CN112326664B - Automatic quality control method for thermal insulation container - Google Patents
Automatic quality control method for thermal insulation container Download PDFInfo
- Publication number
- CN112326664B CN112326664B CN202011031206.2A CN202011031206A CN112326664B CN 112326664 B CN112326664 B CN 112326664B CN 202011031206 A CN202011031206 A CN 202011031206A CN 112326664 B CN112326664 B CN 112326664B
- Authority
- CN
- China
- Prior art keywords
- workpiece
- image
- detection
- axis robot
- plc
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8806—Specially adapted optical and illumination features
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/8411—Application to online plant, process monitoring
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8806—Specially adapted optical and illumination features
- G01N2021/8809—Adjustment for highlighting flaws
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8867—Grading and classifying of flaws using sequentially two or more inspection runs, e.g. coarse and fine, or detecting then analysing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention relates to the technical field of manufacturing of heat preservation containers, in particular to an automatic quality control method of a heat preservation container, which comprises the steps of continuously acquiring images on the surface of a workpiece by using an industrial camera, acquiring sampling images, extracting the acquired sampling images by an image processing unit, judging whether the surface of the workpiece has flaws or not, sending detection results to a PLC (programmable logic controller), sending instructions to a six-axis robot by the PLC according to the received judgment results, grabbing the workpiece into a welding line identification detection device to carry out welding line identification or grabbing the workpiece into a defective product basket, and transferring the workpiece into a punch press to carry out typing processing after the workpiece entering the welding line identification detection device finds a processing safety area. According to the automatic quality control method for the heat preservation container, a visual detection technology is adopted to replace traditional manual identification, visual dynamic capture is changed from manual visual inspection, detection results can be obtained rapidly, false detection and missing detection of manual detection are avoided, accuracy is high, and detection qualification rate is high.
Description
Technical Field
The invention relates to the technical field of manufacturing of thermal insulation containers, in particular to an automatic quality control method of a thermal insulation container.
Background
Machine vision is a branch of the rapid development of artificial intelligence. In short, machine vision is to use a machine instead of a human eye to make measurements and decisions. The machine vision system converts the shot target into an image signal through a machine vision product (namely an image shooting device), transmits the image signal to a special image processing system, obtains form information of the shot target, and converts the form information into a digital signal according to information such as pixel distribution, brightness, color and the like; the image processing system performs various operations on the digital signals to extract characteristics of the object, and further controls the operation of the on-site equipment according to the discrimination result.
The popularity of machine vision in use is mainly in the semiconductor and electronics industries, with approximately 40% -50% being concentrated in the semiconductor industry. Machine vision systems are also widely used in various aspects of quality inspection, and their products are of major importance in applications. In China, the application of vision technology starts in the 90 s, and the popularization of machine vision product technology is insufficient, so that the application of the industries is almost blank.
At present, the defect detection of the thermal insulation container in the market basically adopts a manual identification mode, which is time-consuming and labor-consuming, not only requires a great deal of energy, but also is easy to leak detection and misprime in the detection process, and has low accuracy.
Disclosure of Invention
Therefore, the invention aims to provide an automatic quality control method for the heat preservation container, which adopts a visual detection technology to replace the traditional manual identification, changes the manual visual inspection into visual dynamic capture, can quickly obtain a detection result, avoids the false detection and missing detection of the manual detection, and has higher accuracy and higher detection qualification rate.
The invention solves the technical problems by the following technical means:
an automated quality control method for a thermal container, the quality control method comprising the steps of:
s1: polishing the surface of a workpiece, continuously collecting images on the surface of the workpiece by using an industrial camera, and obtaining sampling images;
s2: the collected sampling image is returned to an image processing unit, the image processing unit performs preprocessing on the received image, highlights image features, judges whether the surface of the workpiece has flaws or not according to the extracted image features, and sends a detection result to a PLC (programmable logic controller);
s3: the PLC controller sends out an instruction to the six-axis robot if the product is qualified according to the received judging result, grabs the workpiece, places the workpiece into a weld recognition and detection device for weld recognition, finds a processing safety area, and then the PLC controller transmits a signal to control the six-axis robot to grab the workpiece and lock the angle and the direction of the workpiece, and the robot is transferred into a punch press for typewriting;
if the product has flaws, the PLC controller gives instructions to the six-axis robot to grasp and put the workpiece into the defective product basket
S4: after the six-axis robot sends the workpiece into a die positioning point of the punch, a signal is transmitted to the punch through the PLC to perform typewriting processing, and after the processing is completed, the six-axis robot takes the workpiece out and enters the next working procedure.
