CN116342599A - Point inspection method, point inspection device, point inspection equipment and point inspection equipment for defect detection equipment and storage medium - Google Patents

Point inspection method, point inspection device, point inspection equipment and point inspection equipment for defect detection equipment and storage medium Download PDF

Info

Publication number
CN116342599A
CN116342599A CN202310612766.4A CN202310612766A CN116342599A CN 116342599 A CN116342599 A CN 116342599A CN 202310612766 A CN202310612766 A CN 202310612766A CN 116342599 A CN116342599 A CN 116342599A
Authority
CN
China
Prior art keywords
defect detection
defect
indication map
length
spot inspection
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.)
Granted
Application number
CN202310612766.4A
Other languages
Chinese (zh)
Other versions
CN116342599B (en
Inventor
王珂
彭克来
杨朝宏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Contemporary Amperex Technology Co Ltd
Original Assignee
Contemporary Amperex Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Contemporary Amperex Technology Co Ltd filed Critical Contemporary Amperex Technology Co Ltd
Priority to CN202310612766.4A priority Critical patent/CN116342599B/en
Publication of CN116342599A publication Critical patent/CN116342599A/en
Application granted granted Critical
Publication of CN116342599B publication Critical patent/CN116342599B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G—PHYSICS
    • 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
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
    • 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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30168—Image quality inspection
    • 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
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Biochemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Quality & Reliability (AREA)
  • Signal Processing (AREA)
  • Geometry (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

The application relates to a spot inspection method, a spot inspection device and a storage medium of defect detection equipment, wherein the spot inspection method comprises the following steps: acquiring a plurality of acquired images of the spot inspection standard component by the defect detection equipment; the spot inspection standard part comprises a plurality of indication diagrams of different defect detection quality indexes; and determining the spot inspection result of the defect detection equipment based on the indication map measurement data of each defect detection quality index in each acquired image. The method can comprehensively identify the detection accuracy of the defect detection equipment, thereby improving the stability of the defect detection equipment.

