CN114862777A - Connecting sheet welding detection method and system - Google Patents
Connecting sheet welding detection method and system Download PDFInfo
- Publication number
- CN114862777A CN114862777A CN202210431797.5A CN202210431797A CN114862777A CN 114862777 A CN114862777 A CN 114862777A CN 202210431797 A CN202210431797 A CN 202210431797A CN 114862777 A CN114862777 A CN 114862777A
- Authority
- CN
- China
- Prior art keywords
- welding
- connecting sheet
- image
- defect
- deep learning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/30108—Industrial image inspection
- G06T2207/30152—Solder
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Evolutionary Biology (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Geometry (AREA)
Abstract
The invention discloses a connecting sheet welding detection method and a system thereof, wherein the detection method comprises the following steps: s1: collecting an image of the connecting sheet by a line scanning laser camera; s2: segmenting and extracting the image to obtain a welding area image of the connecting sheet; s3: inputting the welding area image into a deep learning network model to identify the defect characteristics of the welding area image; s4: and outputting a detection result according to the defect characteristics. The invention can realize visual detection of the welding area of the connecting sheet, greatly improve the detection efficiency, save the labor time and avoid the condition that the detection result is influenced by artificial subjective factors compared with the existing manual detection mode.
Description
Technical Field
The invention relates to the technical field of battery connecting sheet detection, in particular to a connecting sheet welding detection method and a system thereof.
Background
According to the production process of the battery, the battery and the connecting sheet (i.e. the connector) need to be welded and connected by laser welding and the like, and further, the welding area of the connecting sheet needs to be detected: whether the related dimension of welding seam, welding mark or melting width is abnormal or not is judged according to the defect problem, and whether the corresponding connecting sheet is a qualified product or not is judged. The existing connecting piece welding detection mode is as follows: the welding area of the connecting sheet is manually detected by the eyes of a worker to judge whether the welding of the connecting sheet meets the requirements of relevant standards, the detection efficiency of the conventional manual detection mode is low, the labor time is wasted, and the condition that the detection result is influenced by the artificial subjective factors such as visual fatigue of the worker possibly exists.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a connecting sheet welding detection method and a connecting sheet welding detection system, which can solve the technical problems.
(II) technical scheme
In order to solve the above technical problems, the present invention provides the following technical solutions: a connecting sheet welding detection method comprises the following steps:
s1: collecting an image of the connecting sheet by a line scanning laser camera;
s2: segmenting and extracting the image to obtain a welding area image of the connecting sheet;
s3: inputting the welding area image into a deep learning network model to identify the defect characteristics of the welding area image;
s4: and outputting a detection result according to the defect characteristics.
Preferably, the defect is characterized by a weld, weld impression or weld width.
Preferably, step S4 specifically includes: and judging whether the interval of the welding line belongs to a preset numerical range of the interval of the welding line, and if not, determining that the detection result corresponding to the connecting sheet is unqualified.
Preferably, step S4 specifically includes: and judging whether the length of the welding mark belongs to a preset welding mark length value range or not, and if not, determining that the detection result corresponding to the connecting sheet is unqualified.
Preferably, step S4 specifically includes: and judging whether the size of the fusion width belongs to a preset fusion width size numerical range, if not, determining that the detection result corresponding to the connecting sheet is unqualified.
Preferably, step S4 specifically includes: and judging whether the welding seam has a burst point or not, and if so, determining that the detection result corresponding to the connecting sheet is unqualified.
Preferably, the connecting sheet welding detection method further comprises the following steps: collecting a defect image sample; marking each defect feature on the defect image sample; inputting the marked defect image samples into a plurality of different deep learning network models to be selected for model training; comparing the defect feature recognition results output by the deep learning network models to be selected to determine that one of the deep learning network models to be selected is the deep learning network model adopted in step S3.
Preferably, after determining the deep learning network model, the method further includes: and continuously acquiring defect image samples to perform model iteration on the deep learning network model.
In order to solve the above technical problem, the present invention provides another technical solution as follows: a tab weld detection system, comprising:
the line scanning laser camera is used for acquiring images of the connecting sheets;
the image processing module is used for segmenting and extracting the image to obtain a welding area image of the connecting sheet;
the defect identification module is used for inputting the welding area image into the deep learning network model so as to identify the defect characteristics of the welding area image;
and the detection result judging module is used for outputting a detection result according to the defect characteristics.
Preferably, the laser light source of the line scanning laser camera adopts a blue semiconductor laser generator.
