CN109035243A - Method and apparatus for exporting battery pole piece burr information - Google Patents
Method and apparatus for exporting battery pole piece burr information Download PDFInfo
- Publication number
- CN109035243A CN109035243A CN201810907188.6A CN201810907188A CN109035243A CN 109035243 A CN109035243 A CN 109035243A CN 201810907188 A CN201810907188 A CN 201810907188A CN 109035243 A CN109035243 A CN 109035243A
- Authority
- CN
- China
- Prior art keywords
- pole piece
- battery pole
- burr
- information
- piece image
- 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
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
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Abstract
The embodiment of the present application discloses the method and apparatus for exporting battery pole piece burr information.One specific embodiment of this method includes: the battery pole piece image for obtaining battery pole piece to be detected;Above-mentioned battery pole piece image is imported to the burr detection model pre-established, obtain the burr information of above-mentioned battery pole piece to be detected, wherein, above-mentioned burr detection model is used to characterize the corresponding relationship of the burr information of battery pole piece indicated by battery pole piece image and battery pole piece image;According to the preset way of output, obtained burr information is exported.The embodiment realizes the output to the burr information of battery pole piece to be detected, improves the detection efficiency to burr on battery pole piece.
Description
Technical field
The invention relates to field of computer technology, and in particular to the method for exporting battery pole piece burr information
And device.
Background technique
In the production process of battery pole piece, due to punching mode, the structure of die cutting die, die cutting die material and add
The reasons such as work mode are easy to produce burr on battery pole piece.And battery pole piece burr has significant impact for battery quality, is
Important inspection item in quality inspection.
It at this stage, can be by way of artificial detection or semi-automatic optical instrument auxiliary detection come on battery pole piece
Burr detected.
Summary of the invention
The embodiment of the present application proposes the method and apparatus for exporting battery pole piece burr information.
In a first aspect, the embodiment of the present application provides a kind of method for exporting battery pole piece burr information, this method
It include: the battery pole piece image for obtaining battery pole piece to be detected;Above-mentioned battery pole piece image is imported to the burr inspection pre-established
Model is surveyed, the burr information of above-mentioned battery pole piece to be detected is obtained, wherein above-mentioned burr detection model is for characterizing battery pole piece
The corresponding relationship of the burr information of battery pole piece indicated by image and battery pole piece image;According to preset output side
Formula exports obtained burr information.
In some embodiments, above-mentioned that above-mentioned battery pole piece image is imported to the burr detection model pre-established, it obtains
The burr information of above-mentioned battery pole piece to be detected, comprising: in response to getting battery pole piece image, generation burr detection is requested,
Wherein, above-mentioned burr detection request includes above-mentioned battery pole piece image;Based on preset load balancing rule, built from advance
The burr detection model for handling above-mentioned burr detection request is determined at least one vertical burr detection model;By above-mentioned electricity
Pond pole piece image inputs identified burr detection model, obtains the burr information of above-mentioned battery pole piece to be detected.
In some embodiments, above-mentioned burr detection model is depth convolutional neural networks;And above-mentioned depth convolution mind
It is obtained through network is trained in the following manner: obtaining sample set, wherein sample includes sample battery pole piece image and sample
The burr information of sample battery pole piece indicated by battery pole piece image;By the sample battery pole piece of the sample in above-mentioned sample set
Image is defeated as it is expected using the burr information of sample battery pole piece indicated by the sample battery pole piece image of input as input
Out, training obtains above-mentioned depth convolutional neural networks.
In some embodiments, the above method further include: by the battery pole piece image of above-mentioned battery pole piece to be detected and obtain
Detection data set is arrived in the burr information association storage arrived.
In some embodiments, the training of above-mentioned depth convolutional neural networks further include: by above-mentioned detection data set
In, the battery pole piece image of associated storage and burr information shown;Receive data decimation information and the modification of burr information
Information, wherein above-mentioned data decimation information and above-mentioned burr information modification information are users for above-mentioned detection data set
In, detection mistake detection data generate;It is selected from the above-mentioned set of detection data according to above-mentioned data decimation information
Take an at least battery pole piece image;For the battery pole piece image in an above-mentioned at least battery pole piece image, according to above-mentioned
Burr information modification information modifies to the burr information of the battery pole piece image associated storage;By the battery pole piece image with
Modified burr information is as target sample associated storage to target sample collection;Using above-mentioned depth convolutional neural networks as just
Beginning network obtains updated depth convolutional neural networks using the above-mentioned above-mentioned initial network of target sample collection training.
Second aspect, the embodiment of the present application provide a kind of for exporting the device of battery pole piece burr information, above-mentioned dress
Setting includes: acquiring unit, is configured to obtain the battery pole piece image of battery pole piece to be detected;Import unit, be configured to by
Above-mentioned battery pole piece image imports the burr detection model pre-established, obtains the burr information of above-mentioned battery pole piece to be detected,
Wherein, above-mentioned burr detection model is used to characterize the burr of battery pole piece indicated by battery pole piece image and battery pole piece image
The corresponding relationship of information;Output unit is configured to carry out obtained burr information defeated according to the preset way of output
Out.
