domain image in the N binarized images with images shot by various types of workpieces stored in a sample database in advance, calculates the similarity, and screens out the workpiece type with the highest similarity from the sample database, so as to determine the model of the non-glued speed reducer or the motor end cover;
the analysis module sends the model of the non-glued speed reducer or the motor end cover to the detection host; the detection host determines the shape of a gluing path and the extrusion speed of gluing according to the model of the un-glued speed reducer or the motor end cover;
the analysis module further transmits the coordinates of the central point of the maximum connected domain in the N non-glued binarized images to the detection host, and the detection host plans a gluing path according to the coordinates of the central point and the shape of the gluing path;
the detection host sends a gluing path and gluing extrusion speed to a gluing control module; and the gluing control module controls the gluing module to glue according to the gluing path and the gluing extrusion speed.
The gluing module is also connected with an illumination module; the lighting module is an annular light source consisting of two semicircular arc light sources; one of the two semicircular arc light sources is arranged on the same side of the image acquisition module, and the other semicircular arc light source is arranged on the opposite side of the image acquisition module; when the glue is not applied, the two semicircular arc light sources provide illumination at the same time; when the glue is applied, the semicircular light sources on the same side of the image acquisition module are closed, and the semicircular light sources on the opposite side of the image acquisition module are used for independently providing illumination;
when the glue is not applied, the annular light source is adopted to irradiate, so that a clear image can be shot when the end face is shot, and defects, unevenness and the like of the end face can be displayed; when the glue spreading operation is carried out, only illumination in a single direction is adopted, shadows are generated when opposite-side light irradiates the extruded glue, and the shape of the extruded glue can be rapidly judged by utilizing the shape of the shadows, so that analysis and judgment are rapidly carried out.
When the gluing extrusion head performs gluing operation, the image acquisition module continuously shoots gluing positions and obtains images of a plurality of gluing positions, namely gluing images; in the whole process of gluing, the image acquisition module shoots 20-50 images per second;
the image processing module processes the gluing image, firstly, reserving pixels with N pixels at intervals at the position of an extrusion outlet of the gluing extrusion head, and deleting pixels at other positions to obtain a segmented gluing image; then the image processing module carries out grey-scale treatment on the divided gluing image and then carries out binarization treatment to obtain a binarized gluing image;
in the whole gluing process, the image processing module sends the binarized gluing image to the detection host through wireless transmission; the analysis module analyzes the binarized gummed image to obtain a cut-off line in the binarized gummed image, compares the cut-off line of the latest photographed binarized gummed image with the cut-off lines of the photographed previous M binarized gummed images, analyzes the similarity between the cut-off line and the cut-off line in the previous M images, and judges that the gummed image has no break point or path error if the similarity between all the comparison results is greater than a threshold value; and if 1 or more of the similarity of all the comparison results is smaller than the threshold value, judging that the gluing has a breakpoint or a path error.
100≥N≥50,20≥M≥10。
And if the un-glued speed reducer or the motor end cover has defects or the glued end cover has break points or paths are wrong, an audible and visual warning is sent out.
Example 2:
the detection method during actual detection comprises the following steps:
step 1, an image processing module, an image acquisition module and an image transmission module are installed on a gluing module; testing whether the lighting module works normally; testing whether the wireless communication is normal;
step 2, shooting end faces of speed reducers or motors of different types, so as to form a large number of shooting standard images, and storing the shooting standard images in a sample database;
step 3, the detection host machine sends a moving instruction to the gluing control module, the gluing control module moves to the non-gluing speed reducer or the end face of the motor, and when the gluing is not performed, the two semicircular arc light sources provide illumination at the same time, and an image is shot; the un-glued image is sent to an image processing module; the image processing module carries out gray level processing on the non-glued image, and processes the color image into a gray level image to obtain the non-glued gray level image;
the non-glued gray level image is further thresholded by N sections; dividing the gray value of the non-glued gray image into N sections uniformly from the lowest to the highest, and extracting the pixel areas in the range of the gray value belonging to the corresponding sections, wherein N is more than or equal to 2; then binarizing the extracted area image, assigning 0 to the blank area and 255 to the non-blank area; n binarized images are obtained;
n pieces of binarized images are transmitted to a detection host through wireless transmission; the analysis module analyzes the N binarized images and calculates the number of connected domains and the area of the smallest connected domain, wherein the area of the connected domains is smaller than a threshold value, in the N binarized images; judging that the un-glued speed reducer or the motor end cover has defects when the number of the connected domains smaller than the threshold exceeds the threshold or the area of the smallest connected domain is smaller than the threshold, and not gluing and giving out an audible and visual warning; otherwise, judging that the un-glued speed reducer or the motor end cover is qualified, and gluing the motor end cover.
