CN116228755B - Pole piece burr detection method and system - Google Patents
Pole piece burr detection method and system Download PDFInfo
- Publication number
- CN116228755B CN116228755B CN202310504422.1A CN202310504422A CN116228755B CN 116228755 B CN116228755 B CN 116228755B CN 202310504422 A CN202310504422 A CN 202310504422A CN 116228755 B CN116228755 B CN 116228755B
- Authority
- CN
- China
- Prior art keywords
- burr
- area
- pole piece
- defect
- peak
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 56
- 230000007547 defect Effects 0.000 claims abstract description 78
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 37
- 238000000034 method Methods 0.000 claims abstract description 24
- 238000005520 cutting process Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000003860 storage Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000010586 diagram Methods 0.000 claims description 8
- 238000003708 edge detection Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims description 2
- 238000012896 Statistical algorithm Methods 0.000 claims description 2
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 claims description 2
- 229910052782 aluminium Inorganic materials 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims 1
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 abstract description 4
- 229910001416 lithium ion Inorganic materials 0.000 abstract description 4
- 238000004519 manufacturing process Methods 0.000 abstract description 4
- 230000000007 visual effect Effects 0.000 abstract description 4
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 7
- 229910052744 lithium Inorganic materials 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000004880 explosion Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 241000251468 Actinopterygii Species 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000001681 protective effect Effects 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The embodiment of the application provides a pole piece burr detection method and a pole piece burr detection system, which are used for positioning the pole piece position by a graph cutting algorithm after a field pole piece graph is acquired, so that the accuracy and the speed of AI prediction are improved; after a cut picture is obtained, an AI algorithm is needed to detect all suspected burr defect areas with higher confidence; after the suspected burr defect area is obtained, the false judgment possibly caused by noise is performed, so that the method further judges the area by performing traditional algorithm processing on the area; the scheme based on the combination of the AI algorithm and the burr recognition algorithm improves the accuracy compared with the scheme only using the burr recognition algorithm or only using the AI algorithm, only the visual detection method replaces the manual work, eliminates the influence of subjective factors caused by individual differences, physical states and the like on defect judgment, and improves the safety and reliability of lithium ion battery production.
Description
Technical Field
The embodiment of the application relates to the technical field of battery detection, in particular to a pole piece burr detection method and system.
Background
The lithium battery pole piece is easy to generate burrs at the edge of the pole piece in the slitting process, and if the burrs are too large, a protective film between the positive pole piece and the negative pole piece is easy to puncture, so that internal short circuit of the battery is caused, and potential safety hazards such as fire explosion are caused.
The micron-sized burrs which can be clearly seen under a microscope between the positive plate and the negative plate of the lithium battery and the diaphragm are one of the main fierces for causing explosion and ignition of the lithium battery, so that whether the burrs are detected or not is one of important elements for safely using the battery. In the traditional procedure, the problem is solved by manually and periodically carrying out secondary element lower spot check on the burrs of the pole piece. Due to technical limitations, the fish with burrs as a net leakage is difficult to realize as a result of full detection, and the potential hazard of safe burying of lithium electricity is greatly overcome.
Disclosure of Invention
The embodiment of the application provides a pole piece burr detection method and a pole piece burr detection system, which aim to solve the problems that in the prior art, the labor intensity is high in manual measurement, the result is easy to produce manual misjudgment, the result that the burr is inevitably formed as a net-leaking fish, and great hidden danger is caused for the safe burying of lithium electricity is difficult to realize.
In a first aspect, an embodiment of the present application provides a method for detecting burrs of a pole piece, including:
acquiring a field pole piece image, identifying the pole piece position in the field pole piece image, and cutting to obtain a pole piece image;
performing burr defect recognition on the pole piece image based on a pre-trained AI detection model to obtain a burr recognition area;
denoising the burr identification area, searching for a peak based on a defect mask boundary of the burr identification area, and judging the burr identification area as a burr defect area if a mask variance is in a preset mask variance range if a peak mean value of the burr identification area is in a preset peak range.
