LU502746B1 - System, method and terminal for surface defect detection of synchronizer gear sleeve based on machine vision - Google Patents
System, method and terminal for surface defect detection of synchronizer gear sleeve based on machine vision Download PDFInfo
- Publication number
- LU502746B1 LU502746B1 LU502746A LU502746A LU502746B1 LU 502746 B1 LU502746 B1 LU 502746B1 LU 502746 A LU502746 A LU 502746A LU 502746 A LU502746 A LU 502746A LU 502746 B1 LU502746 B1 LU 502746B1
- Authority
- LU
- Luxembourg
- Prior art keywords
- gear sleeve
- synchronizer gear
- detection
- camera
- station
- Prior art date
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/9515—Objects of complex shape, e.g. examined with use of a surface follower device
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30136—Metal
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Abstract
The invention belongs to the technical field of surface defect detection of automobile parts. When shooting different end faces at different stations, the light is uniformly projected to each surface of the synchronizer gear sleeve from different angles by the combination of various types of industrial light sources, so that the defects such as bump, lack of materials and scratch are highlighted. The CCD camera is used to collect images, and the collected images are transmitted to the industrial computer for storage. According to the surface information of synchronizer gear sleeve captured by different detection stations, the surface of synchronizer gear sleeve is divided into different areas. The corresponding algorithm is used in different areas to judge the defects in the detection area, and the general gauge of synchronizer gear sleeve is also detected. Summarize the test results of each station.
Description
DESCRIPTION LU502746
SYSTEM, METHOD AND TERMINAL FOR SURFACE DEFECT DETECTION OF
SYNCHRONIZER GEAR SLEEVE BASED ON MACHINE VISION
The invention belongs to the technical field of surface defect detection of automobile parts, and in particular relates to a system, method and terminal for surface defect detection of synchronizer gear sleeves based on machine vision.
As an important part of automobile, synchronizer gear sleeve is widely used in automobile gearbox and engine. Using machine vision to detect synchronizer gear sleeve has always been one of the hot issues in the scientific research field and enterprise class all over the world. The detection technology of synchronizer gear sleeve is an important guarantee to determine the product quality of synchronizer gear sleeve. With the continuous progress of product testing technology, advanced image acquisition technology, digital signal technology, image processing technology, digital communication technology, etc. are constantly applied to the testing of synchronizer gear ring, so the testing technology of synchronizer gear ring will make rapid development and progress.
Most of the traditional testing techniques of synchronizer gear sleeves are to manually place the collected synchronizer gear sleeve products on the testing platform, and then the quality related parameters of synchronizer gear sleeves are tested by the tester. Moreover, the testing instruments and devices of different synchronizer gear sleeve products are different due to the difference in shape and size. In addition, the synchronizer gear sleeve testing instrument or other contact testing instruments are complicated in use process, heavy in workload, short in service cycle, troublesome in maintenance and expensive, etc. For modern synchronizer gear sleeve manufacturing technology, this testing method can't meet the requirements of production efficiency and output.
Therefore, through the application of digital image processing and other related technologies, a new type of high-efficiency, online non-contact, pipelined, practical and widely applicable detection technology is explored for modern synchronizer gear sleeve detection.
It includes the following detection items: LU502746 i . Detection i
Detection type Unit Location accuracy 0.1x0.1 End face, inner wall 0.1x0.1 End face, inner wall 0.1x0.1 End face, inner wall
Starved feeding 0.1x0.1 End face, inner wall 0.1x0.1 End face, inner wall 0.1x0.1 End face, inner wall 0.1x0.1 End face, inner wall
With the continuous progress of production technology, the market demands higher and higher quality of automobile products, and the synchronizer gear sleeve judged by manual visual inspection can no longer meet the market demand.
With the development of computer vision technology, some defect detection methods based on computer vision have gradually appeared, but these methods are only theoretical research on some specific defects on the upper and lower end faces, and can't be applied to field actual detection.
In view of the above analysis, the problems existing in the prior art are: (1) The traditional testing technology of synchronizer gear sleeve is manual testing on the testing platform. For different types of products, due to the slight difference in appearance and numerous testing items, the testing process is auxiliary and the workload is heavy, so it is difficult to form a unified testing standard. (2) In view of the existing inspection methods, the data statistics and data analysis of defective products can't be realized, and it is necessary to use automatic vision inspection system to provide them with product defect types and inspection standards. (3) The synchronizer gear sleeve is made by sintering. In the existing production technology, there are many factors that cause defects, which makes the further improvement of the performance of the defect detection system meet the bottleneck.