Step 4, if the non-glued speed reducer or the motor end cover is qualified, comparing the maximum connected domain image in the N binarized images with images shot by various types of workpieces stored in a sample database in advance by an analysis module, calculating the similarity, and screening the workpiece model with the highest similarity from the sample database, thereby determining the model of the non-glued speed reducer or the motor end cover;
the analysis module sends the model of the non-glued speed reducer or the motor end cover to the detection host; the detection host determines the shape of a gluing path and the extrusion speed of gluing according to the model of the un-glued speed reducer or the motor end cover;
the analysis module further transmits the coordinates of the central point of the maximum connected domain in the N non-glued binarized images to the detection host, and the detection host plans a gluing path according to the coordinates of the central point and the shape of the gluing path;
the detection host sends a gluing path and gluing extrusion speed to a gluing control module; and the gluing control module controls the gluing module to glue according to the gluing path and the gluing extrusion speed.
Step 5, when gluing, the semicircular light sources on the same side of the image acquisition module are closed, and the semicircular light sources on the opposite side of the image acquisition module are used for providing illumination independently;
when the gluing extrusion head performs gluing operation, the image acquisition module continuously shoots gluing positions and obtains images of a plurality of gluing positions, namely gluing images; in the whole process of gluing, the image acquisition module shoots 20-50 images per second;
the image processing module processes the gluing image, firstly, reserving pixels with N pixels at intervals at the position of an extrusion outlet of the gluing extrusion head, and deleting pixels at other positions to obtain a segmented gluing image; then the image processing module carries out grey-scale treatment on the divided gluing image and then carries out binarization treatment to obtain a binarized gluing image;
in the whole gluing process, the image processing module sends the binarized gluing image to the detection host through wireless transmission; the analysis module analyzes the binarized gummed image to obtain a cut-off line in the binarized gummed image, compares the cut-off line of the latest photographed binarized gummed image with the cut-off lines of the photographed previous M binarized gummed images, analyzes the similarity between the cut-off line and the cut-off line in the previous M images, and judges that the gummed image has no break point or path error if the similarity between all the comparison results is greater than a threshold value; if 1 or more of the similarity of all the comparison results is smaller than the threshold value, judging that the gluing has a break point or a path error, and sending out an audible and visual warning.
The above description is merely of the preferred embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about the changes or substitutions within the technical scope of the present invention, and the changes or substitutions are intended to be covered by the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (3)
1. The high-speed image transmission and analysis system applied to 5G is applied to gluing detection of a speed reducer or a motor end cover, and is characterized by comprising a gluing part and an upper computer, wherein the gluing part comprises a gluing control module, a gluing module, an image acquisition module, an image processing module, an image transmission module and an illumination module; the upper computer comprises a wireless communication module, a detection host, an analysis module and a sample database;
the gluing module is used for gluing the speed reducer or the motor end cover and comprises a gluing extrusion head; the image acquisition module is arranged on the gluing module, and moves along with the gluing module and acquires images of the speed reducer or the motor end cover; the end cover image is processed by the image processing module and then is sent to the wireless communication module of the upper computer through the image transmission module; the detection host acquires an end cover image from the wireless communication module and stores the end cover image in a sample database;
the analysis module is connected with the sample database and the detection host, and is used for analyzing the end cover image to determine whether the end cover has defects, and whether the end cover gluing has break points or path errors;
the analysis module analyzes the end cover image and also identifies the end cover model, and the detection host determines a gluing path and gluing control parameters according to the end cover model;
the image transmission module and the wireless communication module of the upper computer adopt a 5G communication protocol for transmission;
the image acquisition module is arranged on a gluing extrusion head of the gluing module, moves along with the gluing extrusion head, and shoots a speed reducer or a motor end cover which is not glued to obtain an image which is not glued;
the un-glued image is sent to an image processing module; the image processing module carries out gray level processing on the non-glued image, and processes the color image into a gray level image to obtain the non-glued gray level image;
