CN111650210B - Burr detection method and detection system for high-speed high-precision lithium ion battery pole piece - Google Patents
Burr detection method and detection system for high-speed high-precision lithium ion battery pole piece Download PDFInfo
- Publication number
- CN111650210B CN111650210B CN202010531721.0A CN202010531721A CN111650210B CN 111650210 B CN111650210 B CN 111650210B CN 202010531721 A CN202010531721 A CN 202010531721A CN 111650210 B CN111650210 B CN 111650210B
- Authority
- CN
- China
- Prior art keywords
- pole piece
- detection
- light source
- image
- burr
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
- G01N2021/0106—General arrangement of respective parts
- G01N2021/0112—Apparatus in one mechanical, optical or electronic block
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Abstract
A method and a system for detecting burrs of a high-speed high-precision lithium ion battery pole piece are disclosed, wherein the method comprises the steps of S1, electrifying and initializing the detection system; s2, when the detection starts, the high-frequency sampling is carried out on the pole piece of the high-speed line scanning camera; s31, the detection system reads the images collected by the line scanning camera from the memory at preset time intervals; s32, when the detection system reads and detects the scanned image, the line scanning camera simultaneously and parallelly collects the image of the pole piece and stores the image into the memory to wait for the next reading; s4, calculating the length of a pole piece defect post-processing buffer area according to the pole piece winding linear velocity v and the algorithm detection ta time consumption, and performing winding suspension or marking processing according to requirements after the algorithm detects the burr defect; and S5, repeating the steps from S31 to S4 until all the pole pieces are detected. The invention can meet the production requirement under the conditions of high-speed cutting and small burr size.
Description
Technical Field
The invention belongs to the technical field of visual detection, and particularly relates to a burr detection method and a matched detection system for a lithium ion battery pole piece slitting process.
Background
Lithium ion batteries are currently the most widely used power source in the world due to their large capacity and high energy efficiency ratio. As the performance requirements of lithium ion batteries are increasing, the precision requirements for each process of battery manufacturing are also increasing. The production process of the pole piece of the lithium ion battery is taken as a key link, and the quality control is very strict. In the process of slitting the lithium battery pole piece, the defects such as burrs and the like can be generated on the current collector of the pole piece. The burrs can pierce the battery diaphragm during battery assembly, resulting in battery short circuit scrap and even safety issues. Therefore, the burr defect detection of the lithium ion battery pole piece is very important.
The existing burr detection method simply adopts an industrial camera to shoot an image of a pole piece, and then burr detection is carried out by a detection algorithm. However, due to the limitations of the frame rate and the sampling precision of the industrial camera, the requirement of high-speed and high-precision burr detection cannot be met. The existing detection technology cannot meet the production requirements under the conditions of high-speed slitting and small burr size. The electrode plate burr detection method is characterized in that a well-arranged light source structure is needed to polish the electrode plate, and then a proper image acquisition system and an image processing system are designed to meet the requirements of high-speed and high-precision electrode plate burr detection.
Disclosure of Invention
Aiming at the problems, the invention provides a method and a system for detecting burrs of a high-speed high-precision lithium ion battery pole piece in a modular image acquisition system consisting of a herringbone-structured light source and a high-speed line scanning camera; the method has the characteristics that the production requirements can be met under the conditions of high-speed cutting and small burr size.
The light source with the herringbone structure is a customized light source matched with the camera used by the invention, one end of a common surface light source similar to a strip light source is contacted to form the herringbone structure, and the light source and the camera form a modular image acquisition module. In addition, the included angle of the herringbone structure can be adjusted to adapt to different shooting scenes. Furthermore, in order to improve the image acquisition quality, a plane backlight source is arranged on the lower parts of the edge parts of the two sides of the lithium battery pole piece and opposite to the herringbone light source, and is used for improving the contrast of the pole piece. The image acquisition device is a high-speed line scanning camera, and the installation direction of the image acquisition device is vertical to the movement direction of the pole piece. High-speed scanning of the line scanning camera is used for matching high-speed movement in the pole piece rolling process. Meanwhile, the line frame resolution of a common line scanning camera can reach 16384 pixels at most, so that the high-precision burr detection requirement can be met.