In the step S1, a sampling image is obtained by combining an industrial high-speed area array camera with a line structured light and a line scanning camera with a line light source.
The industrial high-speed area array camera is adopted, the millisecond-level detection frequency can be achieved, the detection time is quick, the production efficiency is improved, meanwhile, the defects on the surface of the workpiece can be detected more comprehensively by adopting the mode that the industrial high-speed area array camera is combined with the line scanning camera and the line light source, and the detection is more perfect.
Further, the flaws in the step S2 include, but are not limited to pits, stringing, scratching, uneven brightness, thick lines, and waviness.
Further, the step S2 specifically includes: and returning the acquired sampling image to an image processing unit, performing self-adaptive binarization and morphological opening and closing operation noise reduction treatment on the image, highlighting image characteristics, identifying the outline of the workpiece, extracting an area image of the workpiece, scaling the extracted area image to be the same as the flaw-free reference image, comparing the area image with the flaw-free reference image in pixel point level, detecting the flaw-free workpiece and the flaw-free workpiece, and transmitting the detection result to a PLC (programmable logic controller).
Further, in the step S3, the weld joint recognition and detection device performs weld joint detection through a chromatograph.
When the chromatograph is used for detection, the straight seam after the welding of the workpiece is in a black gray line shape, the surface layer of the unwelded product is silvery white, the color difference is obvious, and the welding seam can be rapidly identified.
Further, in the step S3, the specific operation of searching the machining safety area is as follows: the welding seam detection is carried out on the workpiece which is arranged in the welding seam identification detection device and is opposite to the 90-degree area of the chromatograph,
if no welding line exists, judging the detected 90-degree area as a processing safety area, transmitting a signal to the six-axis robot through the PLC, grabbing a product, locking the angle and the direction of a workpiece, and transferring to a punch press for typewriting processing;
if the welding line is detected, the welding line is rotated by 90 degrees again, the detection and the rotation operation by 90 degrees are repeated until the welding line does not exist in the detection area, the detected 90-degree area is judged to be a processing safety area, a signal is transmitted to the six-axis robot through the PLC, the angle and the direction of the product are grabbed and locked, and the press is transferred to the typing processing of the punch press.
Further, when the welding seam recognition device does not detect the welding seam in the current 90-degree area, the welding seam recognition device rotates 60 degrees to the left and right again by taking the central line of the current 90-degree area as a starting point, if the welding seam is not detected, the current 90-degree area is confirmed to be a machining safety area, and if the welding seam is detected, the current 90-degree area is rotated 30 degrees in the opposite direction of the position of the welding seam, and the machining safety area is confirmed.
Further, a secondary detection step is further included between the steps S2 and S3, specifically: and (3) the PLC controller heats the qualified workpiece to 50-60 ℃ by using a six-axis robot according to the received judging result, takes out the qualified workpiece, rapidly coats a layer of reinforced film liquid, places the workpiece in a vacuum drying box, keeps the temperature and the vacuum for 10-12min, forms a reinforced film layer on the surface of the workpiece, takes out the workpiece, continuously collects images on the surface of the workpiece by using an industrial camera again, acquires a secondary sampling image, grabs the workpiece after the image collection by using the six-axis robot, places the workpiece in an ice water bath at 0-5 ℃, dries the workpiece after the workpiece is cleaned, enters the next procedure, returns the acquired secondary sampling image to an image processing unit, carries out pretreatment on the received image, highlights the image characteristics, judges whether the surface of the workpiece has flaws or not by using the image characteristics, and sends the detecting result to the PLC controller.
