CN118032802A - New energy automobile battery surface foreign matter detection mechanism based on 2D, 3D vision - Google Patents
New energy automobile battery surface foreign matter detection mechanism based on 2D, 3D vision Download PDFInfo
- Publication number
- CN118032802A CN118032802A CN202311825722.6A CN202311825722A CN118032802A CN 118032802 A CN118032802 A CN 118032802A CN 202311825722 A CN202311825722 A CN 202311825722A CN 118032802 A CN118032802 A CN 118032802A
- Authority
- CN
- China
- Prior art keywords
- camera
- frame
- detection
- image
- foreign matter
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 99
- 238000012545 processing Methods 0.000 claims abstract description 19
- 230000000007 visual effect Effects 0.000 claims abstract description 19
- 238000012546 transfer Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 9
- 239000011248 coating agent Substances 0.000 claims description 8
- 238000000576 coating method Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 4
- 239000000463 material Substances 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000012106 screening analysis Methods 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 2
- 238000010191 image analysis Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000000295 complement effect Effects 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012797 qualification Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000011179 visual inspection Methods 0.000 description 2
- 208000032544 Cicatrix Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 231100000241 scar Toxicity 0.000 description 1
- 230000037387 scars Effects 0.000 description 1
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a new energy automobile battery surface foreign matter detection mechanism based on 2D and 3D vision, which relates to the technical field of automobile processing and comprises the following components: the upper side of the support frame is provided with a detection frame, and a detection area is arranged in the support frame; a transfer rack passing through the lower side of the detection rack for moving the product into an inner detection area; the detection frame comprises: the driving assembly and the sliding rail frame are arranged in parallel and are connected with the supporting frame; the assembly frame slides with the sliding rail frame and is connected with the output end of the driving assembly; and the visual detection units are arranged on the lower side of the assembly frame. According to the invention, the detection accuracy is greatly improved in a mode of combining 3D detection with 2D detection, and the battery cover plate is subjected to 3D+2D visual scanning through the machine vision system, so that whether foreign matters appear or not is judged through image analysis, and the positions of the foreign matters and alarm prompts are displayed.
Description
Technical Field
The invention relates to the technical field of automobile processing, in particular to a new energy automobile battery surface foreign matter detection mechanism based on 2D and 3D vision.
Background
The new energy automobile battery is a power battery in an electric automobile, and has the functions of providing power for the automobile, including a driving motor, a controller, illumination and the like, and the safety of the new energy automobile battery is an important consideration, and a series of safety measures are required to be taken in order to ensure the safe use of the battery, so that the integrity of the battery needs to be detected in the battery production process, and the detection of foreign matters on the surface of the battery is one of conventional projects, including scars, objects and the like.
Through retrieval, chinese patent (publication No. CN 114371179A) discloses a system, a method and a device for detecting and removing foreign matters on the surface of a fine blanking die on line, and an image data acquisition module of the patent acquires image data of the surfaces of an upper die and a lower die by using an industrial camera; the image acquisition control module controls the start and stop of the data acquisition module; the image data processing module is used for preprocessing, dividing and extracting texture features of the acquired surface image of the die; meanwhile, the device is used for controlling the starting and stopping of the foreign matter removal module; the foreign matter removal control module performs foreign matter removal.
In the prior art, when detecting the automobile battery, if a single vision module is adopted, the factors affected are more, the accuracy of detection data is lower, the efficiency is lower, and the production efficiency and the product quality can be affected when the automobile battery is produced.
Disclosure of Invention
The invention aims to provide a new energy automobile battery surface foreign matter detection mechanism based on 2D and 3D vision, so as to solve the technical problems in the background art.