The defect detection algorithm based on deep learning provided by the invention utilizes a Convolutional Neural Network (CNN) to process an input image, extracts image characteristics and classifies and positions a defect region.
In order to achieve the above object, the present invention further provides a high-speed high-precision visual detection system for burrs on a lithium ion battery pole piece, which includes mechanical structures such as a camera, a light source, an industrial personal computer, a corresponding light source controller, and a matched detection algorithm, wherein:
the camera is a high-speed line scanning camera, and line frame resolution needs to be selected according to a specific use scene. For example, the width of the battery pole piece after the cutting process is about 10-20cm, the size of the burr is about 5 μm, and in order to ensure the detection accuracy, the defect area should be described by 3-5 pixels, so that the pixel resolution of the camera should reach 1pixel/μm. In order to save cost and improve efficiency, the system adopts two cameras and the light source module to respectively detect the burr detection defects of the two side edges of the pole piece. The system selects a camera with a visual field of view (FOV) of 10 mm. Therefore, the line scanning camera with the line frame resolution of 12K is selected in the system. The speed of the pole piece in winding is about 1m/s, so the sampling frequency of the camera should reach 106Line/second, the system selects a scanning camera with the vertical resolution of 4 pixels and the sampling frequency of 300 KHz. Therefore, the line scanning camera adopted by the system has the resolution of 12 Kx 4 pixels and the frequency of 300KHz so as to meet the detection requirement of high speed and high precision.
The camera is provided with a common optical lens, and the system adopts a lens matched with the working distance of the camera;
the herringbone light source is a pure-color strip-shaped surface light source, white light is adopted in the system, and a light source controller used in a matched mode can be used for adjusting brightness of 256 levels with the light source.
The planar backlight source is a pure-color area light source, white light is adopted in the system, and a light source controller matched with the system can perform 256-level brightness dimming with a light source.
The burr detection system also comprises a mechanical structure part, in particular a fixing clamp with an image acquisition device, a light source angle adjusting mechanical structure and a pole piece air injection cleaning pretreatment mechanism;
the burr detection algorithm adopts a CNN-based defect detection frame, and the image output by the line scanning camera is input into the detection frame after being preprocessed, so that target detection is carried out, and the type and position of the defect are output. Specifically, according to different use environments and requirements, the model in the algorithm can be trained to detect defects such as scratches, inclusions, foil leakage and the like.
The CNN-based defect detection framework needs offline training before actual use, and the specific method comprises the following steps:
(1) implementing the CNN-based defect detection model framework;
(2) collecting a predetermined amount (preferably 200-300) of pole piece images containing defects, marking the positions of the defects by using a rectangular frame by a professional, and giving the types of the defects to obtain a training data sample;
(3) inputting a training data sample into a CNN model for feature extraction calculation, classifying defects in the graph, performing regression calculation to calculate the positions of the defects, and giving the probability that a suspected area is the type of the defects;
(4) and (4) comparing the model calculation result in the step (3) with the actual artificial marking result, calculating the calculation error of the model, and updating the parameters of the model by using a back propagation rule, thereby realizing the optimization of the model.
After the offline training of the CNN model framework is completed, model parameters are called by a matched detection system, and a defect area is predicted online during actual detection.
The defect detection algorithm flow comprises the steps of obtaining an image output by a line scanning camera, carrying out image mean filtering processing on the image to reduce the influence of noise in the image on a result, and then improving the contrast ratio of a defect area and a background area in the image by using gray scale linear change to highlight the defect so as to facilitate detection. And zooming the processed image to a fixed size, and then transmitting the image into the CNN model for defect classification and position prediction.