Description

Point inspection method, point inspection device, point inspection equipment and point inspection equipment for defect detection equipment and storage medium
Technical Field
The present invention relates to the field of defect detection technologies, and in particular, to a point detection method, device, apparatus and storage medium for a defect detection apparatus.
Background
In the production of products, in order to ensure the quality of the products, it is often necessary to detect defects in the products to detect defective products.
Taking appearance defect detection of a battery as an example, a defect detection device is generally used to detect whether the appearance of the battery is defective. Therefore, spot inspection of the defect detecting apparatus is extremely important.
However, the spot inspection method of the defect detecting apparatus in the related art has a problem that the detecting accuracy of the defect detecting apparatus cannot be recognized comprehensively, thereby affecting the stability of the defect detecting apparatus.
Disclosure of Invention
Based on the foregoing, it is necessary to provide a spot inspection method, apparatus, device and storage medium for a defect inspection device, which can comprehensively identify the inspection accuracy of the defect inspection device, thereby improving the stability of the defect inspection device.
In a first aspect, the present application provides a spot inspection method of a defect detection apparatus, the method including:
acquiring a plurality of acquired images of the spot inspection standard component by the defect detection equipment; the spot inspection standard part comprises a plurality of indication diagrams of different defect detection quality indexes;
and determining the spot inspection result of the defect detection equipment based on the indication map measurement data of each defect detection quality index in each acquired image.
In the point inspection method of the defect detection device provided by the embodiment of the application, a plurality of acquired images of a point inspection standard component of the defect detection device are acquired, the point inspection standard component comprises indication diagrams of various different defect detection quality indexes, and then the point inspection result of the defect detection device is determined based on the measurement data of the indication diagrams of each defect detection quality index in each acquired image. In the method, the point detection results of the defect detection equipment are quantitatively evaluated by using a plurality of different defect detection quality indexes, which is equivalent to the detection of the defect detection equipment by using indexes of different dimensions, so that the defect detection equipment can be comprehensively and integrally evaluated, the comprehensive point detection of the defect detection equipment is realized, the point detection accuracy of the defect detection equipment is improved, and the stability of the defect detection equipment is further improved; in addition, in the spot inspection process of the defect detection equipment, the spot inspection result of the defect detection equipment is determined based on the indication map measurement data of each defect detection quality index in a plurality of acquired images of the spot inspection standard component, and spot inspection is performed by the plurality of acquired images, so that the detection accident is reduced, the spot inspection result is more objective and accurate, and the stability of the defect detection equipment is further improved.
In one embodiment, acquiring a plurality of acquired images of an inspection standard by a defect detection device includes:
under the condition that the spot inspection standard part is placed at a preset position of a target product, controlling the defect detection equipment to shoot the spot inspection standard part for multiple times, and acquiring a plurality of acquired images of the spot inspection standard part; the target product represents any product that matches the defect detection device.
In the embodiment of the application, under the condition that the spot inspection standard component is placed at the preset position of the target product, the defect detection equipment is controlled to shoot the spot inspection standard component for multiple times, and a plurality of acquired images of the spot inspection standard component are acquired; the target product represents any product that matches the defect detection device. Through the position of the preset point inspection standard component, when the defect detection equipment is subjected to point inspection, only a plurality of acquired images of the point inspection standard component at the preset position of the target product are required to be acquired, so that the convenience of the defect detection equipment in acquiring the plurality of acquired images of the point inspection standard component is improved; and the acquired image of the spot inspection standard component is acquired at the preset position of the preset target product, so that the definition of the shot acquired image is higher, the accuracy of analyzing a plurality of acquired images is improved, and the spot inspection accuracy of the defect detection equipment is improved.
In one embodiment, the method further comprises:
detecting whether the standard component meets the calibration requirement or not;
and under the condition that the spot inspection standard part meets the calibration requirement, executing the step of acquiring a plurality of acquired images of the spot inspection standard part by the defect detection equipment.
In the embodiment of the application, whether the inspection standard part meets the calibration requirement or not is detected, and under the condition that the inspection standard part meets the calibration requirement, the step of acquiring a plurality of acquired images of the inspection standard part by the defect detection equipment is executed. In the method, before the point inspection is performed on the defect detection equipment, the calibration requirement of the point inspection standard part is detected, and the step of acquiring a plurality of acquired images of the point inspection standard part by the defect detection equipment is performed only on the basis of meeting the calibration requirement, so that the point inspection is performed on the defect detection equipment, namely, the plurality of acquired images of the point inspection standard part acquired by the defect detection equipment are acquired on the basis that the point inspection standard part meets the calibration requirement, the detection precision of the point inspection standard part is improved, and the point inspection accuracy of the defect detection equipment is improved.
In one embodiment, detecting whether the calibration requirements are met by the inspection standard includes:
Acquiring a calibration label of the spot inspection standard component;
determining the latest calibration time of the spot inspection standard component according to the calibration label of the spot inspection standard component;
and under the condition that the latest calibration time is in a preset calibration period, determining that the spot inspection standard component meets the calibration requirement.
In the embodiment of the application, the calibration label of the spot inspection standard component is obtained, the latest calibration time of the spot inspection standard component is determined according to the calibration label of the spot inspection standard component, and the spot inspection standard component is determined to meet the calibration requirement under the condition that the latest calibration time is in a preset calibration period. The latest calibration time of the spot inspection standard component can be intuitively determined through the calibration label of the spot inspection standard component, and whether the spot inspection standard component meets the calibration requirement can be rapidly determined according to the latest calibration time and the preset calibration period, so that the spot inspection speed of the defect detection equipment is improved.
In one embodiment, determining a spot inspection result of the defect inspection apparatus based on the indication map measurement data of each defect inspection quality index in each of the acquired images includes:
acquiring indication map measurement data of each defect detection quality index in each acquired image;
determining an index quantification result of each defect detection quality index based on the indication map measurement data of each defect detection quality index in each acquired image;
And determining the spot inspection result of the defect detection equipment according to the index quantification result of each defect detection quality index.
In the embodiment of the application, the indication map measurement data of each defect detection quality index in each acquired image is obtained, the index quantization result of each defect detection quality index is determined based on the indication map measurement data of each defect detection quality index in each acquired image, and then the point detection result of the defect detection device is determined according to the index quantization result of each defect detection quality index. In the method, the defect detection quality indexes of the acquired images are quantized based on the measurement data of the indication map of each defect detection quality index in the acquired images, so that the spot detection result of the defect detection equipment can be intuitively and accurately determined, and the stability of the defect detection equipment is improved.
In one embodiment, the defect detection quality index includes a defect length, the point inspection standard includes a plurality of length indication maps of gradients of different lengths of the defect length, and acquiring indication map measurement data of each defect detection quality index in each acquired image includes:
and identifying the length indication graphs of different length gradients in each acquired image to obtain the length indication graph measurement data of each length gradient in the acquired image.
In the embodiment of the application, the length indication graphs of different length gradients in each acquired image are identified, and the length indication graph measurement data of each length gradient in the acquired image are obtained. According to the method, as the point inspection standard component comprises the length indication diagrams of the plurality of different length gradients of the defect length, the length indication diagrams of the length gradients in the acquired image are identified, the length indication diagram measurement data of each length gradient in the acquired image can be obtained, the point inspection standard component is provided with the length indication diagrams of the plurality of different length gradients, and the acquired images of the point inspection standard component can accurately carry out point inspection on the length measurement capability of the defect detection device, so that a more accurate point inspection result is obtained.
In one embodiment, determining an index quantization result for each defect detection quality index based on the indicator map measurement data for each defect detection quality index in each acquired image includes:
standard data of each length indication graph is obtained;
and determining the index quantification result of the defect length according to the standard data of each length indication map and the length indication map measurement data of each length gradient.
In the embodiment of the application, standard data of each length indication map is obtained, and an index quantization result of the defect length is determined according to the standard data of each length indication map and length indication map measurement data of each length gradient. In the method, the standard data of each length indication map is obtained by standard defect detection equipment, and the standard data of each length indication map is compared with the length indication map measurement data of the corresponding length gradient, so that the index quantization result of the defect length is more accurate, and the spot detection accuracy of the defect detection equipment is improved.
In one embodiment, the index quantization result includes bias degree and/or linearity degree, and determining the index quantization result of the defect length according to standard data of each length indication map and length indication map measurement data of each length gradient includes:
inputting standard data of each length indication graph and length indication graph measurement data of each length gradient into a preset bias calculation model to obtain bias of defect length; the method comprises the steps of,
and inputting standard data of each length indication graph and length indication graph measurement data of each length gradient into a preset linearity calculation model to obtain linearity of the defect length.
In the embodiment of the application, standard data of each length indication graph and length indication graph measurement data of each length gradient are input into a preset bias calculation model to obtain bias of defect length; and inputting standard data of each length indication map and length indication map measurement data of each length gradient into a preset linearity calculation model to obtain linearity of the defect length. In the method, the accuracy of the index quantization result of the defect detection length is improved by quantifying the detection accuracy of the defect detection equipment through two dimensions of bias degree and linearity.
In one embodiment, the defect detection quality index includes a defect gray scale, a gray scale indication map including a plurality of gray scale levels of the defect gray scale on the point detection standard component, and obtaining indication map measurement data of each defect detection quality index in each acquired image includes:
and identifying gray scale indication graphs of different gray scale gradients in each acquired image to obtain gray scale indication graph measurement data of each gray scale gradient in the acquired image.
In the embodiment of the application, gray scale indication maps of different gray scale gradients in each acquired image are identified, and gray scale indication map measurement data of each gray scale gradient in the acquired image are obtained. In the method, as the point inspection standard component comprises gray indication graphs with various gray levels of defect gray levels, the gray indication graph of each gray level gradient in the acquired image is identified, the gray indication graph measurement data of each gray level gradient in the acquired image can be obtained, and the point inspection standard component is provided with the gray indication graph with various gray levels, and a plurality of acquired images of the point inspection standard component are acquired, so that the gray identification capability of the defect detection equipment can be accurately subjected to point inspection, and a more accurate point inspection result is obtained.
In one embodiment, determining an index quantization result for each defect detection quality index based on the indicator map measurement data for each defect detection quality index in each acquired image includes:
standard data of each gray indication map is obtained;
and determining the index quantification result of the defect gray scale according to the standard data of each gray scale indication map and the gray scale indication map measurement data of each gray scale gradient.
In the embodiment of the application, standard data of each gray indication map is obtained, and an index quantization result of the defect gray level is determined according to the standard data of each gray indication map and gray indication map measurement data of each gray level gradient. In the method, the standard data of each gray indication map is obtained by standard defect detection equipment, and the standard data of each gray indication map is compared with the gray indication map measurement data corresponding to gray gradient, so that the obtained index quantization result of the defect gray is more accurate, and the spot detection accuracy of the defect detection equipment is improved.
In one embodiment, the index quantization result includes bias degree and/or linearity, and determining the index quantization result of the defect gray scale according to standard data of each gray scale indication map and gray scale indication map measurement data of each gray scale gradient includes:
The standard data of each gray scale indication map and the gray scale indication map measurement data of each gray scale gradient are sent to a preset bias calculation model, so that bias of the defect gray scale is obtained; the method comprises the steps of,
and (3) measuring standard data of each gray scale indication map and gray scale indication map measurement data of each gray scale gradient to a preset linearity calculation model to obtain linearity of the defect gray scale.
In the embodiment of the application, standard data of each gray scale indication map and gray scale indication map measurement data of each gray scale gradient are sent to a preset bias calculation model to obtain bias of defect gray scale; and obtaining linearity of the defect gray scale by sending standard data of each gray scale indication map and gray scale indication map measurement data of each gray scale gradient to a preset linearity calculation model. In the method, the accuracy of the index quantization result of the defect detection length is improved by quantifying the detection accuracy of the defect detection equipment through two dimensions of bias degree and linearity.
In one embodiment, the defect detection quality index includes a defect resolution, the point detection standard includes a resolution indication map of the defect resolution, and obtaining indication map measurement data of each defect detection quality index in each acquired image includes:
And carrying out image recognition on the resolution indication map in each acquired image to obtain measurement data of the resolution indication map in each acquired image.
In the embodiment of the application, image recognition is performed on the resolution indication map in each acquired image, and measurement data of the resolution indication map in each acquired image is obtained. In the method, the resolution indication map of the defect resolution is included on the spot inspection standard component, the resolution indication map in the acquired image is identified, the measurement data of the resolution indication map in the acquired image can be obtained, and the resolution capability of the defect detection equipment can be accurately spot inspected by setting the resolution indication map on the spot inspection standard component and acquiring a plurality of acquired images of the spot inspection standard component, so that an accurate spot inspection result is obtained.
In one embodiment, the resolution indication map includes a plurality of cells; image recognition is carried out on the resolution indication map in each acquired image, and measurement data of the resolution indication map in each acquired image is obtained, wherein the method comprises the following steps:
identifying the resolution indication map and obtaining a size measurement value of the resolution indication map;
the resolution indication map measurement data is determined based on the size measurement and the number of cells of the resolution indication map.
In the embodiment of the application, the resolution indication map is identified, the size measurement value of the resolution indication map is obtained, and the measurement data of the resolution indication map is determined according to the size measurement value and the number of cells of the resolution indication map. According to the method, the measurement data of the resolution indication map of the acquired image can be accurately measured through the size measurement value of the resolution indication map of the acquired image and the number of the cells of the resolution indication map, and the resolution of the acquired image is reflected through the measurement data of the resolution indication map, so that the spot inspection accuracy of the defect detection equipment is improved.
In one embodiment, determining the spot inspection result of the defect inspection apparatus according to the index quantization result of each defect inspection quality index includes:
under the condition that index quantification results of all defect detection quality indexes are within a preset tolerance range, determining that point detection results of the defect detection equipment are normal;
and determining that the spot inspection result of the defect detection equipment is abnormal when the index quantification result of any defect detection quality index is not within a preset tolerance range.
In the embodiment of the application, under the condition that index quantization results of all defect detection quality indexes are within a preset tolerance range, determining that point detection results of defect detection equipment are normal; and determining that the spot inspection result of the defect detection equipment is abnormal when the index quantification result of any defect detection quality index is not within a preset tolerance range. And determining the spot inspection result of the defect detection equipment according to whether the index quantification result of each defect detection quality index is in a preset tolerance range, so that the spot inspection result of the defect detection equipment can be rapidly determined, and the spot inspection speed of the defect detection equipment is improved.