The technical problems to be solved by the invention can be realized by the following technical scheme:
The utility model provides a new energy automobile battery surface foreign matter detection mechanism based on 2D, 3D vision, includes rail and conveying frame, one side of rail is provided with the access door, and power distribution cabinet and alarm lamp are installed to one side that the rail side is located the access door
A supporting frame is arranged in the fence, a detection frame is arranged on the upper side of the supporting frame, and the conveying frame passes through the lower side of the detection frame;
The detection frame comprises a driving assembly and a sliding rail frame, wherein the driving assembly and the sliding rail frame are connected with the supporting frame, the outer side of the sliding rail frame is connected with an assembling frame in a sliding manner, the assembling frame is connected with the output end of the driving assembly, and at least one group of visual detection units are arranged on the lower side of the assembling frame;
The visual detection unit comprises a shell, a line scanning camera and a 3D camera are installed in the shell, and a multi-angle switching light source is installed on one side of the line scanning camera and one side of the 3D camera in the shell;
the line scanning camera is matched with the multi-angle switching light source to assist the denoising optimization of the 3D camera, so that the stability of the system is enhanced;
the direction of the light emitted by the multi-angle switching light source and the direction identified by the 3D camera and the line scanning camera are provided with included angles.
As a further scheme of the invention: the scanning width of the line scanning camera and the 3D camera is 700-800mm;
The scanning time of the line scanning camera and the 3D camera is 4.5-6.5s each time, the image processing time is 4.5-5.5s, and the rechecking time is 4-6s.
As a further scheme of the invention: the working method of the detection frame comprises the following steps:
Step one: setting a region of interest, acquiring a 2D image by a line scanning camera, acquiring a 3D image by a 3D camera, and dividing the 2D image into a plurality of subareas according to the structure and the material of a battery plate;
step two: image preprocessing, namely performing primary filtering and contrast enhancement processing on a 2D image, eliminating irrelevant information in the image, recovering useful real information, enhancing the detectability of oil pipe information and simplifying data to the maximum extent, and obtaining a 2D threshold image, thereby improving the reliability of feature extraction, image separation, matching and identification;
Step three: performing secondary filtering on the 2D image, and extracting a preliminary target feature contour on the basis of the 2D threshold image after smoothing and Gao Silv;
step four: performing secondary filtering on the 2D threshold image, performing local secondary analysis on each target feature, reducing misjudgment caused by the uneven characteristics of the coating according to the texture characteristics of the coating, and extracting the target region;
step five: final screening, namely carrying out Z-dimension height measurement in combination with the corresponding 3D image, and carrying out screening analysis again on the target area in the fourth step to judge the foreign matters;
Step six: performing secondary transverse scanning on the area subjected to the foreign matter judgment in the step five, and further judging the height of the foreign matter in the 3D image;
and (5) performing alarm processing on the area which is still judged to be the foreign matter by the secondary scanning.
As a further scheme of the invention: a trigger sensor is arranged in the support frame and is arranged in a detection area preset in the support frame;
After the product moves to the trigger area of the trigger sensor based on the conveying frame, the detection frame starts to detect the product.
As a further scheme of the invention: the 3D camera adopts structured light and shoots products in a scanning mode, and the method comprises the following working steps:
A1: the 3D camera emits a structural light cover to be arranged on the surface of a product by laser with specific wavelength, and light reflected by the filter receiver is used for ensuring that only light with specific wavelength can enter the 3D camera to obtain a facula image;
A2: a chip in the 3D camera calculates the received facula image to obtain depth data of an object;
A3: a line scanning camera and a 3D camera work in parallel to acquire a product image with a specific height, and the product image is used as complement of a shooting result of the 3D camera;
a4: after the online scanning camera and the 3D camera acquire images, the images are imported into software for processing.
As a further scheme of the invention: the processing method of the image acquired by the 3D camera comprises the following steps:
B1: preprocessing, namely selecting a filter to inhibit noise in a product and a background, and simultaneously keeping the shape, the size and specific geometric and topological structure characteristics of a product target undamaged so as to acquire an excellent image, thereby facilitating subsequent processing;
b2: taking the camera position of the first frame of the 3D camera as the origin of a world coordinate system, adopting a KinectFusion iteration closest point method to obtain a position transfer matrix of each frame of the camera relative to the first frame after the camera, establishing a model from big data, calculating the position of the midpoint of each real scene, judging whether foreign matters exceeding Hmm are higher than a reference plane, and judging that H is a positive number larger than 0;
as a further scheme of the invention: the multi-angle switching light source is provided with a plurality of light sources, and the plurality of light sources are sequentially subjected to stroboscopic switching imaging when working;
When the multi-angle switching light source online scanning camera and the 3D camera work, alternately irradiating cross line light;
At least two light source angles are simultaneously covered when the line scan camera and the 3D camera are imaging.