In some embodiments, above-mentioned import unit is further configured to: raw in response to getting battery pole piece image
It detects and requests at burr, wherein above-mentioned burr detection request includes above-mentioned battery pole piece image;It is equal based on preset load
Weighing apparatus rule determines the burr inspection for handling above-mentioned burr detection request from least one the burr detection model pre-established
Survey model;Above-mentioned battery pole piece image is inputted into identified burr detection model, obtains the hair of above-mentioned battery pole piece to be detected
Pierce information.
In some embodiments, above-mentioned burr detection model is depth convolutional neural networks;And above-mentioned apparatus further includes
Network training unit, above-mentioned network training unit are configured to: obtaining sample set, wherein sample includes sample battery pole piece figure
The burr information of sample battery pole piece indicated by picture and sample battery pole piece image;By the sample of the sample in above-mentioned sample set
Battery pole piece image as input, make by the burr information of sample battery pole piece indicated by the sample battery pole piece image by input
For desired output, training obtains above-mentioned depth convolutional neural networks.
In some embodiments, above-mentioned apparatus further include: storage unit is configured to above-mentioned battery pole piece to be detected
Detection data set is arrived in battery pole piece image and the storage of obtained burr information association.
In some embodiments, above-mentioned network training unit is further configured to: will be in the above-mentioned set of detection data
, the battery pole piece image of associated storage and burr information shown;Receive data decimation information and burr information modification letter
Breath, wherein above-mentioned data decimation information and above-mentioned burr information modification information are users in the above-mentioned set of detection data
, detection mistake detection data generate;It is chosen from the above-mentioned set of detection data according to above-mentioned data decimation information
An at least battery pole piece image;For the battery pole piece image in an above-mentioned at least battery pole piece image, according to above-mentioned hair
Thorn information modification information modifies to the burr information of the battery pole piece image associated storage;By the battery pole piece image with repair
Burr information after changing is as target sample associated storage to target sample collection;Using above-mentioned depth convolutional neural networks as initial
Network obtains updated depth convolutional neural networks using the above-mentioned above-mentioned initial network of target sample collection training.
The third aspect, the embodiment of the present application provide a kind of electronic equipment, which includes: one or more processing
Device;Storage device is stored thereon with one or more programs, when said one or multiple programs are by said one or multiple processing
When device executes, so that said one or multiple processors realize the method as described in implementation any in first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer-readable medium, are stored thereon with computer program,
In, the method as described in implementation any in first aspect is realized when which is executed by processor.
Method and apparatus provided by the embodiments of the present application for exporting battery pole piece burr information, obtain to be detected first
The battery pole piece image is then imported the burr detection model that pre-establishes by the battery pole piece image of battery pole piece, obtain to
The burr information of detection battery pole piece exports obtained burr information finally according to the preset way of output, from
And the output to the burr information of battery pole piece to be detected is realized, improve the detection efficiency to burr on battery pole piece.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that one embodiment of the application can be applied to exemplary system architecture figure therein;
Fig. 2 is the flow chart according to one embodiment of the method for exporting battery pole piece burr information of the application;
Fig. 3 is a kind of exemplary architecture figure according to the depth convolutional neural networks of the embodiment of the present application;
Fig. 4 is the signal according to an application scenarios of the method for exporting battery pole piece burr information of the application
Figure;
Fig. 5 is the process according to another embodiment of the method for exporting battery pole piece burr information of the application
Figure;
Fig. 6 is the structural representation according to one embodiment of the device for exporting battery pole piece burr information of the application
Figure;
Fig. 7 is adapted for the structural schematic diagram for the computer system for realizing the electronic equipment of the embodiment of the present application.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can be using the method for being used to export battery pole piece burr information of the embodiment of the present application or for defeated
The exemplary system architecture 100 of the device of battery pole piece burr information out.
As shown in Figure 1, system architecture 100 may include image capture device 101, terminal device 102,103 kimonos of network
Business device 104.Network 103 between image capture device 101, terminal device 102 and server 104 to provide communication link
Medium.Network 103 may include various connection types, such as wired, wireless communication link or fiber optic cables etc..
The various electronics that image capture device 101 can be the battery pole piece image for acquiring battery pole piece to be detected are set
It is standby, for example, camera, camera etc..As an example, image capture device 101 can acquire on battery pole piece production line
Battery pole piece to be detected image, and collected battery pole piece image is sent to terminal device 102.Image capture device
Collected battery pole piece image can also be sent to server 104 by 101.It, can be by adjustment angle, light, filter in practice
Image capture device 101 after mirror, times mirror, focal length is mounted on battery pole piece production line, to collect battery pole piece in real time
The image of battery pole piece on production line.
Terminal device 102 can be hardware, be also possible to software.When terminal device 102 is hardware, can be with aobvious
Display screen and support that information receives and the various electronic equipments of output, including but not limited to smart phone, tablet computer, on knee
Portable computer and desktop computer etc..When terminal device 102 is software, it may be mounted at above-mentioned cited electronics and set
In standby.Multiple softwares or software module (such as providing Distributed Services) may be implemented into it, also may be implemented into single
Software or software module.It is not specifically limited herein.
Server 104 can be to provide the server of various services, such as provide the information shown on terminal device 102
The background server of support.Background server can carry out the data such as the battery pole piece image received the processing such as analyzing, and
Processing result (such as burr information of battery pole piece to be detected) is fed back into terminal device.
It should be noted that server can be hardware, it is also possible to software.When server is hardware, may be implemented
At the distributed server cluster that multiple servers form, individual server also may be implemented into.It, can when server is software
To be implemented as multiple softwares or software module (such as providing Distributed Services), single software or software also may be implemented into
Module.It is not specifically limited herein.
It should be noted that can be by for exporting the method for battery pole piece burr information provided by the embodiment of the present application
Terminal device 102 executes, and can also be executed by server 104.It correspondingly, can for exporting the device of battery pole piece burr information
To be set in terminal device 102, also can be set in server 104.
It should be understood that the number of image capture device, terminal device, network and server in Fig. 1 is only schematic
's.According to needs are realized, any number of terminal device, network and server can have.
With continued reference to Fig. 2, a reality of the method for exporting battery pole piece burr information according to the application is shown
Apply the process 200 of example.The method for being used to export battery pole piece burr information, comprising the following steps:
Step 201, the battery pole piece image of battery pole piece to be detected is obtained.
In the present embodiment, for exporting executing subject (such as end shown in FIG. 1 of the method for battery pole piece burr information
End equipment 102 or server 104) it can be by wired connection mode or radio connection from image capture device (example
Image capture device 101 as shown in Figure 1) obtain the battery pole piece image of battery pole piece to be detected.
It should be pointed out that above-mentioned radio connection can include but is not limited to 3G/4G connection, WiFi connection, bluetooth
Connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection and other currently known or exploitations in the future
Radio connection.
Step 202, battery pole piece image is imported to the burr detection model pre-established, obtains battery pole piece to be detected
Burr information.
In the present embodiment, the battery pole piece image obtained in step 201 can be imported and be built in advance by above-mentioned executing subject
Vertical burr detection model, to obtain the burr information of above-mentioned battery pole piece to be detected.Burr information can be used for describe to
Whether jagged battery pole piece is detected, for example, burr information may include jagged and impulse- free robustness.Herein, above-mentioned burr inspection
It is corresponding with the burr information of battery pole piece indicated by battery pole piece image that survey model can be used for characterizing battery pole piece image
Relationship.
As an example, above-mentioned burr detection model may include characteristic extraction part and mapping table.Wherein, feature mentions
It takes part to can be used for from battery pole piece image extracting feature, feature vector is generated, for example, characteristic extraction part can use
The scheduling algorithms such as histograms of oriented gradients feature extraction algorithm, local binary patterns feature extraction algorithm are mentioned from battery pole piece image
Feature is taken to generate feature vector.Mapping table can be technical staff based on the system to a large amount of feature vector and burr information
Count and pre-establish, be stored with the mapping table of the corresponding relationship of multiple feature vectors and burr information.In this way, above-mentioned hair
The feature of the battery pole piece image obtained in characteristic extraction part extraction step 201 can be used in thorn detection model, to generate
Target feature vector.Later, the target feature vector and multiple feature vectors in mapping table are successively compared, if
Some feature vector and target feature vector in mapping table is same or similar, then by this feature in mapping table
Burr information of the corresponding burr information of vector as battery pole piece indicated by the battery pole piece image obtained in step 201.
In some optional implementations of the present embodiment, above-mentioned burr detection model can be depth convolutional Neural net
Network.As shown in figure 3, depth convolutional neural networks are the neural network of a multilayer, it may include convolutional layer 301, pond layer
302, full articulamentum 303 and classifier 304 etc.., can be based on different production scenes and the characteristics of data in practice, design
The depth convolutional neural networks being made of different depth, the neuron of different number, different convolution pond organizational forms.Its
In, convolutional layer 301 can be by the convolution kernel that convolution operation utilizes weight different to input picture or characteristic image (feature
Map it) is scanned convolution, therefrom extracts the feature of different dimensions, and export to characteristic pattern.Pond layer 302 can pass through pond
Operation carries out dimensionality reduction operation to characteristic pattern, the main feature in keeping characteristics figure.It is available global special by full articulamentum 303
Sign.Burr information can be exported by classifier 304.In practice, classifier 304 can export 0 and 1 two categories label,
In, 0 indicates impulse- free robustness, and 1 indicates jagged.It, can be right using this depth convolutional neural networks operated with convolution, pondization
The robustness with higher such as the deformation of the battery pole piece image acquired on battery pole piece production line, fuzzy, illumination variation, for
The detection of battery pole piece have it is higher can generalization.
Above-mentioned depth convolutional neural networks can be above-mentioned executing subject or other are used to train above-mentioned depth convolution mind
Training obtains in the following manner for executing subject through network:
Firstly, obtaining sample set, wherein sample includes indicated by sample battery pole piece image and sample battery pole piece image
Sample battery pole piece burr information.As an example, burr information may include jagged and impulse- free robustness.It, can be in practice
Indicate that impulse- free robustness, label 1 indicate jagged using label 0.
Then, using the sample battery pole piece image of the sample in sample set as input, by the sample battery pole piece of input
The burr information of sample battery pole piece indicated by image obtains depth convolutional neural networks as desired output, training.As
Output can be compared, if error amount between the two is less than preset threshold value, table by example with desired output
Show trained completion, deconditioning;If error amount between the two is not less than preset threshold value, can be passed using reversed
It broadcasts algorithm (Back Propgation Algorithm, BP algorithm) and gradient descent method (such as stochastic gradient descent algorithm) is right
Network parameter is adjusted, and is chosen sample again from sample set and be trained.
It should be noted that if above-mentioned depth convolutional neural networks are by the method for exporting battery pole piece burr information
Executing subject training obtain, the network structure information and network parameter of the depth convolutional neural networks that training can be completed
Parameter value storage to local.If above-mentioned depth convolutional neural networks are obtained by the training of other executing subjects, other execution
The network structure information of depth convolutional neural networks and the parameter value of network parameter that training is completed can be sent to use by main body
In the executing subject of the method for output battery pole piece burr information.
In some optional implementations, the above-mentioned method for exporting battery pole piece burr information can also include with
Lower content: above-mentioned executing subject can store the battery pole piece image of battery pole piece to be detected and obtained burr information association
To detection data set.
Optionally, the training of above-mentioned depth convolutional neural networks can also include the following contents:
Step S1 carries out battery pole piece image in the above-mentioned set of detection data, associated storage and burr information
Display.
Step S2 receives data decimation information and burr information modification information.Wherein, above-mentioned data decimation information and above-mentioned
Burr information modification information is that user is directed in the above-mentioned set of detection data, the detection data of detection mistake generates.
In practice, after above-mentioned executing subject operation a period of time, the detection data obtained in this time can be shown to use
Family (for example, quality inspection personnel of battery pole piece).User can in each of display detection data battery pole piece image and
Burr information is judged, so that it is determined that whether the corresponding burr information of the battery pole piece image is correct.If incorrect, user
This can be directed to, and detection data sends data decimation information and burr information modification information.Wherein, data decimation information can be with
For selecting the detection data of detection mistake from detection data set, burr information modification information is user for inspection
The battery pole piece image input of sniffing accidentally, correct burr information.
Step S3 chooses an at least battery pole piece according to above-mentioned data decimation information from the above-mentioned set of detection data
Image.
Step S4, for each battery pole piece image in an above-mentioned at least battery pole piece image, according to above-mentioned hair
Thorn information modification information modifies to the burr information of the battery pole piece image associated storage.And by the battery pole piece image with
Modified burr information is as target sample associated storage to target sample collection.
Step S5, it is above-mentioned using above-mentioned target sample collection training using above-mentioned depth convolutional neural networks as initial network
Initial network obtains updated depth convolutional neural networks.
Burr detection model can be constantly updated by above-mentioned implementation, to improve burr detection model detection battery pole
The accuracy rate of burr on picture.
Step 203, according to the preset way of output, obtained burr information is exported.
In the present embodiment, above-mentioned executing subject can be according to the preset way of output, to obtained in step 202
Burr information is exported.Herein, the above-mentioned way of output can be various message stream modes, such as voice prompting mode,
Text display manner etc..In practice, user can need to set according to business scenario the way of output of burr information, for example,
When actual production environment is more noisy, and user can hear voice prompting, but text display side is set by the way of output
Formula.
In application scenes, it can be preset according to practical business scene needs for different burr information
Alignment processing information, wherein processing information is used to indicate subsequent processing operation.For example, when burr information is jagged, it can
To set following processing information: sending the instruction for picking up jagged battery pole piece, to mechanical arm to control mechanical arm to hairiness
The battery pole piece of thorn executes the processing operation picked up.In another example following processing can also be set when burr information is jagged
Information: triggering alarm, it is jagged to remind staff that quality of battery pole piece is unqualified.For another example when burr information is hairless
When thorn, following processing information can be set: record log being generated according to battery pole piece image and burr information, and to record log
Execute storage operation.
With continued reference to the applied field that Fig. 4, Fig. 4 are according to the method for exporting battery pole piece burr information of the present embodiment
One schematic diagram of scape.In the application scenarios of Fig. 4, terminal device 401 obtains the battery pole piece of battery pole piece to be detected first
Image.Later, which can be imported the burr detection model pre-established by terminal device 401, to obtain
The burr information of the battery pole piece to be detected.Finally, terminal device 401 can be right according to preset voice output mode
Obtained burr information is exported.
The method provided by the above embodiment of the application is by importing hair for the battery pole piece image of battery pole piece to be detected
Pierce detection model, the burr information of available battery pole piece to be detected, to realize to burr on battery pole piece to be detected
Automatic detection, improve the detection efficiency of battery pole piece to be detected.
With further reference to Fig. 5, it illustrates another embodiments of the method for exporting battery pole piece burr information
Process 500.This is used to export the process 500 of the method for battery pole piece burr information, comprising the following steps:
Step 501, the battery pole piece image of battery pole piece to be detected is obtained.
In the present embodiment, for exporting executing subject (such as end shown in FIG. 1 of the method for battery pole piece burr information
End equipment 102 or server 104) it can be by wired connection mode or radio connection from image capture device (example
Image capture device 101 as shown in Figure 1) obtain the battery pole piece image of battery pole piece to be detected.
Step 502, in response to getting battery pole piece image, burr detection request is generated.
In the present embodiment, in response to getting battery pole piece image, above-mentioned executing subject can be for the battery obtained
Pole piece image generates a burr detection request, and burr detection request may include above-mentioned battery pole piece image.
Step 503, based on preset load balancing rule, from least one the burr detection model pre-established
Determine the burr detection model for handling burr detection request.
In the present embodiment, at least one burr detection model can be pre-established in above-mentioned executing subject.Herein,
Burr detection model can be used for characterizing the burr information of battery pole piece indicated by battery pole piece image and battery pole piece image
Corresponding relationship.At least one above-mentioned burr detection model can be identical model, and each burr detection model can
With independent operating, it is independent of each other.Herein, load balancing rule can also be preset, in this way, above-mentioned executing subject can root
According to the load balancing rule real-time perfoming load balancing and scheduling, determined for from from least one above-mentioned burr detection model
Optimal (such as load is minimum) the burr detection model of above-mentioned burr detection request is managed, and burr detection request is sent to this
Burr detection model.
Step 504, battery pole piece image is inputted into identified burr detection model, obtains the hair of battery pole piece to be detected
Pierce information.
In the present embodiment, above-mentioned executing subject can be by hair determined by above-mentioned battery pole piece image input step 503
Detection model is pierced, to obtain the burr information of above-mentioned battery pole piece to be detected.
Step 505, according to the preset way of output, obtained burr information is exported.
In the present embodiment, in the present embodiment, above-mentioned executing subject can be according to the preset way of output, to step
Burr information obtained in rapid 504 is exported.Herein, the above-mentioned way of output can be various message stream modes, such as
Voice prompting mode, text display manner etc..
From figure 5 it can be seen that being used to export battery pole piece hair in the present embodiment compared with the corresponding embodiment of Fig. 2
The process 500 for piercing the method for information, which is highlighted, to be determined from least one burr detection model for handling burr detection request
The step of burr detection model.The scheme of the present embodiment description can be simultaneously using multiple burr detection models to be checked as a result,
The burr for surveying battery pole piece is detected, to further improve the efficiency of detection.
With further reference to Fig. 6, as the realization to method shown in above-mentioned each figure, this application provides one kind for exporting electricity
One embodiment of the device of pond pole piece burr information, the Installation practice is corresponding with embodiment of the method shown in Fig. 2, the dress
Setting specifically can be applied in various electronic equipments.
As shown in fig. 6, the present embodiment includes: acquiring unit for exporting the device 600 of battery pole piece burr information
601, import unit 602 and output unit 603.Wherein, acquiring unit 601 is configured to obtain the battery of battery pole piece to be detected
Pole piece image;Import unit 602 is configured to above-mentioned battery pole piece image importing the burr detection model pre-established, obtains
The burr information of above-mentioned battery pole piece to be detected, wherein above-mentioned burr detection model is for characterizing battery pole piece image and battery
The corresponding relationship of the burr information of battery pole piece indicated by pole piece image;Output unit 603 is configured to according to presetting
The way of output, obtained burr information is exported.
In the present embodiment, for exporting acquiring unit 601, the import unit of the device 600 of battery pole piece burr information
602 and output unit 603 specific processing and its brought technical effect can be respectively with reference to step in Fig. 2 corresponding embodiment
201, the related description of step 202 and step 203, details are not described herein.
In some optional implementations of the present embodiment, above-mentioned import unit 602 is further configured to: in response to
Battery pole piece image is got, burr detection request is generated, wherein above-mentioned burr detection request includes above-mentioned battery pole piece figure
Picture;Based on preset load balancing rule, determine from least one the burr detection model pre-established for handling
The burr detection model of above-mentioned burr detection request;Above-mentioned battery pole piece image is inputted into identified burr detection model, is obtained
To the burr information of above-mentioned battery pole piece to be detected.
In some optional implementations of the present embodiment, above-mentioned burr detection model is depth convolutional neural networks;
And above-mentioned apparatus further includes network training unit (not shown), above-mentioned network training unit is configured to: obtaining sample
Collection, wherein sample includes the burr of sample battery pole piece indicated by sample battery pole piece image and sample battery pole piece image
Information;Using the sample battery pole piece image of the sample in above-mentioned sample set as input, by the sample battery pole piece image of input
The burr information of indicated sample battery pole piece obtains above-mentioned depth convolutional neural networks as desired output, training.
In some optional implementations of the present embodiment, above-mentioned apparatus 600 further include: storage unit (is not shown in figure
Out), it is configured to the battery pole piece image of above-mentioned battery pole piece to be detected and the storage of obtained burr information association to having examined
Measured data set.
In some optional implementations of the present embodiment, above-mentioned network training unit is further configured to: will be upper
It states in detection data set, associated storage battery pole piece image and burr information is shown;Receive data decimation letter
Breath and burr information modification information, wherein above-mentioned data decimation information and above-mentioned burr information modification information are users for upper
State what in detection data set, detection mistake detection data generated;According to above-mentioned data decimation information from it is above-mentioned
An at least battery pole piece image is chosen in detection data set;For the battery pole in an above-mentioned at least battery pole piece image
Picture is modified according to burr information of the above-mentioned burr information modification information to the battery pole piece image associated storage;It will
The battery pole piece image and modified burr information are as target sample associated storage to target sample collection;Above-mentioned depth is rolled up
Product neural network obtains updated depth volume using the above-mentioned above-mentioned initial network of target sample collection training as initial network
Product neural network.
Below with reference to Fig. 7, it illustrates the computer systems 700 for the electronic equipment for being suitable for being used to realize the embodiment of the present application
Structural schematic diagram.Electronic equipment shown in Fig. 7 is only an example, function to the embodiment of the present application and should not use model
Shroud carrys out any restrictions.
As shown in fig. 7, computer system 700 includes central processing unit (CPU) 701, it can be read-only according to being stored in
Program in memory (ROM) 702 or be loaded into the program in random access storage device (RAM) 703 from storage section 708 and
Execute various movements appropriate and processing.In RAM 703, also it is stored with system 700 and operates required various programs and data.
CPU 701, ROM 702 and RAM 703 are connected with each other by bus 704.Input/output (I/O) interface 705 is also connected to always
Line 704.
I/O interface 705 is connected to lower component: the importation 706 including keyboard, mouse etc.;It is penetrated including such as cathode
The output par, c 707 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.;Storage section 708 including hard disk etc.;
And the communications portion 709 of the network interface card including LAN card, modem etc..Communications portion 709 via such as because
The network of spy's net executes communication process.Driver 710 is also connected to I/O interface 705 as needed.Detachable media 711, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 710, in order to read from thereon
Computer program be mounted into storage section 708 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communications portion 709, and/or from detachable media
711 are mounted.When the computer program is executed by central processing unit (CPU) 701, limited in execution the present processes
Above-mentioned function.It should be noted that computer-readable medium described herein can be computer-readable signal media or
Computer readable storage medium either the two any combination.Computer readable storage medium for example can be --- but
Be not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.
The more specific example of computer readable storage medium can include but is not limited to: have one or more conducting wires electrical connection,
Portable computer diskette, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only deposit
Reservoir (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory
Part or above-mentioned any appropriate combination.In this application, computer readable storage medium, which can be, any include or stores
The tangible medium of program, the program can be commanded execution system, device or device use or in connection.And
In the application, computer-readable signal media may include in a base band or the data as the propagation of carrier wave a part are believed
Number, wherein carrying computer-readable program code.The data-signal of this propagation can take various forms, including but not
It is limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer
Any computer-readable medium other than readable storage medium storing program for executing, the computer-readable medium can send, propagate or transmit use
In by the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc., Huo Zheshang
Any appropriate combination stated.
The calculating of the operation for executing the application can be write with one or more programming languages or combinations thereof
Machine program code, described program design language include object oriented program language-such as Java, Smalltalk, C+
+, it further include conventional procedural programming language-such as " C " language or similar programming language.Program code can
Fully to execute, partly execute on the user computer on the user computer, be executed as an independent software package,
Part executes on the remote computer or executes on a remote computer or server completely on the user computer for part.
In situations involving remote computers, remote computer can pass through the network of any kind --- including local area network (LAN)
Or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize Internet service
Provider is connected by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit also can be set in the processor, for example, can be described as: a kind of processor packet
Include acquiring unit, import unit and output unit.Wherein, the title of these units is not constituted under certain conditions to the unit
The restriction of itself, for example, acquiring unit is also described as " obtaining the list of the battery pole piece image of battery pole piece to be detected
Member ".
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be
Included in device described in above-described embodiment;It is also possible to individualism, and without in the supplying device.Above-mentioned calculating
Machine readable medium carries one or more program, when said one or multiple programs are executed by the device, so that should
Device: the battery pole piece image of battery pole piece to be detected is obtained;Above-mentioned battery pole piece image is imported to the burr inspection pre-established
Model is surveyed, the burr information of above-mentioned battery pole piece to be detected is obtained, wherein above-mentioned burr detection model is for characterizing battery pole piece
The corresponding relationship of the burr information of battery pole piece indicated by image and battery pole piece image;According to preset output side
Formula exports obtained burr information.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (12)
1. a kind of method for exporting battery pole piece burr information, comprising:
Obtain the battery pole piece image of battery pole piece to be detected;
The battery pole piece image is imported to the burr detection model pre-established, obtains the burr of the battery pole piece to be detected
Information, wherein the burr detection model is for characterizing battery pole piece indicated by battery pole piece image and battery pole piece image
Burr information corresponding relationship;
According to the preset way of output, obtained burr information is exported.
2. according to the method described in claim 1, wherein, the burr pre-established that the battery pole piece image is imported is examined
Model is surveyed, the burr information of the battery pole piece to be detected is obtained, comprising:
In response to getting battery pole piece image, burr detection request is generated, wherein the burr detection request includes the electricity
Pond pole piece image;
Based on preset load balancing rule, determine from least one the burr detection model pre-established for handling
The burr detection model of the burr detection request;
The battery pole piece image is inputted into identified burr detection model, obtains the burr letter of the battery pole piece to be detected
Breath.
3. according to the method described in claim 1, wherein, the burr detection model is depth convolutional neural networks;And
The depth convolutional neural networks are trained in the following manner to be obtained:
Obtain sample set, wherein sample includes the electricity of sample indicated by sample battery pole piece image and sample battery pole piece image
The burr information of pond pole piece;
Using the sample battery pole piece image of the sample in the sample set as input, by the sample battery pole piece image institute of input
The burr information of the sample battery pole piece of instruction obtains the depth convolutional neural networks as desired output, training.
4. according to the method described in claim 3, wherein, the method also includes:
The battery pole piece image of the battery pole piece to be detected and the storage of obtained burr information association are arrived into detection data collection
It closes.
5. according to the method described in claim 4, wherein, the training of the depth convolutional neural networks further include:
Battery pole piece image in the set of detection data, associated storage and burr information are shown;
Receive data decimation information and burr information modification information, wherein the data decimation information and the burr information are repaired
Converting to breath is that user is directed in the detection data set, the detection data of detection mistake generates;
An at least battery pole piece image is chosen from the set of detection data according to the data decimation information;
For the battery pole piece image in an at least battery pole piece image, according to the burr information modification information to this
The burr information of battery pole piece image associated storage is modified;Using the battery pole piece image and modified burr information as
Target sample associated storage is to target sample collection;
It is obtained using the depth convolutional neural networks as initial network using the target sample collection training initial network
To updated depth convolutional neural networks.
6. a kind of for exporting the device of battery pole piece burr information, comprising:
Acquiring unit is configured to obtain the battery pole piece image of battery pole piece to be detected;
Import unit is configured to the battery pole piece image importing the burr detection model that pre-establishes, obtain it is described to
Detect the burr information of battery pole piece, wherein the burr detection model is for characterizing battery pole piece image and battery pole piece figure
As the corresponding relationship of the burr information of indicated battery pole piece;
Output unit is configured to export obtained burr information according to the preset way of output.
7. device according to claim 6, wherein the import unit is further configured to:
In response to getting battery pole piece image, burr detection request is generated, wherein the burr detection request includes the electricity
Pond pole piece image;
Based on preset load balancing rule, determine from least one the burr detection model pre-established for handling
The burr detection model of the burr detection request;
The battery pole piece image is inputted into identified burr detection model, obtains the burr letter of the battery pole piece to be detected
Breath.
8. device according to claim 6, wherein the burr detection model is depth convolutional neural networks;And
Described device further includes network training unit, and the network training unit is configured to:
Obtain sample set, wherein sample includes the electricity of sample indicated by sample battery pole piece image and sample battery pole piece image
The burr information of pond pole piece;
Using the sample battery pole piece image of the sample in the sample set as input, by the sample battery pole piece image institute of input
The burr information of the sample battery pole piece of instruction obtains the depth convolutional neural networks as desired output, training.
9. device according to claim 8, wherein described device further include:
Storage unit is configured to deposit the battery pole piece image of the battery pole piece to be detected and obtained burr information association
Store up detection data set.
10. device according to claim 9, wherein the network training unit is further configured to:
Battery pole piece image in the set of detection data, associated storage and burr information are shown;
Receive data decimation information and burr information modification information, wherein the data decimation information and the burr information are repaired
Converting to breath is that user is directed in the detection data set, the detection data of detection mistake generates;
An at least battery pole piece image is chosen from the set of detection data according to the data decimation information;
For the battery pole piece image in an at least battery pole piece image, according to the burr information modification information to this
The burr information of battery pole piece image associated storage is modified;Using the battery pole piece image and modified burr information as
Target sample associated storage is to target sample collection;
It is obtained using the depth convolutional neural networks as initial network using the target sample collection training initial network
To updated depth convolutional neural networks.
11. a kind of electronic equipment server, comprising:
One or more processors;
Storage device is stored thereon with one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as method as claimed in any one of claims 1 to 5.
12. a kind of computer-readable medium, is stored thereon with computer program, wherein real when described program is executed by processor
Now such as method as claimed in any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810907188.6A CN109035243A (en) | 2018-08-10 | 2018-08-10 | Method and apparatus for exporting battery pole piece burr information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810907188.6A CN109035243A (en) | 2018-08-10 | 2018-08-10 | Method and apparatus for exporting battery pole piece burr information |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109035243A true CN109035243A (en) | 2018-12-18 |
Family
ID=64633504
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810907188.6A Pending CN109035243A (en) | 2018-08-10 | 2018-08-10 | Method and apparatus for exporting battery pole piece burr information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109035243A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110706215A (en) * | 2019-09-26 | 2020-01-17 | 无锡先导智能装备股份有限公司 | Pole piece detection method |
CN112529829A (en) * | 2019-08-28 | 2021-03-19 | 银河水滴科技(北京)有限公司 | Training method and device for burr positioning and burr detection model |
WO2021248554A1 (en) * | 2020-06-11 | 2021-12-16 | 深圳市信宇人科技股份有限公司 | High-speed and high-precision burr detection method and detection system for lithium ion battery electrode sheet |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107133629A (en) * | 2016-02-29 | 2017-09-05 | 百度在线网络技术(北京)有限公司 | Picture classification method, device and mobile terminal |
CN107578034A (en) * | 2017-09-29 | 2018-01-12 | 百度在线网络技术(北京)有限公司 | information generating method and device |
CN107729319A (en) * | 2017-10-18 | 2018-02-23 | 百度在线网络技术(北京)有限公司 | Method and apparatus for output information |
CN107742128A (en) * | 2017-10-20 | 2018-02-27 | 百度在线网络技术(北京)有限公司 | Method and apparatus for output information |
CN108230317A (en) * | 2018-01-09 | 2018-06-29 | 北京百度网讯科技有限公司 | Steel plate defect detection sorting technique, device, equipment and computer-readable medium |
-
2018
- 2018-08-10 CN CN201810907188.6A patent/CN109035243A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107133629A (en) * | 2016-02-29 | 2017-09-05 | 百度在线网络技术(北京)有限公司 | Picture classification method, device and mobile terminal |
CN107578034A (en) * | 2017-09-29 | 2018-01-12 | 百度在线网络技术(北京)有限公司 | information generating method and device |
CN107729319A (en) * | 2017-10-18 | 2018-02-23 | 百度在线网络技术(北京)有限公司 | Method and apparatus for output information |
CN107742128A (en) * | 2017-10-20 | 2018-02-27 | 百度在线网络技术(北京)有限公司 | Method and apparatus for output information |
CN108230317A (en) * | 2018-01-09 | 2018-06-29 | 北京百度网讯科技有限公司 | Steel plate defect detection sorting technique, device, equipment and computer-readable medium |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112529829A (en) * | 2019-08-28 | 2021-03-19 | 银河水滴科技(北京)有限公司 | Training method and device for burr positioning and burr detection model |
CN112529829B (en) * | 2019-08-28 | 2024-04-19 | 银河水滴科技(北京)有限公司 | Training method and device for burr positioning and burr detection model |
CN110706215A (en) * | 2019-09-26 | 2020-01-17 | 无锡先导智能装备股份有限公司 | Pole piece detection method |
WO2021248554A1 (en) * | 2020-06-11 | 2021-12-16 | 深圳市信宇人科技股份有限公司 | High-speed and high-precision burr detection method and detection system for lithium ion battery electrode sheet |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108154196B (en) | Method and apparatus for exporting image | |
CN109344908A (en) | Method and apparatus for generating model | |
CN109325541A (en) | Method and apparatus for training pattern | |
CN109002842A (en) | Image-recognizing method and device | |
CN108985208A (en) | The method and apparatus for generating image detection model | |
CN108446387A (en) | Method and apparatus for updating face registration library | |
CN109145781A (en) | Method and apparatus for handling image | |
CN108776808A (en) | A kind of method and apparatus for detecting ladle corrosion defect | |
CN109492128A (en) | Method and apparatus for generating model | |
CN109117358A (en) | test method and test device for electronic equipment | |
CN109976997A (en) | Test method and device | |
CN108446651A (en) | Face identification method and device | |
CN109145828A (en) | Method and apparatus for generating video classification detection model | |
CN108989882A (en) | Method and apparatus for exporting the snatch of music in video | |
CN108510472A (en) | Method and apparatus for handling image | |
CN109359676A (en) | Method and apparatus for generating vehicle damage information | |
CN109086780A (en) | Method and apparatus for detecting electrode piece burr | |
CN109934242A (en) | Image identification method and device | |
CN109815365A (en) | Method and apparatus for handling video | |
CN109447246A (en) | Method and apparatus for generating model | |
CN108509921A (en) | Method and apparatus for generating information | |
CN110263748A (en) | Method and apparatus for sending information | |
CN109035243A (en) | Method and apparatus for exporting battery pole piece burr information | |
CN108415653A (en) | Screen locking method and device for terminal device | |
CN108960110A (en) | Method and apparatus for generating information |
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 |