In a second aspect, the present application further provides a spot inspection apparatus of a defect detection device, where the apparatus includes:
the image acquisition module is used for acquiring a plurality of acquired images of the spot inspection standard component by the defect detection equipment; the spot inspection standard part comprises a plurality of indication diagrams of different defect detection quality indexes;
and the detection module is used for determining the spot inspection result of the defect detection equipment based on the indication map measurement data of each defect detection quality index in each acquired image.
In a third aspect, embodiments of the present application provide a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the steps of the method provided by any of the embodiments of the first aspect described above when the computer program is executed.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method provided by any of the embodiments of the first aspect described above.
In a fifth aspect, embodiments of the present application also provide a computer program product comprising a computer program which, when executed by a processor, implements the steps of the method provided by any of the embodiments of the first aspect described above.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
FIG. 1 is an application environment diagram of a spot inspection method of a defect detection apparatus in one embodiment;
FIG. 2 is a flow chart of a spot inspection method of a defect inspection apparatus according to one embodiment;
FIG. 3 is a flow chart of a spot inspection method of a defect inspection apparatus according to another embodiment;
FIG. 4 is a flow chart of a spot inspection method of a defect inspection apparatus according to another embodiment;
FIG. 5 is a flow chart of a spot inspection method of a defect inspection apparatus according to another embodiment;
FIG. 6 is a schematic diagram of a spot check standard in one embodiment;
FIG. 7 is a flow chart of a spot inspection method of a defect inspection apparatus according to another embodiment;
FIG. 8 is a flow chart of a spot inspection method of a defect inspection apparatus according to another embodiment;
FIG. 9 is a schematic diagram of a spot check standard in another embodiment;
FIG. 10 is a flow chart of a spot inspection method of a defect inspection apparatus according to another embodiment;
FIG. 11 is a flow chart of a spot inspection method of a defect inspection apparatus according to another embodiment;
FIG. 12 is a flow chart of a spot inspection method of a defect inspection apparatus according to another embodiment;
FIG. 13 is a schematic view of a point inspection standard in another embodiment;
FIG. 14 is a schematic view of a point inspection standard in another embodiment;
FIG. 15 is a flow chart of a spot inspection method of a defect inspection apparatus according to another embodiment;
FIG. 16 is a block diagram showing the structure of a spot check apparatus of the defect detecting device in one embodiment;
fig. 17 is an internal structural view of a computer device in one embodiment.
Detailed Description
Embodiments of the technical solutions of the present application will be described in detail below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical solutions of the present application, and thus are only examples, and are not intended to limit the scope of protection of the present application.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the term "comprising" and any variations thereof in the description of the present application and the claims and the description of the figures above is intended to cover non-exclusive inclusion. In the description of the embodiments of the present application, the meaning of "plurality" is two or more unless explicitly 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 present 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. In the description of the embodiments of the present application, the term "and/or" is merely an association relationship describing an association object, which means that three relationships may exist, for example, a and/or B may mean: 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.
In the production of products, it is often necessary to detect defects in the products by means of a defect detection device in order to detect defective products.
Taking the appearance defect detection of the battery module as an example, a module defect appearance machine is adopted to detect the appearance of the battery module. In order to improve and maintain the performance of the module defect appearance machine, the module defect appearance machine can be subjected to quality detection according to a preset period and method, so that hidden dangers and defects of the module defect appearance machine can be discovered early, prevented early, treated early and the like.
In the related art, the accuracy of detecting the module defect appearance machine is evaluated by quantifying the lens resolution of the module defect appearance machine. However, the visual defect detection of the module defect appearance machine is only evaluated according to the resolution of the lens, and the detection accuracy of the module defect appearance machine cannot be comprehensively and effectively evaluated, so that the detection stability of the module defect appearance machine is affected.
Based on the above consideration, in order to comprehensively identify the detection accuracy of the defect detection device, a point detection method of the defect detection device is provided, multiple indication graphs of different defect detection quality indexes are set on a point detection standard part, multiple acquired images of the point detection standard part are acquired by the defect detection device, and then the point detection result of the defect detection device is determined based on the measurement data of the indication graphs of each defect detection quality index in the acquired images. The method has the advantages that the point detection results of the defect detection equipment are quantitatively evaluated by using a plurality of different defect detection quality indexes, namely, the capability of detecting defects of the defect detection equipment is inspected by using indexes with different dimensions, so that the defect detection equipment can be comprehensively and integrally evaluated, the comprehensive point detection of the defect detection equipment is realized, the point detection accuracy of the defect detection equipment is improved, and the stability of the defect detection equipment is further improved; in addition, in the spot inspection process of the defect detection equipment, the spot inspection result of the defect detection equipment is determined based on the indication map measurement data of each defect detection quality index in a plurality of acquired images of the spot inspection standard component, and spot inspection is performed by the plurality of acquired images, so that the detection accident is reduced, the spot inspection result is more objective and accurate, and the stability of the defect detection equipment is further improved.
The spot inspection method of the defect detection device provided in the embodiment of the present application may be applied to the defect detection device 100 shown in fig. 1, where the defect detection device generally refers to any appearance defect detection device, for example, if the product is a battery module, the corresponding defect detection device may be a module defect appearance machine; the defect detecting device 100 may include a processor 101 and an image capturing device 102, where the image capturing device 102 may be any device having an image capturing function, and the image capturing device 102 may be a charge coupled device (Charge coupled Device, CCD) camera, for example.
In one embodiment, as shown in fig. 2, there is provided a spot inspection method of a defect detecting apparatus, which is exemplified as a processor applied to the defect detecting apparatus, including the steps of:
s201, acquiring a plurality of acquired images of a spot inspection standard component by a defect detection device; the spot inspection standard comprises a plurality of indication diagrams of different defect detection quality indexes.
The point detection standard component is used for measuring the detection accuracy of the defect detection equipment, the point detection standard component comprises indication diagrams of various different defect detection quality indexes, the defect detection equipment collects a plurality of collected images of the point detection standard component, and point detection results of the defect detection equipment can be determined according to the indication diagrams of the different defect detection quality indexes in the plurality of collected images.
Optionally, the spot inspection standard component can be an object with a real object, and the material of the spot inspection standard component can include but is not limited to aluminum alloy, stainless steel, acrylic and the like; also, the planar shape of the spot check standard may include, but is not limited to, oblong, square, circular, etc., and the spot check standard may be sized to accommodate a variety of different defect detection quality indicators; the information such as the size of the indication map of each defect detection quality index in the spot inspection standard component can be directly noted on the spot inspection standard component, can be stored in a processor of the defect detection device, can also be noted on the spot inspection standard component at the same time and stored in the processor of the defect detection device, and it can be understood that various storage modes of the information such as the size of the indication map of each defect detection quality index in the spot inspection standard component are all used for conveniently performing spot inspection on the defect detection device and improving the spot inspection speed of the defect detection device.
The defect detection quality index may be a number, a length, a width, a region, a distance, a size, or the like, and correspondingly, taking the defect detection quality index as an example, the indication map of the defect detection quality index may be a pattern of a certain size.
Optionally, in the spot inspection standard, one defect detection quality index may correspond to a plurality of indication maps, and one indication map may detect a plurality of different defect detection quality indexes; for example, two indication maps of the spot inspection standard correspond to different lengths, and one indication map of the spot inspection standard corresponds to two defect detection quality indexes of length and width.
It should be noted that, the spot inspection standard components corresponding to different inspection products may be different, for example, the sizes of the indication diagrams of the defect detection quality indexes on the spot inspection standard components may be different, taking battery a and battery B as examples, battery a and battery B are batteries of different specifications, the sizes of the indication diagrams of the plurality of different defect detection quality indexes on the spot inspection standard components corresponding to battery a are A1, the sizes of the indication diagrams of the plurality of different defect detection quality indexes on the spot inspection standard components corresponding to battery B are B1, and A1 and B1 may be different sizes.
It should be noted that the size of the indication map of each defect detection quality index in the spot inspection standard may be determined by one or more of the type and size of the inspection product and the type of defect detection quality index.
The point inspection of the defect detection equipment can be realized through the indication map of the defect detection quality index on the point inspection standard component, so that the defect detection equipment can acquire the acquisition image of the point inspection standard component, and further, in order to improve the accuracy of the point inspection, a plurality of acquisition images of the point inspection standard component can be acquired, wherein each acquisition image comprises the indication map of a plurality of different defect detection quality indexes; the plurality of acquired images may be acquired continuously by the defect detection apparatus, or may be acquired one acquired image in each acquisition cycle, and the plurality of acquired images may be acquired in a plurality of acquisition cycles.
The method for acquiring the plurality of acquired images of the point inspection standard component by the defect detection equipment may be that after the processor receives the point inspection instruction of the defect detection equipment sent by the upper computer, the processor responds to the point inspection instruction of the defect detection equipment to control the image acquisition equipment in the defect detection equipment to acquire the plurality of acquired images of the point inspection standard component.
The method for acquiring the plurality of acquired images of the spot inspection standard component by the defect detection device may also be that the spot inspection is performed on the defect detection device according to a preset spot inspection period, and when the spot inspection period is reached each time, the processor controls the image acquisition device of the defect detection device to acquire the plurality of acquired images of the spot inspection standard component.
S202, determining a spot inspection result of the defect detection equipment based on the indication map measurement data of each defect detection quality index in each acquired image.
The indication map measurement data may be measurement data corresponding to an indication map of a defect detection quality index in the acquired image; since the point inspection standard component comprises the indication diagrams of the plurality of different defect detection quality indexes, the collected images also comprise the indication diagrams of the plurality of different defect detection quality indexes, and the indication diagrams in the collected images obtained in the embodiment can be analyzed to determine the indication diagram measurement data of each defect detection quality index in the collected images.
Optionally, the spot inspection result may include that the defect detecting device is normal or the defect detecting device is abnormal, where the defect detecting device indicates that the defect detecting device is higher in accuracy of detecting the appearance of the product, and the defect detecting device may be used normally; the defect detection device abnormality indicates that the defect detection device has low accuracy in detecting the appearance of the product, and the defect detection device uses abnormality.
In one embodiment, the method for determining the spot inspection result of the defect detecting device may be that the spot inspection result of the defect detecting device is determined through a preset spot inspection model; specifically, the defect detection device takes a plurality of acquired images of the spot inspection standard component as input of a spot inspection model, analyzes the measurement data of the indication map of each defect detection quality index in each acquired image through the spot inspection model, and outputs the spot inspection result of the defect detection device.
In another embodiment, the method for determining the spot inspection result of the defect detecting device may also be that a plurality of collected images of the spot inspection standard component of the defect detecting device are analyzed, indication map measurement data of each defect detecting quality index in each collected image is obtained, and the spot inspection result of the defect detecting device is determined by each indication map measurement data; for example, if each indication map measurement data is within the threshold range corresponding to the defect detection quality index, the point detection result of the defect detection device is determined to be normal, and if any indication map measurement data is not within the threshold range corresponding to the defect detection quality index, the point detection result of the defect detection device is determined to be abnormal.
It should be noted that the threshold ranges corresponding to different defect detection quality indexes may be different.
Optionally, if the point detection result of the defect detection device is that the defect detection device is abnormal, health management, maintenance, and the like can be performed on the defect detection device according to the indication map measurement data of each defect detection quality index in each acquired image.
Optionally, the point inspection result may further include a defect level, where the defect level includes a normal defect, a micro defect, a major defect, and the like, and after determining the defect level of the defect detection device according to the indication map measurement data of each defect detection quality index in each collected image, it may further determine whether the defect detection device needs to be repaired and the degree of the repair required according to the defect level; for example, in the case where the defect level is normal, the repair of the defect detecting apparatus is not necessary, in the case where the defect level is a micro defect, the micro repair of the defect detecting apparatus may be performed, and in the case where the defect detecting apparatus is a significant defect, the significant repair of the defect detecting apparatus may be performed.
In the point inspection method of the defect detection device provided by the embodiment of the application, a plurality of acquired images of a point inspection standard component of the defect detection device are acquired, the point inspection standard component comprises indication diagrams of various different defect detection quality indexes, and then the point inspection result of the defect detection device is determined based on the measurement data of the indication diagrams of each defect detection quality index in each acquired image. In the method, the point detection results of the defect detection equipment are quantitatively evaluated by using a plurality of different defect detection quality indexes, which is equivalent to the detection of the defect detection equipment by using indexes of different dimensions, so that the defect detection equipment can be comprehensively and integrally evaluated, the comprehensive point detection of the defect detection equipment is realized, the point detection accuracy of the defect detection equipment is improved, and the stability of the defect detection equipment is further improved; in addition, in the spot inspection process of the defect detection equipment, the spot inspection result of the defect detection equipment is determined based on the indication map measurement data of each defect detection quality index in a plurality of acquired images of the spot inspection standard component, and spot inspection is performed by the plurality of acquired images, so that the detection accident is reduced, the spot inspection result is more objective and accurate, and the stability of the defect detection equipment is further improved.
The following describes how to acquire a plurality of acquired images of a spot check standard by a defect detection apparatus, which in one embodiment includes: under the condition that the spot inspection standard part is placed at a preset position of a target product, controlling the defect detection equipment to shoot the spot inspection standard part for multiple times, and acquiring a plurality of acquired images of the spot inspection standard part; the target product represents any product that matches the defect detection device.
When acquiring a plurality of acquired images of the spot inspection standard component, the defect detection device acquires the plurality of acquired images of the spot inspection standard component placed at a preset position of a target product.
Specifically, the processor may receive an acquisition instruction of the upper computer, where the acquisition instruction is used to indicate that the corresponding spot inspection standard component is placed at a preset position of the target product, and when the spot inspection standard component is placed at the preset position of the target product, the processor controls the image acquisition device of the defect detection device to perform multiple shooting on the spot inspection standard component to obtain multiple acquired images of the spot inspection standard component, where the multiple shooting mode may be continuous shooting or shooting with a preset shooting period.
Optionally, the preset target product position may be a fixture position of the target product, where the fixture position of the target product may place a spot inspection standard component of the target product.
When the spot inspection standard part is placed at the preset position of the target product, the spot inspection standard part can be fixed at the preset position of the target product in a mode of nuts and the like, the spot inspection standard part can be detached at the preset position of the target product, and after the spot inspection of the defect detection equipment is finished, the spot inspection standard part can be detached from the preset position of the target product.