Further, the preparation method of the reinforced membrane liquid comprises the following steps: weighing N, N-dimethylacrylamide and N-isopropylacrylamide with equal molar mass, stirring and dissolving in deionized water, adding modified nano carbon powder, uniformly dispersing by ultrasonic, adding fluorinated diphenyl titanocene and ethylene glycol dimethacrylate, magnetically stirring for 30min, adding into a reactor, reacting for 2-5min under the condition of 50 ℃ and ultraviolet irradiation in nitrogen atmosphere, taking out a reaction product after the reaction is finished, dialyzing for 7d by distilled water, replacing distilled water every 12h, adding into 30-45 ℃ distilled water after the dialysis is finished, and continuously stirring for 10-12h to obtain the reinforced membrane liquid.
Further, the preparation method of the modified nano carbon powder comprises the following steps: adding a silane coupling agent into distilled water, dropwise adding 4-5 drops of acetic acid, carrying out ultrasonic oscillation for 10min to obtain a hydrolysate, adding nano carbon powder into distilled water, carrying out strong stirring and dispersion for 10min, adding the hydrolysate, carrying out constant-temperature reflux for 6h at 80 ℃, carrying out ultrasonic oscillation for 30min after the reaction, centrifuging, separating, washing a solid with absolute ethyl alcohol for three times, and carrying out vacuum drying at 40 ℃ to obtain the modified nano carbon powder.
Because some pits or scratches existing on the surface of the workpiece are extremely tiny, the pits or scratches are not easy to compare in the process of processing by the image processing unit, and thus the omission is caused, the application further increases a secondary detection step between the S1 and the S2 steps, the reinforcing film liquid is coated on the surface of the workpiece, the reinforcing film liquid adopts N, N-dimethylacrylamide and N-isopropylacrylamide as main materials, has temperature sensitivity, is liquid or pasty at the temperature of 10-30 ℃ and is solid at the temperature of more than 30 ℃, therefore, by controlling the temperature, a solid reinforcing film layer is formed on the surface of the workpiece before the secondary image acquisition, and can be eluted in an ice water bath after the image acquisition is completed, and the surface of the workpiece is not influenced.
After one-time detection, pits or scratches on the surface of the workpiece are extremely small, in the coating process, the reinforced film liquid cannot enter the pits or scratches, so that air exists between the pits or scratches and the reinforced film layer, the air in the pits or scratches breaks through the reinforced film layer to overflow, a cavity is reserved on the reinforced film layer, the modified nano carbon powder in the reinforced film liquid is combined, and the modified nano carbon powder has stronger light absorption performance, so that after an image is acquired, the places without defects are darker, and the places with defects are brighter because the reinforced film layer is damaged, so that the defects or scratches on the surface of the workpiece can be further judged by generating strong light-dark contrast, and the probability of omission is reduced to a certain extent.
The invention has the beneficial effects that:
1. according to the automatic quality control method for the heat preservation container, various flaws are converted into data and quantized by adopting a visual detection technology, manual visual inspection is changed into visual dynamic capture, detection results can be obtained rapidly, false detection and missing detection of manual detection are avoided, and the detection qualification rate is higher.
2. The invention adopts visual detection to realize on-line automatic production, reduces inspectors, can automatically classify products according to detection results, adopts visual non-contact measurement, has wider spectral response range, continuous production and lower cost, and has the advantages of easy realization of information integration by machine vision, high precision and good flexibility.
3. According to the automatic quality control method for the heat preservation container, the chromatograph is adopted for automatic recognition to avoid weld joint stamping, compared with the traditional manual recognition of weld joint stamping, on one hand, the intelligent automatic recognition can reduce errors to a certain extent, and on the other hand, the intelligent automatic is utilized to replace manual punching operation, so that potential safety hazards caused by manual operation can be avoided.