As a further scheme of the invention: the working method of the new energy automobile battery surface foreign matter detection mechanism based on 2D and 3D vision comprises the following steps:
s1: the product moves to a detection area inside the supporting frame based on the conveying frame;
s2: the driving assembly in the detection frame drives each visual detection unit to scan from the head end of the product to the tail end of the battery, and the line scanning camera and the 3D camera in the visual detection units take pictures and analyze results;
S3: resetting the detection frame after the scanning is finished;
S4: and analyzing and uploading the detection results of the line scanning camera and the 3D camera to the common control computer according to the respective photographing results, and comprehensively analyzing the detection results of the line scanning camera and the 3D camera by the common control computer and making detection judgment.
As a further scheme of the invention: the common control machine in the S4 comprises the following detection judgment:
a1: through detection, the product moves to the next station through the conveying frame;
a2: and if the detection does not pass, giving an alarm through an alarm lamp, and finally manually intervening, manually detecting the detection, and marking the product after the result of the manual detection is the same as the judgment result of the common control machine.
The invention has the beneficial effects that:
According to the invention, the detection accuracy is greatly improved in a mode of combining 3D detection with 2D detection, and the battery cover plate is subjected to 3D+2D visual scanning through a machine vision system, so that whether foreign matters appear or not is judged through image analysis, and the positions of the foreign matters and alarm prompts are displayed;
When the machine vision system is adopted, the multi-angle switching light source is used for combining multiple light sources in the same shooting range aiming at different materials and foreign body types, stroboscopic switching imaging is sequentially carried out, images with respective combined light source effects are obtained through image extraction processing, the outline of the foreign body is extracted under different images, cameras and light source stations are saved, and more combined light path designs can be provided.
Drawings
Fig. 1 is a schematic structural diagram of a new energy automobile battery surface foreign matter detection mechanism based on 2D and 3D vision;
FIG. 2 is a schematic diagram of an assembly structure of a support frame and a detection frame in the present invention;
FIG. 3 is a schematic diagram of the working path of the visual inspection unit of the present invention;
FIG. 4 is a schematic diagram of the structure of the visual inspection unit of the present invention;
FIG. 5 is a test image I in a particular case;
FIG. 6 is a test image II in a specific case;
FIG. 7 is a test image III in a particular case;
Wherein: 1. a support frame; 2. a detection frame; 3. a conveying frame; 4. a fence; 5. a power distribution cabinet; 6. an alarm lamp; 7. an access door; 21. a drive assembly; 22. a slide rail frame; 23. assembling a frame; 24. a visual detection unit; 241. a housing; 242. a line scanning camera; 243. a 3D camera; 244. the light source is switched at multiple angles.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1-4, the new energy automobile battery surface foreign matter detection mechanism based on 2D and 3D vision comprises a fence 4 and a conveying frame 3, wherein the conveying frame 3 is suitable for 9-module and 12-module stations;
An access door 7 is arranged on one side of the fence 4, and a power distribution cabinet 5 and an alarm lamp 6 are arranged on one side of the fence 4, which is located on the access door 7;
A supporting frame 1 is arranged in the fence 4, a detection frame 2 is arranged on the upper side of the supporting frame 1, and a conveying frame 3 passes through the lower side of the detection frame 2;
The inside of the support frame 1 is provided with a trigger sensor which is arranged in a preset detection area in the support frame 1;
After the product moves to a trigger area of the trigger sensor based on the conveying frame 3, the detection frame 2 starts to detect the product;
The detection frame 2 comprises a driving component 21 and a sliding rail frame 22 which are connected with the support frame 1, wherein the outer side of the sliding rail frame 22 is connected with an assembly frame 23 in a sliding way, the assembly frame 23 is connected with the output end of the driving component 21, a plurality of groups of visual detection units 24 are arranged on the lower side of the assembly frame 23, and each group of visual detection units 24 represents a group of scanning paths;