In addition, the target product can comprise a plurality of detection surfaces, each detection surface can correspond to a preset position, when the defect detection equipment is subjected to spot inspection, a spot inspection standard component can be placed at the preset position of each detection surface of the target product, the spot inspection standard components of each detection surface can be identical or different, and the spot inspection standard component can be determined according to the detection item of each detection surface; and a spot inspection standard part can be placed at a preset position of one detection surface, and after the image acquisition of the detection surface is completed, the spot inspection standard part is detached and then placed on the next detection surface until the image acquisition of all detection surfaces in the target product is completed.
Taking a target product as a battery module as an example, under the condition that the spot inspection standard component is placed at the position of a fixture of the battery module, controlling the defect detection equipment to shoot the spot inspection standard component for multiple times to obtain a plurality of acquired images of the spot inspection standard component; taking the example that the battery module comprises 6 detection surfaces, a spot inspection standard component can be placed on the 6 detection surfaces of the battery module, and a plurality of acquired images of each spot inspection standard component can be acquired in sequence.
It should be noted that, under the condition that the defect detection equipment is not subjected to spot inspection, the spot inspection standard component of the target product can be placed in the standard component cabinet, and under the condition that the defect detection equipment is required to be subjected to spot inspection, the processor can acquire the spot inspection standard component corresponding to the target product from the standard component cabinet and place the spot inspection standard component at the preset position of the target product.
A plurality of standard components are placed in the standard component cabinet, the plurality of standard components can be the same or different, each standard component corresponds to a product identifier, and one standard component can correspond to a plurality of product identifiers; therefore, the processor can control the manipulator to acquire the spot inspection standard part of the target product from the standard part cabinet and place the spot inspection standard part at the preset position of the target product.
In the spot inspection method of the defect detection equipment, under the condition that the spot inspection standard part is placed at the preset position of the target product, the defect detection equipment is controlled to shoot the spot inspection standard part for multiple times, and a plurality of acquired images of the spot inspection standard part are acquired; the target product represents any product that matches the defect detection device. Through the position of the fixed point inspection standard component in advance, when the defect detection equipment is subjected to point inspection, only a plurality of acquired images of the point inspection standard component at the preset position of the target product are required to be acquired, so that the convenience of the defect detection equipment in acquiring the plurality of acquired images of the point inspection standard component is improved; moreover, the preset position of the preset target product ensures that the acquired multiple acquired images of the spot inspection standard component have higher definition, and the accuracy of analyzing the multiple acquired images is improved, so that the spot inspection accuracy of the defect detection equipment is improved.
The calibration is a key link for providing guarantee for accurate data and accurate and reliable guaranteed magnitude of the spot inspection standard component, and the calibration requirement is scientifically determined, so that the defect detection equipment can smoothly finish spot inspection work. Therefore, before acquiring multiple acquired images of the spot check standard by the defect detection device, it is necessary to check the calibration of the spot check standard, whether the spot check standard meets the calibration requirement, and in one embodiment, as shown in fig. 3, the embodiment includes the following steps:
S301, detecting whether the detection point standard part meets the calibration requirement.
Wherein the calibration may be a set of operations under prescribed conditions to determine a relationship between the magnitudes indicated by the indication map of the plurality of different defect detection quality indicators on the spot inspection standard and the corresponding magnitudes reproduced by the standard. Calibration may include the steps of: check, correct, report, or pass through adjustments to eliminate any deviation in accuracy of the compared spot check standards.
Therefore, before the defect detection device is subjected to spot inspection by the spot inspection standard component, whether the spot inspection standard component meets the calibration requirement or not can be detected, and the step of acquiring a plurality of acquired images of the spot inspection standard component by the defect detection device is only performed if the spot inspection standard component meets the calibration requirement.
The calibration requirements may include a calibration period, a calibration parameter, and the like, taking as an example whether the calibration period of the spot check standard meets the preset calibration period, in one embodiment, as shown in fig. 4, the detecting spot check standard meets the calibration requirement, including the following steps:
s401, acquiring a calibration label of the spot inspection standard component.
After the spot inspection standard is calibrated, a calibration label of the spot inspection standard can be updated, wherein the calibration label can comprise an identification of the spot inspection standard, a calibration parameter, a calibration time and the like.
Optionally, the calibration label may be adhered to a preset position of the spot inspection standard component, and after the spot inspection standard component of the target product is obtained, the calibration label at the preset position of the spot inspection standard component is identified to obtain data in the calibration label; the pasting position of the calibration label does not influence the spot inspection of the spot inspection standard component on the defect detection equipment.
The calibration label can also be stuck at a preset position of the standard component cabinet for placing the spot inspection standard component, and the position and the corresponding spot inspection standard component are within a preset distance, so that the calibration label of the spot inspection standard component can be directly obtained from the standard component cabinet.
The calibration label can also be stored in a database, and the calibration label corresponding to the identification of the spot inspection standard is obtained from the database according to the identification of the spot inspection standard.
S402, determining the latest calibration time of the spot inspection standard component according to the calibration label of the spot inspection standard component.
The calibration label of the spot check standard may include a calibration time of each calibration of the spot check standard, and a time corresponding to a last calibration in the calibration label of the spot check standard is determined as a latest calibration time of the spot check standard.
Optionally, the calibration time of the spot inspection standard is stored in the spot inspection standard, and after each time of calibration of the spot inspection standard is completed, the calibration time of the spot inspection standard is updated to the time of the last calibration of the spot inspection standard, so that the calibration time in the calibration tag can be directly determined to be the latest calibration time of the spot inspection standard.
S403, under the condition that the latest calibration time is in a preset calibration period, determining that the spot inspection standard component meets the calibration requirement.
The preset calibration period is a time required to calibrate the inspection standard component once within the preset calibration period, for example, the preset calibration period is 2 days, and the inspection standard component needs to be calibrated once every 2 days at the latest, and the preset calibration period can be stored in the calibration tag.
Determining whether the latest calibration time of the detection point standard component is in a preset calibration period or not, and determining that the point standard component meets the calibration requirement under the condition that the latest calibration time is in the preset calibration period; correspondingly, under the condition that the latest calibration time of the spot inspection standard component is not in a preset calibration period, determining that the spot inspection standard component does not meet the calibration requirement.
Optionally, acquiring the current time, calculating the time length between the current time and the latest calibration period of the spot inspection standard component, and determining that the spot inspection standard component meets the calibration requirement under the condition that the time length is smaller than the preset calibration period; for example, the preset calibration period is 48 hours, if the time length between the current time and the latest calibration period of the spot inspection standard component is 40 hours, the spot inspection standard component is determined to meet the calibration requirement, and if the time length between the current time and the latest calibration period of the spot inspection standard component is 50 hours, the spot inspection standard component is determined to not meet the calibration requirement.
Optionally, the latest calibration parameters of the calibration parameters in the calibration label can be obtained, and if the latest calibration parameters are within the preset standard parameter range, the point detection standard component is determined to meet the calibration requirement, otherwise, the point detection standard component does not meet the calibration requirement; the calibration parameter may be a magnitude parameter of a pointing diagram in the point inspection standard.
In the embodiment of the application, the calibration label of the spot inspection standard component is obtained, the latest calibration time of the spot inspection standard component is determined according to the calibration label of the spot inspection standard component, and the spot inspection standard component is determined to meet the calibration requirement under the condition that the latest calibration time is in a preset calibration period. The latest calibration time of the spot inspection standard component can be intuitively determined through the calibration label of the spot inspection standard component, and whether the spot inspection standard component meets the calibration requirement can be rapidly determined according to the latest calibration time and the preset calibration period, so that the spot inspection speed of the defect detection equipment is improved.
S302, under the condition that the spot inspection standard part meets the calibration requirement, a step of acquiring a plurality of acquired images of the spot inspection standard part by the defect detection equipment is executed.
Specifically, in the case that the spot inspection standard meets the calibration requirement, the step of acquiring a plurality of acquired images of the spot inspection standard by the defect detection device is performed, including: under the condition that the spot inspection standard part meets the calibration requirement, the spot inspection standard part is placed at the preset position of the target product, and under the condition that the spot inspection standard part is placed at the preset position of the target product, the defect detection equipment is controlled to shoot the spot inspection standard part for multiple times, and a plurality of acquired images of the spot inspection standard part are acquired.
Under the condition that the spot inspection standard part does not meet the calibration requirement, the spot inspection standard part can be calibrated first until the spot inspection standard part meets the calibration requirement, and then under the condition that the spot inspection standard part meets the calibration requirement, the step of acquiring a plurality of acquired images of the spot inspection standard part by the defect detection equipment is executed.
It should be noted that, in the embodiment of the present application, the step of acquiring a plurality of acquired images of the inspection standard by the defect detection device is the same as that of the specific implementation of the embodiment.
In the spot inspection method of the defect detection device provided by the embodiment of the application, whether the spot inspection standard part meets the calibration requirement or not is detected, and under the condition that the spot inspection standard part meets the calibration requirement, the step of acquiring a plurality of acquired images of the spot inspection standard part by the defect detection device is executed. In the method, before the point inspection is performed on the defect detection equipment, the calibration requirement of the point inspection standard part is detected, and the step of acquiring a plurality of acquired images of the point inspection standard part by the defect detection equipment is performed only on the basis of meeting the calibration requirement, so that the point inspection is performed on the defect detection equipment, namely, the plurality of acquired images of the point inspection standard part acquired by the defect detection equipment are acquired on the basis that the point inspection standard part meets the calibration requirement, the detection precision of the point inspection standard part is improved, and the point inspection accuracy of the defect detection equipment is improved.
In the following, it is explained by an embodiment how to determine the spot inspection result of the defect detecting device after acquiring a plurality of acquired images of the spot inspection standard, and in an embodiment, as shown in fig. 5, the spot inspection result of the defect detecting device is determined based on the measurement data of the indication map of each defect detection quality index in each acquired image, comprising the steps of:
s501, acquiring the measurement data of an indication map of each defect detection quality index in each acquired image.
The indication map measurement data may be a measurement value in the acquired image indicating a defect detection quality indicator corresponding to the map.
The method comprises the steps that indication map measurement data of each defect detection quality index in each acquired image can be obtained according to a preset analysis model; specifically, a plurality of collected images of the spot inspection standard component are input into an analysis model, and the analysis model analyzes the indication map of each defect detection quality index in each collected image to obtain the measurement data of the indication map of each defect detection quality index in each collected image.
Alternatively, different defect detection quality indexes may correspond to different analysis models, for example, the defect detection quality indexes include a number and a width, and the width analysis model is taken as an example to describe that a plurality of collected images are respectively input into the width analysis model, the width analysis model analyzes a width indication map of the defect detection indexes in each collected image, determines indication map measurement data of the width indication map in each collected image, and determines indication map measurement data of each defect detection quality index in each collected image based on the indication map measurement data.
S502, determining an index quantification result of each defect detection quality index based on the indication map measurement data of each defect detection quality index in each acquired image.
Wherein, the index quantization result of the defect detection quality index is used for quantifying the accuracy of the detection product of the defect detection equipment.
Determining an index quantization result of each defect detection quality index based on a preset quantization model, specifically, inputting the measurement data of the indication map of each defect detection quality index in each acquired image into the quantization model, and analyzing the measurement data of the indication map of each defect detection quality index in each acquired image by the quantization model to obtain the index quantization result of each defect detection quality index.
The quantization models corresponding to different defect detection quality indexes may also be different, for example, the defect detection quality indexes include the number and the width, and the description is continued by taking the width quantization model as an example, the width indication map measurement data in each acquired image is input into the width quantization model, and the width indication map measurement data in each acquired image is analyzed through the width quantization model, so as to output the index quantization result of the width.
Optionally, in order to determine whether the defect detection device maintains standard performance, acquiring a plurality of acquired images of the spot inspection standard component by the defect detection device, and comparing the indication map measurement data of each defect detection quality index in the plurality of acquired images with the corresponding indication map standard data to determine an index quantization result of each defect detection quality index; the indication map standard data may be indication map data of each defect detection quality index in the acquired image of the spot inspection standard by the standard defect detection device.
S503, determining the spot inspection result of the defect detection equipment according to the index quantification result of each defect detection quality index.
The spot inspection result of the defect detecting apparatus may include a defect detecting apparatus normal and a defect detecting apparatus abnormal.
In one embodiment, under the condition that index quantization results of the defect detection quality indexes are all within a preset tolerance range, determining that the spot inspection result of the defect detection equipment is normal; and determining that the spot inspection result of the defect detection equipment is abnormal when the index quantification result of any defect detection quality index is not within a preset tolerance range.
The preset tolerance range may be a fluctuation range allowable by the defect detection quality index under the condition that the defect detection equipment is normal; the tolerance ranges corresponding to the different defect detection quality indexes can be the same or different.
Under the condition that index quantification results of all defect detection quality indexes are within a preset tolerance range, the defect detection equipment determines that the point detection results of the defect detection equipment are normal when all defect detection quality indexes in a plurality of acquired images of the point detection standard component are within a normal range; and under the condition that the index quantification result of any defect detection quality index is not within a preset tolerance range, the defect detection equipment determines that the point detection result of the defect detection equipment is abnormal if the defect detection quality index within an abnormal range exists in each defect detection quality index in a plurality of acquired images of the point detection standard component.
Further, the detection of the product by the defect detection device is stopped under the condition that the point detection result of the defect detection device is abnormal, and the cause of the abnormality of the defect detection device can be determined according to the defect detection quality index of which the index quantification result is not in the preset tolerance range, and the defect detection device is calibrated again and then put into use.
In the embodiment of the application, under the condition that index quantization results of all defect detection quality indexes are within a preset tolerance range, determining that point detection results of defect detection equipment are normal; and determining that the spot inspection result of the defect detection equipment is abnormal when the index quantification result of any defect detection quality index is not within a preset tolerance range. And determining the spot inspection result of the defect detection equipment according to whether the index quantification result of each defect detection quality index is in a preset tolerance range, so that the spot inspection result of the defect detection equipment can be rapidly determined, and the spot inspection speed of the defect detection equipment is improved.