The difficulty of solving the above technical problems lies in:
There are many kinds of surface defects of synchronizer gear sleeve, such as lack of materials, cracks, foreign bodies, bumps, bad characters, etc. The position exists anywhere on the surface of synchronizer gear sleeve, and the state and size of the defects are different. There are many areas of different quality on the same surface, and the detection standards of different areh&/502746 are different. There are various types of synchronizer gear sleeves, and different types have different characteristic information such as inner and outer diameters, characters, number of inner and outer teeth, so it is difficult to make a set of programs compatible with all types.
The significance of solving the above technical problems lies in:
Considering the traditional manual detection mode and the traditional visual detection mode, the detection method provided by the invention can detect defects of different types, shapes and positions, and improve the detection efficiency. Dividing the synchronizer gear sleeve effectively improves the compatibility of equipment, better adapts to complex conditions in actual production, and has better robustness, thus reducing labor intensity, maintenance cost and potential risks, reducing the manpower of enterprises, improving work efficiency, reducing misjudgement caused by errors of machinery itself and artificial fatigue, and enabling enterprises to have the right to independently test the quality of such parts. It is recognized by the purchaser that the production cost is greatly controlled, and the gear quality and delivery speed are improved.
In order to solve the problems existing in the prior art, the invention provides a method, a system and a terminal for surface defect detection of synchronizer gear sleeves based on machine vision.
The invention is realized as follows, a method for surface defect detection of synchronizer gear sleeve based on machine vision, the method for surface defect detection of synchronizer gear sleeve based on machine vision comprises the following steps:
S1, when shooting different end faces at different stations, using the combination of industrial light sources to illuminate, projecting the light evenly on the surface of synchronizer gear sleeve, highlighting the defects of bump, lack of material and scratch, wherein the synchronizer gear sleeve is stationary when the end face of the three stations is taken, and the synchronizer gear sleeve rotates during the rest of the image acquisition process; when shooting the end face, the camera lens module is erected perpendicular to the end face of synchronizer gear sleeve, when shooting the inner wall, the camera is fixed at a certain inclination angle; when shooting the outer wall, the camera shoots at a fixed angle in the horizontal direction; and the combined industrial light sources are all white; adjusting the brightness and position of thé/502746 industrial light source to make the imaging clear without occlusion and overexposure, then using the CCD camera to collect the synchronizer gear sleeve image, and transmitting the collected image to the industrial computer for storage;
S2, the information of different areas on the surface of synchronizer gear sleeve is collected at different stations, and the conversion of color space is realized by mutual conversion between
RGB and HIS; the HSI color space describes the color of the object in terms of chromaticity, saturation and brightness, and the conversion relationship between RGB and HSI color space is as follows:
Zl@-0;+<@-si ; 3
H=atgcon——————; lic ~ GY AR BG = BY $ > 1 — und R, GL, 8)] {(R+G +8) ‚and
RGB
3
According to the product color information, the following algorithm be used to filter the image, and its expression is as follows: x, — Deals)
UE LS
FFE {R883 , and feo =[ [ets 0] ie 2 ; a8 a
Where Sxy represents the set of coordinate points in the neighborhood of a rectangle with a midpoint at (x,y) and a size of mxn;
S3, judging the defect situation in the detection area by using corresponding algorithms in different areas;
S4, summarizing the detection results of each station, determining the surface quality of synchronizer gear sleeve, and flowing the detected parts out of the good material channel, the bad material channel and the waste material channel respectively.
In one embodiment, in the S1, according to the different surface positions of the parts, thé/502746 parts are photographed at three stations, two of which collect the information of the end face and the inner wall, and one station collects the information of the outer wall and the inner synchronizer gear sleeve profile.
In one embodiment, the CCD camera used for shooting the end face of synchronizer gear sleeve is an area array camera; during shooting, coaxially arranging the camera with the combined light source, and adjusting the position of the camera and the light source separately; when shooting the end face, the combined light source lights up at the same time, and the camera collects the end face images respectively, and collects the obtained images;
Among them, the combined light sources used include:
Bowl light, to supplement the area not covered by the annular light source;
Light, by using the straight line propagation of light, passes through an angular annular light source, so that the defects on the upper face of the synchronizer gear sleeve are obvious;
Backlight clearly reflects the contour information of synchronizer gear sleeve, which is convenient for the algorithm to extract the contour of synchronizer gear sleeve.
In one embodiment, CCD camera used for shooting the inner wall of synchronizer gear sleeve is an area array camera; when shooting the inner wall of synchronizer gear sleeve, the combined light source used is all bright, and the parts are driven to rotate by the jig plate; the camera continuously collects the images of the outer wall to complete the image collection of the whole inner wall area of synchronizer gear sleeve;
Among them, the combined light sources used include:
Light, to supplement the light source of the whole synchronizer gear sleeve;
Light, by using the linear propagation of light, passes through an angular annular light source, which makes the defects of the inner wall of the synchronizer gear sleeve obvious;
Backlight clearly reflects the contour information of synchronizer gear sleeve, which is convenient for the algorithm to extract the inner wall contour of synchronizer gear sleeve.
In one embodiment, when shooting the outer wall of the synchronizer gear sleeve, the combined light source is all on, the parts are driven to rotate by the jig plate, and the camera continuously collects the images of the outer wall to complete the image collection of the whole outer wall area of the synchronizer gear sleeve;
Among them, the combined light sources used include: LU502746
Side light, using the straight-line propagation of light, facilitates the outer wall defects to be more easily reflected;
Backlight clearly reflects the contour information of synchronizer gear sleeve, which is convenient for the algorithm to extract the contour of synchronizer gear sleeve.
In one embodiment, in S2, areas are divided according to the external contour information of synchronizer gear sleeve surface, the internal gear root feature and the gear top feature information of product surface at different stations, which provides different detection area standards for later algorithms.
In one embodiment, in S3, by set different grayscale detection parameters and defect screen conditions for surfaces with different processing quality, that edge detection algorithm is adopted to detect the defect in different calibration areas, and the part with sharp grayscale change of the image is extracted as the feature detection basis, and the positioning angle of the general gauge detection is found by using the characteristics of the spherical teeth of the synchronizer gear sleeve, so as to realize the general gauge detection.
In one embodiment, the specific method of that edge detection algorithm includes:
Filtering: eliminate the influence of noise on the derivative which is the basis of edge detection;
Edge enhancement, determining by gradient amplitude, highlights the points with significant changes in the intensity value of the image gray point neighborhood;
Edge detection: detecting by threshold and screening edge points to determine the edge curve.
Another object of the present invention is to provide a detection system for realizing the method for surface defect detection of synchronizer gear sleeve based on machine vision, the system for surface defect detection of synchronizer gear sleeve based on machine vision comprises:
A load material station, connected with the incoming conveyor belt, used for feeding the materials to the gripping position of the clamping jaw;
A feedstock station used for placing incoming materials on the feeding conveyor belt;
A workpiece conveying station, which is placed between the feed conveyor belt, the fe¢d)502746 conveyor belt and the camera detection station and consists of a plurality of pairs of reversible clamping jaws, used for turning and conveying incoming materials between the feed conveyor belt, the feed conveyor belt and the camera detection station;
A camera detection station, in which the synchronizer gear sleeve is sleeved to a specified position, and images are collected at the camera detection station;
A detection and elimination station, according to the judgment of the algorithm, transmits the product NG signal to the supply station to remove the synchronizer gear sleeve;
Feeding conveyor belt, when the synchronizer gear sleeve comes in, it is responsible for the synchronizer gear sleeve's entry detection system;
Blanking conveyor belt, which is responsible for the departure detection system of synchronizer gear sleeve, after the feeding conveyor belt and synchronizer gear sleeve are tested;
A photoelectric sensor, used for judging whether there are parts in each station in the current state;
The PLC controller is connected with the load material station, the feeding station, the workpiece conveying station, the camera detection station, the CCD camera, the photoelectric sensor and the industrial computer respectively, and is used for receiving signals sent by the photoelectric sensor, triggering the CCD camera of the camera detection station to collect images, sending and receiving transmission signals of the industrial computer and controlling the operation of the equipment;
And the industrial computer is connected with the CCD camera, the light source controller and the PLC respectively, and is used for storing the images collected by the CCD camera, processing the images, controlling the light source to turn on and off, and sending the image detection results to the PLC controller or transmitting information.
Another object of the present invention is to provide an information data processing terminal for surface defect detection of synchronizer gear sleeve, the information data processing terminal comprises a memory and a processor, wherein the memory stores a computer program, and the computer program, when executed by the processor, causes the processor to execute the method for surface defect detection of synchronizer gear sleeve based on machine vision.
Combining all the above technical schemes, the invention can realize image acquisition artd/502746 quality detection of synchronizer gear sleeve products through optical design. The advantages and positive effects of the invention are as follows:
Firstly, by adding an adjustable mechanism to the camera and light source, the system can meet the surface defect detection requirements of different types of synchronizer gear sleeves without affecting the production beat and detection accuracy. According to different types, different shapes and different positions of synchronizer gear sleeve surface defects, the detection effect is 100% suitable, which indicates that this method is suitable for synchronizer gear sleeve surface defect detection.
Secondly, the sub-regional algorithm is compatible with various types of synchronizer gear sleeves in production lines, and it also reserves testing space for new products in the future, which improves the flexibility of the system and reduces the equipment investment cost of enterprises, and has certain universality.
Thirdly, the traditional algorithm and deep learning algorithm are used to respectively detect the flat end face and the inner wall teeth with complex shape. At the same time, the algorithm can calculate the size of the detected defects, which is convenient for the on-site production line to set various types of defect detection standards according to the acceptance of downstream customers, greatly improving the detection efficiency and reducing the operating cost of enterprises.
It is to be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit the present disclosure.
The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the disclosure, and together with the specification, serve to explain the principles of the disclosure.
Fig. 1 is a flow chart of a method for surface defect detection of synchronizer gear sleeve based on machine vision in the embodiment of the present invention.
Fig. 2 shows the common defects of synchronizer gear sleeve in the invention provided in the embodiment of the present invention; in which, a is the collision diagram of synchronizer gear sleeve end face; b is the collision diagram of the gear top of synchronizer gear sleeve; c is the scratch diagram of end face of synchronizer gear sleeve; d is the scratch diagram of the outet}502746 wall of synchronizer gear sleeve;
Fig. 3 is a schematic diagram of the lighting environment of the inner wall end face in the invention provided in the embodiment of the present invention; where a is the schematic diagram of optical environment of synchronizer gear sleeve; b is a rendering a picture of the optical environment of the synchronizer gear sleeve.
Fig. 4 is an acquisition diagram of an end-face camera in the invention provided in the embodiment of the present invention.
Fig. 5 is an acquisition diagram of an inner wall camera in the invention provided in the embodiment of the present invention.
Fig. 6 is an acquisition diagram of an outer wall camera in the invention provided in the embodiment of the present invention.
Fig. 7 shows division of the end face calibration area in the invention provided in the embodiment of the present invention; in which, a is the product extraction diagram of the outer circle contour and the inner circle contour of the synchronizer gear sleeve product surface; b is the outline drawing of the outer circle and the inner circle of the synchronizer gear sleeve product surface.
Fig. 8 is an RGB-to-HIS diagram of the invention provided in the embodiment of the present invention; in which, a is RGB image of synchronizer gear sleeve; b HSI image of synchronizer gear sleeve.
Fig. 9 is an effect diagram after image filtering in the invention provided in the embodiment of the present invention.
Fig. 10 is a defect detection diagram related to the invention provided in the embodiment of the present invention; where a is the scratch detection diagram of synchronizer gear sleeve end face; b is the scratch detection chart of the outer wall of synchronizer gear sleeve;
In order to make the above objects, features and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention will be made with reference to the accompanying drawings. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, the invention can be implemented in maryJ502746 other ways different from those described here, and those skilled in the art can make similar improvements without violating the connotation of the invention, so the invention is not limited by the specific implementation disclosed below.
It should be noted that when an element is said to be "fixed" to another element, it may be directly on another element or there may be an intermediate element. When an element is considered to be "connected" to another element, it may be directly connected to another element or there may be intervening elements at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used in the present invention are only for the purpose of illustration, and do not represent the only embodiment.
Unless otherwise defined, all technical and scientific terms used in this invention have the same meanings as commonly understood by those skilled in the technical field of this invention.
In this invention, the terms used in the specification of this invention are only for the purpose of describing specific embodiments, and are not intended to limit the invention. The term "and/or" used in this invention includes any and all combinations of one or more related listed items.
The method and system for surface defect detection of synchronizer gear sleeve based on machine vision make full use of industrial light source and CCD camera, and adopt the machine vision detection method, so that the surface defects of synchronizer gear sleeve can be detected quickly and accurately, and the data can be processed in real time. The technical scheme of the invention is as follows:
As shown in Fig. 1, the method for surface defect detection of synchronizer gear sleeve based on machine vision comprises the following steps:
S101, when shooting different end faces at different stations, using the combination of industrial light sources to illuminate, projecting the light evenly on the surface of synchronizer gear sleeve, highlighting the defects of bump, lack of material and scratch, collecting images by
CCD camera, and transmitting the collected images to industrial computer for storage, where the main defects are shown in Fig. 2.
In S1, according to the different surface positions of the parts, the parts are photographed at three stations, two of which collect the information of the end face and the inner wall, and one station collects the information of the outer wall and the inner synchronizer gear sleeve profile;
the synchronizer gear sleeve is stationary when the end face of the three stations is taken, and thé&J502746 synchronizer gear sleeve rotates during the rest of the image acquisition process; when shooting the end face, the camera lens module is erected perpendicular to the end face of synchronizer gear sleeve, when shooting the inner wall, the camera is fixed at a certain inclination angle; when shooting the outer wall, the camera shoots at a fixed angle in the horizontal direction; and the combined industrial light sources are all white; adjusting the brightness and position of the industrial light source to make the imaging clear without occlusion and overexposure, then using the CCD camera to collect the synchronizer gear sleeve image, and transmitting the collected image to the industrial computer for storage.
The combined light source used for shooting the end face of synchronizer gear sleeve includes bowl light, ring light and backlight; the CCD camera used is an area array camera.
When shooting, the camera is coaxial with the combined light source, and the positions of the camera and the light source can be adjusted separately, as shown in Fig. 3. When shooting the end face, the combined light source lights up at the same time, and the camera collects the end face images respectively, and the collected images are shown in Fig. 4. The function of backlight is to clearly reflect the contour information of synchronizer gear sleeve, which is convenient for the algorithm to extract the contour of synchronizer gear sleeve. The function of the ring is to make use of the straight-line propagation of light, and through the angular ring light source, the defects on the upper face of the synchronizer gear sleeve are obvious; the bowl light is used to supplement the area not covered by the annular light source.
The combined light sources used to photograph the inner wall of synchronizer gear sleeve include surface light, ring light and backlight, and the CCD camera used is an area array camera.
When shooting the inner wall of synchronizer gear sleeve, the combined light source is all bright, the parts are driven to rotate by the jig plate, and the camera continuously collects the images of the outer wall. The collected images are shown in Fig. 5, which completes the image collection of the whole inner wall area of synchronizer gear sleeve.
The combined light sources used for shooting the outer wall of synchronizer gear sleeve include side light and backlight, all the combined light sources are bright, the parts are driven to rotate by the jig plate, and the camera continuously collects the images of the outer wall, and the collected images are shown in Figure 6, which completes the image collection of the entire outet/502746 wall area of synchronizer gear sleeve.
S102, the information of different areas on the surface of synchronizer gear sleeve is collected at different stations
In S2, aiming at the characteristic information of the synchronizer gear sleeve surface at different stations; the surface features are divided into regions to provide different detection region standards for later algorithms.
The features are mainly selected according to the surface information of the product. For synchronizer gear sleeve products, the features are mainly the external contour information of the product surface, the internal gear root feature and the gear top feature of the product surface.
The image of the calibration area is shown in Fig. 7.
S103, judging the defect situation in the detection area by using corresponding algorithms in different areas;
In S3, the defects are detected by setting different gray detection parameters and defect screening conditions for surfaces with different processing qualities. The algorithm detection steps mainly include:
Because most color CCD cameras are RGB color spaces, in order to make the features of the region of interest more obvious, it is necessary to realize the mutual conversion between
RGB color space and other color spaces. Taking the conversion between RGB and HSI as an example, the conversion process of color space will be described. HSI color space describes the color of an object in terms of chromaticity (H), saturation (S) and brightness (I). This color description is the most direct for human observation. And the conversion relationship between
RGB HSI color space is as follows: less
H = arccos4 —2 iR ~GY HR-BNG=- BP
S=| —— 3 rink, a, 8) (R+G +B) ‚and 3
They have different conversion forms of multi-photos, and different conversion forms ak&J502746 used for different application scenarios. As long as the converted hue is an angle, the saturation and brightness are independent of each other. The processing results are shown in Fig. 8.
All the images collected by the camera will be polluted by noise. The amount of image noise is caused by the crosstalk and fluctuation of light in the photosensitive components, or the instability of the sensory components and the long exposure time, which leads to the loss of control of pixels. The noise is uncontrollable and random, and there is no way to predict and eliminate it. We can only reduce the noise in the later stage to avoid the influence of noise on the later image processing. According to the product color information, the following algorithm will be adopted to filter the image, and its expression is as follows: 1 ‘ flop) =— > 26,1)
HI (es, and
A ! fir =[ [eto (where S«y represents the set of coordinate points in the rectangular neighborhood with the midpoint at (x,y) and the size of m*n). The processing results are shown in Fig. 9.
The interesting feature of the invention is the calibration area. Aiming at the detection of defects in different calibration areas, the method adopts edge detection, which aims to extract the part of the image with drastic gray change as the basis of feature detection. Edge detection algorithms are generally divided into three parts: Processing (Gaussian filtering is the most commonly used one, which is used to eliminate the influence of noise on the derivative as the basis of edge detection), edge enhancement (which can be determined by gradient amplitude, highlighting the points with significant changes in the intensity value of the neighborhood of image gray points) and edge point detection (threshold detection is adopted, and edge points are selected to determine the edge curve). The processing results are shown in Fig. 10.
The positioning angle of general gauge detection is found by using the characteristics of spherical teeth of synchronizer gear sleeve, and the general gauge detection is realized.
S104, summarizing the detection results of each station, determining the surface quality of synchronizer gear sleeve, and flowing the detected parts out of the good material channel, the bad material channel and the waste material channel respectively.
In S4, the defects are detected by setting different gray scale detection parameters and)502746 defect screening conditions for surfaces with different processing qualities.
In one embodiment, the system for surface defect detection of synchronizer gear sleeve comprises: a load material station, a feedstock station, a workpiece conveying station, a camera detection station, a detection and elimination station, a feeding conveyor belt, a blanking conveyor belt, a photoelectric sensor, a PLC controller and an industrial computer;
The load material station is connected with the incoming conveyor belt and is used for feeding the materials to the gripping position of the clamping jaw;
The feedstock station is used for placing incoming materials on the feeding conveyor belt;
The workpiece conveying station is placed between the feed conveyor belt, the feed conveyor belt and the camera detection station and consists of a plurality of pairs of reversible clamping jaws, is used for turning and conveying incoming materials between the feed conveyor belt, the feed conveyor belt and the camera detection station;
In the camera detection station, the synchronizer gear sleeve is sleeved to a specified position, and images are collected at the camera detection station;
The detection and elimination station, according to the judgment of the algorithm, transmits the product NG signal to the supply station to remove the synchronizer gear sleeve;
The feeding conveyor belt is responsible for the synchronizer gear sleeve's entry detection system, when the synchronizer gear sleeve comes in;
The blanking conveyor belt is responsible for the departure detection system of synchronizer gear sleeve, after the feeding conveyor belt and synchronizer gear sleeve are tested;
The photoelectric sensor is used for judging whether there are parts in each station in the current state;
The PLC controller is connected with the load material station, the feeding station, the workpiece conveying station, the camera detection station, the CCD camera, the photoelectric sensor and the industrial computer respectively, and is used for receiving signals sent by the photoelectric sensor, triggering the CCD camera of the camera detection station to collect images, sending and receiving transmission signals of the industrial computer and controlling the operation of the equipment;
And the industrial computer is connected with the CCD camera, the light source controllet)502746 and the PLC respectively, and is used for storing the images collected by the CCD camera, processing the images, controlling the light source to turn on and off, and sending the image detection results to the PLC controller or transmitting information.
In one embodiment, the feeding station, connected with the incoming conveyor belt, is used for feeding the materials to the gripping position of the clamping jaw;
The feeding station is used for placing incoming materials on the feeding conveyor belt;
The workpiece conveying station is arranged between the feed conveyor belt, the feed conveyor belt and the camera detection station, and consists of a plurality of pairs of reversible jaws, and is used for turning and conveying incoming materials among the feed conveyor belt, the feed conveyor belt and the camera detection station;
The photoelectric sensor is used for judging whether there are parts in each station in the current state.
Those skilled in the art will easily think of other embodiments of the present disclosure after considering the specification and practicing the disclosure disclosed herein. This application is intended to cover any variations, uses or adaptations of this disclosure, which follow the general principles of this disclosure and include common knowledge or common technical means in this technical field that are not disclosed in this disclosure. And the specification and examples are to be regarded as examples only, and the true scope and spirit of the present disclosure are indicated by the appended claims.
It should be understood that the present disclosure is not limited to the precise structure described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure should be limited by the appended claims.
Claims (10)
1. A method for surface defect detection of synchronizer gear sleeve based on machine vision, characterized in that the method for surface defect detection of synchronizer gear sleeve based on machine vision comprises the following steps: S1, when shooting different end faces at different stations, using the combination of industrial light sources to illuminate, projecting the light evenly on the surface of synchronizer gear sleeve, highlighting the defects of bump, lack of material and scratch, wherein the synchronizer gear sleeve is stationary when the end face of the three stations is taken, and the synchronizer gear sleeve rotates during the rest of the image acquisition process; when shooting the end face, the camera lens module is erected perpendicular to the end face of synchronizer gear sleeve, when shooting the inner wall, the camera is fixed at a certain inclination angle; when shooting the outer wall, the camera shoots at a fixed angle in the horizontal direction; and the combined industrial light sources are all white; adjusting the brightness and position of the industrial light source to make the imaging clear without occlusion and overexposure, then using the CCD camera to collect the synchronizer gear sleeve image, and transmitting the collected image to the industrial computer for storage; S2, the information of different areas on the surface of synchronizer gear sleeve is collected at different stations, and the conversion of color space is realized by mutual conversion between RGB and HIS; the HSI color space describes the color of the object in terms of chromaticity, saturation and brightness, and the conversion relationship between RGB and HSI color space is as follows: learn FI = arccos- A Ti RG) +(R~BXG~ BY Si — mi HR, Er 8)} (R+G +B) „and Pe EC E = > according to the product color information, the following algorithm be used to filter the image:
Fx, y= À s es.) LU502746 HUE (ies, and a À. fee) =[ [gts (5058S where Sxy represents the set of coordinate points in the neighborhood of a rectangle with a midpoint at (x,y) and a size of mxn; S3, judging the defect situation in the detection area by using corresponding algorithms in different areas; S4, summarizing the detection results of each station, determining the surface quality of synchronizer gear sleeve, and flowing the detected parts out of the good material channel, the bad material channel and the waste material channel respectively.
2. The method for surface defect detection of synchronizer gear sleeve based on machine vision according to claim 1, characterized in that in the S1, according to the different surface positions of the parts, the parts are photographed at three stations, two of which collect the information of the end face and the inner wall, and one station collects the information of the outer wall and the inner synchronizer gear sleeve profile.
3. The method for surface defect detection of synchronizer gear sleeve based on machine vision according to claim 2, characterized in that the CCD camera used for shooting the end face of synchronizer gear sleeve is an area array camera; during shooting, coaxially arranging the camera with the combined light source, and adjusting the position of the camera and the light source separately; when shooting the end face, the combined light source lights up at the same time, and the camera collects the end face images respectively, one of which is the background outline of the end face and the other is the front face of the end face, wherein the combined light sources used include: bowl light, to supplement the area not covered by the annular light source; annular light, by using the straight line propagation of light, passing through an angular annular light source, so that the defects on the upper face of the synchronizer gear sleeve are obvious; backlight, used for clearly reflecting the contour information of synchronizer gear sleeve, which is convenient for the algorithm to extract the contour of synchronizer gear sleeve.
4. The method for surface defect detection of synchronizer gear sleeve based on machihé/502746 vision according to claim 2, characterized in that CCD camera used for shooting the inner wall of synchronizer gear sleeve is an area array camera; when shooting the inner wall of synchronizer gear sleeve, the combined light source used is all bright, and the parts are driven to rotate by the jig plate; the camera continuously collects the images of the outer wall to complete the image collection of the whole inner wall area of synchronizer gear sleeve, wherein the combined light sources used include: ceiling light, to supplement the light source of the whole synchronizer gear sleeve; annular light, by using the straight line propagation of light, passing through an angular annular light source, so that the defects on the inner wall of the synchronizer gear sleeve are obvious; backlight, used for clearly reflecting the contour information of synchronizer gear sleeve, which is convenient for the algorithm to extract the inner wall contour of synchronizer gear sleeve.
5. The method for surface defect detection of synchronizer gear sleeve based on machine vision according to claim 2, characterized in that when shooting the outer wall of the synchronizer gear sleeve, the combined light source is all on, the parts are driven to rotate by the jig plate, and the camera continuously collects the images of the outer wall to complete the image collection of the whole outer wall area of the synchronizer gear sleeve, wherein the combined light sources used include: side light, by the straight-line propagation of light, which is convenient to reflect the defect of the outer wall; backlight, used for clearly reflecting the contour information of synchronizer gear sleeve, which is convenient for the algorithm to extract the inner wall contour of synchronizer gear sleeve.
6. The method for surface defect detection of synchronizer gear sleeve based on machine vision according to claim 1, characterized in that in S2, areas are divided according to the external contour information of synchronizer gear sleeve surface, the internal gear root feature and the gear top feature information of product surface at different stations, which provides different detection area standards for later algorithms.
7. The method for surface defect detection of synchronizer gear sleeve based on machihé)502746 vision according to claim 1, characterized in that in S3, by set different gray scale detection parameters and defect screen conditions for surfaces with different processing quality, that edge detection algorithm is adopted to detect the defect in different calibration areas, and the part with sharp gray scale change of the image is extracted as the feature detection basis, and the positioning angle of the general gauge detection is found by the characteristics of the spherical teeth of the synchronizer gear sleeve, so as to realize the general gauge detection.
8. The method for surface defect detection of synchronizer gear sleeve based on machine vision according to claim 7, characterized in that the method of the edge detection algorithm include: filtering: eliminating the influence of noise on the derivative which is the basis of edge detection; edge enhancement: determining by gradient amplitude, highlighting the points with significant changes in the intensity value of the image gray scale point neighborhood, edge detection: detecting by threshold and screening edge points to determine the edge curve.
9. A detection system for realizing the method for surface defect detection of synchronizer gear sleeve based on machine vision according to any one of claims 1-8, characterized in that the system for surface defect detection of synchronizer gear sleeve based on machine vision comprises: a load material station, connected with the incoming conveyor belt, used for feeding the materials to the gripping position of the clamping jaw; a feedstock station, used for placing incoming materials on the feeding conveyor belt; a workpiece conveying station, which is placed between the incoming conveyor belt, the feed conveyor belt and the camera detection station, consists of a plurality of pairs of reversible clamping jaws, is used for turning and conveying incoming materials between the feed conveyor belt, the feed conveyor belt and the camera detection station; a camera detection station, in which the synchronizer gear is sleeved to a specified position, and images are collected at the camera detection station;
a detection and elimination station, according to the judgment of the algorithm, transmittidg)502746 the product NG signal to the supply station to remove the synchronizer gear sleeve; a feeding conveyor belt, when the synchronizer gear sleeve comes in, it is responsible for synchronizer gear sleeve entering detection system; a blanking conveyor belt, which is responsible for the synchronizer sleeve leaving the detection system, after testing the synchronizer gear sleeve; a photoelectric sensor, for judging whether there are parts in each station in the current state; a PLC controller, which is connected with the load material station, the feedstock station, the workpiece conveying station, the camera detection station, the CCD camera, the photoelectric sensor and the industrial computer respectively, and is used for receiving signals sent by the photoelectric sensor, triggering the CCD camera of the camera detection station to collect images, sending and receiving transmission signals of the industrial computer and controlling the operation of the equipment; and an industrial computer, which is connected with the CCD camera, the light source controller and the PLC respectively, and is used for storing the images collected by the CCD camera, processing the images, controlling the light source to turn on and off, and sending the image detection results to the PLC controller or transmitting information.
10. An information data processing terminal for surface defect detection of synchronizer gear sleeve, characterized in that the information data processing terminal comprises a memory and a processor, wherein the memory stores a computer program; when the computer program is executed by the processor, it causes the processor to execute the method for surface defect detection of synchronizer gear sleeve based on machine vision according to any one of claims
1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| LU502746A LU502746B1 (en) | 2022-09-05 | 2022-09-05 | System, method and terminal for surface defect detection of synchronizer gear sleeve based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| LU502746A LU502746B1 (en) | 2022-09-05 | 2022-09-05 | System, method and terminal for surface defect detection of synchronizer gear sleeve based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| LU502746B1 true LU502746B1 (en) | 2023-03-06 |
Family
ID=85415035
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| LU502746A LU502746B1 (en) | 2022-09-05 | 2022-09-05 | System, method and terminal for surface defect detection of synchronizer gear sleeve based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| LU (1) | LU502746B1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117710369A (en) * | 2024-02-05 | 2024-03-15 | 山东省科院易达信息科技有限公司 | Metal aluminum phosphate film defect detection method and system based on computer vision technology |
| CN117710369B (en) * | 2024-02-05 | 2024-04-30 | 山东省科院易达信息科技有限公司 | Metal aluminum phosphate film defect detection method and system based on computer vision technology |
-
2022
- 2022-09-05 LU LU502746A patent/LU502746B1/en active IP Right Grant
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117710369A (en) * | 2024-02-05 | 2024-03-15 | 山东省科院易达信息科技有限公司 | Metal aluminum phosphate film defect detection method and system based on computer vision technology |
| CN117710369B (en) * | 2024-02-05 | 2024-04-30 | 山东省科院易达信息科技有限公司 | Metal aluminum phosphate film defect detection method and system based on computer vision technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113000413B (en) | System, method and terminal for detecting surface defects of synchronizer gear sleeve based on machine vision | |
| CN108765416B (en) | PCB surface defect detection method and device based on rapid geometric alignment | |
| CN102621156B (en) | Image-processing-based automatic micro part sorting system | |
| CN103676236B (en) | A kind of repair the method for defect pixel, system and display floater | |
| CN103743761B (en) | A kind of eyeglass watermark defect image detection device | |
| CN107664644B (en) | Object appearance automatic detection device and method based on machine vision | |
| US20100225666A1 (en) | Digital optical comparator | |
| CN102413354A (en) | Automatic optical detection method, device and system of mobile phone camera module | |
| CN105511123A (en) | High-precision automatic optical inspection system and method based on mechanical arm | |
| CN110261390A (en) | A kind of the surface defect Systems for optical inspection and method of diffusing reflection structure light | |
| CN102374996B (en) | Multicast detection device and method for full-depth tooth side face defects of bevel gear | |
| CN109916910B (en) | Photovoltaic glass edge defect detection system and corresponding method | |
| CN105911067A (en) | Cable protective jacket surface defect detector and detection method thereof | |
| CN206981462U (en) | Stamping parts surface defect detection apparatus based on 3D vision | |
| CN112858332A (en) | Synchronizer gear hub surface defect detection method, system and terminal based on machine vision | |
| CN110333241A (en) | A kind of vision detection system and detection method of firework product | |
| CN110567968A (en) | part defect detection method and device | |
| CN110044921A (en) | Lithium battery open defect detection system and method | |
| CN106841226B (en) | Cable orientation detection and correction system | |
| LU502746B1 (en) | System, method and terminal for surface defect detection of synchronizer gear sleeve based on machine vision | |
| CN101995325A (en) | Appearance detection method and system of image sensor | |
| CN113205499A (en) | Bearing defect modular detection device and method based on machine vision | |
| CN103091332B (en) | Detection method and detection system of U-shaped powder pipe based on machine vision | |
| CN111458345A (en) | Visual detection mechanism for defects of mask | |
| CN213516933U (en) | Piston defect detection device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FG | Patent granted |
Effective date: 20230306 |