Preferably, identifying the pole piece position in the field pole piece image and cutting to obtain a pole piece image, specifically comprising:
performing preliminary identification on the field pole piece graph based on a morphological self-adaptive threshold segmentation algorithm to obtain a burr initial positioning area;
performing free-form surface fitting treatment on the burr initial positioning area, and determining roundness, area, minimum height and minimum width so as to determine a burr fine positioning area based on the roundness, area, minimum height and minimum width;
and cutting out the pole piece image based on the burr fine positioning area.
Preferably, the morphology-based adaptive threshold segmentation algorithm performs preliminary identification on the field pole piece map to obtain a burr initial positioning area, and specifically comprises the following steps:
the field pole piece graph is segmented into black and white images based on a threshold segmentation algorithm, the black and white images are subjected to open operation, the open operation result is expanded to obtain a background area, and a foreground area is obtained through distance transformation to obtain a burr initial positioning area.
Preferably, the burr defect recognition is performed on the pole piece image based on a pre-trained AI detection model to obtain a burr recognition area, which specifically includes:
and after the AI detection model receives the pole piece images, calling a corresponding burr defect detection model, carrying out burr defect recognition based on the burr defect detection model, and outputting a region with the confidence coefficient detected in each pole piece image higher than a preset confidence coefficient threshold value as a burr recognition region.
Preferably, the method further includes the steps of:
and determining the area information of the burr identification area, wherein the area information comprises defect types, a defect mask coordinate set and a defect target detection frame.
Preferably, searching a wave crest based on a defect mask boundary of the burr identification area, wherein the method specifically comprises the following steps of;
determining a mask boundary range based on a mask coordinate set of the burr identification area, performing vertical projection on the burr identification area in the mask boundary range, and searching for a wave crest according to a preset slope and a preset step length.
In a second aspect, an embodiment of the present application provides a pole piece burr detection system, including:
the pole piece identification module is used for acquiring a field pole piece image, identifying the pole piece position in the field pole piece image and cutting to obtain the pole piece image;
the burr primary screening module is used for carrying out burr defect identification on the pole piece image based on a pre-trained AI detection model to obtain a burr identification area;
the burr determination module is used for carrying out denoising processing on the burr identification area, searching for a peak based on the defect mask boundary of the burr identification area, and judging the burr identification area as a burr defect area if the peak mean value of the burr identification area is in a preset peak range and the mask variance is in a preset mask variance range.
In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the steps of the pole piece burr detection method according to the embodiment of the first aspect of the present application when the processor executes the program.
In a fourth aspect, embodiments of the present application provide a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the pole piece burr detection method according to the embodiments of the first aspect of the present application.
According to the pole piece burr detection method and system provided by the embodiment of the application, after the field pole piece diagram is obtained, the pole piece position is required to be positioned by a diagram cutting algorithm, so that the AI prediction accuracy and speed are improved; after a cut picture is obtained, an AI algorithm is needed to detect all suspected burr defect areas with higher confidence; after the suspected burr defect area is obtained, misjudgment possibly caused by noise is performed, so that the area is further judged by performing traditional algorithm processing; the scheme based on the combination of the AI algorithm and the burr recognition algorithm improves the accuracy compared with the scheme only using the burr recognition algorithm or only using the AI algorithm, only the visual detection method replaces the manual work, eliminates the influence of subjective factors caused by individual differences, physical states and the like on defect judgment, and improves the safety and reliability of lithium ion battery production.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a pole piece burr detection method according to an embodiment of the application;
fig. 2 is a schematic structural diagram of an electronic device provided by the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the embodiment of the present application, the term "and/or" is merely an association relationship describing the association object, which indicates that three relationships may exist, for example, a and/or B may indicate: a exists alone, A and B exist together, and B exists alone.
The terms "first", "second" in embodiments of the application are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the application, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion. For example, a system, article, or apparatus that comprises a list of elements is not limited to only those elements or units listed but may alternatively include other elements not listed or inherent to such article, or apparatus. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The lithium battery pole piece is easy to generate burrs at the edge of the pole piece in the slitting process, and if the burrs are too large, a protective film between the positive pole piece and the negative pole piece is easy to puncture, so that internal short circuit of the battery is caused, and potential safety hazards such as fire explosion are caused. Traditional lithium battery pole piece burr detection needs to cut off the pole piece into the festival, uses the measuring instrument to carry out the spot check through the manual work, and spot check process is complicated, and is long, but manual measurement intensity of labour is big, and the result produces artificial erroneous judgement easily.
Therefore, the embodiment of the application provides the pole piece burr detection method and the system, which are based on the scheme of combining the AI algorithm and the burr recognition algorithm, and compared with the method which only uses the burr recognition algorithm or only uses the AI algorithm, the accuracy is improved, the visual detection method only replaces manpower, the influence of subjective factors caused by individual differences, physical states and the like on defect judgment by the manpower is eliminated, and the safety and the reliability of lithium ion battery production are improved. The pole piece burr detection method and system are described below with reference to the accompanying drawings.
Fig. 1 is a schematic diagram of a method for detecting burrs of a pole piece according to an embodiment of the present application, including:
acquiring a field pole piece image, identifying the pole piece position in the field pole piece image, and cutting to obtain a pole piece image;
in this embodiment, a morphology-based adaptive threshold segmentation algorithm performs preliminary identification on the field pole piece map to obtain a burr initial positioning area, including: after threshold segmentation, corrosion and expansion operation are carried out on the original image, the approximate position of the pole piece is found out, specifically: the field pole piece image is divided into a black-and-white image based on a threshold segmentation algorithm, the image is divided into a target object and a background, the black-and-white image is subjected to open operation, the open operation result is expanded to obtain a background area, and a foreground area is obtained through distance transformation to obtain a burr initial positioning area.
Performing free-form surface fitting treatment on the burr initial positioning area, determining burr fine positioning areas, such as roundness, area, minimum height, minimum width and the like, and accurately positioning pole piece areas after screening; the method comprises the following steps: edge detection is carried out on the area where the burr is initially positioned, the outline characteristics of the target area are extracted, a discrete point set is extracted according to the characteristics of the surface of the target object to serve as input data of curve fitting, fitting of the burr edge outline curve is achieved based on an NURBS free curve model and by using a weighted least square method, therefore, data such as roundness, area, minimum height and minimum width of the burr area are calculated, whether the data values are in a preset range or not is compared by a channel, and if the data values are in the preset range, the burr defect area of the pole piece is accurately positioned.
And cutting out the pole piece image based on the burr fine positioning area.
Performing burr defect recognition on the pole piece image based on a pre-trained AI detection model to obtain a burr recognition area; and after the AI detection model receives the pole piece images, calling a corresponding burr defect detection model, carrying out burr defect recognition based on the burr defect detection model, and outputting a region with the confidence coefficient detected in each pole piece image higher than a preset confidence coefficient threshold value as a burr recognition region. And determining the area information of the burr identification area, wherein the area information comprises defect types, a defect mask coordinate set and a defect target detection frame. The mask variance is obtained by calculating the mean value of the peaks of the identification area and the mean value of the preset peaks; the defect types of the AI detection model are classified into burrs, carbon powder, broken aluminum and the like, the defect types are found in the area information output by the AI detection model and are classified into the defect types of the burrs, and coordinate values of corresponding defect masks and rectangular frames of defect targets are found through names and indexes of the defect types of the burrs. And positioning the position of the burr defect through the mask coordinate value, determining the size of a target area of the burr defect according to the target rectangular frame of the defect, performing initial positioning on the target rectangular frame area of the defect by utilizing a self-adaptive threshold segmentation algorithm, performing free-form surface fitting treatment on the initial positioning area to perform fine positioning, and judging whether the identified burr area is the burr defect area by utilizing the mask crest mean value and the mask variance.
Denoising the burr identification area, searching for a peak based on a defect mask boundary of the burr identification area, and judging the burr identification area as a burr defect area if a mask variance is in a preset mask variance range if a peak mean value of the burr identification area is in a preset peak range. The specific algorithm steps are that denoising and binarization processing are carried out on the burr identification area, the peak position of the burr identification area is found through an edge detection algorithm, the local area where the peak of the burr identification area is located is extracted through morphological processing according to the peak position, the height of a curved surface is calculated to be the calculated average value through a statistical algorithm in the peak area, and the mask variance is calculated through the calculated average value. In the field process demand, the height of the burrs of the pole piece cannot exceed half of the thickness of the pole piece, the range of the preset wave peak is determined according to the thickness of the pole piece, and if the wave peak mean value of the burr identification area is larger than the preset wave peak mean value and the mask variance is in the preset mask variance range, the burr identification area is judged to be a burr defect area.