(III) advantageous effects
Compared with the prior art, the invention provides a connecting sheet welding detection method and a system thereof, which have the following beneficial effects: according to the invention, the welding area image is input into the deep learning network model to identify the defect characteristics of the welding area image, and the detection result is further output according to the defect characteristics, so that the visual detection of the welding area of the connecting sheet is realized.
Drawings
FIG. 1 is a flow chart of the steps of a connection tab welding inspection method of the present invention;
fig. 2 is a block diagram of a bonding pad welding detection system according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a connecting sheet welding detection method, which comprises the following steps:
s1: and the line scanning laser camera collects the image of the connecting sheet.
In particular, a line scan laser camera, i.e. a linear laser scanner, may be used to acquire a 3D image, which may image a 3D profile of a connection piece to obtain an image of the connection piece.
S2: and (4) segmenting and extracting the image to obtain an image of the welding area of the connecting sheet.
In step S2, the image acquired in step S1 may be segmented and extracted by a foreground segmentation algorithm to obtain an image of the welding area of the connecting piece.
S3: and inputting the welding area image into a deep learning network model to identify the defect characteristics of the welding area image.
The defect feature may in particular be a weld seam, a weld impression or a weld width of the welded region of the connecting piece.
S4: and outputting a detection result according to the defect characteristics.
When the defect is a weld, the step S4 specifically includes: and judging whether the interval of the welding line belongs to a preset numerical range of the interval of the welding line, and if not, determining that the detection result corresponding to the connecting sheet is unqualified. The preset numerical range of the welding line spacing size can be 4 +/-0.3 mm, and corresponds to the normal numerical range of the welding line spacing size.
When the defect feature is solder printing, the step S4 specifically includes: and judging whether the length of the welding mark belongs to a preset numerical range of the length of the welding mark, and if not, determining that the detection result corresponding to the connecting sheet is unqualified. The preset numerical range of the length of the welding mark can be 11 +/-0.3 mm, and if the preset numerical range is not included, the welding mark is longer or shorter.
When the defect feature is the weld width, the step S4 specifically includes: and judging whether the size of the molten width belongs to a preset numerical range of the molten width, and if not, determining that the detection result corresponding to the connecting sheet is unqualified. The preset numerical range of the melt width can be more than or equal to 1.8 mm.
Further, step S4 may specifically be: and judging whether the welding seam has a burst point or not, and if so, determining that the detection result corresponding to the connecting sheet is unqualified. Most of the explosion points have larger area, large height fluctuation and variable forms, are obviously different from normal welding areas, and have smaller area and are similar to pinhole defects.
In addition, the step S4 can also be used to determine whether the position of the weld deviates from the required position. The defect characteristic can also be the size of the longitudinal distance between the positive and negative connecting sheets, and correspondingly, the preset longitudinal distance between the positive and negative connecting sheets can be 123 +/-0.3 mm, so as to judge whether the connecting sheets deviate.
In addition, the step S4 may also be configured to detect whether the maximum height of the welding region is greater than a preset height threshold, and if so, the detection result corresponding to the connecting sheet is unqualified.
In addition, the welding area image may be blank, that is, no bonding pad welding is detected at all.
It can be understood that, when the detection result of any defect feature is not qualified, the connecting sheet corresponds to an NG product, and further, the corresponding defect feature image and the defect feature data can be stored. And when the detection results of all the defect characteristics are qualified, the connecting sheet is correspondingly a good product.
In addition, the connecting sheet welding detection method further comprises the following steps: collecting a defect image sample; marking each defect feature on the defect image sample; inputting the marked defect image samples into a plurality of different deep learning network models to be selected for model training, so that defect characteristics can be classified; comparing the defect feature recognition results output by the deep learning network models to be selected to determine one of the deep learning network models to be selected as the deep learning network model adopted in the step S3, that is, comparing the truth results of the defect judgment output by the different deep learning network models and combining with manual re-judgment to select the optimal model. In the above model training, it may be specifically noise learning to enhance the fault tolerance of the model using noisy data. In the above defect image sample collection, a dynamic sampling algorithm may be specifically adopted: in general, if the input defects are unevenly distributed and the quantity proportion is maladjusted in the model training process, the prediction accuracy of the model is reduced, and the purpose of the dynamic sampling algorithm is to weaken the problems. The deep learning network model may be CNN, DBN, RNN, RNTN, or the like.
In addition, in order to improve the accuracy of the recognition judgment of the deep learning network model, after determining the deep learning network model, the method may further include: and continuously acquiring defect image samples to perform model iteration on the deep learning network model and perform parameter adjustment on the deep learning network model.
The invention also provides a connection piece welding detection system, which comprises:
and the line scanning laser camera 11 is used for acquiring images of the connecting sheets.
And the image processing module 12 is used for segmenting and extracting the image to obtain an image of the welding area of the connecting sheet.
And the defect identification module 13 is used for inputting the welding area image into the deep learning network model so as to identify the defect characteristics of the welding area image.
And the detection result judging module 14 is used for outputting a detection result according to the defect characteristics.
The specific functions of the connecting sheet welding detection system can be referred to the description of the above connecting sheet welding detection method embodiment, and are not described in detail here.
Preferably, the laser light source of the line scanning laser camera adopts a blue semiconductor laser generator: the concave-convex change of the welding spot in the welding area is small, the welding spot belongs to a tiny object on the surface, according to the relationship between the wavelength of light and the diffraction phenomenon (any obstacle can cause the wave to generate the diffraction phenomenon, but the condition for generating the obvious diffraction phenomenon is harsh), when the length of the gap or the obstacle is smaller than or close to the wavelength of the wave, the more obvious the diffraction effect of the wave is, the longer the wavelength is, the more loose the requirement for meeting the condition for generating the obvious diffraction phenomenon is, so the more easy the wave is to diffract), and the shorter the wavelength of blue light is, so the blue semiconductor laser generator is preferably adopted as the laser source of the line scanning laser camera.
Compared with the prior art, the invention provides a connecting sheet welding detection method and a system thereof, which have the following beneficial effects: according to the invention, the welding area image is input into the deep learning network model to identify the defect characteristics of the welding area image, and the detection result is further output according to the defect characteristics, so that the visual detection of the welding area of the connecting sheet is realized.
It is to be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A connecting sheet welding detection method is characterized by comprising the following steps:
s1: collecting an image of the connecting sheet by a line scanning laser camera;
s2: segmenting and extracting the image to obtain a welding area image of the connecting sheet;
s3: inputting the welding region image into a deep learning network model to identify the defect characteristics of the welding region image;
s4: and outputting a detection result according to the defect characteristics.
2. The connection piece welding detection method according to claim 1, characterized in that: the defect is characterized by a weld, weld mark, or weld width.
3. The connecting sheet welding detection method according to claim 2, wherein the step S4 is specifically: and judging whether the interval of the welding line belongs to a preset numerical range of the interval of the welding line, and if not, determining that the detection result corresponding to the connecting sheet is unqualified.
4. The connecting sheet welding detection method according to claim 2, wherein the step S4 is specifically: and judging whether the length of the welding mark belongs to a preset welding mark length value range or not, and if not, determining that the detection result corresponding to the connecting sheet is unqualified.
5. The connecting sheet welding detection method according to claim 2, wherein the step S4 is specifically: and judging whether the size of the fusion width belongs to a preset fusion width size numerical range, and if not, determining that the detection result corresponding to the connecting sheet is unqualified.
6. The connecting sheet welding detection method according to claim 2, wherein the step S4 is specifically: and judging whether the welding seam has a detonation point or not, and if so, determining that the detection result corresponding to the connecting sheet is unqualified.
7. The connection piece welding detection method according to claim 1, further comprising the steps of: collecting a defect image sample; marking each defect feature on the defect image sample; inputting the labeled defect image samples into a plurality of different deep learning network models to be selected for model training; comparing the defect feature recognition results output by the deep learning network models to be selected to determine that one of the deep learning network models to be selected is the deep learning network model adopted in the step S3.
8. The connection tab welding inspection method according to claim 7, further comprising, after determining the deep learning network model: continuously acquiring the defect image samples to perform model iteration on the deep learning network model.
9. A connection piece welding detection system, comprising:
the line scanning laser camera is used for acquiring images of the connecting sheets;
the image processing module is used for segmenting and extracting the image to obtain a welding area image of the connecting sheet;
the defect identification module is used for inputting the welding area image into a deep learning network model to identify the defect characteristics of the welding area image;
and the detection result judging module is used for outputting a detection result according to the defect characteristics.
