CN113743473A - Intelligent identification and detection method for automatic spraying process of complex parts - Google Patents
Intelligent identification and detection method for automatic spraying process of complex parts Download PDFInfo
- Publication number
- CN113743473A CN113743473A CN202110901319.1A CN202110901319A CN113743473A CN 113743473 A CN113743473 A CN 113743473A CN 202110901319 A CN202110901319 A CN 202110901319A CN 113743473 A CN113743473 A CN 113743473A
- Authority
- CN
- China
- Prior art keywords
- image
- spraying
- automatic
- detection method
- identification
- 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.)
- Pending
Links
- 238000005507 spraying Methods 0.000 title claims abstract description 84
- 238000001514 detection method Methods 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000008569 process Effects 0.000 title claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000005516 engineering process Methods 0.000 claims abstract description 6
- 238000012360 testing method Methods 0.000 claims description 17
- 239000011159 matrix material Substances 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 10
- 238000011156 evaluation Methods 0.000 claims description 8
- 239000003973 paint Substances 0.000 claims description 8
- 239000007921 spray Substances 0.000 claims description 8
- 230000003287 optical effect Effects 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000005286 illumination Methods 0.000 claims description 4
- 238000003709 image segmentation Methods 0.000 claims description 4
- 239000002904 solvent Substances 0.000 claims description 4
- 239000000853 adhesive Substances 0.000 claims description 3
- 230000001070 adhesive effect Effects 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 11
- 238000004422 calculation algorithm Methods 0.000 abstract description 2
- 230000007547 defect Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 239000000843 powder Substances 0.000 description 3
- 239000007787 solid Substances 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/06—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness for measuring thickness ; e.g. of sheet material
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/30—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration by the use of histogram techniques
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20164—Salient point detection; Corner detection
Abstract
The invention discloses an intelligent identification and detection method for an automatic spraying process of a complex part, and belongs to the technical field of intelligent manufacturing. The method comprises the steps of S1, processing the part outline image; s2, intelligently identifying the part types; 3. performing part spraying; the automatic spraying quality detection method based on the machine vision technology has the advantages that automatic identification and spraying quality detection of parts are realized by utilizing the machine vision technology and based on a part characteristic detection algorithm, the identification and detection efficiency is improved, and the identification and detection accuracy is also ensured.
Description
Technical Field
The invention relates to the field of automatic processing, in particular to an intelligent identification and detection method for an automatic spraying process of complex parts.
Background
The production process of the parts is an important process in the production process of the discrete manufacturing industry, and has an important supporting function for the whole production. The parts produced by a part professional factory per year exceed 200 thousands of parts, and the problems of quality fluctuation, manual occupational health, complicated quality record data distortion, insufficient process data deep mining and utilization and the like are obvious because of old part quality detection means and low automation degree. The problems of improvement of production efficiency and controllability of quality of parts are solved by automatic and informatization modification and automatic identification and detection. In the automatic spraying process of complex parts, the types and models of the parts are various, and the manual identification, sorting, processing quality defect judgment and other operations are low in efficiency and easy to make mistakes.
Disclosure of Invention
The invention aims to solve the problems in the prior art, provides an intelligent identification and detection method applied to the automatic spraying process of complex parts, realizes the automatic detection and identification of the parts by utilizing a machine vision technology based on a detection algorithm and part characteristics, improves the efficiency of the detection and identification of the parts, and ensures the accuracy of the detection and identification.
In order to achieve the above object, the technical solution of the present invention is as follows:
an intelligent identification and detection method for an automatic spraying process of complex parts comprises the following steps:
s1, part outline image processing: the method comprises the steps that an image information acquisition system is used for acquiring image information data of a part to be detected, and the acquired image information data are preprocessed through image binaryzation, image contrast enhancement, image filtering, image segmentation and other technologies;
s2, part type identification: extracting and analyzing the shape characteristics of the part based on data information obtained by preprocessing the part image, matching the shape characteristics with the part characteristics of a part model library, and identifying the model of the part;
s3, part spraying execution: matching a spraying process according to the part type identification result, and performing part spraying operation;
s4, spray surface image processing: the image information acquisition system acquires the surface image of the part after the spraying operation is executed again, and performs noise processing and image enhancement on the surface image;
s5, detecting the spraying flatness: according to the surfaces of the parts with the mirror surface and the non-mirror surface, adopting different light source irradiation schemes and detection schemes to perform corresponding flatness evaluation;
s6, judging the spraying quality: measuring the spraying thickness of each sprayed part by using an automatic paint film measuring instrument, and judging the thickness of different spraying types according to the thickness measurement value;
s7, comprehensive evaluation of spraying quality: and comprehensively evaluating the overall spraying quality of the part according to the part model and the flatness detection result identified in the step by combining hardness test, solvent resistance test, adhesive force test and impact resistance test.
