CN116758064B - Lithium battery diaphragm quality detection method based on electron scanning microscope - Google Patents
Lithium battery diaphragm quality detection method based on electron scanning microscope Download PDFInfo
- Publication number
- CN116758064B CN116758064B CN202311013120.0A CN202311013120A CN116758064B CN 116758064 B CN116758064 B CN 116758064B CN 202311013120 A CN202311013120 A CN 202311013120A CN 116758064 B CN116758064 B CN 116758064B
- Authority
- CN
- China
- Prior art keywords
- diaphragm
- pixel block
- super pixel
- super
- representing
- 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
- 229910052744 lithium Inorganic materials 0.000 title claims abstract description 48
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 title claims abstract description 46
- 238000001514 detection method Methods 0.000 title claims abstract description 33
- 238000013441 quality evaluation Methods 0.000 claims abstract description 54
- 230000007547 defect Effects 0.000 claims abstract description 51
- 238000000034 method Methods 0.000 claims abstract description 43
- 238000011156 evaluation Methods 0.000 claims abstract description 12
- 238000005259 measurement Methods 0.000 claims description 35
- 230000005856 abnormality Effects 0.000 claims description 17
- 239000012528 membrane Substances 0.000 claims description 16
- 230000011218 segmentation Effects 0.000 claims description 15
- 238000012797 qualification Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 6
- 238000003708 edge detection Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 abstract description 5
- 238000004519 manufacturing process Methods 0.000 abstract description 4
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 7
- 229910001416 lithium ion Inorganic materials 0.000 description 7
- 238000009826 distribution Methods 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000001788 irregular Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000001303 quality assessment method Methods 0.000 description 3
- 238000012163 sequencing technique Methods 0.000 description 3
- 239000000243 solution Substances 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 229910000733 Li alloy Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 210000001787 dendrite Anatomy 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 239000003792 electrolyte Substances 0.000 description 1
- 239000008151 electrolyte solution Substances 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003301 hydrolyzing effect Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 239000001989 lithium alloy Substances 0.000 description 1
- 239000007773 negative electrode material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 229920006254 polymer film Polymers 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 239000007774 positive electrode material Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000000452 restraining effect Effects 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
- G01N23/22—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material
- G01N23/225—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material using electron or ion
- G01N23/2251—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material using electron or ion using incident electron beams, e.g. scanning electron microscopy [SEM]
-
- 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
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- 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
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2223/00—Investigating materials by wave or particle radiation
- G01N2223/40—Imaging
- G01N2223/401—Imaging image processing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2223/00—Investigating materials by wave or particle radiation
- G01N2223/60—Specific applications or type of materials
- G01N2223/61—Specific applications or type of materials thin films, coatings
-
- 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
-
- 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)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Chemical & Material Sciences (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Image Processing (AREA)
Abstract
The application provides a lithium battery diaphragm quality detection method based on an electron scanning microscope, which comprises the following steps: dividing the acquired diaphragm gray level image of the battery diaphragm to obtain a plurality of super pixel blocks; determining whether the super pixel block is a suspected defect area or not based on the local characteristic information and the global characteristic information of the super pixel block; determining a quality evaluation chart of the corresponding diaphragm gray level image based on the characteristic information of the pixel points contained in each suspected defect area and the local characteristic information of the corresponding super pixel block; and determining a quality detection result of the battery diaphragm based on the quality evaluation graph of the diaphragm gray level image. The method eliminates the influence of strong and weak textures on the accuracy of the hole area depth evaluation result caused by different stretching degrees in the process of manufacturing the diaphragm; further, the phenomenon that pixel points in a smaller hole area in the diaphragm gray level image are misjudged to be in a super pixel block corresponding to a non-suspected defect area is prevented from occurring, and the accuracy of a quality detection result of the battery diaphragm is improved.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to a lithium battery diaphragm quality detection method based on an electron scanning microscope.
Background
The lithium battery is a battery using a non-hydrolytic electrolyte solution and mainly comprises two major types of lithium metal batteries and lithium ion batteries, wherein lithium metal or lithium alloy is used as a positive electrode material and a negative electrode material. Lithium batteries are typically composed of electrode plates, a separator, a cell casing plate, an IC safety protection circuit, an electrolyte, an external battery package, and the like, wherein the separator is located in a region between the positive and negative electrode plates.
The lithium battery diaphragm is a polymer film with a micropore structure, and can allow lithium ions to pass through and inhibit electrons from passing through. The quality and performance of the diaphragm determine the interface structure, internal resistance and the like of the battery, directly influence the capacity, circulation, safety performance and other characteristics of the battery, and the diaphragm with excellent performance plays an important role in improving the comprehensive performance of the battery. The quality inspection of the diaphragm basically comprises the detection of permeability, the detection of physical properties, the detection of thickness and the like, and the quality inspection of the lithium battery diaphragm at the present stage is mainly carried out by a professional instrument, so that the requirement of large-scale rapid detection is difficult to meet, the detection cost is high, for example, the diaphragm is easily influenced by the pore structure of the diaphragm when the thickness is detected by a thickness meter, and the measurement of average thickness is not facilitated; when the porosity of the diaphragm is detected by a washing liquid method, the diaphragm is greatly influenced by experimental environment, and multiple detection experiments are needed. In contrast, when the image segmentation method or the image clustering method is used for acquiring the lithium battery diaphragm image for the electronic scanning microscope, the lithium battery diaphragm image in different states needs to be acquired, and the traditional image clustering method is difficult to accurately detect the quality of the lithium battery diaphragm in a plurality of states.
Disclosure of Invention
The invention mainly solves the technical problem of providing a lithium battery diaphragm quality detection method based on an electron scanning microscope, and solves the problem of poor accuracy of a lithium battery diaphragm quality detection result in the prior art.
In order to solve the technical problems, the invention adopts the following technical scheme: the lithium battery diaphragm quality detection method based on the electron scanning microscope comprises the following steps: dividing the acquired diaphragm gray level image of the battery diaphragm to obtain a plurality of super pixel blocks; the diaphragm gray level image is a surface gray level image of a battery diaphragm containing holes, and each super pixel block has corresponding local characteristic information and global characteristic information; determining whether the super pixel block is a suspected defect area or not based on the local characteristic information and the global characteristic information of the super pixel block; determining a quality evaluation chart of the corresponding diaphragm gray level image based on the characteristic information of the pixel points contained in each suspected defect area and the local characteristic information of the corresponding super pixel block; and determining a quality detection result of the battery diaphragm based on the quality evaluation graph of the diaphragm gray level image.
Dividing the acquired diaphragm gray level image of the battery diaphragm to obtain a plurality of super pixel blocks, wherein the method comprises the following steps: obtaining a diaphragm gray image of a battery diaphragm through an electron scanning microscope; edge detection is carried out on the diaphragm gray level image to obtain edge information, wherein the edge information comprises hole edge pixel points and gradient amplitude values and gradient directions corresponding to the hole edge pixel points; and dividing the diaphragm gray level image based on the edge information to obtain a plurality of super pixel blocks corresponding to the diaphragm gray level image.
Wherein determining whether the super pixel block is a suspected defect region based on the local feature information and the global feature information of the super pixel block comprises: determining the hole depth spread of the super pixel block based on the local characteristic information and the global characteristic information of the super pixel block; determining a segmentation threshold based on the hole depth spread of all super pixel blocks corresponding to the diaphragm gray level image; and comparing the hole depth spread of each super pixel block with a segmentation threshold value respectively, and determining whether the super pixel block is a suspected defect area or not.
Comparing the hole depth spread of each super pixel block with a segmentation threshold value respectively, and determining whether the super pixel block is a suspected defect area or not comprises the following steps: determining that the super pixel block is a suspected defect area in response to the hole depth spread of the super pixel block being greater than the segmentation threshold; and determining the super pixel block as a non-defect area in response to the hole depth spread of the super pixel block not being greater than the segmentation threshold.
The local characteristic information comprises gradient amplitude, gradient direction and gray level; the global feature information comprises feature information corresponding to each super pixel block; determining the hole depth spread of the super pixel block based on the local feature information and the global feature information of the super pixel block comprises: determining amplitude deviation, texture deviation and gray level deviation corresponding to the super pixel block based on the gradient amplitude, gradient direction and gray level corresponding to the super pixel block;
Determining the hole depth spread of the super pixel block based on the amplitude deviation, texture deviation, gray scale deviation and the similarity between the super pixel block and other super pixel blocks corresponding to the super pixel block by the following formula ；
；
；
Wherein: Representing the aperture depth spread of the a-th super pixel block; /(I) Representing the amplitude deviation of the a-th super pixel block; Representing texture deviation of the a-th super pixel block; /(I) Representing the gray scale deviation of the a-th super pixel block; /(I)Representing the similarity of the a-th super pixel block and the b-th super pixel block; k represents the number of super pixel blocks corresponding to the diaphragm gray level image; /(I)Representing a metric distance sequence of an a-th super pixel block; /(I)Representing a metric distance sequence of the b-th super pixel block; Representation/> And/>Pearson correlation coefficient therebetween.
The method for determining the amplitude deviation, the texture deviation and the gray level deviation corresponding to the super pixel block based on the gradient amplitude, the gradient direction and the gray level corresponding to the super pixel block comprises the following steps: determining entropy weights corresponding to three dimensions of gradient amplitude, gradient direction and gray level corresponding to the super pixel blocks by using an entropy weight method;
Determining a gray scale deviation of the super pixel block based on the gray scale of the super pixel block and the entropy weight of the gray scale by the following formula ；
；
Wherein: Representing the gray scale deviation of the a-th super pixel block; /(I) Information entropy representing gray values in the a-th super pixel block; /(I)Entropy weight representing gray level of the a-th super pixel block; /(I)、/>Representing the maximum value and the minimum value of entropy weights of gray levels corresponding to all super pixel blocks in the diaphragm gray level image; /(I)Representing a first scaling factor;
Determining the amplitude deviation of the super pixel block based on the gradient amplitude of the super pixel block and the entropy weight of the gradient amplitude by the following formula ；
；
Wherein: representing the amplitude deviation of the a-th super pixel block; /(I) Information entropy representing gradient amplitude in the a-th super pixel block; /(I)Entropy weight representing gradient magnitude of the a-th super pixel block; /(I)、/>Representing the maximum value and the minimum value of entropy weights of gradient amplitudes corresponding to all super pixel blocks in the diaphragm gray level image; /(I)Representing a second scaling factor;
determining texture deviation of the super pixel block based on the gradient direction of the super pixel block and entropy weight of the gradient direction by the following formula ；
；
Wherein: Representing texture deviation of the a-th super pixel block; /(I) Information entropy representing gradient amplitude in the a-th super pixel block; /(I)Entropy weight representing gradient direction of the a-th super pixel block; /(I)、/>Representing the maximum value and the minimum value of entropy weights of all super pixel blocks in the diaphragm gray level image in the gradient direction; /(I)Representing a third scaling factor.
The characteristic information of the pixel points comprises the degree level of the pixel points; based on the characteristic information of the pixel points contained in each suspected defect area and the local characteristic information of the corresponding super pixel block, determining a quality evaluation chart of the corresponding diaphragm gray level image, wherein the quality evaluation chart comprises the following steps: traversing a super pixel block corresponding to the suspected defect area, and determining a measurement level sequence of the pixel points based on the measurement level of the pixel points in the super pixel block and the measurement level of the adjacent pixel points; determining an abnormality index of the pixel point based on the measurement level sequence of the pixel point and the measurement level sequences of the adjacent pixel points; determining a saliency index of the pixel point based on the gray value of the pixel point and the gray values of the adjacent pixel points; determining a diaphragm quality index of the pixel point based on the saliency index of the pixel point and the abnormality index of the pixel point; determining a quality evaluation index of the pixel point based on the minimum diaphragm quality index in the super pixel block to which the pixel point belongs; and determining a quality evaluation graph corresponding to the diaphragm gray level image based on the quality evaluation indexes of all pixel points in the super pixel block corresponding to the suspected defect area.
Wherein determining the abnormality index of the pixel based on the metric sequence of the pixel and the metric sequence of its neighboring pixels comprises:
calculating to obtain the abnormality index of the pixel point based on the following formula ；
；
Wherein: An abnormality index indicating an i-th pixel point; /(I) Representing the number of pixel points in a local window corresponding to the pixel points; j. j+1 represents the jth and the jth+1th pixel points in the local window respectively; /(I)Representing the longest common subsequence between the metric level sequence corresponding to the jth pixel point and the metric level sequence corresponding to the ith pixel point; /(I)Representing the longest common subsequence between the metric level sequence corresponding to the j+1th pixel point and the metric level sequence corresponding to the i pixel point; Representing the longest common subsequence/> And longest common subsequence/>Similarity between;
Determining a saliency index of a pixel based on a gray value of the pixel and gray values of neighboring pixels, comprising:
the saliency index of the pixel point is calculated based on the following formula ；
；
Wherein: A saliency index representing the ith pixel point; /(I) Information entropy representing gray values of all pixel points in a local window corresponding to the ith pixel point; /(I)An average value of information entropy representing gray values of pixel points in the super pixel block to which the ith pixel point belongs; /(I)Entropy weight representing gray level of super pixel block to which ith pixel point belongs;
Determining a diaphragm quality index of the pixel based on the saliency index of the pixel and the anomaly index of the pixel, comprising:
calculating to obtain diaphragm quality index of pixel point based on the following formula ；
；
Wherein: representing the membrane quality index of the ith pixel point; /(I) A saliency index representing the ith pixel point; /(I)An abnormality index indicating an i-th pixel point;
Determining a quality assessment index of a pixel point based on a membrane quality index of the pixel point and a minimum membrane quality index in a super pixel block to which the pixel point belongs, comprising:
the quality evaluation index of the pixel point is calculated based on the following formula ；
；
Wherein: A quality assessment index representing an i-th pixel; /(I) Representing a minimum membrane quality index in the super pixel block; /(I)Representing the membrane quality index of the i-th pixel.
The method for determining the quality evaluation graph corresponding to the diaphragm gray level image based on the quality evaluation indexes of all pixel points in the super pixel block corresponding to the suspected defect area comprises the following steps: determining a quality evaluation graph corresponding to the diaphragm gray level image based on the quality evaluation indexes of the pixel points in each super pixel block corresponding to the non-defect area and the quality evaluation indexes of the pixel points in each super pixel block corresponding to the suspected defect area; wherein, the quality evaluation index of the pixel points in each super pixel block corresponding to the non-defect area is 1.
Wherein, based on the quality evaluation graph of the diaphragm gray level image, the quality detection result of the battery diaphragm is determined, comprising: performing image matching on the quality evaluation graph of the diaphragm gray level image and a preset evaluation graph, and determining a matching result; the matching result comprises the number and position information of unmatched pixel points; the unmatched pixel points are the pixel points which are unmatched with a preset evaluation chart in the diaphragm gray level chart; determining the quality qualification rate based on the total number of the matched pixel points in the diaphragm gray level image and the total number of all the pixel points in the diaphragm gray level image; the total number of the matched pixel points is the difference value between the total number of all the pixel points in the diaphragm gray level image and the number of the unmatched pixel points; and taking the quality qualification rate and the position information of the unmatched pixel points in the diaphragm gray level image as quality detection results.
The beneficial effects of the application are as follows: different from the condition of the prior art, the provided lithium battery diaphragm quality detection method based on the electron scanning microscope comprises the following steps: dividing the acquired diaphragm gray level image of the battery diaphragm to obtain a plurality of super pixel blocks; the diaphragm gray level image is a surface gray level image of a battery diaphragm containing holes, and each super pixel block has corresponding local characteristic information and global characteristic information; determining whether the super pixel block is a suspected defect area or not based on the local characteristic information and the global characteristic information of the super pixel block; determining a quality evaluation chart of the corresponding diaphragm gray level image based on the characteristic information of the pixel points contained in each suspected defect area and the local characteristic information of the corresponding super pixel block; and determining a quality detection result of the battery diaphragm based on the quality evaluation graph of the diaphragm gray level image. According to the method, whether the super pixel blocks are suspected defect areas or not is determined through the local characteristic information and the global characteristic information of the super pixel blocks corresponding to the diaphragm gray level image of the battery diaphragm, and the influence of strong and weak textures on the accuracy of the depth evaluation result of the hole area caused by different stretching degrees in the diaphragm manufacturing process is eliminated; the quality evaluation graph of the diaphragm gray image is determined through the characteristic information of the pixel points and the local characteristic information of the corresponding super pixel blocks, so that the phenomenon that the pixel points in the small hole area in the diaphragm gray image are misjudged to be in the super pixel blocks corresponding to the non-suspected defect area can be prevented, and the accuracy of the quality detection result of the battery diaphragm is further improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an embodiment of a method for detecting the quality of a lithium battery diaphragm based on an electron scanning microscope;
FIG. 2 is a flowchart of a specific embodiment of step S1 in the method for detecting the quality of a lithium battery separator based on an electron scanning microscope provided in FIG. 1;
FIG. 3 is a flowchart of a step S2 of the method for detecting the quality of a lithium battery separator based on an electron scanning microscope according to an embodiment of the present invention;
FIG. 4 is a flowchart of a step S21 of the method for detecting the quality of a lithium battery separator based on an electron scanning microscope according to an embodiment of the present invention;
Fig. 5 is a flowchart of a specific embodiment of step S3 in the method for detecting quality of a lithium battery separator based on the electron scanning microscope provided in fig. 1.
Detailed Description
The following describes embodiments of the present application in detail with reference to the drawings.
In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, interfaces, techniques, etc., in order to provide a thorough understanding of the present application.
The term "and/or" is herein merely an association relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship. Further, "a plurality" herein means two or more than two.
In order to enable those skilled in the art to better understand the technical scheme of the invention, the following describes in further detail a linkage zooming method provided by the invention with reference to the accompanying drawings and the specific embodiments.
An important function of lithium battery diaphragm is for lithium ion provides the passageway of transmission, and lithium ion diffuses between positive and negative pole through the hole on the lithium battery diaphragm, and the size of hole is more even, and the transmission passageway that provides for lithium ion is more even, and in addition, the degree of depth of hole is more even, and the electric field on lithium battery diaphragm surface is more even, can play the growth of restraining lithium dendrite to a certain extent. Therefore, the invention considers the quality of the lithium battery diaphragm to be measured through the uniformity and the depth of the holes on the lithium battery diaphragm.
Referring to fig. 1, fig. 1 is a flow chart of an embodiment of a method for detecting quality of a lithium battery separator based on an electron scanning microscope according to the present invention.
In this embodiment, a method for detecting quality of a lithium battery diaphragm based on an electronic scanning microscope is provided, and the method embodiment provided in the embodiment of the application can be executed in a mobile terminal, a computer terminal or a similar computing device. The lithium battery diaphragm quality detection method based on the electron scanning microscope comprises the following steps.
S1: dividing the acquired diaphragm gray level image of the battery diaphragm to obtain a plurality of super pixel blocks; the diaphragm gray level image is a surface gray level image of a battery diaphragm containing holes, and each super pixel block is provided with corresponding local characteristic information and global characteristic information.
S2: and determining whether the super pixel block is a suspected defect area based on the local characteristic information and the global characteristic information of the super pixel block.
S3: and determining a quality evaluation chart of the corresponding diaphragm gray level image based on the characteristic information of the pixel points contained in each suspected defect area and the local characteristic information of the corresponding super pixel block.
S4: and determining a quality detection result of the battery diaphragm based on the quality evaluation graph of the diaphragm gray level image.
The battery separator in this embodiment will be described in detail taking a lithium battery separator as an example.
Specifically, the specific embodiment of obtaining the plurality of super pixel blocks in step S1 is as follows.
Referring to fig. 2, fig. 2 is a flowchart of a specific embodiment of step S1 in the method for detecting quality of a lithium battery separator based on the electron scanning microscope provided in fig. 1.
S11: and obtaining a diaphragm gray-scale image of the battery diaphragm through an electron scanning microscope.
In a specific embodiment, according to the size of the lithium battery diaphragm and the size of the hole, a scanning electron microscope is used to acquire a surface image of the lithium battery diaphragm in the current state, and the acquired image is a diaphragm gray image.
In another embodiment, the membrane gray scale image may be pre-processed in order to eliminate noise interference during image acquisition and improve the quality of the acquired image. Wherein the preprocessing includes denoising processing. For example, the membrane gray scale image is preprocessed using a bilateral filtering denoising method.
Because the lithium battery diaphragm is formed in the preparation process, for example, in the dry method and the wet method, the porous structure on the lithium battery diaphragm is generated through the stretching step, the thickness of the lithium battery diaphragm may be uneven in the stretching process, the distribution of gray values in different hole areas reflected in the gray image of the diaphragm may be different, the larger the hole depth is, and the higher the gray value of the pixel point in the hole area is. The larger the hole depth is, the more the shape of the hole accords with the standard, the more lithium ions are transmitted, and the similarity of pixel points in the hole area is larger. If the hole depth is shallow and the hole gap is small, the hole is in a closed state to a certain extent on the diaphragm gray scale image.
S12: and performing edge detection on the diaphragm gray level image to obtain edge information. The edge information comprises a hole edge pixel point, and a gradient amplitude value and a gradient direction corresponding to the hole edge pixel point.
Specifically, edge detection is carried out on the diaphragm gray level image by using a canny edge detection algorithm, so that hole edge pixel points in the diaphragm gray level image are obtained. The hole edge pixel points in the diaphragm gray level image form a hole edge line.
And calculating the gradient amplitude and gradient direction of each hole edge pixel point by adopting a Sobel operator.
S13: and dividing the diaphragm gray level image based on the edge information to obtain a plurality of super pixel blocks corresponding to the diaphragm gray level image.
Specifically, a simple linear iterative clustering (SIMPLE LINEAR ITERATIVE Clustering, SLIC) algorithm is adopted to segment the diaphragm gray level image based on the edge information corresponding to the diaphragm gray level image, so as to obtain a plurality of super-pixel blocks corresponding to the diaphragm gray level image.
In a specific embodiment, the measurement distance in the clustering process of the SLIC algorithm is composed of a gray level difference value and a Euclidean distance between two pixel points, a diaphragm gray level image is divided into K super pixel blocks, and the size of K is taken as a tested value of 100, and can be set according to actual conditions.
Specifically, the specific embodiment of determining whether the super pixel block is a suspected defective area in step S2 is as follows.
Referring to fig. 3, fig. 3 is a flowchart of a step S2 in the method for detecting quality of a lithium battery separator based on the electron scanning microscope provided in fig. 1 according to an embodiment.
S21: and determining the hole depth spread of the super pixel block based on the local characteristic information and the global characteristic information of the super pixel block.
In this embodiment, the local feature information includes gradient magnitude, gradient direction, and gray level; the global feature information includes feature information corresponding between the super pixel block and each other super pixel block.
In this embodiment, the gray value of each pixel point in the super pixel block is counted, and the range of the gray value of the pixel point in the super pixel block is determined. And determining the gray level corresponding to the super pixel block based on the gray value of each pixel point in the super pixel block. Gray scale is a number of levels that are divided into logarithmic relationships between white and black.
And determining the gradient amplitude of the super pixel block according to the gradient amplitude of the pixel points at the edge of each hole in the super pixel block. Specifically, the gradient amplitude of each hole edge pixel point in the super pixel block can be averaged to obtain the gradient amplitude corresponding to the super pixel block.
And determining the gradient direction of the super pixel block according to the gradient direction of the pixel points at the edge of each hole in the super pixel block. Specifically, the gradient directions of the pixel points at the edge of each hole in the super pixel block can be averaged to obtain the gradient direction corresponding to the super pixel block.
Based on the above embodiment, three dimensions of gradient amplitude, gradient direction and gray level information are extracted in each super pixel block.
The feature information corresponding to the super pixel blocks and other super pixel blocks comprises the similarity corresponding to the super pixel blocks and other super pixel blocks.
If the image information in a super-pixel block is similar to the image information in the diaphragm gray level image, and the image information distribution difference in the super-pixel block is very small, the probability that the super-pixel block contains the pixel points in the deep hole area is larger.
Referring to fig. 4, fig. 4 is a flowchart of a step S21 of the method for detecting quality of a lithium battery separator based on the electron scanning microscope provided in fig. 3.
S211: and determining amplitude deviation, texture deviation and gray level deviation corresponding to the super pixel block based on the gradient amplitude, gradient direction and gray level corresponding to the super pixel block.
In a specific embodiment, an entropy weight method is used to determine entropy weights corresponding to three dimensions of gradient amplitude, gradient direction and gray level corresponding to the super pixel block. The larger the weight, the more information the corresponding dimension contains, and the better the effect as a distinguishing feature in the diaphragm gray scale image.
The entropy weight of the gradient amplitude corresponding to the super pixel block is marked as f, the entropy weight of the gradient direction is marked as d, and the entropy weight of the gray level is marked as h.
Determining a gray scale deviation of the super pixel block based on the gray scale of the super pixel block and the entropy weight of the gray scale by the following formula；
；
Wherein: Representing the gray scale deviation of the a-th super pixel block; /(I) Information entropy representing gray values in the a-th super pixel block; /(I)Entropy weight representing gray level of the a-th super pixel block; /(I)、/>Representing the maximum value and the minimum value of entropy weights of gray levels corresponding to all super pixel blocks in the diaphragm gray level image; /(I)Representing the first scaling factor.
The larger the value of (a) is, the larger the difference between the distribution of the pixel points in the a super pixel block and the rest of the pixel points in the diaphragm gray scale image is.
Determining the amplitude deviation of the super pixel block based on the gradient amplitude of the super pixel block and the entropy weight of the gradient amplitude by the following formula；
；
Wherein: representing the amplitude deviation of the a-th super pixel block; /(I) Information entropy representing gradient amplitude in the a-th super pixel block; /(I)Entropy weight representing gradient magnitude of the a-th super pixel block; /(I)、/>Representing the maximum value and the minimum value of entropy weights of gradient amplitudes corresponding to all super pixel blocks in the diaphragm gray level image; /(I)Representing a second scaling factor.
Determining texture deviation of the super pixel block based on the gradient direction of the super pixel block and entropy weight of the gradient direction by the following formula；
；
Wherein: Representing texture deviation of the a-th super pixel block; /(I) Information entropy representing gradient amplitude in the a-th super pixel block; /(I)Entropy weight representing gradient direction of the a-th super pixel block; /(I)、/>Representing the maximum value and the minimum value of entropy weights of all super pixel blocks in the diaphragm gray level image in the gradient direction; /(I)Representing a third scaling factor.
Above-mentioned、/>、/>All to prevent the denominator in the formula from being 0, it may take a checked value of 0.001.
S212: and determining the hole depth spread of the super pixel block based on the amplitude deviation, the texture deviation, the gray scale deviation and the similarity between the super pixel block and other super pixel blocks corresponding to the super pixel block.
In one embodiment, the hole depth spread of a superpixel block is determined based on the corresponding amplitude deviation, texture deviation, gray scale deviation, and similarity between the superpixel block and other superpixel blocks by the following formula；
；
；
Wherein: Representing the aperture depth spread of the a-th super pixel block; /(I) Representing the amplitude deviation of the a-th super pixel block; Representing texture deviation of the a-th super pixel block; /(I) Representing the gray scale deviation of the a-th super pixel block; /(I)Representing the similarity of the a-th super pixel block and the b-th super pixel block; k represents the number of super pixel blocks corresponding to the diaphragm gray level image; /(I)Representing a metric distance sequence of an a-th super pixel block; /(I)Representing a metric distance sequence of the b-th super pixel block; Representation/> And/>Pearson correlation coefficient therebetween.
The measurement distance sequence is a sequence with the length of K, which is formed by sequencing from small to large of measurement distances from the seed point of each super pixel block to the seed points of the rest super pixel blocks corresponding to the diaphragm gray level image. Wherein, the seed point is the cluster center. The metric distance in this embodiment is determined based on the gray level difference between the two seed points and the euclidean distance. For example, the number of the cells to be processed,Wherein/>、/>The minimum value and the maximum value of the measurement distances between the seed points of the K super pixel blocks and the a super pixel block are respectively.
The smaller the value of a, b, the lower the similarity of the image information within the two super-pixel blocks, the greater the difference.
The hole depth spread of the super pixel blocks reflects the distribution of hole depths in each super pixel block. The more uneven the depth of the diaphragm hole area in the a-th super pixel block,The greater the value of (2); the greater the difference in membrane hole area and the remaining hole depths in the a-th superpixel block,/>The larger the value of/>The smaller the value of (i.e./>)The larger the value of (2), the larger the difference in distribution of the pixels in the super-pixel block from the pixels in the rest of the super-pixel blocks in the diaphragm gray scale image.The smaller the value of a, the greater the difference in the sequence of metric distances between the seed points of the a-th superpixel block and the seed points of the b-th superpixel block, the greater the difference between the image information within the a-th superpixel block and the image information of the b-th superpixel block. The larger the difference of the image information of the pixel points in the super pixel block is, the larger the entropy weight of the amplitude deviation, the entropy weight of the texture deviation and the entropy weight of the gray scale deviation corresponding to the super pixel block are, namely/>The larger the value of (i.e./>)The larger the value of a, the more non-uniform the depth of the hole area within the a-th super pixel block.
And calculating the hole depth spread of each super pixel block by the implementation mode.
The hole depth spread considers the local characteristics in each super pixel block and the global characteristics of the hole area, and can eliminate the influence of strong and weak textures caused by different stretching degrees in the manufacturing process of the battery diaphragm on the accuracy of the hole area depth evaluation result.
S22: and determining a segmentation threshold based on the hole depth spread of all super pixel blocks corresponding to the diaphragm gray level image.
Specifically, the maximum inter-class variance method can be utilized to process the hole depth spread of all super pixel blocks corresponding to the diaphragm gray level image, and the segmentation threshold value can be determined.
S23: and comparing the hole depth spread of each super pixel block with a segmentation threshold value respectively, and determining whether the super pixel block is a suspected defect area or not.
In one embodiment, the super-pixel block is determined to be a suspected defect region in response to the hole depth spread of the super-pixel block being greater than the segmentation threshold.
Specifically, the non-uniformity of the holes on the battery diaphragm is represented by different degrees of similarity among super pixel blocks in the diaphragm gray level image, and for holes with poor uniformity, such as holes with blocked lithium ions and irregular shapes in the stretching process, the local characteristics of the pixel points in the suspected defect areas are also different.
In a particular embodiment, the super-pixel block is determined to be a non-defective region in response to the hole depth spread of the super-pixel block not being greater than the segmentation threshold.
Specifically, the specific embodiment of the quality evaluation chart for determining the corresponding diaphragm gradation image in step S3 is as follows.
In an embodiment, the characteristic information of the pixel point includes a degree level of the pixel point.
Specifically, each super pixel block is traversed, the measurement distance between each pixel point in the super pixel block and the seed point of the super pixel block where the pixel point is located is obtained, the measurement distances are sequenced from small to large, each measurement distance quantity which is not equal is used as a measurement level, for example, the sequencing result of partial measurement distances is [5,5,7,7,7,9,16], and the quantization result of the super pixel block is 5,7, 9 and 16 degrees. The pixel points in each super pixel block have higher similarity with the seed points of the super pixel blocks, so that the more similar the measurement distance is between the pixel points and the seed points of the super pixel blocks, the higher the similarity is between local features among the pixel points, and the measurement distances between the contained pixel points and the seed points are similar for the super pixel blocks with regular uniform holes in the diaphragm gray level image. For the suspected defect area, the measurement distance between the contained pixel point and the seed point has more measurement magnitude due to uneven depth and irregular shape of the holes in the area of the super pixel block.
Referring to fig. 5, fig. 5 is a flowchart of a step S3 in the method for detecting quality of a lithium battery separator based on the electron scanning microscope provided in fig. 1 according to an embodiment.
S31: traversing the super pixel block corresponding to the suspected defect area, and determining a measurement level sequence of the pixel points based on the measurement level of the pixel points in the super pixel block and the measurement level of the adjacent pixel points.
Specifically, taking each pixel point as a center in the super pixel block, taking a local window with the size of 3*3, calculating the degree level corresponding to each pixel point in the local window, and sequencing all the degree levels in the local window according to the positions of the pixel points to form a measurement level sequence corresponding to the local window. For example, the local window of the ith pixel point is noted as，/>The corresponding metric-level sequence is denoted/>，/>Wherein/>、/>Are respectively/>The degree magnitude of the first pixel point of the first row and the second pixel point of the first row in the interior,/>Is the magnitude of the third pixel in the third row.
S32: and determining the abnormality index of the pixel point based on the measurement level sequence of the pixel point and the measurement level sequences of the adjacent pixel points.
In one embodiment, the anomaly index of the pixel point is calculated based on the following formula。/>
；
Wherein: An abnormality index indicating an i-th pixel point; /(I) Representing the number of pixel points in a local window corresponding to the pixel points; j. j+1 represents the jth and the jth+1th pixel points in the local window respectively; /(I)Representing the longest common subsequence between the metric level sequence corresponding to the jth pixel point and the metric level sequence corresponding to the ith pixel point; /(I)Representing the longest common subsequence between the metric level sequence corresponding to the j+1th pixel point and the metric level sequence corresponding to the i pixel point; Representing the longest common subsequence/> And longest common subsequence/>Similarity between them.
S33: and determining the saliency index of the pixel point based on the gray value of the pixel point and the gray values of the adjacent pixel points.