The vision detecting unit 24 includes a housing 241, a line scanning camera 242 and a 3D camera 243 are mounted inside the housing 241, and a multi-angle switching light source 244 is mounted inside the housing 241 at one side of the line scanning camera 242 and the 3D camera 243;
The line scanning camera 242 is matched with the multi-angle switching light source 244 to assist the denoising optimization of the 3D camera 243, so that the stability of the system is enhanced;
the direction in which the multi-angle switching light source 244 emits light is set at an angle to the direction recognized by the 3D camera 243 and the line scanning camera 242;
The multiple angle switching light source 244 is provided with multiple light sources, the multiple light sources are sequentially subjected to stroboscopic switching imaging during working, and in the same position, the stroboscopic switching of three angles is completed through the cooperation among the AOI controller, the light sources, the line scanning camera 242 and the 3D camera 243, and the luminance is instantaneously improved by 30 times in a short time through the AOI controller, so that the problem that the light sources with different angles are needed in a single lighting mode aiming at the surface of a complex structure cannot be solved, and a plurality of detection stations are correspondingly added in multiple lighting modes in the traditional vision scheme, so that the cost is high and the time consumption is long;
when the multi-angle switching light source 244 works on the line scanning camera 242 and the 3D camera 243, cross line light alternately irradiates;
when line scan camera 242 and 3D camera 243 image, both light source angles are covered.
The scan width of both the line scan camera 242 and the 3D camera 243 is 760mm;
the scanning time of each time of the line scanning camera 242 and the 3D camera 243 is 6s, the image processing time is 5s, the rechecking time is 6s, and the detection beat of the whole product is 35s;
the working method of the detection frame 2 comprises the following steps:
Step one: setting a region of interest, acquiring a 2D image by a line scanning camera 242, acquiring a 3D image by a 3D camera 243, and dividing the 2D image into a plurality of subareas according to the structure and the material of a battery plate, wherein the subareas comprise black grooves between coating areas, a single rectangular coating area and a partition area without a coating in the middle;
the process of acquiring a 3D image by the 3D camera 243 includes:
z1, acquiring a Z-map picture in a 16-bit PNG format by using a 3D sensor;
z2 and Z-map are linear pictures after calibration, and the gray value of each pixel represents the distance from the actual measured point to the sensing end face;
z3, obtaining a complete image of each column of scanning by using an image stitching algorithm based on a grating ruler;
Z4, extracting each characteristic point for analysis, so as to calculate measurement information such as height, section difference, flatness and the like;
step two: image preprocessing, namely performing primary filtering and contrast enhancement processing on a 2D image, eliminating irrelevant information in the image, recovering useful real information, enhancing the detectability of oil pipe information and simplifying data to the maximum extent, and obtaining a 2D threshold image, thereby improving the reliability of feature extraction, image separation, matching and identification;
Step three: performing secondary filtering on the 2D image, and extracting a preliminary target feature contour on the basis of the 2D threshold image after smoothing and Gao Silv;
step four: performing secondary filtering on the 2D threshold image, performing local secondary analysis on each target feature, reducing misjudgment caused by the uneven characteristics of the coating according to the texture characteristics of the coating, and extracting the target region;
step five: final screening, namely carrying out Z-dimension height measurement in combination with the corresponding 3D image, and carrying out screening analysis again on the target area in the fourth step to judge the foreign matters;
Step six: performing secondary transverse scanning on the area subjected to the foreign matter judgment in the step five, and further judging the height of the foreign matter in the 3D image;
and (5) performing alarm processing on the area which is still judged to be the foreign matter by the secondary scanning.