10. The tab weld detection system of claim 9, wherein: the laser light source of the line scanning laser camera adopts a blue semiconductor laser generator.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210431797.5A CN114862777A (en) | 2022-04-22 | 2022-04-22 | Connecting sheet welding detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210431797.5A CN114862777A (en) | 2022-04-22 | 2022-04-22 | Connecting sheet welding detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114862777A true CN114862777A (en) | 2022-08-05 |
Family
ID=82632645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210431797.5A Pending CN114862777A (en) | 2022-04-22 | 2022-04-22 | Connecting sheet welding detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114862777A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117783147A (en) * | 2024-02-27 | 2024-03-29 | 宁德时代新能源科技股份有限公司 | Welding detection method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108021938A (en) * | 2017-11-29 | 2018-05-11 | 中冶南方工程技术有限公司 | A kind of Cold-strip Steel Surface defect online detection method and detecting system |
| CN108508087A (en) * | 2018-03-14 | 2018-09-07 | 中车青岛四方机车车辆股份有限公司 | Lap weld molten wide detection method, device and system |
| CN109859177A (en) * | 2019-01-17 | 2019-06-07 | 航天新长征大道科技有限公司 | Industrial x-ray image assessment method and device based on deep learning |
| CN112184648A (en) * | 2020-09-22 | 2021-01-05 | 苏州中科全象智能科技有限公司 | Piston surface defect detection method and system based on deep learning |
| CN113592813A (en) * | 2021-07-30 | 2021-11-02 | 深圳大学 | New energy battery welding defect detection method based on deep learning semantic segmentation |
-
2022
- 2022-04-22 CN CN202210431797.5A patent/CN114862777A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108021938A (en) * | 2017-11-29 | 2018-05-11 | 中冶南方工程技术有限公司 | A kind of Cold-strip Steel Surface defect online detection method and detecting system |
| CN108508087A (en) * | 2018-03-14 | 2018-09-07 | 中车青岛四方机车车辆股份有限公司 | Lap weld molten wide detection method, device and system |
| CN109859177A (en) * | 2019-01-17 | 2019-06-07 | 航天新长征大道科技有限公司 | Industrial x-ray image assessment method and device based on deep learning |
| CN112184648A (en) * | 2020-09-22 | 2021-01-05 | 苏州中科全象智能科技有限公司 | Piston surface defect detection method and system based on deep learning |
| CN113592813A (en) * | 2021-07-30 | 2021-11-02 | 深圳大学 | New energy battery welding defect detection method based on deep learning semantic segmentation |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117783147A (en) * | 2024-02-27 | 2024-03-29 | 宁德时代新能源科技股份有限公司 | Welding detection method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113362326B (en) | Method and device for detecting defects of welding spots of battery | |
| WO2021169335A1 (en) | Visual online detection method for laser welding point of lithium battery tab | |
| CN102455171B (en) | Method for detecting geometric shape of back of tailor-welding weld and implementing device thereof | |
| CN111815572B (en) | Method for detecting welding quality of lithium battery based on convolutional neural network | |
| CN109886298A (en) | A kind of detection method for quality of welding line based on convolutional neural networks | |
| CN111815555A (en) | Metal additive manufacturing image detection method and device combining anti-neural network with local binary | |
| CN107402220A (en) | A kind of selective laser fusing shaping powdering quality vision online test method and system | |
| CN109916910B (en) | Photovoltaic glass edge defect detection system and corresponding method | |
| CN116423005B (en) | Tin soldering process optimization method and system for improving welding precision | |
| Chu et al. | A study on welding quality inspection system for shell-tube heat exchanger based on machine vision | |
| CN112150410A (en) | Automatic detection method and system for weld defects | |
| CN113470005B (en) | Welding spot detection device and welding spot detection method for cylindrical battery cap | |
| CN109741295B (en) | Product quality detection method and device | |
| CN116597391B (en) | Synchronous on-line monitoring method for weld surface morphology and penetration state | |
| CN114862777A (en) | Connecting sheet welding detection method and system | |
| KR101026720B1 (en) | High-speed laser vision sensor system, high-speed image processing method and weld bead inspection mehtod using the same | |
| CN115601359A (en) | Welding seam detection method and device | |
| CN113077416A (en) | Welding spot welding defect detection method and system based on image processing | |
| CN115121895A (en) | Selective wave-soldering early warning method and device based on deep learning and storage medium | |
| CN113781458A (en) | Artificial intelligence based identification method | |
| CN114627122A (en) | Defect detection method and device | |
| CN116563277B (en) | Machine vision-based copper-clad aluminum surface defect detection method and system | |
| CN117455917A (en) | Establishment of false alarm library of etched lead frame and false alarm on-line judging and screening method | |
| CN116664508A (en) | Weld surface quality detection method and computer readable storage medium | |
| CN115213563B (en) | Laser intelligent welding method and system |
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 |