Detailed Description
The present invention will be described in detail with reference to the following specific examples:
the invention discloses an automatic quality control method of a heat preservation container, which comprises the following steps:
example 1
S1: polishing the surface of a workpiece, continuously collecting images on the surface of the workpiece by using an industrial camera, and particularly, obtaining a sampling image by adopting a mode of adding a line structured light by using an industrial high-speed area array camera and adding a line light source by using a line scanning camera;
s2: returning the collected sampling image to an image processing unit, carrying out self-adaptive binarization and morphological opening and closing operation noise reduction treatment on the image, highlighting image characteristics, identifying the outline of a workpiece, extracting an area image of the workpiece, scaling the extracted area image to be the same as a flaw-free reference image, comparing the area image with the flaw-free reference image in pixel point level, judging whether flaws such as pits, wiredrawing, scratches, uneven brightness, thick lines, ripples exist on the surface of the workpiece, detecting the flaw-free workpiece and the flaw-free workpiece by setting a threshold value, and sending the detection result to a PLC (programmable logic controller);
s3: the PLC controller sends out instructions to the six-axis robot if the product is qualified according to the received judging result, grabs the workpiece and places the workpiece into the welding seam identification and detection device, carries out welding seam identification by utilizing the chromatograph, carries out welding seam detection on the workpiece placed in the welding seam identification and detection device and right opposite to the 90-degree area of the chromatograph,
if no welding line exists, judging the detected 90-degree area as a processing safety area, transmitting a signal to the six-axis robot through the PLC, grabbing a product, locking the angle and the direction of a workpiece, and transferring to a punch press for typewriting processing;
if the welding line is detected, rotating by 90 degrees again, repeating the detection and rotation by 90 degrees until no welding line exists in the detection area, judging the detected 90-degree area as a processing safety area, transmitting a signal to the six-axis robot through the PLC, grabbing a product and locking the angular orientation of the product, and transferring the product into a punch press for typewriting processing;
if the product has flaws, the PLC controller gives instructions to the six-axis robot, and the workpiece is grabbed and placed into the defective product basket;
s4: after the six-axis robot sends the workpiece into a die positioning point of the punch, a signal is transmitted to the punch through the PLC to perform typewriting processing, and after the processing is completed, the six-axis robot takes the workpiece out and enters the next working procedure.
Example two
In the step S3, when the weld seam recognition device does not detect a weld seam in the current 90 ° region, the weld seam recognition device further rotates 60 ° to the left and right with the center line of the current 90 ° region as the starting point, and if the weld seam is not detected, the current 90 ° region is confirmed to be a machining safety region, and if the weld seam is detected, the current 90 ° region is rotated 30 ° in the opposite direction of the position of the weld seam, and the weld seam is determined to be the machining safety region.
Example III
Preparation of modified nano carbon powder: weighing silane coupling agent KH-570, adding into distilled water with the volume of 10 times, dropwise adding acetic acid with the volume of same, ultrasonically oscillating for 10min to obtain hydrolysate, weighing nano carbon powder, adding into distilled water with the mass of 20 times of nano carbon powder, strongly stirring and dispersing for 10min, adding hydrolysate, wherein the mass ratio of nano carbon powder to silane coupling agent is 1:1, refluxing at the constant temperature of 80 ℃ for 6h, ultrasonically oscillating the reaction solution for 30min after the reaction is finished, centrifuging, separating, washing the solid with absolute ethyl alcohol for three times, and vacuum drying at the temperature of 40 ℃ to obtain modified nano carbon powder.
Preparation of reinforced membrane liquid: weighing N, N-dimethylacrylamide and N-isopropylacrylamide with equal molar mass, stirring and dissolving in deionized water, adding modified nano carbon powder, uniformly dispersing by ultrasonic, adding fluorinated diphenyl titanocene and ethylene glycol dimethacrylate, wherein the mass ratio of the modified nano carbon powder to the fluorinated diphenyl titanocene to the ethylene glycol dimethacrylate to the N, N-dimethylacrylamide is 1:0.1:0.2:2, magnetically stirring for 30min, adding into a reactor, reacting for 2-5min at the reaction temperature of 50 ℃ under the condition of ultraviolet irradiation, taking out a reaction product after the reaction is finished, dialyzing for 7d by distilled water, changing distilled water once every 12h, adding 10 times of distilled water with the mass of 30-45 ℃ after the dialysis is finished, and continuously stirring for 10-12h to obtain the reinforced membrane liquid.