Determining a mask boundary range based on a mask coordinate set of the burr identification area, performing vertical projection on the burr identification area in the mask boundary range, and searching for a wave crest according to a preset slope and a preset step length.
The embodiment of the application also provides a pole piece burr detection system, which is based on the pole piece burr detection method in each embodiment, and comprises the following steps:
the pole piece identification module is used for acquiring a field pole piece image, identifying the pole piece position in the field pole piece image and cutting to obtain the pole piece image;
the burr primary screening module is used for carrying out burr defect identification on the pole piece image based on a pre-trained AI detection model to obtain a burr identification area;
the burr determination module is used for carrying out denoising processing on the burr identification area, searching for a peak based on the defect mask boundary of the burr identification area, and judging the burr identification area as a burr defect area if the peak mean value of the burr identification area is in a preset peak range and the mask variance is in a preset mask variance range.
Based on the same conception, fig. 2 illustrates a physical structure diagram of an electronic device, as shown in fig. 2, the electronic device may include: processor 310, communication interface (Communications Interface) 320, memory 330 and communication bus 340, wherein processor 310, communication interface 320, memory 330 accomplish communication with each other through communication bus 340. Processor 310 may invoke logic instructions in memory 330 to perform a pole piece spur detection method comprising:
acquiring a field pole piece image, identifying the pole piece position in the field pole piece image, and cutting to obtain a pole piece image;
performing burr defect recognition on the pole piece image based on a pre-trained AI detection model to obtain a burr recognition area;
denoising the burr identification area, searching for a peak based on a defect mask boundary of the burr identification area, and judging the burr identification area as a burr defect area if a mask variance is in a preset mask variance range if a peak mean value of the burr identification area is in a preset peak range.
Further, the logic instructions in the memory 330 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Based on the same conception, the embodiments of the present application also provide a non-transitory computer readable storage medium storing a computer program, the computer program containing at least one piece of code executable by a master control device to control the master control device to implement the steps of the pole piece burr detection method according to the above embodiments. Examples include:
acquiring a field pole piece image, identifying the pole piece position in the field pole piece image, and cutting to obtain a pole piece image;
performing burr defect recognition on the pole piece image based on a pre-trained AI detection model to obtain a burr recognition area;
denoising the burr identification area, searching for a peak based on a defect mask boundary of the burr identification area, and judging the burr identification area as a burr defect area if a mask variance is in a preset mask variance range if a peak mean value of the burr identification area is in a preset peak range.
Based on the same technical concept, the embodiment of the present application also provides a computer program, which is used to implement the above-mentioned method embodiment when the computer program is executed by the master control device.
The program may be stored in whole or in part on a storage medium that is packaged with the processor, or in part or in whole on a memory that is not packaged with the processor.
Based on the same technical concept, the embodiment of the application also provides a processor, which is used for realizing the embodiment of the method. The processor may be a chip.
In summary, according to the pole piece burr detection method and system provided by the embodiment of the application, after the field pole piece diagram is obtained, the pole piece position is required to be positioned by a graph cutting algorithm, so that the accuracy and the speed of AI prediction are improved; after a cut picture is obtained, an AI algorithm is needed to detect all suspected burr defect areas with higher confidence; after the suspected burr defect area is obtained, the area needs to be processed by the traditional algorithm to further judge because of misjudgment caused by noise; the scheme based on the combination of the AI algorithm and the burr recognition algorithm improves the accuracy compared with the scheme only using the burr recognition algorithm or only using the AI algorithm, only the visual detection method replaces the manual work, eliminates the influence of subjective factors caused by individual differences, physical states and the like on defect judgment, and improves the safety and reliability of lithium ion battery production.
The embodiments of the present application may be arbitrarily combined to achieve different technical effects.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions in accordance with the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital subscriber line), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk), etc.
Those of ordinary skill in the art will appreciate that implementing all or part of the above-described method embodiments may be accomplished by a computer program to instruct related hardware, the program may be stored in a computer readable storage medium, and the program may include the above-described method embodiments when executed. And the aforementioned storage medium includes: ROM or random access memory RAM, magnetic or optical disk, etc.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (4)
1. The pole piece burr detection method is characterized by comprising the following steps of:
s1, acquiring a field pole piece diagram, identifying the pole piece position in the field pole piece diagram and cutting to obtain a pole piece image, wherein the method specifically comprises the following steps of:
the on-site pole piece image is initially identified by a morphology-based self-adaptive threshold segmentation algorithm to obtain a burr initial positioning area, which is specifically as follows: dividing the field pole piece graph into black and white images based on a threshold segmentation algorithm, performing open operation on the black and white images, expanding the open operation result to obtain a background area, and obtaining a foreground area through distance transformation to obtain a burr initial positioning area;
performing free-form surface fitting treatment on the burr initial positioning area, determining roundness, area, minimum height and minimum width, and determining a burr fine positioning area according to the roundness, area, minimum height and minimum width, wherein the method specifically comprises the following steps: edge detection is carried out on the area where the burr is initially positioned, the outline characteristics of the target area are extracted, a discrete point set is extracted according to the characteristics of the surface of the target object to serve as input data of curve fitting, fitting of a burr edge outline curve is achieved based on a NURBS free curve model and by using a weighted least square method, roundness-like, area, minimum height and minimum width data of the burr area are calculated, whether the data value is in a preset range or not is compared, and if the data value is in the preset range, the burr defect area of the pole piece is accurately positioned;
cutting to obtain a pole piece image based on the burr fine positioning area;
s2, performing burr defect recognition on the pole piece image based on a pre-trained AI detection model to obtain a burr recognition area, wherein the method specifically comprises the following steps:
after the AI detection model receives the pole piece images, calling a corresponding burr defect detection model, carrying out burr defect recognition based on the burr defect detection model, and outputting a region with the confidence coefficient higher than a preset confidence coefficient threshold value detected in each pole piece image as a burr recognition region;
determining the area information of the burr identification area, wherein the area information comprises defect types, a defect mask coordinate set and a defect target detection frame;
the defect types of the AI detection model are divided into burrs, carbon powder and broken aluminum, the defect types of the burrs are found in the area information output by the AI detection model, and coordinate values of corresponding defect masks and rectangular frames of defect targets are found through names and indexes of the burr defect types;
positioning the position of the burr defect through mask coordinate values, determining the size of a target area of the burr defect according to the target rectangular frame of the defect, performing initial positioning on the target rectangular frame area of the defect by utilizing a self-adaptive threshold segmentation algorithm, and performing free-form surface fitting treatment on the initial positioning area to perform fine positioning;
s3, denoising the burr identification area, searching for a peak based on a defect mask boundary of the burr identification area, and judging that the burr identification area is a burr defect area if a mask variance is in a preset mask variance range if a peak mean value of the burr identification area is in a preset peak range, wherein the method specifically comprises the following steps of:
denoising and binarizing the burr identification area;
determining a mask boundary range based on a mask coordinate set of the burr identification area, performing vertical projection on the burr identification area in the mask boundary range, and searching for a wave crest according to a preset slope and a preset step length;
determining a preset wave crest range according to the thickness of the pole piece;
finding the peak position of the burr identification area through an edge detection algorithm, extracting a local area where the peak of the burr identification area is located through morphological processing according to the peak position, calculating the height of a curved surface in the peak area through a statistical algorithm to obtain the mean value of the calculated peak, and calculating the mask variance through the calculated mean value, wherein the mask variance is a variance obtained through calculation of the mean value of the peak of the identification area and the mean value of a preset peak;
if the peak mean value of the burr identification area is larger than the preset peak mean value, and the mask variance is in the preset mask variance range, judging that the burr identification area is a burr defect area.
2. A pole piece burr detection system, characterized in that the system is applied to the pole piece burr detection method of claim 1, the system comprising:
the pole piece identification module is used for acquiring a field pole piece image, identifying the pole piece position in the field pole piece image and cutting to obtain the pole piece image;
the burr primary screening module is used for carrying out burr defect identification on the pole piece image based on a pre-trained AI detection model to obtain a burr identification area;
the burr determination module is used for carrying out denoising processing on the burr identification area, searching for a peak based on the defect mask boundary of the burr identification area, and judging the burr identification area as a burr defect area if the peak mean value of the burr identification area is in a preset peak range and the mask variance is in a preset mask variance range.
3. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor performs the steps of the pole piece burr detection method of claim 1 when the program is executed.
4. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the pole piece spur detection method according to claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310504422.1A CN116228755B (en) | 2023-05-08 | 2023-05-08 | Pole piece burr detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310504422.1A CN116228755B (en) | 2023-05-08 | 2023-05-08 | Pole piece burr detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116228755A CN116228755A (en) | 2023-06-06 |
| CN116228755B true CN116228755B (en) | 2023-10-20 |
Family
ID=86569829
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310504422.1A Active CN116228755B (en) | 2023-05-08 | 2023-05-08 | Pole piece burr detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116228755B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116503384B (en) * | 2023-06-21 | 2023-12-29 | 惠州市金思维科技有限公司 | Method and system for rapidly extracting lead screw defect area based on computer vision |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086780A (en) * | 2018-08-10 | 2018-12-25 | 北京百度网讯科技有限公司 | Method and apparatus for detecting electrode piece burr |
| CN113313713A (en) * | 2021-08-02 | 2021-08-27 | 南京帝感智能科技有限公司 | Method and system for online detection of burrs of lithium battery pole piece |
| CN115456955A (en) * | 2022-08-19 | 2022-12-09 | 燕山大学 | Method for detecting internal burr defect of ball cage dust cover |
-
2023
- 2023-05-08 CN CN202310504422.1A patent/CN116228755B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086780A (en) * | 2018-08-10 | 2018-12-25 | 北京百度网讯科技有限公司 | Method and apparatus for detecting electrode piece burr |
| CN113313713A (en) * | 2021-08-02 | 2021-08-27 | 南京帝感智能科技有限公司 | Method and system for online detection of burrs of lithium battery pole piece |
| CN115456955A (en) * | 2022-08-19 | 2022-12-09 | 燕山大学 | Method for detecting internal burr defect of ball cage dust cover |
Non-Patent Citations (2)
| Title |
|---|
| 电机铜排表面毛刺缺陷检测技术研究;范剑英;刘力源;赵首博;仪器仪表学报(第03期);全文 * |
| 范剑英 ; 刘力源 ; 赵首博.电机铜排表面毛刺缺陷检测技术研究.仪器仪表学报.2019,(第03期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116228755A (en) | 2023-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112001902A (en) | Defect detection method and related device, equipment and storage medium | |
| CN108009544B (en) | Target detection method and device | |
| CN110047095B (en) | Tracking method and device based on target detection and terminal equipment | |
| CN116228755B (en) | Pole piece burr detection method and system | |
| CN110796646A (en) | Method and device for detecting defects of screen area of electronic device | |
| CN115880248A (en) | Surface scratch defect identification method and visual detection equipment | |
| CN111862013A (en) | Insulator detection method, device and equipment based on deep convolutional neural network | |
| CN114964650B (en) | Gas leakage alarm method and device based on acoustic imaging | |
| CN111797726A (en) | Flame detection method and device, electronic equipment and storage medium | |
| CN115526885A (en) | Product image defect detection method, system, device and medium | |
| CN114004788A (en) | Defect detection method, device, equipment and storage medium | |
| CN113496215A (en) | Method and device for detecting human face of living body and electronic equipment | |
| CN109308264B (en) | Method for evaluating data desensitization effect, corresponding device and storage medium | |
| CN111783648A (en) | Method and device for extracting guardrail in road point cloud | |
| WO2022247684A1 (en) | Detection method and system for base-station feeder line, and related apparatus | |
| CN115713620A (en) | Infrared small target detection method and device, computing equipment and storage medium | |
| CN111046878B (en) | Data processing method and device, computer storage medium and computer | |
| CN114863330A (en) | Target object detection method, system and computer storage medium | |
| CN115100546A (en) | Mobile-based small target defect identification method and system for power equipment | |
| CN110853059B (en) | Image identification method for target ring number | |
| CN113340352A (en) | Valve hall monitoring method, device and system | |
| CN107122728B (en) | Building method is detected in SAR image based on evidence theory algorithm | |
| CN118037719B (en) | Product defect detection method, device and storage medium | |
| CN114078140B (en) | Landslide track extraction method based on landslide boundary polygons and slope map | |
| CN111609324B (en) | Pipeline leakage detection method and device |
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 |