the non-glued gray level image is further thresholded by N sections; dividing the gray value of the non-glued gray image into N sections uniformly from the lowest to the highest, and extracting the pixel areas in the range of the gray value belonging to the corresponding sections, wherein N is more than or equal to 2; then binarizing the extracted area image, assigning 0 to the blank area and 255 to the non-blank area; n binarized images are obtained;
n pieces of binarized images are transmitted to a detection host through wireless transmission; the analysis module analyzes the N binarized images and calculates the number of connected domains and the area of the smallest connected domain, wherein the area of the connected domains is smaller than a threshold value, in the N binarized images; when the number of the communicating domains smaller than the threshold exceeds the threshold or the area of the smallest communicating domain is smaller than the threshold, judging that the un-glued speed reducer or the motor end cover has defects and cannot glue; otherwise, judging that the non-glued speed reducer or the motor end cover is qualified, and gluing the motor end cover;
the sample database is pre-stored with workpiece standard images of various models, and the workpiece standard images are subjected to gray level processing and N-segment thresholding;
if the non-glued speed reducer or the motor end cover is qualified, the analysis module compares the largest connected domain image in the N binarized images with images shot by various types of workpieces stored in a sample database in advance, calculates the similarity, and screens out the workpiece type with the highest similarity from the sample database, so as to determine the model of the non-glued speed reducer or the motor end cover;
the analysis module sends the model of the non-glued speed reducer or the motor end cover to the detection host; the detection host determines the shape of a gluing path and the extrusion speed of gluing according to the model of the un-glued speed reducer or the motor end cover;
the analysis module further transmits the coordinates of the central point of the maximum connected domain in the N non-glued binarized images to the detection host, and the detection host plans a gluing path according to the coordinates of the central point and the shape of the gluing path;
the detection host sends a gluing path and gluing extrusion speed to a gluing control module; the gluing control module controls the gluing module to glue according to the gluing path and the gluing extrusion speed;
the gluing module is also connected with an illumination module; the lighting module is an annular light source consisting of two semicircular arc light sources; one of the two semicircular arc light sources is arranged on the same side of the image acquisition module, and the other semicircular arc light source is arranged on the opposite side of the image acquisition module; when the glue is not applied, the two semicircular arc light sources provide illumination at the same time; when the glue is applied, the semicircular light sources on the same side of the image acquisition module are closed, and the semicircular light sources on the opposite side of the image acquisition module are used for independently providing illumination;
when the gluing extrusion head performs gluing operation, the image acquisition module continuously shoots gluing positions and obtains images of a plurality of gluing positions, namely gluing images; in the whole process of gluing, the image acquisition module shoots 20-50 images per second;
the image processing module processes the gluing image, firstly, reserving pixels with N pixels at intervals at the position of an extrusion outlet of the gluing extrusion head, and deleting pixels at other positions to obtain a segmented gluing image; then the image processing module carries out grey-scale treatment on the divided gluing image and then carries out binarization treatment to obtain a binarized gluing image;
in the whole gluing process, the image processing module sends the binarized gluing image to the detection host through wireless transmission; the analysis module analyzes the binarized gummed image to obtain a cut-off line in the binarized gummed image, compares the cut-off line of the latest photographed binarized gummed image with the cut-off lines of the photographed previous M binarized gummed images, analyzes the similarity between the cut-off line and the cut-off line in the previous M images, and judges that the gummed image has no break point or path error if the similarity between all the comparison results is greater than a threshold value; and if 1 or more of the similarity of all the comparison results is smaller than the threshold value, judging that the gluing has a breakpoint or a path error.
2. The high-speed image transmission and analysis system for 5G applications according to claim 1, wherein:
100≥N≥50,20≥M≥10。
3. the high-speed image transmission and analysis system for 5G applications according to claim 1, wherein:
and if the un-glued speed reducer or the motor end cover has defects or the glued end cover has break points or paths are wrong, an audible and visual warning is sent out.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210931999.6A CN115338091B (en) | 2022-08-04 | 2022-08-04 | High-speed image transmission and analysis system under 5G application |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210931999.6A CN115338091B (en) | 2022-08-04 | 2022-08-04 | High-speed image transmission and analysis system under 5G application |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115338091A CN115338091A (en) | 2022-11-15 |