The 3D camera 243 adopts structured light and photographs the product by scanning, comprising the following working steps:
a1: the 3D camera 243 emits light rays with a specific wavelength from a Laser with a structure light cover arranged on the surface of the product and reflected by the filter receiver so as to ensure that only the light rays with the specific wavelength can enter the 3D camera 243 to obtain a facula image;
A2: the chip inside the 3D camera 243 calculates the received light spot image to obtain the depth data of the object;
A3: a line scanning camera 242 works in parallel with the 3D camera 243 to acquire a product image with a specific height as complement of the shooting result of the 3D camera 243;
a4: after the online scanning camera 242 and the 3D camera 243 acquire images, they are imported into software for processing.
A method for processing an image acquired by the 3D camera 243, comprising the steps of:
B1: preprocessing, namely selecting a filter to inhibit noise in a product and a background, and simultaneously keeping the shape, the size and specific geometric and topological structure characteristics of a product target undamaged so as to acquire an excellent image, thereby facilitating subsequent processing;
B2: taking the camera position of the first frame of the 3D camera 243 as the origin of the world coordinate system, adopting KinectFusion iteration closest point method to obtain the position transfer matrix of each frame relative to the first frame of the camera after that, establishing a model from big data, calculating the position of the midpoint of each real scene, and judging whether foreign matters exceeding 5mm above the reference plane exist.
The working principle of the invention is as follows:
the product moves to a detection area inside the supporting frame 1 based on the conveying frame 3;
The driving assembly 21 in the detection frame 2 drives each visual detection unit 24 to move along the sliding rail frame 22, the visual detection units scan from the head end of a product to the tail end of a battery, and the line scanning camera 242 and the 3D camera 243 in the visual detection units 24 take pictures and analyze results;
after the scanning is finished, the driving component 21 in the detection frame 2 drives each visual detection unit 24 to reset through the assembly frame 23;
The line scanning camera 242 and the 3D camera 243 analyze and upload to the co-controller according to the respective photographing results, and the co-controller comprehensively analyzes the detection results of the line scanning camera 242 and the 3D camera 243 and makes detection judgment.
The detection passes, marked ok, the product moves to the next station through the conveyor 3;
And if the detection does not pass, giving an alarm through an alarm lamp 6, finally performing manual intervention, performing manual detection on the detection, and marking the product after the result of the manual detection is the same as the judgment result of the common control machine.
Specific cases
A certain automobile processing factory adopts the foreign matter detection mechanism to detect the surface of the battery of the new energy automobile, and before the new energy automobile is used, a plurality of groups of sample images are tested, and the test images are shown in fig. 5 to 7;
and in subsequent daily use, its statistics are shown in chart 1:
Table 1: data statistics table
The statistical time period is 2021.07.27 to 2021.10.19, the total number of vehicles 10761 is counted, the qualification rate reaches more than 98%, and the leak detection rate of the shielding area is close to 0%. Regarding the problem of the edge deformation of the central power supply channel, the problem of the edge deformation of the central power supply channel is basically solved by optimizing and properly expanding the shielding area, the final qualification rate reaches more than 99.5 percent, and the initial project estimation standard is met.
The foregoing describes one embodiment of the present invention in detail, but the description is only a preferred embodiment of the present invention and should not be construed as limiting the scope of the invention. All equivalent changes and modifications within the scope of the present invention are intended to be covered by the present invention.
Claims (7)
1. New energy automobile battery surface foreign matter detection mechanism based on 2D, 3D vision, its characterized in that includes:
The upper side of the support frame (1) is provided with a detection frame (2), and a detection area is arranged in the support frame (1);
the conveying frame (3) passes through the lower side of the detection frame (2) and is used for moving the product into a detection area inside the support frame (1);
the detection frame (2) comprises:
The driving assembly (21) and the sliding rail frame (22) are arranged in parallel, and are connected with the supporting frame (1);
The assembly frame (23) slides with the sliding rail frame (22), and the assembly frame (23) is connected with the output end of the driving assembly (21);
a visual detection unit (24), at least one group of visual detection units (24) is arranged on the lower side of the assembly frame (23);
the visual detection unit (24) comprises a shell (241), a line scanning camera (242) and a 3D camera (243) are installed inside the shell (241), and a multi-angle switching light source (244) is installed inside the shell (241) on one side of the line scanning camera (242) and one side of the 3D camera (243).