Preferably, the detection method of the lithium battery pole piece burr detection system includes the following steps:
s1, installing the light source and the image acquisition system on a pole piece rolling production line, debugging the light source and the camera well, obtaining a good pole piece sampling image, electrifying and initializing the detection system;
s2, when the detection starts, the high-speed line scanning camera carries out high-frequency sampling on the pole piece after air injection cleaning, and calculates the corresponding sampling frequency according to the winding linear speed, so that the sampling frequency of the camera is synchronous with the movement speed of the pole piece;
s31, the detection system reads line scanning camera images from the memory at preset time intervals, then carries out preprocessing according to the complete images after line frame splicing of the scanning cameras, carries out smooth noise reduction on input images by using mean value filtering, then carries out linear gray scale transformation to highlight defect areas, then inputs the preprocessed result images into a CNN defect detection model, carries out burr detection, and completes detection in extremely short time;
s32, when the system reads and detects the scanned image, the camera still collects the image of the pole piece and stores the image into the memory in parallel at the moment, and waits for the next reading;
s4, according to the winding linear velocity v of the pole piece and the total time t of the detection algorithmaThe length of a pole piece defect post-processing buffer zone is easy to calculate, and the length is Lc=v*taAnd after the defect detection algorithm detects the burr defect, pausing winding or marking processing is carried out according to requirements. The algorithm calculates the relative position of the burr and processes the burr in the buffer area.
And S5, repeating the steps from S31 to S4 until all the pole pieces are detected.
Preferably, the CNN defect detection model is modified according to the YOLO v3 framework. Because the content information in the industrial defect image is less, and the requirement of high-speed detection is considered, the original YoLO v3 framework is precisely modified to adapt to the defect detection task. Specifically, the CNN defect detection model includes a backbone feature extraction network VGG16 model and three additional convolution branches for predicting the result. The backbone network VGG16 result contains 5 consecutive building blocks consisting of convolutional layers, pooling layers, and activation functions. These 5 building blocks have 13 layers in total for extracting features from the image. In order to improve the detection precision of the model on the small defect area and reduce the calculation time, an additional 3 prediction convolution branches are directly led out from the VGG16 network of the backbone to detect the defects on the multi-scale features. Specifically, the first prediction convolution branch is led out from the 5 th building block of the VGG16 backbone network, is subjected to feature extraction by a 3 × 3 convolution layer, and is predicted by a 1 × 1 convolution layer. The feature output by the 5 th layer is used for predicting the result, then passes through the first up-sampling layer, is expanded by 2 times and then is fused with the feature from the 4 th building block, then enters the second prediction convolution branch, passes through a 3 x 3 convolution layer to extract the feature, and then the result is predicted by a 1 x 1 convolution layer. Similarly, the fused features are expanded by a factor of 2 through a second upsampling layer and fused with features from the 3 rd building block. Then, the prediction convolution branch enters a third prediction convolution branch, the characteristics are extracted through a 3 x 3 convolution layer, and the result is predicted through a 1 x 1 convolution layer. The result prediction is carried out through the characteristics of three different scales, so that the detection precision of the model on the defects is improved, and particularly, the detection precision on small defect types such as foil leakage and the like is improved.
Preferably, since the types of defects of the lithium battery pole pieces are not many and the variation is less, each prediction convolution branch predicts 3 different suspected defect area candidate frames at each pixel point position of the feature map.
In order to ensure the imaging quality and the detection precision, the whole system needs to be preliminarily debugged. Firstly, a hardware part comprises the adjustment of the installation position and the working distance of a camera, so that clear and complete pole piece edge images can be obtained; meanwhile, brightness and angle adjustment of the herringbone light source are carried out, and a good sampling image is obtained by matching with camera debugging; and secondly, a system part comprises image reading interval time, camera parameter setting and exposure parameters so as to obtain a high-quality sampling image by coordinating with the motion of a pole piece wound at a high speed.