CN115338091B true CN115338091B (en) | 2024-01-19 |
Family
ID=83950377
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210931999.6A Active CN115338091B (en) | 2022-08-04 | 2022-08-04 | High-speed image transmission and analysis system under 5G application |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115338091B (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0814867A (en) * | 1994-07-04 | 1996-01-19 | Mazda Motor Corp | Method of checking condition of outer surface and device therefor |
JP2002109513A (en) * | 2000-09-28 | 2002-04-12 | Toyota Motor Corp | Coating defect detector and mask image preparing method |
CN101995223A (en) * | 2009-08-25 | 2011-03-30 | 比亚迪股份有限公司 | Chip appearance detection method and system |
CN109127194A (en) * | 2018-08-22 | 2019-01-04 | 广州瑞松北斗汽车装备有限公司 | Automobile gluing vision follows detection method |
CN111097664A (en) * | 2019-12-20 | 2020-05-05 | 广西柳州联耕科技有限公司 | Real-time deviation rectifying method based on robot gluing |
CN111375522A (en) * | 2018-12-27 | 2020-07-07 | 德州易能新能源科技有限公司 | Gluing device and gluing method |
CN113313712A (en) * | 2021-07-30 | 2021-08-27 | 季华实验室 | Battery gluing defect detection method and device, electronic equipment and storage medium |
CN113344901A (en) * | 2021-06-25 | 2021-09-03 | 北京市商汤科技开发有限公司 | Gluing defect detection method and device, storage medium and electronic equipment |
KR20220013593A (en) * | 2020-07-27 | 2022-02-04 | 케이티엠엔지니어링(주) | A System for Investigating A Reducer Condition of a Train |
-
2022
- 2022-08-04 CN CN202210931999.6A patent/CN115338091B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0814867A (en) * | 1994-07-04 | 1996-01-19 | Mazda Motor Corp | Method of checking condition of outer surface and device therefor |
JP2002109513A (en) * | 2000-09-28 | 2002-04-12 | Toyota Motor Corp | Coating defect detector and mask image preparing method |
CN101995223A (en) * | 2009-08-25 | 2011-03-30 | 比亚迪股份有限公司 | Chip appearance detection method and system |
CN109127194A (en) * | 2018-08-22 | 2019-01-04 | 广州瑞松北斗汽车装备有限公司 | Automobile gluing vision follows detection method |
CN111375522A (en) * | 2018-12-27 | 2020-07-07 | 德州易能新能源科技有限公司 | Gluing device and gluing method |
CN111097664A (en) * | 2019-12-20 | 2020-05-05 | 广西柳州联耕科技有限公司 | Real-time deviation rectifying method based on robot gluing |
KR20220013593A (en) * | 2020-07-27 | 2022-02-04 | 케이티엠엔지니어링(주) | A System for Investigating A Reducer Condition of a Train |
CN113344901A (en) * | 2021-06-25 | 2021-09-03 | 北京市商汤科技开发有限公司 | Gluing defect detection method and device, storage medium and electronic equipment |
CN113313712A (en) * | 2021-07-30 | 2021-08-27 | 季华实验室 | Battery gluing defect detection method and device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN115338091A (en) | 2022-11-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111127402A (en) | Visual detection method for welding quality of robot | |
CN110569841B (en) | Contact gateway key component target detection method based on convolutional neural network | |
CN107154039B (en) | Rubber tube online defect detection method | |
CN109840900B (en) | Fault online detection system and detection method applied to intelligent manufacturing workshop | |
CN102262093A (en) | Machine vision-based on-line detection method for printing machine | |
CN111229648A (en) | Solar cell panel flaw detection system and detection method based on machine vision | |
CN111311487B (en) | Rapid splicing method and system for photovoltaic module images | |
CN110930376A (en) | Method and system for detecting welding spot burrs based on machine vision | |
CN111126196A (en) | Equipment oil leakage detection method | |
CN113470005A (en) | Welding spot detection device and welding spot detection method for cylindrical battery cap | |
CN115456999B (en) | Saw chain surface defect automatic detection system and defect detection method based on machine vision | |
CN115493843B (en) | Quality monitoring method and equipment based on bearing retainer | |
CN104535589A (en) | Online detection method and device for low-voltage current mutual inductor | |
CN112718552A (en) | Automatic quality defect inspection device for LED circuit board and working method thereof | |
CN105023018A (en) | Jet code detection method and system | |
CN115424008A (en) | Method and system for detecting light modulation and focusing of laser projector production line | |
CN116908107A (en) | Paint surface flaw detection system based on machine vision | |
CN115338091B (en) | High-speed image transmission and analysis system under 5G application | |
CN111833350B (en) | Machine vision detection method and system | |
CN117035669A (en) | Enterprise safety production management method and system based on artificial intelligence | |
CN112927170B (en) | Automatic defect removing method in semiconductor manufacturing process | |
CN115266932A (en) | Gearbox gear shaft flaw detection method | |
CN112270663B (en) | Asphalt pavement sieving and repairing system based on honeycomb network environment | |
CN113933311A (en) | Machine vision flaw tracking and positioning system | |
CN113888506A (en) | Coated medicine shape defect detection algorithm based on deep segmentation network |
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 |