In one embodiment, the saliency index of the pixel is calculated based on the following formula；
；
Wherein: A saliency index representing the ith pixel point; /(I) Information entropy representing gray values of all pixel points in a local window corresponding to the ith pixel point; /(I)An average value of information entropy representing gray values of pixel points in the super pixel block to which the ith pixel point belongs; /(I)And the entropy weight value of the gray level of the super pixel block to which the ith pixel point belongs is represented.
S34: and determining the diaphragm quality index of the pixel point based on the saliency index of the pixel point and the abnormality index of the pixel point.
In one embodiment, the diaphragm quality index of the pixel is calculated based on the following formula；
；
Wherein: representing the membrane quality index of the ith pixel point; /(I) A saliency index representing the ith pixel point; /(I)And the abnormality index of the i-th pixel point.
U is used to characterize the likelihood that each pixel is located in a non-uniform hole in the super pixel block.
The more prominent the local features of the ith pixel point in the a-th super pixel block,The larger the value of/>The greater the value of (2); the larger the difference of the measurement distance between the ith pixel point and the adjacent pixel point, the larger the difference of the similarity between the ith pixel point and the seed point in the a super pixel block, and the greater the difference of the measurement distance between the ith pixel point and the adjacent pixel pointAnd/>The greater the difference of/>The greater the value of (2); i.e./>The larger the value of (i) the greater the probability that the ith pixel point is located in an irregular hole area of uneven depth in the a-th super pixel block.
The diaphragm low-quality index considers the factors of different stretching degrees of the hole areas in the lithium battery diaphragms in different states, can prevent the phenomenon that pixel points in the smaller hole areas in the diaphragm gray images are misjudged to be in super-pixel blocks of non-defect areas, and improves the accuracy of subsequent evaluation indexes and quality detection results.
S35: and determining the quality evaluation index of the pixel point based on the minimum diaphragm quality index in the super pixel block to which the pixel point belongs.
In one embodiment, the quality evaluation index of the pixel point is calculated based on the following formula；
；
Wherein: A quality assessment index representing an i-th pixel; /(I) Representing a minimum membrane quality index in the super pixel block; /(I)Representing the membrane quality index of the i-th pixel.
S36: and determining a quality evaluation graph corresponding to the diaphragm gray level image based on the quality evaluation indexes of all pixel points in the super pixel block corresponding to the suspected defect area.
In a specific embodiment, according to the position information of each super pixel block in the diaphragm gray level image, a quality evaluation graph corresponding to the diaphragm gray level image is determined based on the quality evaluation indexes of the pixel points in each super pixel block corresponding to the non-defect region and the quality evaluation indexes of the pixel points in each super pixel block corresponding to the suspected defect region. Wherein, the quality evaluation index of the pixel points in each super pixel block corresponding to the non-defect area is 1.
Specifically, specific embodiments of determining the quality detection result of the battery separator in step S4 are as follows.
In one embodiment, the quality evaluation graph of the diaphragm gray level image is subjected to image matching with a preset evaluation graph, and a matching result is determined. The matching result comprises the number and position information of unmatched pixel points; the unmatched pixel points are the pixel points which are unmatched with the preset evaluation graph in the diaphragm gray level graph.
And carrying out image matching on the quality evaluation graph of the diaphragm gray level image and a preset evaluation graph by utilizing a BBS template matching algorithm, and determining a matching result.
Determining the quality qualification rate based on the total number of the matched pixel points in the diaphragm gray level image and the total number of all the pixel points in the diaphragm gray level image; the total number of matched pixels is the difference between the total number of all pixels in the diaphragm gray scale image and the number of unmatched pixels.
And taking the quality qualification rate and the position information of the unmatched pixel points in the diaphragm gray level image as quality detection results.
The lithium battery diaphragm quality detection method based on the electron scanning microscope provided by the embodiment comprises the following steps: dividing the acquired diaphragm gray level image of the battery diaphragm to obtain a plurality of super pixel blocks; the diaphragm gray level image is a surface gray level image of a battery diaphragm containing holes, and each super pixel block has corresponding local characteristic information and global characteristic information; determining whether the super pixel block is a suspected defect area or not based on the local characteristic information and the global characteristic information of the super pixel block; determining a quality evaluation chart of the corresponding diaphragm gray level image based on the characteristic information of the pixel points contained in each suspected defect area and the local characteristic information of the corresponding super pixel block; and determining a quality detection result of the battery diaphragm based on the quality evaluation graph of the diaphragm gray level image. According to the method, whether the super pixel blocks are suspected defect areas or not is determined through the local characteristic information and the global characteristic information of the super pixel blocks corresponding to the diaphragm gray level image of the battery diaphragm, and the influence of strong and weak textures on the accuracy of the depth evaluation result of the hole area caused by different stretching degrees in the diaphragm manufacturing process is eliminated; the quality evaluation graph of the diaphragm gray image is determined through the characteristic information of the pixel points and the local characteristic information of the corresponding super pixel blocks, so that the phenomenon that the pixel points in the small hole area in the diaphragm gray image are misjudged to be in the super pixel blocks corresponding to the non-suspected defect area can be prevented, and the accuracy of the quality detection result of the battery diaphragm is further improved.
The foregoing description of various embodiments is intended to highlight differences between the various embodiments, which may be the same or similar to each other by reference, and is not repeated herein for the sake of brevity.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of modules or units is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical, or other forms.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a usb 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.
The foregoing is only the embodiments of the present invention, and therefore, the patent protection scope of the present invention is not limited thereto, and all equivalent structures or equivalent flow changes made by the content of the present specification and the accompanying drawings, or direct or indirect application in other related technical fields, are included in the patent protection scope of the present invention.
Claims (5)
1. The lithium battery diaphragm quality detection method based on the electron scanning microscope is characterized by comprising the following steps of:
Dividing the acquired diaphragm gray level image of the battery diaphragm to obtain a plurality of super pixel blocks; the diaphragm gray level image is a surface gray level image of the battery diaphragm containing holes, and each super pixel block has corresponding local characteristic information and global characteristic information;
determining whether the super pixel block is a suspected defect area or not based on the local characteristic information and the global characteristic information of the super pixel block;
Determining a quality evaluation chart of the corresponding diaphragm gray level image based on the characteristic information of the pixel points contained in each suspected defect area and the local characteristic information of the corresponding super pixel block;
determining a quality detection result of the battery diaphragm based on the quality evaluation graph of the diaphragm gray level image;
The determining whether the super pixel block is a suspected defect area based on the local feature information and the global feature information of the super pixel block comprises:
determining the hole depth spread of the super pixel block based on the local characteristic information and the global characteristic information of the super pixel block;
determining a segmentation threshold based on hole depth spread of all the super pixel blocks corresponding to the diaphragm gray level image;
comparing the hole depth spread of each super pixel block with the segmentation threshold value respectively, and determining whether the super pixel block is a suspected defect area or not;
The local characteristic information comprises gradient amplitude, gradient direction and gray level; the global feature information comprises feature information corresponding to each super pixel block and each other super pixel block;
the determining the hole depth spread of the super pixel block based on the local feature information and the global feature information of the super pixel block comprises the following steps:
determining amplitude deviation, texture deviation and gray level deviation corresponding to the super pixel block based on the gradient amplitude, the gradient direction and the gray level corresponding to the super pixel block;
Determining the hole depth spread of the super pixel block based on the amplitude deviation, the texture deviation, the gray scale deviation and the similarity between the super pixel block and other super pixel blocks corresponding to the super pixel block by the following formula ；
Wherein: Representing the aperture depth spread of the a-th super pixel block; /(I) Representing the amplitude deviation of the a-th super pixel block; /(I)Representing texture deviation of the a-th super pixel block; /(I)Representing the gray scale deviation of the a-th super pixel block; Representing the similarity of the a-th super pixel block and the b-th super pixel block; k represents the number of the super pixel blocks corresponding to the diaphragm gray scale image; /(I) Representing a metric distance sequence of an a-th super pixel block; /(I)Representing a metric distance sequence of the b-th super pixel block; /(I)Representation/>And/>Pearson correlation coefficient therebetween;
The determining, based on the gradient magnitude, the gradient direction, and the gray level corresponding to the super pixel block, a magnitude deviation, a texture deviation, and a gray level deviation corresponding to the super pixel block includes:
determining entropy weights corresponding to the gradient amplitude, the gradient direction and the gray level corresponding to the super pixel block respectively by using an entropy weight method;
determining a gray scale deviation of the super pixel block based on a gray scale of the super pixel block and an entropy weight of the gray scale by the following formula ；
Wherein: representing the gray scale deviation of the a-th super pixel block; /(I) Information entropy representing gray values in the a-th super pixel block; /(I)An entropy weight representing the gray level of the a-th super pixel block; /(I)、/>Representing the maximum value and the minimum value of the entropy weight of the gray level corresponding to all the super pixel blocks in the diaphragm gray level image; /(I)Representing a first scaling factor;
Determining the amplitude deviation of the super pixel block based on the gradient amplitude of the super pixel block and the entropy weight of the gradient amplitude by the following formula ；
Wherein: representing the amplitude deviation of the a-th super pixel block; /(I) Information entropy representing gradient amplitude in the a-th super pixel block; /(I)Entropy weight representing gradient magnitude of the a-th super pixel block; /(I)、/>Representing the maximum value and the minimum value of the entropy weight of the gradient amplitude corresponding to all the super pixel blocks in the diaphragm gray level image; /(I)Representing a second scaling factor;
determining texture deviation of the super pixel block based on a gradient direction of the super pixel block and an entropy weight of the gradient direction by the following formula ；
Wherein: Representing texture deviation of the a-th super pixel block; /(I) Information entropy representing gradient amplitude in the a-th super pixel block; /(I)Entropy weight representing gradient direction of the a-th super pixel block; /(I)、/>Representing the maximum value and the minimum value of entropy weights of all the super pixel blocks in the diaphragm gray level image in the gradient direction; /(I)Representing a third scaling factor;
The characteristic information of the pixel points comprises a measurement level of the pixel points;
the determining a quality evaluation chart of the corresponding diaphragm gray level image based on the feature information of the pixel points contained in each suspected defect area and the local feature information of the corresponding super pixel block includes:
Traversing the super pixel block corresponding to the suspected defect area, and determining a measurement level sequence of the pixel points based on the measurement level of the pixel points in the super pixel block and the measurement level of the adjacent pixel points;
determining an abnormality index of the pixel point based on the measurement level sequence of the pixel point and the measurement level sequences of the adjacent pixel points;
determining a saliency index of the pixel point based on the gray value of the pixel point and the gray values of the adjacent pixel points;
Determining a diaphragm quality index of the pixel point based on the saliency index of the pixel point and the abnormality index of the pixel point;
determining a quality evaluation index of the pixel point based on a membrane quality index of the pixel point and the minimum membrane quality index in the super pixel block to which the pixel point belongs;
determining a quality evaluation chart corresponding to the diaphragm gray level image based on the quality evaluation indexes of the pixel points in the super pixel block corresponding to the suspected defect area;
The determining the abnormality index of the pixel point based on the measurement level sequence of the pixel point and the measurement level sequence of the adjacent pixel point comprises the following steps:
Calculating the abnormality index of the pixel point based on the following formula ；
Wherein: An abnormality index indicating an ith pixel point; /(I) Representing the number of the pixel points in the local window corresponding to the pixel points; j. j+1 represents the jth and the jth+1th pixel points in the local window respectively; /(I)Representing the longest common subsequence between the metric level sequence corresponding to the jth pixel point and the metric level sequence corresponding to the ith pixel point; /(I)Representing the longest common subsequence between the metric level sequence corresponding to the j+1th pixel point and the metric level sequence corresponding to the i th pixel point; /(I)Representing the longest common subsequence/>And the longest common subsequenceSimilarity between;
The determining the saliency index of the pixel point based on the gray value of the pixel point and the gray values of the adjacent pixel points comprises:
Calculating the significance index of the pixel point based on the following formula ；
Wherein: A saliency index representing the ith pixel point; /(I) Information entropy representing gray values of the pixel points in the local window corresponding to the ith pixel point; /(I)An average value of information entropy representing gray values of the pixel points in the super pixel block to which the ith pixel point belongs; /(I)An entropy weight representing the gray level of the super pixel block to which the ith pixel point belongs;
The determining the diaphragm quality index of the pixel point based on the saliency index of the pixel point and the abnormality index of the pixel point comprises:
Calculating to obtain the diaphragm quality index of the pixel point based on the following formula ；
Wherein: representing the diaphragm quality index of the ith pixel point; /(I) A saliency index representing the ith pixel point; an abnormality index indicating an ith pixel point;
The determining the quality evaluation index of the pixel point based on the membrane quality index of the pixel point and the minimum membrane quality index in the super pixel block to which the pixel point belongs includes:
calculating the quality evaluation index of the pixel point based on the following formula ；
Wherein: Representing a quality evaluation index of the ith pixel point; /(I) Representing the smallest of the membrane quality indices in the super pixel block; /(I)And (5) representing the diaphragm quality index of the ith pixel point.
2. The method for detecting the quality of a lithium battery separator according to claim 1, wherein,
The method for dividing the acquired diaphragm gray level image of the battery diaphragm to obtain a plurality of super pixel blocks comprises the following steps:
obtaining a diaphragm gray level image of the battery diaphragm through an electron scanning microscope;
Performing edge detection on the diaphragm gray level image to obtain edge information, wherein the edge information comprises the hole edge pixel points and gradient amplitude values and gradient directions corresponding to the hole edge pixel points;
And dividing the diaphragm gray level image based on the edge information to obtain a plurality of super pixel blocks corresponding to the diaphragm gray level image.
3. The method for detecting the quality of a lithium battery separator according to claim 1, wherein,
Comparing the hole depth spread of each super pixel block with the segmentation threshold value, and determining whether the super pixel block is a suspected defect area comprises the following steps:
determining the super pixel block as the suspected defect area in response to the hole depth spread of the super pixel block being greater than the segmentation threshold;
and determining the super pixel block as a non-defect area in response to the hole depth spread of the super pixel block not being greater than the segmentation threshold.
4. The method for detecting the quality of a lithium battery separator according to claim 1, wherein,
The determining a quality evaluation chart corresponding to the diaphragm gray level image based on the quality evaluation indexes of the pixel points in the super pixel block corresponding to the suspected defect area comprises the following steps:
Determining a quality evaluation graph corresponding to the diaphragm gray level image based on the quality evaluation indexes of the pixel points in the super pixel blocks corresponding to the non-defect areas and the quality evaluation indexes of the pixel points in the super pixel blocks corresponding to the suspected defect areas; wherein, the quality evaluation index of the pixel point in each super pixel block corresponding to the non-defect area is 1.
5. The method for detecting the quality of a lithium battery separator according to claim 1, wherein,
The determining the quality detection result of the battery diaphragm based on the quality evaluation chart of the diaphragm gray level image comprises the following steps:
Performing image matching on the quality evaluation graph of the diaphragm gray level image and a preset evaluation graph, and determining a matching result; the matching result comprises the number and position information of unmatched pixel points; the unmatched pixel points are the pixel points which are unmatched with the preset evaluation graph in the diaphragm gray level graph;
Determining quality qualification rate based on the total number of matched pixel points in the diaphragm gray scale image and the total number of all the pixel points in the diaphragm gray scale image; the total number of the matched pixel points is the difference value between the total number of all the pixel points in the diaphragm gray level image and the number of the unmatched pixel points;
And taking the quality qualification rate and the position information of the unmatched pixel points in the diaphragm gray level image as the quality detection result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311013120.0A CN116758064B (en) | 2023-08-14 | 2023-08-14 | Lithium battery diaphragm quality detection method based on electron scanning microscope |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311013120.0A CN116758064B (en) | 2023-08-14 | 2023-08-14 | Lithium battery diaphragm quality detection method based on electron scanning microscope |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116758064A CN116758064A (en) | 2023-09-15 |
| CN116758064B true CN116758064B (en) | 2024-04-19 |
Family
ID=87951712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311013120.0A Active CN116758064B (en) | 2023-08-14 | 2023-08-14 | Lithium battery diaphragm quality detection method based on electron scanning microscope |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116758064B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109360186A (en) * | 2018-08-31 | 2019-02-19 | 广州超音速自动化科技股份有限公司 | Lithium battery diaphragm detection method, electronic equipment, storage medium and system |
| CN114170140A (en) * | 2021-11-10 | 2022-03-11 | 佛山科学技术学院 | Membrane defect identification method based on Yolov4 |
| CN115578374A (en) * | 2022-11-01 | 2023-01-06 | 江苏南通元辰钢结构制造有限公司 | Mechanical part casting quality evaluation method and system |
| CN115588022A (en) * | 2022-11-10 | 2023-01-10 | 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 |
| US11657494B1 (en) * | 2022-01-14 | 2023-05-23 | GM Global Technology Operations LLC | Method to detect defects in battery pouch cells using angled flash thermography |
-
2023
- 2023-08-14 CN CN202311013120.0A patent/CN116758064B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109360186A (en) * | 2018-08-31 | 2019-02-19 | 广州超音速自动化科技股份有限公司 | Lithium battery diaphragm detection method, electronic equipment, storage medium and system |
| CN114170140A (en) * | 2021-11-10 | 2022-03-11 | 佛山科学技术学院 | Membrane defect identification method based on Yolov4 |
| US11657494B1 (en) * | 2022-01-14 | 2023-05-23 | GM Global Technology Operations LLC | Method to detect defects in battery pouch cells using angled flash thermography |
| CN115578374A (en) * | 2022-11-01 | 2023-01-06 | 江苏南通元辰钢结构制造有限公司 | Mechanical part casting quality evaluation method and system |
| CN115588022A (en) * | 2022-11-10 | 2023-01-10 | 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 |
Non-Patent Citations (1)
| Title |
|---|
| 锂离子电池隔膜质量问题概述;贾红英;科技创新导报;20180321(第09期);108-109 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116758064A (en) | 2023-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115294140A (en) | Hardware part defect detection method and system | |
| CN111369523B (en) | Method, system, equipment and medium for detecting cell stack in microscopic image | |
| CN113034516A (en) | Deep learning algorithm for segmenting abnormal regions in image | |
| CN112801949A (en) | Method and device for determining discharge area in ultraviolet imaging detection technology | |
| CN114972339B (en) | Data enhancement system for bulldozer structural member production abnormity detection | |
| CN117764864B (en) | Nuclear magnetic resonance tumor visual detection method based on image denoising | |
| CN117351214B (en) | Heat tracing cable detection method and system based on image processing | |
| CN111724331B (en) | Porous medium image reconstruction method based on generation network | |
| CN115760858A (en) | Kidney pathological section cell identification method and system based on deep learning | |
| CN116758064B (en) | Lithium battery diaphragm quality detection method based on electron scanning microscope | |
| CN117333489B (en) | Film damage detection device and detection system | |
| CN114184972A (en) | Method and equipment for automatically estimating SOH (state of health) of battery by combining data driving with electrochemical mechanism | |
| CN116503393B (en) | Circuit board plasma nano coating quality detection method based on image processing | |
| CN108122229B (en) | Full-reference electrical impedance imaging image quality evaluation method | |
| CN108985350B (en) | Method and device for recognizing blurred image based on gradient amplitude sparse characteristic information, computing equipment and storage medium | |
| CN109685757B (en) | Non-reference image quality evaluation method and system based on gray difference statistics | |
| CN113628225B (en) | Fuzzy C-means image segmentation method and system based on structural similarity and image region block | |
| CN115841491A (en) | Quality detection method of porous metal material | |
| Chabrier et al. | Evaluating the segmentation result of a gray-level image | |
| CN113868831A (en) | Battery capacity consistency estimation method and system | |
| CN111597934A (en) | System and method for processing training data for statistical applications | |
| Kalaiselvi et al. | A Study on Validation Metrics of Digital Image Processing | |
| CN116309613B (en) | Method for detecting diffusion capacity of lithium battery diaphragm | |
| CN118014996B (en) | Electric energy meter circuit board defect detection method and system based on image recognition | |
| CN117689637B (en) | Visual detection method for processing quality of new energy battery hardware |
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 |