The detection is carried out by using the prepared enhanced membrane liquid, and the detection is concretely as follows:
s1: polishing the surface of the workpiece, continuously collecting images on the surface of the workpiece by using an industrial camera, and obtaining sampling images.
S2: the collected sampling image is returned to an image processing unit, the image processing unit performs preprocessing on the received image, highlights image features, judges whether the surface of the workpiece has flaws or not according to the extracted image features, and sends a detection result to a PLC (programmable logic controller);
s3: according to the received judging result, the PLC controller uses a six-axis robot to heat a qualified workpiece to 50-60 ℃ in a heating box, takes out, rapidly coats a layer of reinforced film liquid, places the workpiece in a vacuum drying box, keeps the temperature at 50 ℃ and the vacuum degree at 45 Pa-12 min, forms a reinforced film layer on the surface of the workpiece, takes out and uses an industrial camera to continuously acquire images on the surface of the workpiece again, acquires a subsampled image, grabs the workpiece after the image acquisition by the six-axis robot, places the workpiece in an ice water bath at 0-5 ℃, cleans the workpiece, dries the workpiece to enter the next procedure, returns the acquired subsampled image to an image processing unit, carries out pretreatment on the received image, highlights the image characteristics, judges whether the surface of the workpiece has flaws or not by the image processing unit, and sends the detecting result to the PLC controller again;
s4: the PLC controller sends out instructions to the six-axis robot if the product is qualified according to the received judging result, grabs the workpiece and places the workpiece into the welding seam identification and detection device, carries out welding seam identification by utilizing the chromatograph, carries out welding seam detection on the workpiece placed in the welding seam identification and detection device and right opposite to the 90-degree area of the chromatograph,
if no welding line exists, then the center line of the current 90-degree area is taken as a starting point, the welding line is rotated by 60 degrees to the left and right for detecting the welding line, if the welding line is not detected, the current 90-degree area is confirmed to be a processing safety area, if the welding line is detected, the current 90-degree area is rotated by 30 degrees in the opposite direction of the position of the welding line, the current 90-degree area is confirmed to be the processing safety area, a signal is transmitted to a six-axis robot through a PLC, the angle and the direction of a product are grabbed, the workpiece is locked, and the punching machine is shifted to typewriting processing;
if the welding line is detected, rotating by 90 degrees again, repeating the detection and rotation by 90 degrees until no welding line exists in the detection area and no welding line exists in the range of 30 degrees of left-right rotation, judging the detected 90-degree area as a processing safety area, transmitting a signal to a six-axis robot through a PLC (programmable logic controller), grabbing a product and locking the angle and the direction of the product, and transferring the product into a punch press for typewriting;
if the product has flaws, the PLC controller gives instructions to the six-axis robot, and the workpiece is grabbed and placed into the defective product basket;
s3: after the six-axis robot sends the workpiece into a die positioning point of the punch, a signal is transmitted to the punch through the PLC to perform typewriting processing, and after the processing is completed, the six-axis robot takes the workpiece out and enters the next working procedure.
The automatic quality control method of the heat preservation container in the first to third embodiments is utilized to detect flaws of the produced heat preservation container and print on a punch press, meanwhile, the existing manual detection and manual operation punch press technology is adopted to compare, after the heat preservation container works for 8 hours, statistics is carried out on the number of detections and the qualification rate of products obtained by the detection, and the statistical results are shown in the table 1:
TABLE 1
As can be seen from the data in Table 1, the automatic quality control method for the thermal insulation container has the advantages that the processing efficiency is obviously higher than that of the traditional manual detection method, the qualification rate of the detected and processed product is obviously higher than that of the traditional manual detection and processing technology, the omission ratio can be obviously reduced in the image acquisition stage after the secondary detection step through the comparison of the data in the first embodiment, the second embodiment and the third embodiment, the detection qualification rate can reach 100%, and the qualification rate of the final character punching processing can be obviously improved through the further verification in the step S3 through the comparison of the data in the first embodiment, the second embodiment and the third embodiment.
The above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made thereto without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered by the scope of the claims of the present invention. The technology, shape, and construction parts of the present invention, which are not described in detail, are known in the art.
Claims (6)
1. An automatic quality control method for a thermal insulation container is characterized by comprising the following steps:
s1: polishing the surface of a workpiece, continuously collecting images on the surface of the workpiece by using an industrial camera, and obtaining sampling images;
s2: the collected sampling image is returned to an image processing unit, the image processing unit performs preprocessing on the received image, highlights image features, judges whether the surface of the workpiece has flaws or not according to the extracted image features, and sends a detection result to a PLC (programmable logic controller);
s3: the PLC controller sends out an instruction to the six-axis robot if the product is qualified according to the received judging result, grabs the workpiece, places the workpiece into a weld recognition and detection device for weld recognition, finds a processing safety area, and then the PLC controller transmits a signal to control the six-axis robot to grab the workpiece and lock the angle and the direction of the workpiece, and the robot is transferred into a punch press for typewriting;
if the product has flaws, the PLC controller gives instructions to the six-axis robot, and the workpiece is grabbed and placed into the defective product basket;
s4: after the six-axis robot sends the workpiece into a die positioning point of the punch press, a signal is transmitted to the punch press through the PLC to carry out typewriting processing, and after the processing is finished, the six-axis robot takes out the workpiece and enters the next working procedure;
the method further comprises a secondary detection step between the steps S2 and S3, specifically: according to the received judging result, the PLC controller heats the qualified workpiece to 50-60 ℃ by using a six-axis robot, takes out the workpiece, rapidly coats a layer of reinforced film liquid, places the workpiece in a vacuum drying box, keeps the temperature and the vacuum for 10-12min, forms a reinforced film layer on the surface of the workpiece, takes out the workpiece again to continuously acquire images on the surface of the workpiece by using an industrial camera, acquires a secondary sampling image, grabs the workpiece after the image acquisition is placed in an ice water bath at 0-5 ℃ by using the six-axis robot, dries the workpiece after the cleaning, enters the next procedure, returns the acquired secondary sampling image to an image processing unit, carries out pretreatment on the received image, highlights the image characteristics, judges whether the surface of the workpiece has flaws or not by using the image processing unit, and sends the detection result to the PLC controller;
the preparation method of the reinforced membrane liquid comprises the following steps: weighing N, N-dimethylacrylamide and N-isopropylacrylamide with equal molar mass, stirring and dissolving in deionized water, adding modified nano carbon powder, uniformly dispersing by ultrasonic, adding fluorinated diphenyl titanocene and ethylene glycol dimethacrylate, magnetically stirring for 30min, adding into a reactor, reacting for 2-5min under the condition of 50 ℃ and ultraviolet irradiation in nitrogen atmosphere, taking out a reaction product after the reaction is finished, dialyzing for 7d by distilled water, replacing distilled water every 12h, adding into 30-45 ℃ distilled water after the dialysis is finished, and continuously stirring for 10-12h to obtain reinforced membrane liquid;
the preparation method of the modified nano carbon powder comprises the following steps: adding a silane coupling agent into distilled water, dropwise adding 4-5 drops of acetic acid, carrying out ultrasonic oscillation for 10min to obtain a hydrolysate, adding nano carbon powder into distilled water, carrying out strong stirring and dispersion for 10min, adding the hydrolysate, carrying out constant-temperature reflux for 6h at 80 ℃, carrying out ultrasonic oscillation for 30min after the reaction is finished, centrifuging, separating, washing a solid with absolute ethyl alcohol for three times, and carrying out vacuum drying at 40 ℃ to obtain the modified nano carbon powder.
2. The automated quality control method of a thermal container according to claim 1, wherein in step S1, a sampling image is obtained by using an industrial high-speed area-array camera with line structured light in combination with a line scanning camera with line light source.
3. The automated quality control method of insulated containers of claim 2, wherein the defects in step S2 include, but are not limited to pits, stringiness, scratches, uneven brightness, thick lines, and waviness.
4. The automated quality control method of a thermal container according to claim 3, wherein the step S2 specifically comprises: and returning the acquired sampling image to an image processing unit, performing self-adaptive binarization and morphological opening and closing operation noise reduction treatment on the image, highlighting image characteristics, identifying the outline of the workpiece, extracting an area image of the workpiece, scaling the extracted area image to be the same as the flaw-free reference image, comparing the area image with the flaw-free reference image in pixel point level, detecting the flaw-free workpiece and the flaw-free workpiece, and transmitting the detection result to a PLC (programmable logic controller).
5. The automated quality control method of a thermal container according to claim 4, wherein in step S3, the weld recognition and detection device performs weld detection by a chromatograph.
6. The automated quality control method of a thermal container according to claim 5, wherein in step S3, the searching for the machining safety area is specifically performed as: the welding seam detection is carried out on the workpiece which is arranged in the welding seam identification detection device and is opposite to the 90-degree area of the chromatograph,
if no welding line exists, judging the detected 90-degree area as a processing safety area, transmitting a signal to the six-axis robot through the PLC, grabbing a product, locking the angle and the direction of a workpiece, and transferring to a punch press for typewriting processing;
if the welding line is detected, the welding line is rotated by 90 degrees again, the detection and the rotation operation by 90 degrees are repeated until the welding line does not exist in the detection area, the detected 90-degree area is judged to be a processing safety area, a signal is transmitted to the six-axis robot through the PLC, the angle and the direction of the product are grabbed and locked, and the press is transferred to the typing processing of the punch press.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011031206.2A CN112326664B (en) | 2020-09-27 | 2020-09-27 | Automatic quality control method for thermal insulation container |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011031206.2A CN112326664B (en) | 2020-09-27 | 2020-09-27 | Automatic quality control method for thermal insulation container |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112326664A CN112326664A (en) | 2021-02-05 |
| CN112326664B true CN112326664B (en) | 2023-06-13 |
Family
ID=74304443
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011031206.2A Active CN112326664B (en) | 2020-09-27 | 2020-09-27 | Automatic quality control method for thermal insulation container |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112326664B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB595844A (en) * | 1945-01-04 | 1947-12-18 | Kodak Ltd | Improvements in and relating to the production and processing of photographic materials |
| US4889790A (en) * | 1988-02-26 | 1989-12-26 | Morton Thiokol, Inc. | Method of forming a conformable mask on a printed circuit board |
| JP2004325346A (en) * | 2003-04-25 | 2004-11-18 | Matsushita Electric Ind Co Ltd | Method of detecting pinhole and method of producing membrane electrode assembly |
| WO2011040628A1 (en) * | 2009-09-29 | 2011-04-07 | Fujifilm Corporation | Colorant multimer, colored curable composition, color filter and method for producing the same, and solid-state image sensor, image display device, liquid crystal display device and organic el display with the color filter |
| AU2010249031A1 (en) * | 2009-05-13 | 2011-12-01 | Sio2 Medical Products, Inc. | Outgassing method for inspecting a coated surface |
| CN104685970A (en) * | 2012-09-28 | 2015-06-03 | 吉坤日矿日石能源株式会社 | Device for inspecting substrate having irregular rough surface and inspection method using same |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2210395Y (en) * | 1994-10-08 | 1995-10-18 | 冶金工业部钢铁研究总院 | Device for determining diffusive hydrogen when metal deposition |
| CN108838099A (en) * | 2018-03-28 | 2018-11-20 | 广州大学 | Safety pin badge Defect Detection system and method based on machine vision |
| CN210938738U (en) * | 2019-09-10 | 2020-07-07 | 东莞市铁犀智能科技有限公司 | Can adjust loading attachment of thermos cup welding seam polishing angle |
| CN110480449A (en) * | 2019-09-10 | 2019-11-22 | 东莞市铁犀智能科技有限公司 | A kind of vacuum cup production line |
| CN211490915U (en) * | 2019-12-20 | 2020-09-15 | 温州金石机器人科技有限公司 | Track polishing processing assembly line |
| CN111545983A (en) * | 2020-03-30 | 2020-08-18 | 江苏统联科技股份有限公司 | Automatic labeling mechanism for straight weld joint of short pipe of stainless steel welded pipe |
-
2020
- 2020-09-27 CN CN202011031206.2A patent/CN112326664B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB595844A (en) * | 1945-01-04 | 1947-12-18 | Kodak Ltd | Improvements in and relating to the production and processing of photographic materials |
| US4889790A (en) * | 1988-02-26 | 1989-12-26 | Morton Thiokol, Inc. | Method of forming a conformable mask on a printed circuit board |
| JP2004325346A (en) * | 2003-04-25 | 2004-11-18 | Matsushita Electric Ind Co Ltd | Method of detecting pinhole and method of producing membrane electrode assembly |
| AU2010249031A1 (en) * | 2009-05-13 | 2011-12-01 | Sio2 Medical Products, Inc. | Outgassing method for inspecting a coated surface |
| WO2011040628A1 (en) * | 2009-09-29 | 2011-04-07 | Fujifilm Corporation | Colorant multimer, colored curable composition, color filter and method for producing the same, and solid-state image sensor, image display device, liquid crystal display device and organic el display with the color filter |
| CN104685970A (en) * | 2012-09-28 | 2015-06-03 | 吉坤日矿日石能源株式会社 | Device for inspecting substrate having irregular rough surface and inspection method using same |
Non-Patent Citations (1)
| Title |
|---|
| 翟茂林,哈鸿飞.功能性PolyNIPAAm系高聚物.高分子通报.1999,(第02期),第37-44、76页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112326664A (en) | 2021-02-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110220917B (en) | Crown cap surface defect online detection method based on image processing | |
| CN107203990B (en) | Label breakage detection method based on template matching and image quality evaluation | |
| CN112037203A (en) | Side surface defect detection method and system based on complex workpiece outer contour registration | |
| CN106383121B (en) | It is a kind of can adaptive multi-brand visible detection method and system | |
| CN105403147A (en) | Embedded bottle pre-form detection system and detection method | |
| CN109142509B (en) | Round steel magnetic powder flaw detection method and device | |
| CN107486412A (en) | A kind of target surface Defect Detection system based on machine vision | |
| He et al. | A critical review for machining positioning based on computer vision | |
| CN110108712A (en) | Multifunctional visual sense defect detecting system | |
| CN110827256A (en) | Optical and thermal infrared multi-stage imaging detection method and device for defects of transparent component | |
| CN110728657A (en) | Annular bearing outer surface defect detection method based on deep learning | |
| CN113177924A (en) | Industrial production line product flaw detection method | |
| CN103543205A (en) | Method and system for detecting foreign matters in bottled liquid | |
| CN113744247A (en) | PCB welding spot defect identification method and system | |
| Fu et al. | Medicine glass bottle defect detection based on machine vision | |
| CN112326664B (en) | Automatic quality control method for thermal insulation container | |
| CN114594138A (en) | Semiconductor device substrate detection system and method | |
| CN111539951B (en) | Visual detection method for outline size of ceramic grinding wheel head | |
| Shuangyang | Fast inspection of food packing seals using machine vision | |
| CN111644728B (en) | Direct high-precision forming method for repairing rigid impact auxiliary electric arc additive hot-working die | |
| CN102914546A (en) | System and method for detecting mist spray tank covers on the basis of machine vision | |
| CN108460763B (en) | Automatic detection and identification method for magnetic powder inspection image | |
| CN202869994U (en) | Machine vision based aerosol can cover quality detecting system | |
| RU2787072C1 (en) | Method for promptly detecting surface defects of crown caps based on image processing | |
| Huang et al. | A Technology of Surface Defects for the Solar Wafer by Dual Vision |
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 |