In the point inspection method of the defect detection device provided by the embodiment of the application, the indication map measurement data of each defect detection quality index in each acquired image is obtained, the index quantization result of each defect detection quality index is determined based on the indication map measurement data of each defect detection quality index in each acquired image, and then the point inspection result of the defect detection device is determined according to the index quantization result of each defect detection quality index. In the method, the defect detection quality indexes of the acquired images are quantized based on the measurement data of the indication map of each defect detection quality index in the acquired images, so that the spot detection result of the defect detection equipment can be intuitively and accurately determined, and the stability of the defect detection equipment is improved.
The defect detection quality index may include a defect length, and in the following, taking the defect detection quality index including the defect length as an example, how to obtain the measurement data of the indication map of the defect length in each acquired image is described, in one embodiment, obtaining the measurement data of the indication map of each defect detection quality index in each acquired image includes: and identifying the length indication graphs of different length gradients in each acquired image to obtain the length indication graph measurement data of each length gradient in the acquired image.
Wherein the spot inspection standard comprises a plurality of length indication diagrams of different length gradients of defect lengths.
As shown in fig. 6, fig. 6 may be a length indication diagram of a plurality of different length gradients including defect lengths on the spot inspection standard, where fig. 6 includes 5 length gradients, respectively: 10.5+/-0.01, 12.5+/-0.01, 14.5+/-0.01, 16.5+/-0.01 and 18.5+/-0.01, and the width of the length gradient can be 4+/-0.01; the unit of the dimension in fig. 6 may be millimeter, and it should be noted that fig. 6 includes 5 length gradients and specific values only as examples, and the number of the length gradients and the specific values of the length of the defect length on the spot inspection standard may be determined according to the actual scenario, and the specific values thereof may be set according to the defect length of the actual product.
The length indication map of different length gradients in each acquired image can be identified according to the length detection model, and length indication map measurement data of each length gradient in each acquired image can be obtained.
For example, length indication map measurement data of a length gradient from short to long in an acquired image can be obtained as follows: 10.48, 12.49, 14.51, 16.49, 18.51.
In the spot inspection method of the defect detection device provided by the embodiment of the application, the length indication graphs of different length gradients in each acquired image are identified, and the length indication graph measurement data of each length gradient in the acquired image are obtained. According to the method, as the point inspection standard component comprises the length indication diagrams of the plurality of different length gradients of the defect length, the length indication diagrams of the length gradients in the acquired image are identified, the length indication diagram measurement data of each length gradient in the acquired image can be obtained, the point inspection standard component is provided with the length indication diagrams of the plurality of different length gradients, and the acquired images of the point inspection standard component can accurately carry out point inspection on the length measurement capability of the defect detection device, so that a more accurate point inspection result is obtained.
Accordingly, in the case where the defect detection quality index includes a defect length, an explanation will be given below of how to determine an index quantization result of the defect length by an embodiment, in which, as shown in fig. 7, the index quantization result of each defect detection quality index is determined based on the indicator map measurement data of each defect detection quality index in each acquired image, including the steps of:
s701, standard data of each length indication map is acquired.
The standard data of each length indication graph can be the size information of each length indication graph, namely, the length gradient, the standard data of the spot inspection standard part can be read from the acquired image of the spot inspection standard part, and the standard data of each length indication graph can also be obtained from the database of the processor.
Standard data of each length indication graph in the spot inspection standard component can be detected and determined according to the length indication graph of the spot inspection standard component by standard defect detection equipment; the standard defect detection equipment is high in accuracy and precision.
Optionally, acquiring a plurality of acquired images of the spot inspection standard component by the standard defect detection device, identifying length indication graphs of different length gradients in each acquired image to obtain a plurality of length data of each length gradient, and determining an average value of the plurality of length data under each length gradient as standard data of each length indication graph.
Taking the spot check standard of fig. 6 as an example, the standard data of each length indication map may be 10.5, 12.5, 14.5, 16.5, 18.5.
S702, determining the index quantification result of the defect length according to the standard data of each length indication map and the length indication map measurement data of each length gradient.
The method for obtaining the index quantization result of the defect length may be to obtain the absolute value of the difference between the standard data of each length indication map and the length indication map measurement data of the corresponding length gradient, obtain the absolute difference of each length indication map, and determine the absolute difference of each length indication map as the index quantization result of the defect length.
The method of obtaining the index quantization result of the defect length may also be to obtain the absolute value of the difference between the standard data of each length indication map and the length indication map measurement data of the corresponding length gradient, to obtain the absolute difference of each length indication map, and to determine the average value of the absolute differences of each length indication map as the index quantization result of the defect length.
In the spot inspection method of the defect detection device provided by the embodiment of the application, standard data of each length indication map is obtained, and an index quantization result of the defect length is determined according to the standard data of each length indication map and length indication map measurement data of each length gradient. In the method, the standard data of each length indication map is obtained by standard defect detection equipment, and the standard data of each length indication map is compared with the length indication map measurement data of the corresponding length gradient, so that the index quantization result of the defect length is more accurate, and the spot detection accuracy of the defect detection equipment is improved.
In quantifying the defect length, the bias degree and/or the linearity may be used to quantify the defect length, and in the case where the index quantification result includes the bias degree and/or the linearity, the index quantification result of the defect length is described below by an embodiment, and in an embodiment, as shown in fig. 8, determining the index quantification result of the defect length according to standard data of each length indication map and length indication map measurement data of each length gradient includes the following steps:
s801, standard data of each length indication map and length indication map measurement data of each length gradient are input into a preset bias calculation model, and bias of the defect length is obtained.
The degree of bias is an indicator of the error of the measurement defect detection device.
Inputting the standard data of each length indication graph and the length indication graph measurement data of each length gradient into a preset bias degree calculation model, and analyzing the standard data of each length indication graph and the length indication graph measurement data of each length gradient through the bias degree calculation model to obtain the bias degree of the defect length.
Alternatively, the degree of bias may refer to the difference between the observed average and the standard value for the same characteristic on the same part; thus, the bias calculation model can be expressed by formula (1).
Figure SMS_1
（1）
Wherein, is%Bias A Indicating the degree of deviation of the defect length,mthe number of length gradients is shown,irepresent the firstiThe length gradient of the strip is set,
Figure SMS_2
representing the first of a plurality of acquired imagesiThe length of each length gradient indicates the average value of the map measurement data,U i represent the firstiStandard data of the length indication map for each length gradient,T 1 indicating product defect length tolerance bands, i.e.T 1 Representing the product allowed maximum defect length minus the product allowed minimum defect length.
Thus, the average value of the length indication map measurement data for each length gradient is determined from the length indication map measurement data for each length gradient, and the bias degree of the defect length is determined from the standard data for each length indication map, the average value of the length indication map measurement data for each length gradient, and the product defect length tolerance zone.
Alternatively, the defect detection apparatus may set the number of acquired images of the spot inspection standard to be 5 times or more.
S802, inputting standard data of each length indication graph and length indication graph measurement data of each length gradient into a preset linearity calculation model to obtain linearity of the defect length.
Inputting the standard data of each length indication graph and the length indication graph measurement data of each length gradient into a preset linearity calculation model, and analyzing the standard data of each length indication graph and the length indication graph measurement data of each length gradient through the linearity calculation model to obtain the linearity of the defect length.
Optionally, the linearity represents a difference in bias error over an expected operating range of the defect detection apparatus; therefore, the linearity calculation model of the defect length can be expressed by formula (2).
Figure SMS_3
（2）
Wherein, is%Linearity A Representing the linearity of the defect length.
Thus, the average value of the length indication map measurement data for each length gradient is determined from the length indication map measurement data for each length gradient, and the bias degree of the defect length is determined from the standard data for each length indication map and the average value of the length indication map measurement data for each length gradient.
Correspondingly, the bias degree and the linearity of the defect length correspond to a tolerance range, and when the index quantification result of the defect length is within a preset tolerance range, the bias degree of the defect length is within the preset bias tolerance range, and the linearity of the defect length is within the preset linearity tolerance range; taking the tolerance boundary as 5% as an example, in the case that the bias degree of the defect length is less than 5% and the linearity of the defect length is less than 5%, the defect length is determined to be within the preset tolerance range.
In the spot inspection method of the defect detection device provided by the embodiment of the application, standard data of each length indication graph and length indication graph measurement data of each length gradient are input into a preset bias degree calculation model to obtain bias degree of defect length; and inputting standard data of each length indication map and length indication map measurement data of each length gradient into a preset linearity calculation model to obtain linearity of the defect length. In the method, the accuracy of the index quantization result of the defect detection length is improved by quantifying the detection accuracy of the defect detection equipment through two dimensions of bias degree and linearity.
The defect detection quality index may also include a defect gray scale, and in the following, taking the defect detection quality index including the defect gray scale as an example, how to obtain the measurement data of the indication map of the defect length in each collected image is described, in one embodiment, obtaining the measurement data of the indication map of each defect detection quality index in each collected image includes: and identifying gray scale indication graphs of different gray scale gradients in each acquired image to obtain gray scale indication graph measurement data of each gray scale gradient in the acquired image.
The point inspection standard component comprises a gray scale indication map of a plurality of different gray scale levels of defect gray scales; as shown in fig. 9, fig. 9 may be a gray scale indication chart of 5 different gray scale levels including a defect gray scale on the spot inspection standard, it should be noted that fig. 9 includes 5 gray scale gradients only as an example, and the number of gray scale gradients and specific gray scale values of the defect gray scale on the spot inspection standard may be determined according to an actual scene, and specific values thereof may be set according to the defect gray scale of an actual product.
The gray scale indication map of different gray scale gradients in each acquired image can be identified according to the gray scale detection model, and gray scale indication map measurement data of each gray scale gradient in each acquired image is obtained.
In the spot inspection method of the defect detection device provided by the embodiment of the application, gray scale indication graphs of different gray scale gradients in each acquired image are identified, and gray scale indication graph measurement data of each gray scale gradient in the acquired image are obtained. In the method, as the point inspection standard component comprises gray indication graphs with various gray levels of defect gray levels, the gray indication graph of each gray level gradient in the acquired image is identified, the gray indication graph measurement data of each gray level gradient in the acquired image can be obtained, and the point inspection standard component is provided with the gray indication graph with various gray levels, and a plurality of acquired images of the point inspection standard component are acquired, so that the gray identification capability of the defect detection equipment can be accurately subjected to point inspection, and a more accurate point inspection result is obtained.
Accordingly, in the case where the defect detection quality index may include a defect gray scale, an embodiment of how to determine an index quantization result of the defect gray scale is described below, and in one embodiment, as shown in fig. 10, the index quantization result of each defect detection quality index is determined based on the indication map measurement data of each defect detection quality index in each acquired image, including the steps of:
S1001, standard data of each gradation indication map is acquired.
The standard data of each gray indication map may be gray information of each gray indication map, that is, gray level gradient, the standard data of each gray indication map may be read from an acquired image of the spot inspection standard member, or the standard data of each gray indication map may be obtained from a database of the processor.
Standard data of each gray indication map in the spot inspection standard component can be determined by testing the gray indication map of the spot inspection standard component according to standard defect detection equipment; the standard defect detection equipment is high in accuracy and precision.
Optionally, acquiring a plurality of acquired images of the spot inspection standard component by the standard defect detection device, identifying gray scale indication graphs of different gray scale gradients in each acquired image to obtain a plurality of gray scale data of each gray scale gradient, and determining an average value of the plurality of gray scale data under each gray scale gradient as standard data of each gray scale indication graph.
Taking the spot check standard of fig. 9 as an example, standard data of each length indication map may be 80, 110, 140, 170, 200.
S1002, determining index quantization results of the defect gray scale according to standard data of each gray scale indication map and gray scale indication map measurement data of each gray scale gradient.
The method for obtaining the index quantization result of the defect gray scale may be to obtain the absolute value of the difference between the standard data of each gray scale indication map and the gray scale indication map measurement data corresponding to the gray scale gradient, obtain the absolute difference of each gray scale indication map, and determine the absolute difference of each gray scale indication map as the index quantization result of the defect gray scale.
The method of obtaining the index quantization result of the defect gray scale may also be to obtain the absolute value of the difference between the standard data of each gray scale indication map and the gray scale indication map measurement data corresponding to the gray scale gradient, obtain the absolute difference of each gray scale indication map, and determine the average value of the absolute differences of each gray scale indication map as the index quantization result of the defect gray scale.
In the spot inspection method of the defect detection device provided by the embodiment of the application, standard data of each gray scale indication map is obtained, and an index quantization result of defect gray scale is determined according to the standard data of each gray scale indication map and gray scale indication map measurement data of each gray scale gradient. In the method, the standard data of each gray indication map is obtained by standard defect detection equipment, and the standard data of each gray indication map is compared with the gray indication map measurement data corresponding to gray gradient, so that the obtained index quantization result of the defect gray is more accurate, and the spot detection accuracy of the defect detection equipment is improved.
Similarly, when quantifying the defective gray scale, the defective gray scale may be quantified using the bias degree and/or the linearity, and in the case where the index quantification result includes the bias degree and/or the linearity, the index quantification result of the defective gray scale is described below by way of one embodiment, and in one embodiment, as shown in fig. 11, the index quantification result of the defective gray scale is determined from the standard data of each gray scale indication map and the gray scale indication map measurement data of each gray scale gradient, including the steps of:
s1101, standard data of each gray scale indication map and gray scale indication map measurement data of each gray scale gradient are sent to a preset bias calculation model, and bias of the defect gray scale is obtained.
Inputting the standard data of each gray scale indication map and the gray scale indication map measurement data of each gray scale gradient into a preset bias degree calculation model, and analyzing the standard data of each gray scale indication map and the gray scale indication map measurement data of each gray scale gradient through the bias degree calculation model to obtain the bias degree of the defect gray scale.
Alternatively, the bias calculation model of the defect gradation may be expressed by formula (3).
Figure SMS_4
（3）
Wherein, is%Bias B Indicating the degree of bias of the defect length, nThe number of gray-scale gradients is indicated,jrepresent the firstjThe gradient of the gray level is that,
Figure SMS_5
representing the first of a plurality of acquired imagesjAverage of gray scale indication map measurement data for each gray scale gradient,U j represent the firstjStandard data of gray scale indication maps of individual gray scale gradients,T 2 representing product defect gray scale tolerance bands, i.e.T 2 Representing the product allowed maximum defect grayscale minus the product allowed minimum defect grayscale.
Therefore, the average value of the gray indication map measurement data of each gray level gradient is determined according to the gray indication map measurement data of each gray level gradient, and the bias degree of the defect gray level is determined according to the standard data of each gray indication map, the average value of the gray indication map measurement data of each gray level gradient and the product defect gray level tolerance band.
S1102, standard data of each gray scale indication map and gray scale indication map measurement data of each gray scale gradient are sent to a preset linearity calculation model, and linearity of the defect gray scale is obtained.
Inputting the standard data of each gray scale indication map and the gray scale indication map measurement data of each gray scale gradient into a preset linearity calculation model, and analyzing the standard data of each gray scale indication map and the gray scale indication map measurement data of each gray scale gradient through the linearity calculation model to obtain the linearity of the defect gray scale.
Alternatively, the linearity calculation model of the defect gray scale may be expressed by formula (4).
Figure SMS_6
（4）
Wherein, is%Linearity B And the linearity of the defect gray scale is represented.
Therefore, the average value of the gradation indicating map measurement data for each gradation gradient is determined based on the gradation indicating map measurement data for each gradation gradient, and the bias of the defective gradation is determined based on the standard data for each gradation indicating map and the average value of the gradation indicating map measurement data for each gradation gradient.
Correspondingly, the bias degree and the linearity of the defect gray scale correspond to a tolerance range, and when the index quantization result of the defect gray scale is within a preset tolerance range, the bias degree of the defect gray scale is represented to be within the preset bias tolerance range, and the linearity of the defect gray scale is represented to be within the preset linearity tolerance range; taking the tolerance boundary as 5% as an example, when the bias degree of the defect gray scale is less than 5% and the linearity of the defect gray scale is less than 5%, determining that the defect gray scale is within the preset tolerance range.
In the spot inspection method of the defect detection device provided by the embodiment of the application, standard data of each gray scale indication map and gray scale indication map measurement data of each gray scale gradient are sent to a preset bias calculation model, so that bias of defect gray scales is obtained; and obtaining linearity of the defect gray scale by sending standard data of each gray scale indication map and gray scale indication map measurement data of each gray scale gradient to a preset linearity calculation model. In the method, the accuracy of the index quantization result of the defect detection length is improved by quantifying the detection accuracy of the defect detection equipment through two dimensions of bias degree and linearity.
The defect detection quality index may further include a defect resolution, and the point detection standard may further include a resolution indication map of the defect resolution in addition to the indication map of the defect length and the defect gray scale, and in one embodiment, acquiring indication map measurement data of each defect detection quality index in each acquired image includes: and carrying out image recognition on the resolution indication map in each acquired image to obtain measurement data of the resolution indication map in each acquired image.
And identifying the resolution indication map in each acquired image according to a preset resolution detection model to obtain the measurement data of the resolution indication map in each acquired image.
In the spot inspection method of the defect detection device provided by the embodiment of the application, image recognition is performed on the resolution indication map in each acquired image, and the measurement data of the resolution indication map in each acquired image is obtained. In the method, the resolution indication map of the defect resolution is included on the spot inspection standard component, the resolution indication map in the acquired image is identified, the measurement data of the resolution indication map in the acquired image can be obtained, and the resolution capability of the defect detection equipment can be accurately spot inspected by setting the resolution indication map on the spot inspection standard component and acquiring a plurality of acquired images of the spot inspection standard component, so that an accurate spot inspection result is obtained.
The resolution indication map includes a plurality of cells; in one embodiment, as shown in fig. 12, performing image recognition on the resolution indication map in each acquired image to obtain measurement data of the resolution indication map in each acquired image, including the following steps:
and S1201, identifying the resolution indication map and acquiring a size measurement value of the resolution indication map.
The resolution determines the degree of refinement of the image details. Therefore, the resolution indication map in the acquired image can be identified, and the size measurement value of the resolution indication map can be acquired.
Since the resolution may be expressed as the number of pixels included in a unit length, a plurality of cells in the resolution indication map may be expressed by black and white checkerboards, for example, as shown in fig. 13, fig. 13 may be a resolution diagram including a defect resolution on a spot inspection standard, and the resolution diagram in fig. 13 is black Bai Qige of 9×9; it should be noted that, the resolution indication chart of the black-and-white checkers of 9×9 shown in fig. 13 is merely an example, and the specific size of the black-and-white checkers on the spot inspection standard is not limited, and the specific numerical value thereof may be set according to the defect resolution of the actual product.
After a plurality of acquired images of the spot inspection standard component are acquired by the defect detection equipment, respectively carrying out size recognition on the resolution indication graphs in the acquired images, and determining size measurement values of the resolution indication graphs in the acquired images. The size measurement value of the resolution indication map in each acquired image can be identified according to a preset size identification algorithm.
S1202, determining the measurement data of the resolution indication map according to the size measurement value and the number of cells of the resolution indication map.
The number of cells of the resolution indication map includes the number of cells in the horizontal direction and the number of cells in the vertical direction, for example, in fig. 13, the number of cells in the horizontal direction of the resolution indication map is 9 and the number of cells in the vertical direction is 9.
The method for obtaining the number of cells of the resolution indication map may be to obtain the number of cells of the resolution indication map in the spot inspection standard component from a database, or may identify the number of cells of the resolution indication map from the acquired image.
Since the resolution may be expressed as the number of pixels included in a unit length, a ratio of the size measurement value to the number of cells of the resolution indication map may be determined as resolution indication map measurement data, which may represent the size of the resolution of the captured image.
In the spot inspection method of the defect detection device provided by the embodiment of the application, the resolution indication map is identified, the size measurement value of the resolution indication map is obtained, and the measurement data of the resolution indication map is determined according to the size measurement value and the number of cells of the resolution indication map. According to the method, the measurement data of the resolution indication map of the acquired image can be accurately measured through the size measurement value of the resolution indication map of the acquired image and the number of the cells of the resolution indication map, and the resolution of the acquired image is reflected through the measurement data of the resolution indication map, so that the spot inspection accuracy of the defect detection equipment is improved.
In one embodiment, the index quantification result of the defect resolution may be determined according to the resolution indication map measurement data of the acquired image, and the spot inspection result of the defect detection device may be determined according to the index quantification result of the defect resolution. For example, if the index quantization result of the defect resolution is greater than the preset resolution threshold, determining that the index quantization result of the defect resolution is within the preset tolerance range, otherwise, determining that the index quantization result of the defect resolution is not within the preset tolerance range.
It should be noted that, according to the point detection result of the defect detection device determined by the processor in the defect detection device, the point detection result of the defect detection device not only includes the image acquisition capability of the image acquisition device in the defect detection device, but also represents the processing capability of the processor, and when the point detection result of the defect detection device is normal, it is determined that both the image acquisition device and the processor in the defect detection device are normal.
Under the condition of excessive resource requirements and the like, the third party equipment can also analyze and process a plurality of acquired images shot by the image acquisition equipment so as to save processor resources, and at the moment, the third party equipment and the processor are normal.
In one embodiment, as shown in fig. 14, fig. 14 is a schematic diagram of a spot inspection standard, where the spot inspection standard includes a length indication map of 5 different defect lengths, a gray level indication map of 5 different defect gray levels, and a resolution indication map of 1 defect resolution, and a main body material of the spot inspection standard is an aluminum alloy material, for example, AL6061; and the flatness of the spot inspection standard part is required to be 0.02, the perpendicularity is required to be 0.02, the parallelism is required to be 0.02, and the total length occupied by the gray scale gradients of various defects is 45+/-0.01.
In an embodiment, taking the spot inspection standard component of fig. 14 as an example, the embodiment of the present application further provides a spot inspection method of a defect detection device, taking the defect detection device as a module defect appearance machine as an example for explanation, as shown in fig. 15, the embodiment includes the following steps:
s1501, acquiring a spot inspection standard in a standard cabinet, and acquiring a calibration label of the spot inspection standard.
S1502, the latest calibration time of the spot inspection standard component is obtained from the calibration label, and whether the spot inspection standard component meets the calibration requirement is determined according to the latest calibration time.
S1503, if the spot inspection standard component does not meet the calibration requirement, calibrating the spot inspection standard component until the spot inspection standard component meets the calibration requirement.
S1504, under the condition that the spot inspection standard part meets the calibration requirement, placing the spot inspection standard part at the position of a fixture clamp of the battery module.
S1505, the CCD camera in the control module defect appearance machine shoots the spot inspection standard part for a plurality of times, and a plurality of acquired images of the spot inspection standard part are obtained.
S1506, analyzing the plurality of acquired images to obtain the measurement data of the indication map of each defect detection quality index in each acquired image; the defect detection quality index comprises indication map measurement data under a plurality of different gradients;
the defect detection quality index comprises defect length, defect gray scale, defect resolution and the like.
S1507, determining the bias degree and the linearity of each defect detection quality index according to the indication map measurement data and the indication map standard data of each defect detection quality index in each acquired image.
S1508, determining that the spot inspection result of the defect detection device is normal under the condition that the bias degree and the linearity of each defect detection quality index are within the preset tolerance range.
S1509, in the case where there is any defect detection quality index whose bias degree and linearity are not within the preset tolerance range, determining that the spot detection result of the defect detection apparatus is abnormal.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a spot inspection device of the defect detection equipment for realizing the spot inspection method of the defect detection equipment. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the point inspection device of one or more defect detection apparatuses provided below may refer to the limitation of the point inspection method of the defect detection apparatus hereinabove, and will not be repeated herein.
In one embodiment, as shown in fig. 16, there is provided a spot inspection apparatus 1600 of a defect detection device, comprising: an image acquisition module 1601 and a detection module 1602, wherein:
an image acquisition module 1601 for acquiring a plurality of acquired images of the spot inspection standard by the defect detection apparatus; the spot inspection standard part comprises a plurality of indication diagrams of different defect detection quality indexes;
the detecting module 1602 is configured to determine a spot inspection result of the defect detecting device based on the indication map measurement data of each defect detection quality index in each of the acquired images.
In one embodiment, the image acquisition module 1601 includes:
the image acquisition unit is used for controlling the defect detection equipment to shoot the spot inspection standard piece for multiple times under the condition that the spot inspection standard piece is placed at the preset position of the target product, so as to acquire a plurality of acquired images of the spot inspection standard piece; the target product represents any product that matches the defect detection device.
In one embodiment, the apparatus 1600 further comprises:
the calibration module is used for detecting whether the standard component meets the calibration requirement or not;
and the execution module is used for executing the step of acquiring a plurality of acquired images of the spot inspection standard component by the defect detection equipment under the condition that the spot inspection standard component meets the calibration requirement.
In one embodiment, the calibration module includes:
the label acquisition unit is used for acquiring the calibration label of the spot inspection standard component;
the time determining unit is used for determining the latest calibration time of the spot inspection standard component according to the calibration label of the spot inspection standard component;
and the calibration unit is used for determining that the spot inspection standard component meets the calibration requirement under the condition that the latest calibration time is in a preset calibration period.
In one embodiment, the detection module 1602 includes:
the data acquisition unit is used for acquiring the indication map measurement data of each defect detection quality index in each acquired image;
an index quantization unit for determining an index quantization result of each defect detection quality index based on the indication map measurement data of each defect detection quality index in each acquired image;
and the analysis unit is used for determining the spot inspection result of the defect detection equipment according to the index quantification result of each defect detection quality index.
In one embodiment, the defect detection quality indicator comprises a defect length, the spot inspection standard comprises a length indication map of a plurality of different length gradients of the defect length, and the data acquisition unit comprises:
the first identification subunit is used for identifying the length indication graphs of different length gradients in each acquired image to obtain the length indication graph measurement data of each length gradient in the acquired image.
In one embodiment, the index quantization unit includes:
the first acquisition subunit is used for acquiring standard data of each length indication graph;
a first determining subunit, configured to determine an index quantization result of the defect length according to the standard data of each length indication map and the length indication map measurement data of each length gradient.
In one embodiment, the index quantization result includes bias and/or linearity, and the first determination subunit includes:
the first calculating subunit is used for inputting the standard data of each length indication graph and the length indication graph measurement data of each length gradient into a preset bias degree calculation model to obtain the bias degree of the defect length; and inputting standard data of each length indication map and length indication map measurement data of each length gradient into a preset linearity calculation model to obtain linearity of the defect length.
In one embodiment, the defect detection quality index includes a defect gray scale, the gray scale indication map of a plurality of different gray scale levels including the defect gray scale on the spot inspection standard, and the data acquisition unit includes:
the second recognition subunit is used for recognizing the gray indication map of different gray gradients in each acquired image to obtain the gray indication map measurement data of each gray gradient in the acquired image.
In one embodiment, the index quantization unit includes:
a second acquisition subunit, configured to acquire standard data of each gray indication map;
and the second determination subunit is used for determining the index quantization result of the defect gray scale according to the standard data of each gray scale indication map and the gray scale indication map measurement data of each gray scale gradient.
In one embodiment, the index quantization result includes bias and/or linearity, and the second determination subunit includes:
the second calculation subunit is used for sending the standard data of each gray scale indication map and the gray scale indication map measurement data of each gray scale gradient to a preset bias calculation model to obtain bias of the defect gray scale; and obtaining linearity of the defect gray scale by sending standard data of each gray scale indication map and gray scale indication map measurement data of each gray scale gradient to a preset linearity calculation model.
In one embodiment, the defect detection quality indicator includes a defect resolution, the point inspection standard includes a resolution indication map of the defect resolution, and the data acquisition unit includes:
and the third recognition subunit is used for carrying out image recognition on the resolution indication map in each acquired image and acquiring measurement data of the resolution indication map in each acquired image.
In one embodiment, the resolution indication map includes a plurality of cells; the third recognition subunit includes:
the fourth recognition subunit is used for recognizing the resolution indication graph and acquiring a size measurement value of the resolution indication graph;
and a third determining subunit, configured to determine the resolution indication map measurement data according to the size measurement value and the number of cells of the resolution indication map.
In one embodiment, the analysis unit comprises:
the first analysis subunit is used for determining that the spot inspection result of the defect detection equipment is normal under the condition that the index quantification result of each defect detection quality index is within a preset tolerance range;
and the second analysis subunit is used for determining that the spot inspection result of the defect detection equipment is abnormal when the index quantification result of any defect detection quality index is not within a preset tolerance range.
The respective modules in the spot inspection device of the defect inspection apparatus described above may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 16. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing spot check data of the defect detection device. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a spot inspection method of a defect detection apparatus.
It will be appreciated by those skilled in the art that the structure shown in fig. 16 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the computer device to which the present application is applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
The implementation principle and technical effect of each step implemented by the processor in the embodiment of the present application are similar to those of the point detection method of the defect detection device, and are not described herein again.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.
The steps implemented when the computer program is executed by the processor in the embodiment of the present application implement principles and technical effects similar to those of the point detection method of the defect detection apparatus described above, and are not described herein again.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
The steps implemented when the computer program is executed by the processor in the embodiment of the present application implement principles and technical effects similar to those of the point detection method of the defect detection apparatus described above, and are not described herein again.
It should be noted that, the data (including, but not limited to, data for analysis, stored data, displayed data, etc.) referred to in the present application are all information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to comply with the related laws and regulations and standards of the related countries and regions.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as Static Random access memory (Static Random access memory AccessMemory, SRAM) or dynamic Random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims (17)

1. A spot inspection method of a defect inspection apparatus, the method comprising:
acquiring a plurality of acquired images of the spot inspection standard component by the defect detection equipment; the spot inspection standard component comprises a plurality of indication diagrams of different defect detection quality indexes;
and determining a spot inspection result of the defect detection equipment based on the indication map measurement data of each defect detection quality index in each acquired image.
2. The method of claim 1, wherein acquiring a plurality of acquired images of the inspection standard by the defect inspection apparatus comprises:
under the condition that the spot inspection standard component is placed at a preset position of a target product, controlling the defect detection equipment to shoot the spot inspection standard component for multiple times, and acquiring a plurality of acquired images of the spot inspection standard component; the target product represents any product that matches the defect detection device.
3. The method according to claim 1 or 2, characterized in that the method further comprises:
detecting whether the spot inspection standard component meets the calibration requirement;
and executing the step of acquiring a plurality of acquired images of the spot inspection standard by the defect detection equipment under the condition that the spot inspection standard meets the calibration requirement.
4. A method according to claim 3, wherein said detecting whether the spot check standard meets calibration requirements comprises:
acquiring a calibration label of the spot inspection standard component;
determining the latest calibration time of the spot inspection standard component according to the calibration label of the spot inspection standard component;
and under the condition that the latest calibration time is in a preset calibration period, determining that the spot inspection standard component meets the calibration requirement.
5. The method according to claim 1 or 2, wherein determining the spot inspection result of the defect detection apparatus based on the indication map measurement data of each defect detection quality index in each of the acquired images comprises:
acquiring indication map measurement data of each defect detection quality index in each acquired image;
determining an index quantification result of each defect detection quality index based on the indication map measurement data of each defect detection quality index in each acquired image;
and determining the spot inspection result of the defect detection equipment according to the index quantification result of each defect detection quality index.
6. The method of claim 5, wherein the defect detection quality indicator comprises a defect length, the spot inspection standard comprises a plurality of length indication maps of different length gradients of the defect length, the acquiring the indication map measurement data of each defect detection quality indicator in each of the acquired images comprises:
and identifying the length indication graphs of different length gradients in each acquired image to obtain the length indication graph measurement data of each length gradient in the acquired image.
7. The method of claim 6, wherein determining an index quantization result for each defect detection quality index based on the indicator map measurement data for each defect detection quality index in each of the acquired images comprises:
standard data of each length indication graph is obtained;
and determining the index quantification result of the defect length according to the standard data of each length indication map and the length indication map measurement data of each length gradient.
8. The method of claim 7, wherein the index quantization result includes bias degree and/or linearity degree, and wherein determining the index quantization result of the defect length based on standard data of each length indication map and length indication map measurement data of each length gradient includes:
inputting standard data of each length indication map and length indication map measurement data of each length gradient into a preset bias calculation model to obtain bias of the defect length; the method comprises the steps of,
and inputting standard data of each length indication graph and length indication graph measurement data of each length gradient into a preset linearity calculation model to obtain the linearity of the defect length.
9. The method of claim 5, wherein the defect detection quality indicator comprises a defect gray scale, the spot inspection standard comprises gray scale indication maps of a plurality of different gray scale levels of the defect gray scale, the acquiring indication map measurement data of each defect detection quality indicator in each of the acquired images comprises:
and identifying gray scale indication graphs of different gray scale gradients in each acquired image to obtain gray scale indication graph measurement data of each gray scale gradient in the acquired image.
10. The method of claim 9, wherein determining an index quantization result for each defect detection quality index based on the indicator map measurement data for each defect detection quality index in each of the acquired images comprises:
standard data of each gray indication map is obtained;
and determining the index quantization result of the defect gray according to the standard data of each gray indication map and the gray indication map measurement data of each gray gradient.
11. The method according to claim 10, wherein the index quantization result includes bias degree and/or linearity degree, and the determining the index quantization result of the defective gray scale based on standard data of each gray scale indication map and gray scale indication map measurement data of each gray scale gradient includes:
The standard data of each gray scale indication map and the gray scale indication map measurement data of each gray scale gradient are sent to a preset bias calculation model, and the bias of the defect gray scale is obtained; the method comprises the steps of,
and obtaining the linearity of the defect gray scale by sending the standard data of each gray scale indication map and the gray scale indication map measurement data of each gray scale gradient to a preset linearity calculation model.
12. The method of claim 5, wherein the defect inspection quality indicator comprises a defect resolution, the point inspection standard comprises a resolution indicator of the defect resolution, the acquiring indicator measurement data for each defect inspection quality indicator in each of the acquired images comprises:
and carrying out image recognition on the resolution indication map in each acquired image to obtain measurement data of the resolution indication map in each acquired image.
13. The method of claim 12, wherein the resolution indication map comprises a plurality of cells; the image recognition is performed on the resolution indication map in each acquired image, and the measurement data of the resolution indication map in each acquired image is obtained, including:
Identifying the resolution indication map and acquiring a size measurement value of the resolution indication map;
and determining the measurement data of the resolution indication map according to the size measurement value and the cell number of the resolution indication map.
14. The method according to claim 5, wherein the determining the spot inspection result of the defect inspection apparatus based on the index quantization result of each of the defect inspection quality indexes includes:
under the condition that index quantization results of the defect detection quality indexes are all within a preset tolerance range, determining that point detection results of the defect detection equipment are normal;
and determining that the point detection result of the defect detection equipment is abnormal when the index quantification result of any defect detection quality index is not within a preset tolerance range.
15. A spot inspection apparatus of a defect inspection device, the apparatus comprising:
the image acquisition module is used for acquiring a plurality of acquired images of the spot inspection standard component by the defect detection equipment; the spot inspection standard component comprises a plurality of indication diagrams of different defect detection quality indexes;
and the detection module is used for determining the spot inspection result of the defect detection equipment based on the indication map measurement data of each defect detection quality index in each acquired image.
16. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 14 when the computer program is executed.
17. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 14.
CN202310612766.4A 2023-05-29 2023-05-29 Point inspection method, point inspection device, point inspection equipment and point inspection equipment for defect detection equipment and storage medium Active CN116342599B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310612766.4A CN116342599B (en) 2023-05-29 2023-05-29 Point inspection method, point inspection device, point inspection equipment and point inspection equipment for defect detection equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310612766.4A CN116342599B (en) 2023-05-29 2023-05-29 Point inspection method, point inspection device, point inspection equipment and point inspection equipment for defect detection equipment and storage medium

Publications (2)

Publication Number Publication Date
CN116342599A true CN116342599A (en) 2023-06-27
CN116342599B CN116342599B (en) 2023-11-14

Family

ID=86893314

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310612766.4A Active CN116342599B (en) 2023-05-29 2023-05-29 Point inspection method, point inspection device, point inspection equipment and point inspection equipment for defect detection equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116342599B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117723551A (en) * 2024-02-18 2024-03-19 宁德时代新能源科技股份有限公司 Battery detection device, point detection method, battery production device and detection method
CN117890378A (en) * 2024-02-22 2024-04-16 宁德时代新能源科技股份有限公司 Battery appearance defect detection system and point detection method
CN117890379A (en) * 2024-02-22 2024-04-16 宁德时代新能源科技股份有限公司 Tab ultrasonic welding detection system and spot inspection method

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111833303A (en) * 2020-06-05 2020-10-27 北京百度网讯科技有限公司 Product detection method and device, electronic equipment and storage medium
CN112241699A (en) * 2020-10-13 2021-01-19 无锡先导智能装备股份有限公司 Object defect category identification method and device, computer equipment and storage medium
CN113487607A (en) * 2021-09-06 2021-10-08 深圳新视智科技术有限公司 Defect detection method and device based on multi-view-field image
CN114935576A (en) * 2022-06-14 2022-08-23 广汽本田汽车有限公司 Method, device, equipment and medium for verifying accuracy of workpiece visual detection equipment
CN115184359A (en) * 2022-06-01 2022-10-14 贵州开放大学(贵州职业技术学院) Surface defect detection system and method capable of automatically adjusting parameters
US20220383479A1 (en) * 2021-05-20 2022-12-01 Hon Hai Precision Industry Co., Ltd. Method for detecting defects in images, computer device, and storage medium
CN115829925A (en) * 2022-10-09 2023-03-21 深圳思谋信息科技有限公司 Appearance defect detection method and device, computer equipment and storage medium
CN115937101A (en) * 2022-11-15 2023-04-07 苏州凌云光工业智能技术有限公司 Quality detection method, device, equipment and storage medium

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111833303A (en) * 2020-06-05 2020-10-27 北京百度网讯科技有限公司 Product detection method and device, electronic equipment and storage medium
CN112241699A (en) * 2020-10-13 2021-01-19 无锡先导智能装备股份有限公司 Object defect category identification method and device, computer equipment and storage medium
US20220383479A1 (en) * 2021-05-20 2022-12-01 Hon Hai Precision Industry Co., Ltd. Method for detecting defects in images, computer device, and storage medium
CN113487607A (en) * 2021-09-06 2021-10-08 深圳新视智科技术有限公司 Defect detection method and device based on multi-view-field image
CN115184359A (en) * 2022-06-01 2022-10-14 贵州开放大学(贵州职业技术学院) Surface defect detection system and method capable of automatically adjusting parameters
CN114935576A (en) * 2022-06-14 2022-08-23 广汽本田汽车有限公司 Method, device, equipment and medium for verifying accuracy of workpiece visual detection equipment
CN115829925A (en) * 2022-10-09 2023-03-21 深圳思谋信息科技有限公司 Appearance defect detection method and device, computer equipment and storage medium
CN115937101A (en) * 2022-11-15 2023-04-07 苏州凌云光工业智能技术有限公司 Quality detection method, device, equipment and storage medium

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117723551A (en) * 2024-02-18 2024-03-19 宁德时代新能源科技股份有限公司 Battery detection device, point detection method, battery production device and detection method
CN117890378A (en) * 2024-02-22 2024-04-16 宁德时代新能源科技股份有限公司 Battery appearance defect detection system and point detection method
CN117890379A (en) * 2024-02-22 2024-04-16 宁德时代新能源科技股份有限公司 Tab ultrasonic welding detection system and spot inspection method

Also Published As

Publication number Publication date
CN116342599B (en) 2023-11-14

Similar Documents

Publication Publication Date Title
CN116342599B (en) Point inspection method, point inspection device, point inspection equipment and point inspection equipment for defect detection equipment and storage medium
WO2021000524A1 (en) Hole protection cap detection method and apparatus, computer device and storage medium
CN109949305B (en) Product surface defect detection method and device and computer equipment
CN110930352B (en) Object color difference defect detection method, device, computer equipment and storage medium
CN111814740B (en) Pointer instrument reading identification method, device, computer equipment and storage medium
CN115063584A (en) Pipeline steam leakage detection method and detection system based on deep learning
CN113469971A (en) Image matching method, image matching detection device and storage medium
CN113808132B (en) Three-dimensional network model quality detection method and device and computer equipment
CN116067671B (en) Method, system and medium for testing vehicle paint quality
CN117011365A (en) Dimension measuring method, dimension measuring device, computer equipment and storage medium
CN116448960A (en) Chip quality detection method and device, electronic equipment and storage medium
CN111259903A (en) Identification table counting method and device, readable storage medium and computer equipment
CN116137061A (en) Training method and device for quantity statistical model, electronic equipment and storage medium
CN112668365A (en) Material warehousing identification method, device, equipment and storage medium
CN116385460A (en) Cell image processing method, device and computer equipment
CN116007504A (en) Crack detection module, device and computer equipment based on image technology
CN110017998A (en) Vehicle checking method, device and equipment
CN115526855A (en) Method and device for detecting subfissure defect of battery piece, computer equipment and storage medium
Hassan et al. Compressed air leakage detection and quantification through infrared thermography
CN116665135B (en) Thermal runaway risk early warning method and device for battery pack of energy storage station and electronic equipment
CN113191017B (en) Virtual measurement model construction method, virtual measurement method, system, electronic device and computer-readable storage medium
JP2012042370A (en) Assembly inspection device, assembly inspection method, and assembly inspection program
CN112364948B (en) Vehicle information storage method based on principal component analysis
CN116563841B (en) Detection method and detection device for power distribution network equipment identification plate and electronic equipment
CN111145674B (en) Display panel detection method, electronic device and storage medium

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