Furthermore, the image information acquisition system comprises a camera, an illumination light source, an optical lens, an industrial personal computer and an encoder, the camera shoots part pictures and transmits the part pictures to the image acquisition card, the image acquisition card converts analog image signals into digital signals through analog-to-digital conversion and transmits the digital signals to the industrial personal computer, the industrial personal computer performs image processing, and an output port of the encoder is connected with a trigger port of the camera and used for controlling automatic acquisition of the camera.
Further, in step S2, the part shape features include geometric features, intensity features and color features; the geometric features refer to the length, area, angle and aspect ratio of the object, the intensity features refer to the gray value distribution of the object, and the color features refer to the color gray value of the pixel.
Further, in step S4, a mean filtering method is used to perform noise processing, and a histogram equalization method is used to perform image enhancement.
Further, in step S5, a dot matrix projection method is used for the mirror surface of the part, a dot matrix light source is used to project an object with a regular shape on the surface of the part after spraying, and then whether the surface of the part is flat or not is determined according to the deviation of the position of the projection of the object on the part to be measured relative to the position of the projection on the flat part.
Further, in step S5, for the non-specular surface, the surface of the object is obliquely irradiated by the line light source with concentrated energy and high brightness; and filtering the light straight line in the obtained image by adopting a sliding average filter to obtain a smoother road surface mesh image, and preliminarily judging the convex foreign matter or pit area on the surface of the part after subtracting the image from the original image.
Further, step S6 specifically includes: reading a spraying program used in the spraying execution process, and identifying the spraying type; reading the spraying thickness of each spraying part in the automatic paint film measuring instrument; and finally, judging whether the spraying thickness of the part is qualified or not according to the spraying type and the qualified judging standard of the spraying thickness.
In summary, the invention has the following advantages:
the automatic identification of the part model is realized based on the factors such as the size, the shape, the key characteristics and the like of the part; on the basis of automatic identification of part models, aiming at different quality detection requirements of each part, the automatic detection of the flatness and defects of the part is realized; the efficiency of part identification and detection is greatly improved, the probability of error identification and detection is reduced, and a solid foundation is laid for improving the overall production efficiency and quality; an exemplary case based on machine vision automatic detection is established, and reference experience is provided for subsequent popularization of the detection to component assembly and other business directions.
Drawings
FIG. 1 is a flow chart of an embodiment of the present invention;
Detailed Description
The present invention will be described in further detail with reference to examples, but the embodiments of the present invention are not limited thereto.
Example 1
The invention aims to complete the model identification and detection based on the part characteristics aiming at the part production in the discrete manufacturing production process, and achieves the following effects:
the invention provides an intelligent identification and detection method for an automatic spraying process of complex parts, which comprises the following steps as shown in figure 1:
s1, part outline image processing: the method comprises the steps that an image information acquisition system is used for acquiring image information data of a part to be detected, and the acquired image information data are preprocessed through image binaryzation, image contrast enhancement, image filtering, image segmentation and other technologies;
s2, part type identification: extracting and analyzing the shape characteristics of the part based on data information obtained by preprocessing the part image, matching the shape characteristics with the part characteristics of a part model library, and identifying the model of the part;
s3, part spraying execution: matching a spraying process according to the part type identification result, and performing part spraying operation;
s4, spray surface image processing: the image information acquisition system acquires the surface image of the part after the spraying operation is executed again, and performs noise processing and image enhancement on the surface image;
s5, detecting the spraying flatness: according to the surfaces of the parts with the mirror surface and the non-mirror surface, adopting different light source irradiation schemes and detection schemes to perform corresponding flatness evaluation;
s6, judging the spraying quality: measuring the spraying thickness of each sprayed part by using an automatic paint film measuring instrument, and judging the thickness of different spraying types according to the thickness measurement value;
s7, comprehensive evaluation of spraying quality: and comprehensively evaluating the overall spraying quality of the part according to the part model and the flatness detection result identified in the step by combining hardness test, solvent resistance test, adhesive force test and impact resistance test.