In general, compared with the prior art, the method and the system for detecting the burrs of the lithium battery pole piece based on the high-speed line scanning camera and the herringbone structure light source provided by the invention have the following beneficial effects:
(1) the herringbone structure light source can well polish the surface of the lithium battery pole piece according to the sampling characteristics of a camera, so that a clear image is obtained, and a light source pair is formed with a plane backlight source at the lower part of the pole piece, so that burr defects and a pole piece background are easily distinguished;
(2) the technical scheme of the invention can be used for detecting the burr defect of the lithium battery pole piece with the width of about 20cm, which is as small as 5 microns when the lithium battery pole piece is wound at the speed of 1m/s, and the burr detection accuracy and the recall rate can reach more than 99 percent, thereby realizing the high-speed and high-precision detection of the lithium battery pole piece.
(3) The image acquisition module has the advantage of modularization, and the hardware structure and the supporting detection software system can adapt to the pole piece burr detection of different width very nimble, have improved efficiency, have better suitability and economic nature.
Drawings
FIG. 1 is a schematic diagram of an image acquisition module comprising a high-speed line-scan camera and a chevron-shaped light source according to the present invention;
FIG. 2 is a schematic top view of the structure of FIG. 1;
FIG. 3 is a schematic diagram of an optical path structure of the image capturing module shown in FIG. 1;
FIG. 4 is a schematic diagram of a top view of a hardware layout of the inspection system according to the present invention;
FIG. 5 is a schematic view of the A-direction structure of FIG. 4;
FIG. 6 is a block diagram of a detection system according to the present invention;
FIG. 7 is a block diagram of the detection algorithm according to the present invention;
FIG. 8 is a schematic view of a defect inspection frame according to the present invention;
FIG. 9 is a schematic diagram showing a screenshot of a detection result of the detection system used in conjunction with the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Referring to fig. 1 to 5, fig. 1 to 5 disclose a high-speed and high-precision burr detection system for a lithium ion battery pole piece, which includes an image acquisition module 1 and a detection module 2, where the image acquisition module 1 includes a light source 11 and a line scanning camera 12, the light source 11 is used to illuminate a predetermined position of the pole piece, the line scanning camera 12 scans and photographs the illuminated position of the pole piece in an incoming line, and transmits the photographed image to the detection module 2.
Preferably, the detection module 2 processes the shot image according to the following method for detecting the burr of the high-speed high-precision lithium ion battery pole piece.
Preferably, the light source 11 includes a first light source 111 and a second light source 112, the first light source 111 is disposed on a first mounting member 113; the second light source 112 is arranged on the second mounting part 114, the upper ends of the first mounting part 113 and the second mounting part 114 are pivoted through a rotating shaft 115 to form a herringbone light source, the line scanning camera 12 is arranged on the central line of the herringbone light source, and the lens of the line scanning camera 12 is aligned with the irradiation area of the light source 11.
Preferably, a planar backlight 13 is further arranged below the pole piece 15 on the side away from the light source 11, and the light emitting direction of the planar backlight 13 faces to the lower bottom surface of the pole piece; used for distinguishing burr defects from pole piece backgrounds.
Preferably, the number of the image acquisition modules 1 is two, and the two image acquisition modules are respectively located on two sides of the pole piece in the length direction and used for acquiring burrs on two sides of the pole piece.
Preferably, the invention further comprises an air injection cleaning device 14, wherein the air injection cleaning device 14 is positioned on the upstream side of the image acquisition module 1 and is used for removing dust from the pole piece.
As shown in fig. 6, the system for detecting burrs according to the present invention is configured such that after hardware of the system is installed and debugged, initialization of all components is completed by a detection software, an industrial personal computer controls a light source of a chevron structure to reach a predetermined brightness through a light source controller, the industrial personal computer is connected to a plurality of high-speed line scanning cameras through a switch, and after sampling of an image acquisition module is completed, a software system calls an algorithm to complete burr detection, and feeds a detection result back to an execution end to complete a predetermined action.
With reference to fig. 7, the detection steps of the present invention are illustrated below:
s1, debugging the position of the light source, the angle of the light source, the installation position of the camera and the working distance, and setting the parameters of the image acquisition module. Simultaneously installing the air injection cleaning device and the processing execution end of the buffer area at a preset position;
s2, when the detection starts, the detection system software controls the air injection cleaning device to remove impurities on the surface of the lithium battery pole piece through the PLC, so that the impurities are prevented from influencing the subsequent burr detection;
and S31, the image acquisition module samples the pole piece image at a set frequency to obtain the surface image of the pole piece, and the surface image is stored in the memory for later use. The two image acquisition modules are used for distinguishing and acquiring edge images on two sides of the pole piece;
s32, the detection software system acquires the images acquired in the step S31 at regular intervals, the images acquired by line scanning are spliced into a large image according to lines, the images on the two sides acquired by the two image modules are combined into an image, then the matched defect detection software system carries out filtering and noise reduction on the image, then the image gray level transformation algorithm is used for carrying out contrast adjustment on the pole piece image, the defect area is highlighted, and the preprocessed image is sent to a CNN detection frame to detect burrs in the image. Meanwhile, the image module still synchronously continues to acquire images for later use;
s4, because the detection algorithm needs a certain time, the area acquired and detected last time enters a set buffer processing area, the detection result of the system is fed back to an execution end through a PLC, and the preset shutdown check or other marking work is executed;
and S5, repeating the steps from S31 to S4 until all the pole pieces are detected.
Preferably, as shown in fig. 8, the convolution kernel parameters of each layer of the CNN structural model used in the present invention are shown in the following table. Wherein Conv represents an abbreviation of the convolutional layer. The CNN model adopts a VGG16 structure as a main network, so that in an off-line training stage, a pre-training model on a public image data set is used in the defect image training process of the invention by adopting a transfer learning method, and the pre-training model is used for improving the model detection accuracy, and reducing the training time and the number of required training samples.
FIG. 9 is a schematic diagram showing a screenshot of a detection result of the detection system used in conjunction with the present invention.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (7)
1. A burr detection method for a high-speed high-precision lithium ion battery pole piece comprises the following steps:
s1, electrifying and initializing the detection system;
s2, when the detection starts, the high-speed line scanning camera pole piece carries out high-frequency sampling, and the corresponding sampling frequency is calculated according to the winding linear speed, so that the camera sampling frequency is synchronous with the pole piece moving speed;
s31, the detection system reads line scanning camera images from the memory at preset time intervals, then carries out preprocessing according to the complete images after line frame splicing of the scanning cameras, carries out smooth noise reduction on input images by using mean value filtering, then carries out linear gray scale transformation to highlight defect areas, then inputs the preprocessed result images into a CNN defect detection model, carries out burr detection, and completes detection in extremely short time;
s32, when the detection system reads and detects the scanned image, the line scanning camera simultaneously and parallelly collects the image of the pole piece and stores the image into the memory to wait for the next reading;
s4, calculating the length of a pole piece defect post-processing buffer area according to the pole piece winding linear speed v and the total time consumption ta of a defect detection algorithm, wherein the length is Lc = v × ta, and the defect detection algorithm pauses winding or marks processing as required after detecting a burr defect; calculating the relative position of the burr by an algorithm, and processing the burr in the buffer area;
s5, repeating the steps S31 to S4 until all the pole pieces are detected;
the CNN defect detection model comprises a main feature extraction network VGG16 model and three additional convolution branches for predicting results; the backbone network VGG16 result contains 5 consecutive building blocks consisting of convolutional layers, pooling layers and activation functions; these 5 building blocks have 13 layers in total for extracting features from the image; in order to improve the detection precision of the model on the small defect area and reduce the calculation time, additional 3 prediction convolution branches are directly led out from the VGG16 network of the backbone to detect the defects on the multi-scale characteristic;
the first prediction convolution branch is led out from the 5 th construction module of the main feature extraction network VGG16 model, the feature is extracted through a 3 x 3 convolution layer, and then the result is predicted through a 1 x 1 convolution layer; the features output by the 5 th layer are subjected to the first upsampling layer after being used for predicting the result, are expanded by 2 times and then are fused with the features from the 4 th building module, then enter a second prediction convolution branch, are subjected to feature extraction by a 3 x 3 convolution layer, and are subjected to the result prediction by a 1 x 1 convolution layer; the fused features are expanded by 2 times through a second upper sampling layer and then fused with the features from the 3 rd building block; then, the prediction convolution branch enters a third prediction convolution branch, the characteristics are extracted through a 3 x 3 convolution layer, and the result is predicted through a 1 x 1 convolution layer.
2. The method for detecting the burrs of the high-speed high-precision lithium ion battery pole piece according to claim 1, wherein each prediction convolution branch predicts 3 different suspected defect area candidate frames at each pixel point position of the feature map.
3. The utility model provides a burr detecting system of high-speed high accuracy lithium ion battery pole piece which characterized in that: the pole piece detection device comprises an image acquisition module (1) and a detection module (2), wherein the image acquisition module (1) comprises a light source (11) and a line scanning camera (12), the light source (11) is used for illuminating a preset part of a pole piece, the line scanning camera (12) is used for scanning and photographing the illuminated part of the pole piece in an incoming line mode, and the photographed image is transmitted to the detection module (2);
the detection module (2) processes the shot image according to the burr detection method of the high-speed high-precision lithium ion battery pole piece in claim 1 or 2.
4. The system for detecting the burrs of the pole piece of the high-speed high-precision lithium ion battery is characterized in that the light source (11) comprises a first light source (111) and a second light source (112), wherein the first light source (111) is arranged on a first mounting piece (113); the second light source (112) is arranged on a second mounting part (114), the upper ends of the first mounting part (113) and the second mounting part (114) are pivoted through a rotating shaft (115) to form a herringbone light source, the line scanning camera (12) is arranged on the central line of the herringbone light source, and the lens of the line scanning camera (12) is aligned with the irradiation area of the light source (11).
5. The system for detecting the burrs of the pole piece of the high-speed high-precision lithium ion battery according to claim 4, wherein a planar backlight (13) is further arranged below the pole piece on the side far away from the light source (11), and the light emitting direction of the planar backlight (13) faces to the lower bottom surface of the pole piece; used for distinguishing burr defects from pole piece backgrounds.
6. The system for detecting the burrs of the pole piece of the high-speed high-precision lithium ion battery according to claim 3 or 4, wherein the number of the image acquisition modules (1) is two, and the two image acquisition modules are respectively located at two sides of the pole piece in the length direction and are used for acquiring the burrs at two sides of the pole piece.
7. The system for detecting the burrs of the pole piece of the high-speed high-precision lithium ion battery according to claim 3 or 4, further comprising a gas injection cleaning device (14), wherein the gas injection cleaning device (14) is located at the upstream side of the image acquisition module (1) and is used for removing dust from the pole piece.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010531721.0A CN111650210B (en) | 2020-06-11 | 2020-06-11 | Burr detection method and detection system for high-speed high-precision lithium ion battery pole piece |
| PCT/CN2020/097452 WO2021248554A1 (en) | 2020-06-11 | 2020-06-22 | High-speed and high-precision burr detection method and detection system for lithium ion battery electrode sheet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010531721.0A CN111650210B (en) | 2020-06-11 | 2020-06-11 | Burr detection method and detection system for high-speed high-precision lithium ion battery pole piece |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111650210A CN111650210A (en) | 2020-09-11 |
| CN111650210B true CN111650210B (en) | 2021-10-22 |
Family
ID=72351393
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010531721.0A Active CN111650210B (en) | 2020-06-11 | 2020-06-11 | Burr detection method and detection system for high-speed high-precision lithium ion battery pole piece |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111650210B (en) |
| WO (1) | WO2021248554A1 (en) |
Families Citing this family (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112670549B (en) * | 2020-12-11 | 2023-12-29 | 曙鹏科技（深圳）有限公司 | Battery manufacturing method, battery and electronic equipment |
| CN113033483B (en) * | 2021-04-20 | 2024-02-02 | 北京百度网讯科技有限公司 | Method, device, electronic equipment and storage medium for detecting target object |
| CN113267145B (en) * | 2021-05-12 | 2023-01-17 | 无锡先导智能装备股份有限公司 | Method and device for controlling feeding of pole piece of winding machine, electronic equipment and storage medium |
| CN113740345B (en) * | 2021-08-27 | 2024-03-22 | 电子科技大学(深圳)高等研究院 | Burr detection method and system under high-speed sampling rate |
| CN113686878B (en) * | 2021-09-03 | 2024-02-09 | 太原理工大学 | Multi-stage joint detection method and system for surface defects of special steel bar |
| CN114529510B (en) * | 2022-01-11 | 2023-05-23 | 三门三友科技股份有限公司 | Automatic detection and classification method for cathode copper on-line quality |
| CN114589108A (en) * | 2022-01-21 | 2022-06-07 | 厦门聚视智创科技有限公司 | High-speed flexible circulation detection device with simple structure |
| CN114441542A (en) * | 2022-01-28 | 2022-05-06 | 天津市海迅科技发展有限公司 | Control method based on visual detection |
| CN114523002A (en) * | 2022-02-05 | 2022-05-24 | 上海研视信息科技有限公司 | Sleeve deformation area detecting system based on machine vision |
| CN114923930A (en) * | 2022-03-31 | 2022-08-19 | 广州超音速自动化科技股份有限公司 | Detection device and method for detecting lithium deposition condition of battery pole piece by using line scanning camera |
| CN115841445A (en) * | 2022-04-18 | 2023-03-24 | 宁德时代新能源科技股份有限公司 | Method, device and system for detecting cathode pole piece of composite material belt |
| CN114894810A (en) * | 2022-07-12 | 2022-08-12 | 荣旗工业科技(苏州)股份有限公司 | Lug detection method and equipment |
| CN115588022B (en) * | 2022-11-10 | 2023-04-11 | 合肥惠强新能源材料科技有限公司 | Lithium battery isolation film quality detection system based on process index data |
| CN116129221B (en) * | 2023-01-16 | 2024-02-20 | 五邑大学 | Lithium battery defect detection method, system and storage medium |
| CN116416268B (en) * | 2023-06-09 | 2023-08-18 | 浙江双元科技股份有限公司 | Method and device for detecting edge position of lithium battery pole piece based on recursion dichotomy |
| CN116581418B (en) * | 2023-07-13 | 2023-11-14 | 深圳先进储能材料国家工程研究中心有限公司 | Automatic disassembling method and device for waste battery packs |
| CN117173156B (en) * | 2023-10-23 | 2024-02-20 | 杭州百子尖科技股份有限公司 | Pole piece burr detection method, device, equipment and medium based on machine vision |
| CN117214453B (en) * | 2023-11-07 | 2024-04-05 | 长春迈克赛德医疗科技有限公司 | Sample suction needle system and sample suction method |
| CN117451629A (en) * | 2023-11-17 | 2024-01-26 | 广州市翔哲自动化设备有限公司 | Editable multi-angle light source equipment for bipolar ear detection |
| CN117309889A (en) * | 2023-11-27 | 2023-12-29 | 宁德时代新能源科技股份有限公司 | Pole piece edge detection device and method |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202083648U (en) * | 2011-05-27 | 2011-12-21 | 北京京东方光电科技有限公司 | Optical detection device and glass substrate detection system |
| JP5988474B2 (en) * | 2012-03-01 | 2016-09-07 | 東レエンジニアリング株式会社 | Equipment for inspecting the end face of laminated sheet material |
| CN203396714U (en) * | 2013-05-02 | 2014-01-15 | 上海工程技术大学 | Vehicle-mounted high speed dynamic track surface defect video detecting device |
| CN105158257B (en) * | 2015-05-21 | 2018-07-20 | 苏州华兴致远电子科技有限公司 | Slide plate measurement method and device |
| CN106409711B (en) * | 2016-09-12 | 2019-03-12 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of solar energy silicon crystal chip defect detecting system and method |
| CN107941813A (en) * | 2017-12-25 | 2018-04-20 | 广东斯玛特自动化科技有限公司 | Lithium battery pole slice cuts burr detection device |
| CN107883883A (en) * | 2017-12-29 | 2018-04-06 | 中国科学院自动化研究所（洛阳）机器人与智能装备创新研究院 | A kind of on-line checking experimental rig of lithium battery pole slice burr |
| CN109035243A (en) * | 2018-08-10 | 2018-12-18 | 北京百度网讯科技有限公司 | Method and apparatus for exporting battery pole piece burr information |
| CN109324061B (en) * | 2018-10-11 | 2023-09-22 | 广东德尔智慧工厂科技有限公司 | Burr detection device and method for lithium battery pole piece |
| CN109754401B (en) * | 2019-03-15 | 2020-09-08 | 苏州杰锐思智能科技股份有限公司 | Online measuring device and method for burrs at edge of lithium battery pole piece |
| CN110135521A (en) * | 2019-05-28 | 2019-08-16 | 陕西何止网络科技有限公司 | Pole-piece pole-ear defects detection model, detection method and system based on convolutional neural networks |
| CN210572007U (en) * | 2019-08-16 | 2020-05-19 | 研祥智能科技股份有限公司 | LED support defect image capturing device and detection equipment |
| CN110987960A (en) * | 2019-12-16 | 2020-04-10 | 广州量子激光智能装备有限公司 | Online burr detection device and online burr data acquisition structure |
-
2020
- 2020-06-11 CN CN202010531721.0A patent/CN111650210B/en active Active
- 2020-06-22 WO PCT/CN2020/097452 patent/WO2021248554A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| CN111650210A (en) | 2020-09-11 |
| WO2021248554A1 (en) | 2021-12-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111650210B (en) | Burr detection method and detection system for high-speed high-precision lithium ion battery pole piece | |
| CN111612737B (en) | Artificial board surface flaw detection device and detection method | |
| CN210604434U (en) | Online detection device for typical defects of curved glass of mobile phone | |
| CN113239930B (en) | Glass paper defect identification method, system, device and storage medium | |
| CN113762240B (en) | Cladding layer geometric feature prediction method and system based on deep learning | |
| CN105067639A (en) | Device and method for automatically detecting lens defects through modulation by optical grating | |
| WO2021093109A1 (en) | Mobile phone-based miniature microscopic image acquisition device, image splicing method, and image recognition method | |
| CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
| CN111340798A (en) | Application of deep learning in product appearance flaw detection | |
| CN110501347A (en) | A kind of rapid automatized Systems for optical inspection and method | |
| CN115184359A (en) | Surface defect detection system and method capable of automatically adjusting parameters | |
| Yang et al. | An automatic aperture detection system for LED cup based on machine vision | |
| CN103357672A (en) | Online strip steel boundary detection method | |
| CN113920090A (en) | Preform appearance defect automatic detection method based on deep learning | |
| CN110044921A (en) | Lithium battery open defect detection system and method | |
| CN112215203A (en) | Pavement disease detection method and device based on deep learning | |
| CN113781458A (en) | Artificial intelligence based identification method | |
| CN108156359A (en) | Intelligent industrial camera | |
| CN110728269B (en) | High-speed rail contact net support pole number plate identification method based on C2 detection data | |
| CN111929239A (en) | AOI detection device and detection method for PCB part defects | |
| CN103454283A (en) | Line detection system and method | |
| CN117309892B (en) | Defect detection method, device and system for blue film of battery and light source controller | |
| CN113706590A (en) | Automatic focusing method and system based on reinforcement learning and application equipment thereof | |
| CN106370673A (en) | Automatic lens flaw detection method | |
| CN202602795U (en) | Automatic focusing system orientating to linear array charge coupled device (CCD) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |