CN110222679A - A kind of general battery polarity automatic testing method based on deep learning - Google Patents
A kind of general battery polarity automatic testing method based on deep learning Download PDFInfo
- Publication number
- CN110222679A CN110222679A CN201910386913.4A CN201910386913A CN110222679A CN 110222679 A CN110222679 A CN 110222679A CN 201910386913 A CN201910386913 A CN 201910386913A CN 110222679 A CN110222679 A CN 110222679A
- Authority
- CN
- China
- Prior art keywords
- cathode
- anode
- battery
- detected
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- 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
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- 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)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to battery polar detection technique fields, specifically disclose a kind of general battery polarity automatic testing method based on deep learning, the method includes obtaining the picture of position to be detected;Determine battery polar region to be detected;Identification classification is carried out to the battery polar region to be detected using deep learning algorithm model, obtain battery polar classification results, the present invention is based on deep learnings to carry out automatic detection classification to battery polar, all sample patterns, training sample only need to be provided, model will learn the feature representation to classification automatically, it can be good at the feature of the complicated battery polar of processing, accurately identification battery polar effectively solves the unstability of traditional detection method, improves production efficiency and product quality.
Description
Technical field
The present invention relates to battery polar detection technique field more particularly to a kind of general battery poles based on deep learning
Property automatic testing method.
Background technique
When the battery pack of production power battery or other products, need anode and cathode by multiple batteries according to certain
Sequence is welded into battery pack.Misplaced in order to prevent, leakage is put, and is led to product short circuit and is resulted in waste of resources, needs accurately to distinguish
The positive-negative polarity of each cell area.
The anode of battery posts highland barley paper, and the reeded silver color border circular areas of the intermediate surrounding of anode, cathode without highland barley paper,
Centre is the border circular areas of silver color un-grooved, rather than anode includes that anode does not paste highland barley paper, cathode, cathode one layer of highland barley paper of patch
Two layers of highland barley paper is pasted with cathode, non-cathode includes that positive, positive highland barley paper, two layers of highland barley paper of anode patch, the cathode of not pasting pastes one layer
Highland barley paper and cathode paste two layers of highland barley paper, although each polarity have in the color of appearance centainly can discrimination, exist again
Extremely similar feature.
Detection for battery polar, by the way of the mostly artificial screening used in industry at present or traditional morphology
Analysis method, but since the diversity of battery polar feature, two kinds of traditional detection methods have very big drawback, it is difficult to have steady
Fixed differentiation is extremely easy detection failure, the identification battery polar of mistake.
Summary of the invention
In view of the above technical problems, the present invention provides a kind of, and the general battery polarity based on deep learning detects automatically
Method can be good at the feature of the complicated battery polar of processing, accurately identify battery polar, effectively solve traditional detection side
The unstability of method, improves production efficiency and product quality.
In order to solve the above technical problem, the present invention provides concrete scheme it is as follows:
A kind of general battery polarity automatic testing method based on deep learning, which comprises
Obtain the picture of position to be detected;
Determine battery polar region to be detected;
Identification classification is carried out to the battery polar region to be detected using deep learning algorithm model, obtains battery polar point
Class result.
The present invention is based on deep learnings to carry out automatic detection classification to battery polar, only need to provide all sample patterns,
Training sample, model will learn the feature representation to classification automatically, can be good at the feature of the complicated battery polar of processing,
Accurately identification battery polar effectively solves the unstability of traditional detection method, improves production efficiency and product quality.
Optionally, the deep learning algorithm model includes anode, non-anode, four disaggregated model of cathode and non-cathode.
Optionally, the feature input of the positive model includes anode;
The feature input of the non-positive model includes that anode does not paste highland barley paper, cathode, cathode one layer of highland barley paper of patch and cathode patch
Two layers of highland barley paper;
The feature input of the cathode model includes cathode;
The feature input of the non-cathode model does not paste highland barley paper, two layers of highland barley paper of anode patch, cathode including anode, anode and pastes one
Layer highland barley paper and cathode paste two layers of highland barley paper.
Optionally, the battery polar classification results include anode, non-anode, four class polarity of cathode and non-cathode.
Optionally, the method also includes:
Construct multilayer convolutional neural networks;
Using the error reverse conduction algorithm training multilayer convolutional neural networks, battery polar identification model is obtained;
The output node layer of the multilayer convolutional network is revised as 4, and utilizes the power of trained battery polar identification model
The weight of modified multilayer convolutional neural networks is initialized again;
Modified multilayer convolutional neural networks are trained with anode, non-anode, cathode and non-negative pole data set, are obtained just
Pole, non-anode, four disaggregated model of cathode and non-cathode.
Optionally, the multilayer convolutional neural networks include input layer, hidden layer and output layer;
Data of the input layer for entire multilayer convolutional neural networks input;
The hidden layer includes anode, four non-anode, cathode and non-cathode training patterns;
The output layer is for exporting battery polar classification results.
Optionally, the picture for obtaining position to be detected, specifically includes:
Battery to be detected is manually placed in the enterprising line position of positioning module and sets fixation;
Industrial camera automatically takes pictures to battery to be detected on positioning module, obtains the picture of position to be detected.
Optionally, the industrial camera automatically takes pictures to battery to be detected on positioning module, specifically includes:
The industrial camera determines the number taken pictures according to the focal length of number of batteries to be detected on positioning module and industrial camera,
If repeatedly taking pictures, the plurality of pictures obtained after repeatedly taking pictures detects after being spliced into a picture.
Optionally, determination battery polar region to be detected, specifically includes:
Using the method for region segmentation, the correct pole that the detection position of each battery to be detected and the position should place is determined
Property, finally determine battery polar region to be detected.
Compared with prior art, the beneficial effects of the present invention are: the present invention is based on deep learning to battery polar carry out
Automatic detection classification, only need to provide all sample patterns, training sample, model will learn the mark sheet to classification automatically
It reaches, can be good at the feature of the complicated battery polar of processing, accurately identify battery polar, effectively solution traditional detection method
Unstability, improve production efficiency and product quality.
Detailed description of the invention
Fig. 1 is a kind of process of the general battery polarity automatic testing method based on deep learning in the embodiment of the present invention
Figure.
Fig. 2 is the acquisition flow chart of deep learning algorithm model in the embodiment of the present invention.
Fig. 3 is the flow chart that the picture of position to be detected is obtained in the embodiment of the present invention.
Specific embodiment
For the technical solution that the present invention will be described in detail, below in conjunction with the attached drawing of the embodiment of the present invention, to of the invention real
The technical solution for applying example carries out clear, complete description.Obviously, described embodiment is a part of the embodiments of the present invention,
Instead of all the embodiments.Based on described the embodiment of the present invention, those of ordinary skill in the art are without creativeness
Every other embodiment obtained, shall fall within the protection scope of the present invention under the premise of labour.
Unless otherwise defined, all technical and scientific terms used herein and belong to technical field of the invention
The normally understood meaning of technical staff it is identical.Term used herein is intended merely to description specific embodiment
Purpose, it is not intended that in the limitation present invention.Term " and or " used herein includes one or more relevant listed items
Any and all combinations.
For example, a kind of general battery polarity automatic testing method based on deep learning, which comprises
Obtain the picture of position to be detected;
Determine battery polar region to be detected;
Identification classification is carried out to the battery polar region to be detected using deep learning algorithm model, obtains battery polar point
Class result.
The present embodiment is based on deep learning and carries out automatic detection classification to battery polar, need to only provide all sample moulds
Type, training sample, model will learn the feature representation to classification automatically, can be good at the spy of the complicated battery polar of processing
Sign, accurately identifies battery polar, effectively solves the unstability of traditional detection method, improves production efficiency and product quality.
In some embodiments, it is detected automatically as shown in Figure 1, providing a kind of general battery polarity based on deep learning
Method, which comprises
S1, the picture for obtaining position to be detected;
S2, battery polar region to be detected is determined;
S3, identification classification is carried out to the battery polar region to be detected using deep learning algorithm model, obtains battery pole
Property classification results.
Specifically, the present embodiment is mainly used in when producing the battery pack of power battery or other products, needing will be more
The anode and cathode of a battery are welded into battery pack in a certain order, and misplaced in order to prevent, leakage is put, cause product short circuit and
It results in waste of resources, needs accurately to distinguish the positive-negative polarity of each cell area, battery polar is carried out based on deep learning
Automatic detection classification, provides all sample patterns, and training sample makes model learn the feature representation to classification, picture automatically
Acquisition can be obtained by the shooting of industrial camera, after the picture for obtaining position to be detected, according to the feature of actual product, really
Battery polar region to be detected on the picture of fixed position to be detected, the product can be battery pack or battery pack comprising
Multiple batteries, and the anode and cathode of multiple batteries are welded according to certain sequence, are determining battery polar to be detected
Behind region, identification classification is carried out to battery polar region to be detected using preparatory trained deep learning algorithm model, is obtained
To battery polar classification results, the unstability of traditional detection method is effectively solved, production operation efficiency is improved and product uses
Quality.
In some embodiments, the deep learning algorithm model includes that anode, non-anode, cathode and non-cathode four are classified
Model.
The polar character of battery has diversity, and e.g., the anode of battery posts highland barley paper, and the intermediate surrounding of anode is fluted
Silver color border circular areas;For cathode without highland barley paper, centre is the border circular areas of silver color un-grooved;Rather than anode includes that anode does not paste
Highland barley paper, cathode, cathode paste one layer of highland barley paper and cathode pastes two layers of highland barley paper;Non- cathode include anode, anode do not paste highland barley paper,
Two layers of highland barley paper of anode patch, cathode paste one layer of highland barley paper and cathode pastes two layers of highland barley paper.In order to realize, processing is multiple well
The feature of miscellaneous battery polar accurately identifies battery polar effect, the deep learning algorithm model in the example include anode,
Non- anode, four disaggregated model of cathode and non-cathode, positive, non-anode, cathode and four disaggregated model of non-cathode are preparatory training
Obtained model, therefore, in the picture for inputting position to be detected and after determining battery polar region to be detected, each model can
Identification classification is carried out to the battery polar region to be detected, obtains battery polar classification results.
In some embodiments, the feature input of the positive model includes anode.
The feature input of the non-anode model includes that anode does not paste highland barley paper, cathode, cathode one layer of highland barley paper of patch and bears
Paste two layers of highland barley paper in pole.
The feature input of the cathode model includes cathode.
The feature input of the non-cathode model does not paste highland barley paper, anode patch two layers highland barley paper, cathode including anode, anode
It pastes one layer of highland barley paper and cathode pastes two layers of highland barley paper.
Specifically, feature input is the feature of battery polar, e.g., positive model in the training process of each model
Feature input includes anode;The feature input of non-anode model includes that anode does not paste highland barley paper, cathode, cathode one layer of highland barley paper of patch
Two layers of highland barley paper is pasted with cathode;The feature input of cathode model includes cathode;The feature of non-cathode model is inputted including anode, just
Highland barley paper, two layers of highland barley paper of anode patch, cathode are not pasted and pastes one layer of highland barley paper and cathode two layers of highland barley paper of patch in pole.Each battery pole
Property input all correspond to a weight, by change weight, rebuild the characteristic information of battery polar, can be by the battery pole of input
Property output be correct battery polar.Wherein, the battery polar classification results include anode, non-anode, cathode and non-cathode
Four class polarity.
In some embodiments, in a kind of general battery polarity automatic testing method based on deep learning provided,
S3, identification classification is carried out to the battery polar region to be detected using deep learning algorithm model, obtains battery polar point
Class is as a result, as shown in Fig. 2, the acquisition process of its deep learning algorithm model includes:
S301, building multilayer convolutional neural networks.
Multilayer convolutional neural networks include the full articulamentum of multiple convolution sums, are become full articulamentum based on the method for deep learning
At convolutional layer, convolution layering is carried out to all sample characteristics, input is image, is exported as battery polar classification results.
S302, the multilayer convolutional neural networks are trained using error reverse conduction algorithm, obtains battery polar identification mould
Type.
Using the error reverse conduction algorithm training multilayer convolutional neural networks, to obtain battery polar identification mould
Type, wherein objective function used in training process is the classification and battery wrong polarity of the battery correct polarity of input picture
The classification cross entropy with the battery polar identification model prediction result respectively.
S303, the output node layer of the multilayer convolutional network is revised as to 4, and is identified using trained battery polar
The weight of the modified multilayer convolutional neural networks of the weights initialisation of model.
S304, modified multilayer convolutional neural networks are instructed with anode, non-anode, cathode and non-negative pole data set
Practice, obtains anode, non-anode, four disaggregated model of cathode and non-cathode.
In some embodiments, the multilayer convolutional neural networks include input layer, hidden layer and output layer;
Data of the input layer for entire multilayer convolutional neural networks input;
The hidden layer includes anode, four non-anode, cathode and non-cathode training patterns;
The output layer is for exporting battery polar classification results.
Specifically, obtaining data first in the building of multilayer convolutional neural networks, successively constructing neuron, each layer
It can regard a linear regression model (LRM) as, wherein first layer is input layer, provides the data of entire multilayer convolutional neural networks
Input, each neuron of input layer do not input, and are provided solely for 1 output, and in this example, the picture of position to be detected is made
For input layer, all characteristic informations comprising picture, the second layer is hidden layer, including anode, non-anode, cathode and non-cathode four
A training pattern, third layer are output layer, for exporting battery polar classification results.Then using successively training mechanism, to every
Layer carries out tuning using Wake-Sleep deep learning algorithm, only adjusts one layer every time, successively adjusts, this process is considered as
It is the process of a feature-learning feature learning.The Wake stage is cognitive process, passes through the input feature vector of lower layer
Input and upward cognition Encoder weight generate each layer of abstract expression Code, then pass through current generation Decoder
Weight generates a reconstruction information Reconstruction, calculates input feature vector and reconstruction information residual error.In this example, feature
Input is the feature of battery polar, including anode, anode do not paste highland barley paper, two layers of highland barley paper of anode patch, cathode, cathode and paste one layer
Highland barley paper and cathode paste two layers of highland barley paper, and the input of each battery polar can correspond to a weight, by changing weight, rebuild
The characteristic information of battery polar can export the battery polar of input as correct battery polar, by the multilayer convolution net
The output node layer of network is revised as 4, and utilizes the modified multilayer of weights initialisation of trained battery polar identification model
The weight of convolutional neural networks, with anode, non-anode, cathode and non-negative pole data set to modified multilayer convolutional neural networks
It is trained, obtains anode, non-anode, four disaggregated model of cathode and non-cathode.
In some embodiments, as shown in figure 3, the picture of the S1, acquisition position to be detected, specifically include:
S101, it battery to be detected is manually placed in the enterprising line position of positioning module sets fixation;
S102, industrial camera automatically take pictures to battery to be detected on positioning module, obtain the picture of position to be detected.
Wherein, S102, industrial camera automatically take pictures to battery to be detected on positioning module, specifically include:
The industrial camera determines the number taken pictures according to the focal length of number of batteries to be detected on positioning module and industrial camera,
If repeatedly taking pictures, the plurality of pictures obtained after repeatedly taking pictures detects after being spliced into a picture.
In some embodiments, the S2, determine battery polar region to be detected, specifically include:
Using the method for region segmentation, the correct pole that the detection position of each battery to be detected and the position should place is determined
Property, finally determine battery polar region to be detected.
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
Therefore it cannot understand limitations on the scope of the patent of the present invention.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention
Range, therefore, protection scope of the present invention should be determined by the appended claims.
Claims (9)
1. a kind of general battery polarity automatic testing method based on deep learning, which is characterized in that the described method includes:
Obtain the picture of position to be detected;
Determine battery polar region to be detected;
Identification classification is carried out to the battery polar region to be detected using deep learning algorithm model, obtains battery polar point
Class result.
2. the general battery polarity automatic testing method according to claim 1 based on deep learning, which is characterized in that
The deep learning algorithm model includes anode, non-anode, four disaggregated model of cathode and non-cathode.
3. the general battery polarity automatic testing method according to claim 2 based on deep learning, which is characterized in that
The feature input of the anode model includes anode;
The feature input of the non-positive model includes that anode does not paste highland barley paper, cathode, cathode one layer of highland barley paper of patch and cathode patch
Two layers of highland barley paper;
The feature input of the cathode model includes cathode;
The feature input of the non-cathode model does not paste highland barley paper, two layers of highland barley paper of anode patch, cathode including anode, anode and pastes one
Layer highland barley paper and cathode paste two layers of highland barley paper.
4. the general battery polarity automatic testing method according to claim 3 based on deep learning, which is characterized in that
The battery polar classification results include anode, non-anode, four class polarity of cathode and non-cathode.
5. the general battery polarity automatic testing method according to claim 2 based on deep learning, which is characterized in that
The method also includes:
Construct multilayer convolutional neural networks;
Using the error reverse conduction algorithm training multilayer convolutional neural networks, battery polar identification model is obtained;
The output node layer of the multilayer convolutional network is revised as 4, and utilizes the power of trained battery polar identification model
The weight of modified multilayer convolutional neural networks is initialized again;
Modified multilayer convolutional neural networks are trained with anode, non-anode, cathode and non-negative pole data set, are obtained just
Pole, non-anode, four disaggregated model of cathode and non-cathode.
6. the general battery polarity automatic testing method according to claim 5 based on deep learning, which is characterized in that
The multilayer convolutional neural networks include input layer, hidden layer and output layer;
Data of the input layer for entire multilayer convolutional neural networks input;
The hidden layer includes anode, four non-anode, cathode and non-cathode training patterns;
The output layer is for exporting battery polar classification results.
7. the general battery polarity automatic testing method according to claim 1 based on deep learning, which is characterized in that
The picture for obtaining position to be detected, specifically includes:
Battery to be detected is manually placed in the enterprising line position of positioning module and sets fixation;
Industrial camera automatically takes pictures to battery to be detected on positioning module, obtains the picture of position to be detected.
8. the general battery polarity automatic testing method according to claim 7 based on deep learning, which is characterized in that
The industrial camera automatically takes pictures to battery to be detected on positioning module, specifically includes:
The industrial camera determines the number taken pictures according to the focal length of number of batteries to be detected on positioning module and industrial camera,
If repeatedly taking pictures, the plurality of pictures obtained after repeatedly taking pictures detects after being spliced into a picture.
9. the general battery polarity automatic testing method according to claim 1 based on deep learning, which is characterized in that
The determination battery polar region to be detected, specifically includes:
Using the method for region segmentation, the correct pole that the detection position of each battery to be detected and the position should place is determined
Property, finally determine battery polar region to be detected.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910386913.4A CN110222679B (en) | 2019-05-10 | 2019-05-10 | General battery polarity automatic detection method based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910386913.4A CN110222679B (en) | 2019-05-10 | 2019-05-10 | General battery polarity automatic detection method based on deep learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110222679A true CN110222679A (en) | 2019-09-10 |
CN110222679B CN110222679B (en) | 2023-07-11 |
Family
ID=67820623
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910386913.4A Active CN110222679B (en) | 2019-05-10 | 2019-05-10 | General battery polarity automatic detection method based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110222679B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117372414A (en) * | 2023-11-09 | 2024-01-09 | 东莞市兆丰精密仪器有限公司 | Battery polarity detection method, device, equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103925893A (en) * | 2014-04-17 | 2014-07-16 | 广东正业科技股份有限公司 | Quality detection method of battery cells |
CN104091322A (en) * | 2014-05-06 | 2014-10-08 | 无锡日联科技有限公司 | Detection method for Lamination lithium ion battery |
CN207123496U (en) * | 2017-06-22 | 2018-03-20 | 惠州市德赛电池有限公司 | A kind of battery plus-negative plate identification equipment |
CN109360186A (en) * | 2018-08-31 | 2019-02-19 | 广州超音速自动化科技股份有限公司 | Lithium battery diaphragm detection method, electronic equipment, storage medium and system |
CN109490320A (en) * | 2018-11-23 | 2019-03-19 | 奇瑞汽车股份有限公司 | Machine vision-based power battery pack positive and negative pole abnormity detection system and method |
CN109598721A (en) * | 2018-12-10 | 2019-04-09 | 广州市易鸿智能装备有限公司 | Defect inspection method, device, detection device and the storage medium of battery pole piece |
-
2019
- 2019-05-10 CN CN201910386913.4A patent/CN110222679B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103925893A (en) * | 2014-04-17 | 2014-07-16 | 广东正业科技股份有限公司 | Quality detection method of battery cells |
CN104091322A (en) * | 2014-05-06 | 2014-10-08 | 无锡日联科技有限公司 | Detection method for Lamination lithium ion battery |
CN207123496U (en) * | 2017-06-22 | 2018-03-20 | 惠州市德赛电池有限公司 | A kind of battery plus-negative plate identification equipment |
CN109360186A (en) * | 2018-08-31 | 2019-02-19 | 广州超音速自动化科技股份有限公司 | Lithium battery diaphragm detection method, electronic equipment, storage medium and system |
CN109490320A (en) * | 2018-11-23 | 2019-03-19 | 奇瑞汽车股份有限公司 | Machine vision-based power battery pack positive and negative pole abnormity detection system and method |
CN109598721A (en) * | 2018-12-10 | 2019-04-09 | 广州市易鸿智能装备有限公司 | Defect inspection method, device, detection device and the storage medium of battery pole piece |
Non-Patent Citations (1)
Title |
---|
秦文丽: "基于图像识别的太阳能电池片缺陷检测", 《设备管理与维修》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117372414A (en) * | 2023-11-09 | 2024-01-09 | 东莞市兆丰精密仪器有限公司 | Battery polarity detection method, device, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110222679B (en) | 2023-07-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106469302B (en) | A kind of face skin quality detection method based on artificial neural network | |
CN107066445B (en) | The deep learning method of one attribute emotion word vector | |
CN105426908B (en) | A kind of substation's attributive classification method based on convolutional neural networks | |
CN104166859B (en) | Based on SSAE and FSALS SVM Classification of Polarimetric SAR Image | |
CN110188331A (en) | Model training method, conversational system evaluation method, device, equipment and storage medium | |
CN110991435A (en) | Express waybill key information positioning method and device based on deep learning | |
CN107832768A (en) | Efficient method to go over files and marking system based on deep learning | |
CN106570464A (en) | Human face recognition method and device for quickly processing human face shading | |
CN107633511A (en) | A kind of blower fan vision detection system based on own coding neutral net | |
CN111612125B (en) | Novel HTM time pool method and system for online learning | |
CN107832780A (en) | Low confidence sample processing method and system are sorted based on artificial intelligence plank | |
CN111709477A (en) | Method and tool for garbage classification based on improved MobileNet network | |
CN108460399A (en) | A kind of child building block builds householder method and system | |
CN108492294A (en) | A kind of appraisal procedure and device of image color harmony degree | |
CN109961095A (en) | Image labeling system and mask method based on non-supervisory deep learning | |
CN114092769A (en) | Transformer substation multi-scene inspection analysis method based on federal learning | |
CN107463996A (en) | From step coorinated training learning method | |
CN108345889A (en) | A kind of application process carrying out registration identification to communication cabinet using Raspberry Pi | |
CN109961437A (en) | A kind of conspicuousness fabric defect detection method under the mode based on machine teaching | |
CN110222679A (en) | A kind of general battery polarity automatic testing method based on deep learning | |
CN113160966A (en) | Tongue picture diagnosis method and tongue picture diagnosis system based on multi-task learning | |
CN114971565A (en) | Block chain intelligent service system based on internet | |
CN114549489A (en) | Carved lipstick quality inspection-oriented instance segmentation defect detection method | |
CN112529188B (en) | Knowledge distillation-based industrial process optimization decision model migration optimization method | |
CN110175588A (en) | A kind of few sample face expression recognition method and system based on meta learning |
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 |