Example 2
The embodiment provides an intelligent identification and detection method for an automatic spraying process of a complex part, which comprises the following steps:
step S1, part outline image processing: firstly, placing a part to be detected in a view field of an industrial camera, and shooting a picture of the part by the industrial camera in an image information acquisition system; and then preprocessing the acquired part image data in the modes of image contrast enhancement, image filtering, image segmentation, image binarization and the like, and providing a data basis for subsequent part type identification, flatness detection, defect detection and surface pollutant detection.
The image information acquisition system consists of a hardware part consisting of a camera, an illumination light source, an optical lens, an industrial personal computer and an encoder. Wherein:
the main function of the camera, which is the most critical part, is to convert the optical signal into an electrical signal. The system selects a CMOS industrial camera with model BFLY-PGE-50A2C-CS, and the resolution is 2592 × 1944;
the method comprises the following steps that an illumination light source is a decisive factor influencing image quality, part surface detection needs to distinguish whether a mirror surface is detected, a dot matrix light source is selected for the mirror surface in a targeted mode, and a linear light source is selected for a non-mirror surface;
the industrial personal computer is a computer specially designed for an industrial field, and in view of the functional performance requirements of the image information acquisition system on image processing, the industrial personal computer is configured by adopting a VGA (video graphics array) display card with a CPU (central processing unit) above I3, an 8G memory, a solid state disk about 500GB and a 2G memory, the working temperature is 10-60 ℃, and the industrial personal computer is also provided with a gigabit network, a serial port, a parallel port and a USB port;
the encoder is connected with the output signal to a trigger port of the camera and is used for controlling the automatic acquisition of the camera, so that the object to be detected is synchronous with the camera, and the resolution of the image acquired by the camera is consistent. The encoder adopts a model with the resolution of more than 2000P/R and the maximum allowable rotating speed of more than 6000R/min.
Step S2, part type identification: the part type identification is to extract the shape features of the part based on the part data information obtained by processing the part image, wherein the shape features comprise geometric features (the area, the perimeter, the shape and the like of the object), intensity features (the gray value distribution of the object, such as the mean value, the standard deviation and the like) and color features (the color gray value of a pixel) and the like; and analyzing the shape characteristics on the basis of extracting the image characteristics of the part, describing different areas, finding out the mutual relation among the different areas, matching with the characteristics of each part in the part type characteristic library, and identifying the type of the part.
Step S3, part spraying execution: and matching the spraying process according to the part type identification result to perform part spraying operation.
Step S4, spray surface image processing: and acquiring a surface image of the part executed by the spraying operation, and performing preprocessing operations such as noise processing, image enhancement and the like on the image so as to perform flatness detection and defect detection in the following.
Noise in an image may originate from different stages of image acquisition, image transmission, etc. And (3) noise processing is carried out by adopting an average filtering mode, namely, the collected image f (i, j) is taken as a matrix array of W x H, W and H are the row number and the column number of the matrix, all pixel points in the neighborhood of each pixel point (i, j) in f (i, j) are averaged, the obtained gray value is given to d (i, j), and d (i, j) is the image after the average filtering. The pixel gray-scale value of each point of d (i, j) can be described as follows:
where i is 1, 2 … … W, j is 1, 2 … H, s is a predefined area with point (i, j) as the core, and k is the total number of pixels in the predefined area.
The specific operations of image enhancement are: image enhancement is the process of highlighting a region of interest in an image by certain processes while preventing or removing certain non-essential or unwanted information from the image processing. The patent adopts a histogram equalization method, and comprises the following steps:
A) calculating a histogram H (k) of the original image P (i, j), wherein k represents the kth column of the histogram, and the value of H (k) is the height of the kth column in the histogram, namely the number of pixels of which all gray values are less than or equal to k in the collected image;
B) calculating cumulative sums of histograms
C) Calculating a merging transformation function: (N) 255(N/N) minn(S (N)) - (N/N)), N being the number of initialized merging gray levels, generally 256, N being a value from 0 to N;
D) the merging transformation function yields a new image: p (i, j) ═ f (P (i, j)).