2. The new energy automobile battery surface foreign matter detection mechanism based on 2D and 3D vision according to claim 1 is characterized in that a trigger sensor is installed in the support frame (1), and the trigger sensor is installed in a preset detection area in the support frame (1);
after the product moves to the triggering area of the triggering sensor based on the conveying frame (3), the detection frame (2) starts to detect the product.
3. The new energy automobile battery surface foreign matter detection mechanism based on 2D, 3D vision according to claim 1, characterized in that the working method of the detection frame (2) comprises the following steps:
Step one: setting a region of interest, acquiring a 2D image by a line scanning camera (242), acquiring a 3D image by a 3D camera (243), and dividing the 2D image into a plurality of subareas according to the structure and the material of the battery plate;
step two: image preprocessing, namely performing primary filtering and contrast enhancement processing on the 2D image to obtain a 2D threshold image;
Step three: performing secondary filtering on the 2D image, and extracting a preliminary target feature contour on the basis of the 2D threshold image after smoothing and Gao Silv;
step four: performing secondary filtering on the 2D threshold image, performing local secondary analysis on each target feature, reducing misjudgment caused by the uneven characteristics of the coating, and extracting the target region;
step five: final screening, namely carrying out Z-dimension height measurement in combination with the corresponding 3D image, and carrying out screening analysis again on the target area in the fourth step to judge the foreign matters;
Step six: performing secondary transverse scanning on the area subjected to the foreign matter judgment in the step five, and further judging the height of the foreign matter in the 3D image;
and (5) performing alarm processing on the area which is still judged to be the foreign matter by the secondary scanning.
4. The new energy automobile battery surface foreign matter detection mechanism based on 2D, 3D vision of claim 3, wherein the 3D camera (243) adopts structured light and shoots the product by scanning, comprising the following working steps:
A1: the 3D camera (243) emits a structural photomask to be arranged on the surface of a product by laser with specific wavelength, and receives light reflected by the structural photomask through a filter to obtain a facula image;
A2: a chip inside the 3D camera (243) calculates the received facula image to obtain depth data of an object;
a3: a line scanning camera (242) and a 3D camera (243) work in parallel to acquire a product image with a specific height;
A4: after the online scanning camera (242) and the 3D camera (243) acquire images, the images are imported into software for processing.
5. The new energy automobile battery surface foreign matter detection mechanism based on 2D and 3D vision of claim 4, wherein the processing method of the image acquired by the 3D camera (243) comprises the following steps:
b1: preprocessing, namely selecting a filter to inhibit noise in a product and a background, and simultaneously keeping the shape, the size and specific geometric and topological structure characteristics of a product target from being damaged;
B2: the camera position of the first frame of the 3D camera (243) is taken as the origin of a world coordinate system, a KinectFusion iteration closest point method is adopted to obtain a position transfer matrix of each frame of the camera relative to the first frame after the camera is adopted, a model is built from big data, the position of the midpoint of each real scene is calculated, and whether foreign matters exceeding Hmm above a reference plane exist or not is judged.
6. The new energy automobile battery surface foreign matter detection mechanism based on 2D and 3D vision of claim 1, wherein the multi-angle switching light source (244) is provided with a plurality of light sources, and the plurality of light sources are sequentially stroboscopic switched to image when in operation;
When the multi-angle switching light source (244) works on the online scanning camera (242) and the 3D camera (243), cross line light alternately irradiates;
at least two light source angles are simultaneously covered when the line scan camera (242) and the 3D camera (243) image.
7. The new energy automobile battery surface foreign matter detection mechanism based on 2D and 3D vision according to claim 1, wherein the working method of the new energy automobile battery surface foreign matter detection mechanism based on 2D and 3D vision comprises the following steps:
S1: the product moves to a detection area inside the supporting frame (1) based on the conveying frame (3);
S2: the driving assembly (21) in the detection frame (2) drives each visual detection unit (24) to scan from the head end of the product to the tail end of the battery, and the line scanning camera (242) and the 3D camera (243) in the visual detection units (24) take pictures and analyze results;
s3: after the scanning is finished, resetting the detection frame (2);
S4: the line scanning camera (242) and the 3D camera (243) analyze and upload to the common control computer according to the respective photographing results, and the common control computer comprehensively analyzes the detection results of the line scanning camera (242) and the 3D camera (243) and makes detection judgment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311825722.6A CN118032802A (en) | 2023-12-27 | 2023-12-27 | New energy automobile battery surface foreign matter detection mechanism based on 2D, 3D vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311825722.6A CN118032802A (en) | 2023-12-27 | 2023-12-27 | New energy automobile battery surface foreign matter detection mechanism based on 2D, 3D vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118032802A true CN118032802A (en) | 2024-05-14 |
Family
ID=90997659
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311825722.6A Pending CN118032802A (en) | 2023-12-27 | 2023-12-27 | New energy automobile battery surface foreign matter detection mechanism based on 2D, 3D vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118032802A (en) |
-
2023
- 2023-12-27 CN CN202311825722.6A patent/CN118032802A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1995553B1 (en) | System and method for identifying a feature of a workpiece | |
| CN109772733B (en) | Defect bamboo block detecting and sorting device and method based on vision | |
| CN108332689B (en) | Optical measurement system and method for detecting surface roughness and surface damage | |
| CN106091926B (en) | The detection device and method of the miniature workpiece inside groove size of the asynchronous exposure of multi-point source | |
| CN109900711A (en) | Workpiece, defect detection method based on machine vision | |
| US9047657B2 (en) | Method and system for optically inspecting outer peripheral surfaces of parts | |
| CN107052086A (en) | Stamping parts surface defect detection apparatus and detection method based on 3D vision | |
| EP4016058B1 (en) | Automatic machine of vision on detection device for workpiece with complex curved surface | |
| CN110216080A (en) | A kind of Quality Monitoring Control System of the PCB processing producing line based on image comparison | |
| CN110146516B (en) | Fruit grading device based on orthogonal binocular machine vision | |
| CN206981462U (en) | Stamping parts surface defect detection apparatus based on 3D vision | |
| CN110966956A (en) | Binocular vision-based three-dimensional detection device and method | |
| CN112304954A (en) | Part surface defect detection method based on line laser scanning and machine vision | |
| WO2014189566A1 (en) | High-speed, triangulation-based, 3-d method and system for inspecting manufactured parts and sorting the inspected parts | |
| CN114280075A (en) | Online visual inspection system and method for surface defects of pipe parts | |
| CN116678826A (en) | Appearance defect detection system and method based on rapid three-dimensional reconstruction | |
| CN113566733A (en) | Line laser vision three-dimensional scanning device and method | |
| CN207081666U (en) | A kind of zipper detecting device based on machine vision | |
| TW419634B (en) | Automatic detection system and method using bar code positioning | |
| CN103198472A (en) | Detection method for quality of heavy-duty car connecting rod finished product and detection system thereof | |
| CN114252452A (en) | Online detection device and method for appearance defects and contour dimension of small-sized revolving body | |
| CN103091332B (en) | Detection method and detection system of U-shaped powder pipe based on machine vision | |
| CN118032802A (en) | New energy automobile battery surface foreign matter detection mechanism based on 2D, 3D vision | |
| CN117761060A (en) | Visual detection system and detection method thereof | |
| US20140347438A1 (en) | Triangulation-based, 3-d method and system for imaging the outer peripheral surface of a part |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |