CN110706215A - Pole piece detection method - Google Patents
Pole piece detection method Download PDFInfo
- Publication number
- CN110706215A CN110706215A CN201910916538.XA CN201910916538A CN110706215A CN 110706215 A CN110706215 A CN 110706215A CN 201910916538 A CN201910916538 A CN 201910916538A CN 110706215 A CN110706215 A CN 110706215A
- Authority
- CN
- China
- Prior art keywords
- pole piece
- boundary
- reference point
- pixel points
- points
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
- G06T2207/10004—Still image; Photographic image
Abstract
The application provides a pole piece detection method, which comprises the following steps: acquiring images of the pole piece and the background; extracting the boundary of the pole piece and the background; selecting pixel points on the boundary as reference points, and acquiring adjacent pixel points of the reference points; judging whether burrs exist at the reference point or not according to the information of the adjacent pixel points of the reference point; and judging whether the boundary has burrs or not according to the judgment result of each reference point. In the application, whether burr exists at the reference point is judged according to the information of the adjacent pixel points of the reference point, so that whether burr exists at the whole boundary is determined, the detection efficiency is greatly improved for manual selective inspection, and the possibility of missed inspection is avoided.
Description
Technical Field
The application relates to the field of battery manufacturing, in particular to a pole piece detection method.
Background
In the production process of the lithium battery, the pole pieces may generate burr defects in the die cutting forming and cutting processes, if burrs puncture the diaphragms for separating the positive and negative pole pieces, serious consequences can be caused, battery leakage can be caused when the burrs are light, and battery explosion can be caused when the burrs are heavy. However, the size of the burr is small, usually in the order of micrometers, and a common image detection device cannot detect the burr defect. The detection of pole piece burr at present generally adopts artifical selective examination, and detection efficiency is lower, and in addition, the selective examination probably leads to some burr defects to miss to examine and cause serious consequence.
Disclosure of Invention
The application provides a pole piece detection method capable of detecting burrs.
The application provides a pole piece detection method, which comprises the following steps: acquiring images of the pole piece and the background; extracting the boundary of the pole piece and the background; selecting pixel points on the boundary as reference points, and acquiring adjacent pixel points of the reference points; judging whether burrs exist at the reference point or not according to the information of the adjacent pixel points of the reference point; and judging whether the boundary has burrs or not according to the judgment result of each reference point.
Further, according to the information of the adjacent pixel points of the reference point, whether burrs exist at the reference point is judged, including: acquiring the number of adjacent pixel points of the reference point; when the number of the adjacent pixel points of the reference point is two, judging that no burr exists at the reference point; and when the number of the adjacent pixel points of the reference point is at least three, judging that burrs exist at the reference point.
Further, when the number of the adjacent pixel points of the reference point is three, two of the three pixel points of the reference point are located on the boundary, and the other one of the three pixel points of the reference point is located on the burr.
Further, extracting the boundary between the pole piece and the background includes: extracting edge points by adopting an edge operator; connecting the edge points into a line, forming the boundary.
Further, the edge operator includes at least one of a gradient operator, a roberts operator, a laplacian operator, and a sobel operator.
Further, the image is acquired in the pole piece conveying process.
Further, the boundary includes a first boundary line, a second boundary line and an end point, and the end point is an intersection point of the first boundary line and the second boundary line; when the reference point is an end point and a burr exists at the end point, pixel points which are adjacent to the end point and located on the burr and the end point are arranged along the second boundary line; or the arrangement direction of the pixel point adjacent to the end point and on the burr and the end point is intersected with the second boundary line.
Further, when the reference point is an end point and a burr exists at the end point, pixel points adjacent to the end point and the end point are arranged in a triangular mode.
The application also provides another pole piece detection method, which comprises the following steps: acquiring images of the pole piece and the background; extracting the boundary of the pole piece and the background; selecting pixel points on the sections as reference points, and acquiring adjacent pixel points of the reference points; determining whether burrs exist in the section where the reference point is located according to the information of the adjacent pixel points of the reference point; wherein the boundary comprises a plurality of segments.
Further, the pole piece detection method comprises the following steps: and judging whether the boundary has burrs or not according to the judgment result of each section.
In the application, whether burr exists at the reference point is judged according to the information of the adjacent pixel points of the reference point, so that whether burr exists at the whole boundary is determined, the detection efficiency is greatly improved for manual selective inspection, and the possibility of missed inspection is avoided.
Drawings
Fig. 1 is a schematic structural diagram of a pole piece of the present application.
FIG. 2 is a schematic flow chart of an embodiment of a pole piece detection method according to the present application.
Fig. 3 is a schematic flow chart of step 2 of the pole piece detection method shown in fig. 2.
Fig. 4 is an enlarged partial view of a first position of the pole piece shown in fig. 1.
Fig. 5 is an enlarged partial view of a second location of the pole piece shown in fig. 1.
FIG. 6 is a diagram of the end points of the boundary and the pixels adjacent to the end points.
FIG. 7 is a schematic flow chart of another embodiment of the pole piece detection method of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. Unless otherwise defined, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs. The use of "first," "second," and similar terms in the description and in the claims does not indicate any order, quantity, or importance, but rather is used to distinguish one element from another. Also, the use of the terms "a" or "an" and the like do not denote a limitation of quantity, but rather denote the presence of at least one. "plurality" or "a number" means two or more. Unless otherwise indicated, "front", "rear", "lower" and/or "upper" and the like are for convenience of description and are not limited to one position or one spatial orientation. The word "comprising" or "comprises", and the like, means that the element or item listed as preceding "comprising" or "includes" covers the element or item listed as following "comprising" or "includes" and its equivalents, and does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
Referring to fig. 1 to 7, the present application provides a pole piece detection method, including: acquiring images of the pole piece and the background; extracting the boundary of the pole piece and the background; selecting pixel points on the boundary as reference points, and acquiring adjacent pixel points of the reference points; and judging whether burrs exist at the reference point according to the adjacent pixel points.
Referring to fig. 1, the pole piece 1 has a boundary 10, and in an ideal state, any boundary line of the boundary is a straight line, but in practice, the entire boundary line may be curved to some extent, but may be regarded as an infinite number of straight line segments with smaller sizes locally. For the boundary of the qualified area, each pixel point on the boundary only has two adjacent pixel points on the boundary; for a pixel with a burr, besides two adjacent pixels located on the boundary 10, there is also one pixel located on the burr. Therefore, the detection of the burrs can be performed based on the adjacent pixel points corresponding to each pixel point.
Referring to fig. 2, the method for detecting a pole piece of the present embodiment includes:
step S1: images of the pole piece and the background are acquired.
Optionally, images of the pole piece and the background are acquired by a camera. In this embodiment, the image is obtained in the pole piece transmission process, so that online detection is realized, and the production efficiency is not affected.
Step S2: and extracting the boundary of the pole piece and the background.
Referring to fig. 1, in the present embodiment, the boundary 10 is rectangular, and the boundary 10 includes four boundary lines connected end to end, only the boundary line 101 and the boundary line 102 are labeled in the figure.
Referring to fig. 3, step S2 may be optionally performed by a processing module, such as an industrial computer. The step S2 includes:
substep S21: and extracting edge points reflecting gray level changes by adopting an edge operator.
Optionally, the edge operator includes at least one of a gradient operator, a Roberts operator, a Laplacian operator, and a Sobel operator, and the Sobel operator is selected in this embodiment.
Substep S22: connecting the edge points into a line, forming the boundary.
Optionally, the sub-step S22 may further include removing some of the apparently abnormal edge points, and supplementing the discontinuity points between some of the edge points.
Step S3: and selecting the pixel points on the boundary as reference points, and acquiring the adjacent pixel points of the reference points.
In this embodiment, each pixel point on the boundary 10 is sequentially used as a reference point to detect the entire boundary, which of course has a high requirement on the calculation processing capability of the processing module. In other embodiments, only a part of the pixels on the boundary may be selected as the reference points, so as to reduce the requirement on the processing capability of the processing module. Referring to fig. 4, for example, a pixel 11 (the size of the pixel is enlarged in the drawing to facilitate understanding, and the actual pixel is a point on the boundary) is used as a reference point, and the adjacent pixels of the reference point are known as a pixel 12 and a pixel 13; referring to fig. 5, for example, the pixel 14 is used as the reference point, and the adjacent pixels of the reference point are the pixel 15, the pixel 16 and the pixel 17, and the adjacent pixels 15, the pixel 16 and the pixel 17 of the reference point 14 in fig. 5 are arranged in a triangle.
Step S4: and judging whether burrs exist at the reference point or not according to the information of the adjacent pixel points of the reference point.
It is easy to understand that the pixel 12 and the pixel 13 in fig. 4 are points on the boundary 10, and the pixel 12 and the pixel 13 are respectively located at two sides of the pixel 11; pixel 15 and pixel 16 are located on boundary 10 and on both sides of pixel 11, respectively, and pixel 17 is not located on the boundary, so that pixel 17 can be determined to be the pixel on burr 3. That is, a burr 3 exists at the pixel point 14.
Certainly, a pixel point may also have a plurality of burrs at one point (of course, the actual possibility is small), and the corresponding pixel point has more than three adjacent pixel points. That is, when the number of the adjacent pixel points of one pixel point is two, it can be determined that no burr exists at the point; when the number of the adjacent pixel points of one pixel point is not less than three, the burr at the point can be judged.
Referring to fig. 6, for four endpoints (i.e. four vertices of a rectangle), taking the endpoint 21 where the first boundary line 101 and the second boundary line 102 intersect as an example, the adjacent pixels of the endpoint 21 are only the pixel 22 and the pixel 23, and the adjacent pixels 22, 23 of the endpoint 21 and the endpoint 22 are arranged in a triangle; if there is a burr at the end point 21, there are at least three pixel points at the end point 21, namely, the pixel point 22, the pixel point 23, and the pixel point 24, but the specific arrangement manner of the pixel points is different from that of the embodiment shown in fig. 5. Referring to fig. 5 and 6, the pixel points 24 and the end points 21 (i.e., the reference points) on the burrs are arranged along the second boundary line 102 of the boundary 10, and when the extending directions of the burrs are different, the arrangement directions of the pixel points 24 and the end points 21 may intersect with the second boundary line 102; when the reference point is not the end point, the arrangement direction of the pixel 17 and the pixel 14 (i.e., the reference point) on the burr intersects the first boundary line 101.
In other embodiments, whether burrs exist or not can be judged according to the arrangement mode of the adjacent pixel points of the reference points. For example, when the datum point has no burr, the adjacent pixel points of the datum point are linearly arranged; when burrs exist in the datum points, the adjacent pixel points of the datum points are arranged in a triangular mode. Of course, this manner of determination is essentially the same as in the previous embodiment. In other words, the information of the neighboring pixels of the reference point may be the number or the arrangement manner.
Step S5: and judging whether the boundary has burrs or not according to the judgment result of each reference point.
It can be understood that whether burrs exist on each pixel point on the boundary is judged respectively, and finally, the judgment result of each pixel point is summarized, so that whether burrs exist on the whole boundary can be judged. Because every pixel point on the boundary is regarded as the benchmark in proper order, therefore do not have the possibility of missing the detection, the accuracy of detecting is very high, take a picture simultaneously, process this a series of processes and go on when the pole piece conveys to realize efficient on-line measuring, can not influence the efficiency of whole battery production. The detection precision of the pole piece detection method can reach 2um, and detection of various fine burrs can be met.
Referring to fig. 7, in another embodiment, a pole piece detection method includes:
step S10: images of the pole piece and the background are acquired.
Step S20: and extracting the boundary of the pole piece and the background.
Steps S10 and S20 are similar to steps S1 and S2 of the previous embodiment, and are not repeated here.
Step S30: and selecting pixel points on the sections as reference points respectively, and acquiring adjacent pixel points of the reference points.
The boundary 10 comprises a plurality of segments. Optionally, each pixel point on the segment is sequentially used as a reference point, and a pixel point corresponding to each reference point is obtained.
Step S40: and determining whether burrs exist in the section where the reference point is located according to the information of the adjacent pixel points of the reference point.
It can be understood that whether burrs exist in each pixel point in the section is judged respectively, and finally, the judgment result of each pixel point is summarized, so that whether burrs exist in the whole section can be judged. During detection, each region of interest can be used as a section, and whether burrs exist in the region of interest can be judged independently.
Step S50: and judging whether the boundary has burrs or not according to the judgment result of each section.
Optionally, the result of whether each section has a burr is summarized, so as to determine whether the entire boundary has a burr. It should be noted that the detection of each segment is performed independently, and the processing module only needs to process the reference point of one segment and the pixel point adjacent to the reference point at each time, so that the requirement on the processing performance of the processing module is greatly reduced, and the detection efficiency is improved.
In the application, whether burr exists at the reference point is judged according to the information of the adjacent pixel points of the reference point, so that whether burr exists at the whole boundary is determined, the detection efficiency is greatly improved for manual selective inspection, and the possibility of missed inspection is avoided.
Although the present application has been described with reference to a preferred embodiment, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the application, and all changes, substitutions and alterations that fall within the spirit and scope of the application are to be understood as being covered by the following claims.
Claims (10)
1. A pole piece detection method is characterized by comprising the following steps:
acquiring images of the pole piece and the background;
extracting the boundary of the pole piece and the background;
selecting pixel points on the boundary as reference points, and acquiring adjacent pixel points of the reference points;
judging whether burrs exist at the reference point or not according to the information of the adjacent pixel points of the reference point;
and judging whether the boundary has burrs or not according to the judgment result of each reference point.
2. The pole piece detection method of claim 1, wherein judging whether burrs exist at a reference point according to information of adjacent pixel points of the reference point comprises:
acquiring the number of adjacent pixel points of the reference point;
when the number of the adjacent pixel points of the reference point is two, judging that no burr exists at the reference point; and when the number of the adjacent pixel points of the reference point is at least three, judging that burrs exist at the reference point.
3. The pole piece detection method of claim 2, wherein when the number of the adjacent pixel points of the reference point is three, two of the three adjacent pixel points of the reference point are located on the boundary, and the other one is located on the burr.
4. The pole piece detection method of claim 1, wherein extracting the boundary between the pole piece and the background comprises:
extracting edge points by adopting an edge operator;
connecting the edge points into a line, forming the boundary.
5. The pole piece detection method of claim 4, wherein the edge operator comprises at least one of a gradient operator, a Roberts operator, a Laplace operator, and a Sobel operator.
6. The pole piece inspection method of claim 1, wherein the image is acquired during pole piece transfer.
7. The pole piece detection method of claim 1, wherein the boundary comprises a first boundary line, a second boundary line and an end point, wherein the end point is an intersection of the first boundary line and the second boundary line;
when the reference point is an end point and a burr exists at the end point, pixel points which are adjacent to the end point and located on the burr and the end point are arranged along the second boundary line; or the arrangement direction of the pixel point adjacent to the end point and on the burr and the end point is intersected with the second boundary line.
8. The pole piece detection method of claim 7, wherein when the reference point is an end point and no burr is present at the end point, the pixel points adjacent to the end point are arranged in a triangular shape with respect to the end point.
9. A pole piece detection method is characterized by comprising the following steps:
acquiring images of the pole piece and the background;
extracting the boundary of the pole piece and the background;
selecting pixel points on the sections as reference points, and acquiring adjacent pixel points of the reference points;
determining whether burrs exist in the section where the reference point is located according to the information of the adjacent pixel points of the reference point;
wherein the boundary comprises a plurality of segments.
10. The pole piece detection method of claim 9, comprising:
and judging whether the boundary has burrs or not according to the judgment result of each section.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910916538.XA CN110706215A (en) | 2019-09-26 | 2019-09-26 | Pole piece detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910916538.XA CN110706215A (en) | 2019-09-26 | 2019-09-26 | Pole piece detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110706215A true CN110706215A (en) | 2020-01-17 |
Family
ID=69196424
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910916538.XA Pending CN110706215A (en) | 2019-09-26 | 2019-09-26 | Pole piece detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110706215A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109324061A (en) * | 2018-10-11 | 2019-02-12 | 广东德尔智慧工厂科技有限公司 | A kind of burr detection device and method of lithium battery pole slice |
| CN109754406A (en) * | 2019-03-15 | 2019-05-14 | 苏州杰锐思自动化设备有限公司 | Lithium battery pole slice burr detection device and method based on two-dimensional silhouette instrument |
| CN109886918A (en) * | 2019-01-14 | 2019-06-14 | 广州量子激光智能装备有限公司 | Wire drawing burr detection method, electronic equipment and the storage medium of lithium battery pole slice |
| CN110276747A (en) * | 2019-06-06 | 2019-09-24 | 中南大学 | A kind of insulator breakdown detection and failure ranking method based on image analysis |
-
2019
- 2019-09-26 CN CN201910916538.XA patent/CN110706215A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109324061A (en) * | 2018-10-11 | 2019-02-12 | 广东德尔智慧工厂科技有限公司 | A kind of burr detection device and method of lithium battery pole slice |
| CN109886918A (en) * | 2019-01-14 | 2019-06-14 | 广州量子激光智能装备有限公司 | Wire drawing burr detection method, electronic equipment and the storage medium of lithium battery pole slice |
| CN109754406A (en) * | 2019-03-15 | 2019-05-14 | 苏州杰锐思自动化设备有限公司 | Lithium battery pole slice burr detection device and method based on two-dimensional silhouette instrument |
| CN110276747A (en) * | 2019-06-06 | 2019-09-24 | 中南大学 | A kind of insulator breakdown detection and failure ranking method based on image analysis |
Non-Patent Citations (1)
| Title |
|---|
| 周湘辰: "基于机器视觉的锂离子电池极片瑕疵检测系统设计与研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9471057B2 (en) | Method and system for position control based on automated defect detection feedback | |
| CN107895362B (en) | Machine vision method for detecting quality of miniature wiring terminal | |
| TWI734888B (en) | Conveyor inspection system and conveying device | |
| US20210150700A1 (en) | Defect detection device and method | |
| CN109829911B (en) | PCB surface detection method based on contour out-of-tolerance algorithm | |
| WO2023126030A1 (en) | Switch interface integrity inspection method | |
| CN107066638B (en) | Position detection device, position detection method, information processing program, and recording medium | |
| CN114022503A (en) | Detection method, detection system, device and storage medium | |
| CN110146513A (en) | Method of determining defects and determining defects device | |
| WO2023109557A1 (en) | Connector inspection method, electronic device and storage medium | |
| CN112200790A (en) | Cloth defect detection method, device and medium | |
| JP4279833B2 (en) | Appearance inspection method and appearance inspection apparatus | |
| CN108107611B (en) | Self-adaptive defect detection method and device and electronic equipment | |
| JP2016517071A (en) | Improved analysis of wear evaluation of multi-shaft belt based on images | |
| JP5889778B2 (en) | Automatic unevenness detection apparatus and automatic unevenness detection method for flat panel display | |
| CN110706215A (en) | Pole piece detection method | |
| JP5299196B2 (en) | Marker detection device and program for marker detection device | |
| CN111353974A (en) | Method and device for detecting image boundary defects | |
| CN115147386A (en) | Defect detection method and device for U-shaped pipe and electronic equipment | |
| CN107004622B (en) | Defective product mark recognition device for matrix arrangement chip | |
| CN113012137B (en) | Panel defect inspection method, system, terminal device and storage medium | |
| JP2010071980A (en) | Fin extraction inspection method of heat exchanger | |
| WO2022246643A1 (en) | Image acquisition method and apparatus, and storage medium | |
| CN108303640B (en) | Line detection method and device | |
| JP6114559B2 (en) | Automatic unevenness detector for flat panel display |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200117 |