The acquired original image is transformed by the equalization method, so that the histogram of the original image is uniformly distributed, interested parts in the image are selectively highlighted, the parts are enhanced, useless information is suppressed, and the use value of the image is improved.
Step S5, detecting the spraying flatness: and analyzing and processing the part image by utilizing different light source irradiation schemes and detection schemes based on the surface of the part with the mirror surface and the non-mirror surface so as to evaluate the flatness.
Detecting and evaluating the mirror surface flatness: and for the surface of the mirror part, a dot matrix projection method is adopted, a dot matrix light source is used, and an object with a regular shape is projected on the surface of the sprayed part. And then, according to the deviation of the position of the projection in the part to be detected relative to the position of the projection in the flat part, the more uneven the surface is, the more severe the deviation is, and the flatness of the part is judged according to the deviation. Through summarizing a large number of parts with uneven surfaces, five modes of the defects of the uneven surfaces of the parts are summarized, namely: the surface presents bumps, sunken points, ridges, surface camber, and corners. For the surfaces with different defects, the dot matrixes in the images acquired by the dot matrix projection can present different arrangement rules. The Euclidean example judgment method, also called Euclidean distance, is a commonly used distance definition, and can represent the real distance between two points in an m-dimensional space, and the calculation formula is as follows:
wherein: d represents a value of Euclidean distance, Xi1I-dimensional coordinate, X, representing a first pointi1Representing the coordinates of the second point in the ith dimension. When the dimension is two-dimensional, the euclidean distance represents the distance between two points on the plane.
And obtaining each projection point in the dot matrix projection image, and sequencing the projection points to arrange the obtained points according to the sequence of the front row and the rear row. The points obtained in the detected part image are in one-to-one correspondence with the points obtained in the flat part image according to the arrangement sequence, so that the deviation amount of each point in the detected part image relative to the ideal position of each point can be obtained, the maximum distance value is compared with a certain threshold value, and the detected part image is considered to be uneven when the maximum distance value is larger than the threshold value.
Non-mirror surface flatness detection and evaluation: the non-mirror surface is irradiated with a line light source with concentrated energy and high brightness obliquely, and if the surface of the object is relatively flat, the light beam projected on the surface will keep a straight state, but when the surface of the object is uneven, the light beam projected on the surface will be bent and not straight due to the modulation of the uneven surface, and the bent part is irradiated with a concave area of the part.
The light straight line in the image is filtered by adopting a sliding average filter, the basic principle is to replace the average value of each point and adjacent points in the laser straight line, and the calculation principle can be expressed by the following formula:
of formula (II) to (III)'(i，j)A new ordinate value, P, representing the filtered value of a point of coordinates (i, j) in the image(i，j)The ordinate value at the filter front point (i, j) is represented, and 2N is the number of samples calculated per step by the moving average filter. After the image is smoothed by the sliding smoothing filter, a smoother road surface mesh image can be obtained, and after the image is subtracted from the original image, the primary judgment can be carried out on the convex foreign matter or the pit area.
Step S6, spray quality determination: measuring the spraying thickness of each spraying part by using an automatic paint film measuring instrument, and judging the thickness of different spraying types according to the measured value;
more specifically, firstly, a spraying type is identified by reading a spraying program used in the spraying execution process; then, the spraying thickness of each spraying part in the automatic paint film measuring instrument is read; and finally, judging whether the spraying thickness is qualified according to the spraying type and the qualified spraying thickness judgment standard, wherein the judgment standard is shown in the following table:
| type of spray | Spray thickness (mum) | Remarks for note |
| Spray paint | 30-50 | |
| Sprinkling point | ＞30 | |
| Plain powder | 50-70 | |
| Sand grain powder | 60-80 | |
| Orange peel powder | 80-100 |
And S7, comprehensively evaluating the spraying quality, and judging whether the spraying quality is qualified or not according to the part model and the flatness detection result identified in the previous step and the part spraying qualification standard. The step is to comprehensively evaluate the overall spraying quality of the part based on the flatness evaluation result and the judgment result of the spraying thickness of the part in the previous step and in combination with the subsequent manual test results of hardness test, solvent resistance test, adhesion test, impact resistance test and the like.
The invention realizes the automatic identification of the part model based on the factors such as the size, the shape, the key characteristics and the like of the part; on the basis of automatic identification of part models, aiming at different quality detection requirements of each part, the automatic detection of the flatness and defects of the part is realized; the efficiency of part identification and detection is greatly improved, the probability of error identification and detection is reduced, and a solid foundation is laid for improving the overall production efficiency and quality; an exemplary case based on machine vision automatic detection is established, and reference experience is provided for subsequent popularization of the detection to component assembly and other business directions.
It is not necessary to state that for simplicity of description, each of the above-described method embodiments is described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and elements referred to are not necessarily required in this application.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a ROM, a RAM, etc.
Claims (7)
1. An intelligent identification and detection method for an automatic spraying process of complex parts is characterized by comprising the following steps:
s1, part outline image processing: the method comprises the steps that an image information acquisition system is used for acquiring image information data of a part to be detected, and the acquired image information data are preprocessed through image binaryzation, image contrast enhancement, image filtering, image segmentation and other technologies;
s2, part type identification: extracting and analyzing the shape characteristics of the part based on data information obtained by preprocessing the part image, matching the shape characteristics with the part characteristics of a part model library, and identifying the model of the part;
s3, part spraying execution: matching a spraying process according to the part type identification result, and performing part spraying operation;
s4, spray surface image processing: the image information acquisition system acquires the surface image of the part after the spraying operation is executed again, and performs noise processing and image enhancement on the surface image;
s5, detecting the spraying flatness: according to the surfaces of the parts with the mirror surface and the non-mirror surface, adopting different light source irradiation schemes and detection schemes to perform corresponding flatness evaluation;
s6, judging the spraying quality: measuring the spraying thickness of each sprayed part by using an automatic paint film measuring instrument, and judging the thickness of different spraying types according to the thickness measurement value;
s7, comprehensive evaluation of spraying quality: and comprehensively evaluating the overall spraying quality of the part according to the part model and the flatness detection result identified in the step by combining hardness test, solvent resistance test, adhesive force test and impact resistance test.
2. The intelligent identification and detection method for the automatic spraying process of the complex parts as claimed in claim 1, wherein the image information acquisition system comprises a camera, an illumination light source, an optical lens, an industrial personal computer and an encoder, the camera shoots part pictures and transmits the part pictures to the image acquisition card, the image acquisition card converts analog image signals into digital signals through analog-to-digital conversion and transmits the digital signals to the industrial personal computer, the industrial personal computer performs image processing, and an output port of the encoder is connected with a trigger port of the camera and is used for controlling automatic acquisition of the camera.
3. The intelligent identification and detection method for the automatic spraying process of the complex parts as claimed in claim 1, wherein in the step S2, the shape features of the parts comprise geometric features, intensity features and color features; the geometric features refer to the length, area, angle and aspect ratio of the object, the intensity features refer to the gray value distribution of the object, and the color features refer to the color gray value of the pixel.
4. The intelligent identification and detection method for the automatic spraying process of the complex parts as claimed in claim 1, wherein in step S4, noise processing is performed by means of mean filtering, and image enhancement is performed by means of histogram equalization.
5. The intelligent identification and detection method for the automatic spraying process of the complex parts as claimed in claim 2, wherein in step S5, a dot matrix projection method is adopted for the surface of the mirror part, a dot matrix light source is used to project an object with a regular shape on the surface of the sprayed part, and then whether the surface of the part is flat or not is judged according to the deviation condition of the projected position of the object in the part to be detected relative to the projected position in the flat part.
6. The intelligent identification and detection method for the automatic spraying process of the complex parts as claimed in claim 1, wherein in step S5, for the non-specular surface, a line light source with concentrated energy and high brightness is used to irradiate the surface of the object obliquely; and filtering the light straight line in the obtained image by adopting a sliding average filter to obtain a smoother road surface mesh image, and preliminarily judging the convex foreign matter or pit area on the surface of the part after subtracting the image from the original image.
7. The intelligent identification and detection method for the automatic spraying process of the complex parts as claimed in claim 1, wherein the step S6 specifically comprises: reading a spraying program used in the spraying execution process, and identifying the spraying type; reading the spraying thickness of each spraying part in the automatic paint film measuring instrument; and finally, judging whether the spraying thickness of the part is qualified or not according to the spraying type and the qualified judging standard of the spraying thickness.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110901319.1A CN113743473A (en) | 2021-08-06 | 2021-08-06 | Intelligent identification and detection method for automatic spraying process of complex parts |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110901319.1A CN113743473A (en) | 2021-08-06 | 2021-08-06 | Intelligent identification and detection method for automatic spraying process of complex parts |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113743473A true CN113743473A (en) | 2021-12-03 |
Family
ID=78730359
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110901319.1A Pending CN113743473A (en) | 2021-08-06 | 2021-08-06 | Intelligent identification and detection method for automatic spraying process of complex parts |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113743473A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114227677A (en) * | 2021-12-15 | 2022-03-25 | 成都飞机工业（集团）有限责任公司 | Industrial robot spraying operation planning method, device, equipment and storage medium |
| CN114719791A (en) * | 2022-03-23 | 2022-07-08 | 江苏大中电机股份有限公司 | Flatness measuring method of motor closed slot punching sheet based on image processing |
| CN116045791A (en) * | 2023-04-03 | 2023-05-02 | 成都飞机工业（集团）有限责任公司 | Metal paint coating thickness assessment method |
| CN117483209A (en) * | 2024-01-02 | 2024-02-02 | 深圳市深海龙腾科技有限公司 | Method and system for controlling production quality of reflective film based on machine vision |
| CN117557554A (en) * | 2024-01-05 | 2024-02-13 | 海斯福(深圳)科技有限公司 | Intelligent detection method and system for spraying flatness of fluorine-containing coating |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103008215A (en) * | 2012-11-28 | 2013-04-03 | 北京羽林军石油科技有限公司 | Method for spraying bicomponent modified epoxy resin with 100 percent solid content on inner wall of steel pipe |
| CN106624025A (en) * | 2016-09-30 | 2017-05-10 | 图灵视控（北京）科技有限公司 | Intelligent flexible machining system and detecting system based on machine vision |
| CN108972573A (en) * | 2018-06-12 | 2018-12-11 | 浙江大学 | A kind of industrial robot automation wheel hub polishing system and method based on characteristics of image identification |
| CN109543267A (en) * | 2018-11-13 | 2019-03-29 | 福州大学 | Handicraft surface based on image procossing sprays simulation and optimization method |
| CN109590181A (en) * | 2018-11-15 | 2019-04-09 | 株洲飞鹿高新材料技术股份有限公司 | A kind of Workpiece painting method, spray equipment and paint finishing based on binocular vision |
| CN110961322A (en) * | 2019-12-10 | 2020-04-07 | 安徽佳森精密科技有限公司 | Automatic spraying method for television backboard |
| CN112452581A (en) * | 2020-10-13 | 2021-03-09 | 江苏三立液压机械有限公司 | Moving workpiece automatic spraying robot system based on machine vision and working method |
-
2021
- 2021-08-06 CN CN202110901319.1A patent/CN113743473A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103008215A (en) * | 2012-11-28 | 2013-04-03 | 北京羽林军石油科技有限公司 | Method for spraying bicomponent modified epoxy resin with 100 percent solid content on inner wall of steel pipe |
| CN106624025A (en) * | 2016-09-30 | 2017-05-10 | 图灵视控（北京）科技有限公司 | Intelligent flexible machining system and detecting system based on machine vision |
| CN108972573A (en) * | 2018-06-12 | 2018-12-11 | 浙江大学 | A kind of industrial robot automation wheel hub polishing system and method based on characteristics of image identification |
| CN109543267A (en) * | 2018-11-13 | 2019-03-29 | 福州大学 | Handicraft surface based on image procossing sprays simulation and optimization method |
| CN109590181A (en) * | 2018-11-15 | 2019-04-09 | 株洲飞鹿高新材料技术股份有限公司 | A kind of Workpiece painting method, spray equipment and paint finishing based on binocular vision |
| CN110961322A (en) * | 2019-12-10 | 2020-04-07 | 安徽佳森精密科技有限公司 | Automatic spraying method for television backboard |
| CN112452581A (en) * | 2020-10-13 | 2021-03-09 | 江苏三立液压机械有限公司 | Moving workpiece automatic spraying robot system based on machine vision and working method |
Non-Patent Citations (2)
| Title |
|---|
| 苏景存: ""基于机器视觉的机器人喷涂技术研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 1, pages 4 * |
| 谢剑: ""基于机器视觉的表面平整度检测方法研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 3, pages 138 - 1944 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114227677A (en) * | 2021-12-15 | 2022-03-25 | 成都飞机工业（集团）有限责任公司 | Industrial robot spraying operation planning method, device, equipment and storage medium |
| CN114227677B (en) * | 2021-12-15 | 2024-02-20 | 成都飞机工业（集团）有限责任公司 | Industrial robot spraying operation planning method, device, equipment and storage medium |
| CN114719791A (en) * | 2022-03-23 | 2022-07-08 | 江苏大中电机股份有限公司 | Flatness measuring method of motor closed slot punching sheet based on image processing |
| CN114719791B (en) * | 2022-03-23 | 2022-11-01 | 江苏大中电机股份有限公司 | Flatness measuring method of motor closed slot punching sheet based on image processing |
| CN116045791A (en) * | 2023-04-03 | 2023-05-02 | 成都飞机工业（集团）有限责任公司 | Metal paint coating thickness assessment method |
| CN117483209A (en) * | 2024-01-02 | 2024-02-02 | 深圳市深海龙腾科技有限公司 | Method and system for controlling production quality of reflective film based on machine vision |
| CN117483209B (en) * | 2024-01-02 | 2024-04-09 | 深圳市深海龙腾科技有限公司 | Method and system for controlling production quality of reflective film based on machine vision |
| CN117557554A (en) * | 2024-01-05 | 2024-02-13 | 海斯福(深圳)科技有限公司 | Intelligent detection method and system for spraying flatness of fluorine-containing coating |
| CN117557554B (en) * | 2024-01-05 | 2024-04-23 | 海斯福(深圳)科技有限公司 | Intelligent detection method and system for spraying flatness of fluorine-containing coating |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113743473A (en) | Intelligent identification and detection method for automatic spraying process of complex parts | |
| CN107784669A (en) | A kind of method that hot spot extraction and its barycenter determine | |
| CN112651968B (en) | Wood board deformation and pit detection method based on depth information | |
| CN111754583A (en) | Automatic method for vehicle-mounted three-dimensional laser radar and camera external parameter combined calibration | |
| CN109540925B (en) | Complex ceramic tile surface defect detection method based on difference method and local variance measurement operator | |
| CN115115612B (en) | Surface defect detection method and system for mechanical parts | |
| CN114252449B (en) | Aluminum alloy weld joint surface quality detection system and method based on line structured light | |
| CN113706566B (en) | Edge detection-based perfuming and spraying performance detection method | |
| CN114219773B (en) | Pre-screening and calibrating method for bridge crack detection data set | |
| CN112419185B (en) | Accurate high-reflectivity removing method based on light field iteration | |
| CN111127384A (en) | Strong reflection workpiece vision measurement method based on polarization imaging | |
| Ben-Zrihem et al. | Approximate nearest neighbor fields in video | |
| CN111968079A (en) | Three-dimensional pavement crack extraction method based on section local extreme value and segmentation sparsity | |
| CN117011292A (en) | Method for rapidly detecting surface quality of composite board | |
| CN115546098A (en) | Grinding wheel wear state identification method, computing device and storage medium | |
| CN110705553A (en) | Scratch detection method suitable for vehicle distant view image | |
| CN108230334B (en) | High-concentration wind-blown sand image segmentation method based on gray threshold | |
| CN111862080B (en) | Deep learning defect identification method based on multi-feature fusion | |
| CN111292346B (en) | Method for detecting contour of casting box body in noise environment | |
| CN111951234A (en) | Model detection method | |
| CN109741302B (en) | SD card form recognition system and method based on machine vision | |
| CN114565564B (en) | Fitting centroid sub-pixel positioning method based on correlation method threshold iteration | |
| CN114018946B (en) | OpenCV-based high-reflectivity bottle cap defect detection method | |
| CN114708284A (en) | Bundled bar end face information code image segmentation and enhancement method | |
| CN110232709B (en) | Method for extracting line structured light strip center by variable threshold segmentation |
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 |