CN109086827A - Method and apparatus for detecting monocrystaline silicon solar cell defect - Google Patents
Method and apparatus for detecting monocrystaline silicon solar cell defect Download PDFInfo
- Publication number
- CN109086827A CN109086827A CN201810907537.4A CN201810907537A CN109086827A CN 109086827 A CN109086827 A CN 109086827A CN 201810907537 A CN201810907537 A CN 201810907537A CN 109086827 A CN109086827 A CN 109086827A
- Authority
- CN
- China
- Prior art keywords
- defect
- solar cell
- silicon solar
- monocrystaline silicon
- defect classification
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Photovoltaic Devices (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The embodiment of the present application discloses the method and apparatus for detecting monocrystaline silicon solar cell defect.One specific embodiment of this method includes the electroluminescent image for obtaining monocrystaline silicon solar cell to be detected；Electroluminescent image is input to defect classification model trained in advance, obtain defect information, defect information is used to indicate the defect classification of defect included by monocrystaline silicon solar cell, and wherein defect classification model is used to predict the defect classification of defect included by monocrystaline silicon solar cell according to the electroluminescent image for being input to monocrystaline silicon solar cell therein.The embodiment realizes on the basis of the defect of the monocrystaline silicon solar cell of real-time detection online production, improves the accuracy rate of the defect of identification monocrystaline silicon solar cell.
Description
Technical field
The invention relates to field of computer technology, and in particular to field of artificial intelligence, more particularly, to
The method and apparatus for detecting monocrystaline silicon solar cell defect.
Background technique
Monocrystaline silicon solar cell electroluminescent (English Electroluminescent, abbreviation EL) image, is by right
The additional forward bias voltage of monocrystaline silicon solar cell, power supply inject a large amount of nonequilibrium carriers to monocrystaline silicon solar cell,
Electroluminescent relies on a large amount of nonequilibrium carriers injected from diffusion region constantly recombination luminescence, releases photon；It is caught using camera
These photons are grasped, the image shown after being handled by computer.The electricity of monocrystaline silicon solar cell can be passed through
Photoluminescence image whether there is latent defect and external defect to detect monocrystaline silicon solar cell.And according to testing result to list
Crystal silicon solar batteries do corresponding processing, such as discard, do over again.
There are mainly two types of modes in defect classification application for existing monocrystaline silicon solar cell quality inspection system.First is pure
Artificial quality inspection mode, i.e., visually observe the photo in production environment dependent on industry specialists and provide judgement；Second assists for machine
Artificial quality inspection mode, mainly filtered out by the quality inspection system with certain judgement and do not have defective photo, by artificial right
The photo of doubtful existing defects carries out detection judgement.Wherein, the quality inspection system of the second way has cured artificial experience, has one
Fixed automatic capability.
Summary of the invention
The embodiment of the present application proposes a kind of method and apparatus for detecting monocrystaline silicon solar cell defect.
In a first aspect, the embodiment of the present application provides a kind of method for detecting monocrystaline silicon solar cell defect, it should
Method includes: the electroluminescent image for obtaining monocrystaline silicon solar cell to be detected；Electroluminescent image is input in advance
Trained defect classification model, obtains defect information, and defect information is used to indicate defect included by monocrystaline silicon solar cell
Defect classification, wherein defect classification model is used for according to being input to the electroluminescent image of monocrystaline silicon solar cell therein
Predict the defect classification of defect included by monocrystaline silicon solar cell.
In some embodiments, electroluminescent image is input to defect classification model trained in advance, obtains defect letter
Breath, comprising: obtain the current load information for the defect classification model that at least one is trained in advance；According at least one training in advance
The current load information of defect classification model determine target defect disaggregated model；Electroluminescent image is input to target to lack
Disaggregated model is fallen into, defect information is obtained.
In some embodiments, defect classification model be include convolutional layer, pond layer, full articulamentum and sorter network
Depth convolutional neural networks model.
In some embodiments, defect classification model is trained in the following way obtains: training sample set is obtained,
Wherein, training sample includes the electroluminescent image and defect classification of monocrystaline silicon solar cell；Utilize the side of machine learning
Method, using the electroluminescent image of the monocrystaline silicon solar cell in the training sample in training sample set as initial imperfection point
The input of class model, defect classification that the electroluminescent image with the monocrystaline silicon solar cell of input is corresponding are lacked as initial
The desired output of disaggregated model is fallen into, training obtains defect classification model.
In some embodiments, this method further include: full in response to defect classification corresponding to monocrystaline silicon solar cell
Sufficient preset condition, triggering warning device alarm.
In some embodiments, defect classification model updates in the following way: obtaining user and is held according to alarm
Capable response operation；The defect information that indicated defect classification updates monocrystaline silicon solar cell is operated according to response；It is based on
The defect information of updated monocrystaline silicon solar cell adjusts defect classification model.
Second aspect, the embodiment of the present application provide it is a kind of for detecting the device of monocrystaline silicon solar cell defect, should
Device includes: acquiring unit, is configured to obtain the electroluminescent image of monocrystaline silicon solar cell to be detected；Defect information
Generation unit is configured to for electroluminescent image being input to defect classification model trained in advance, obtains defect information, defect
Information is used to indicate the classification of defect included by monocrystaline silicon solar cell, and wherein defect classification model is input to for basis
The classification of defect included by the electroluminescent image prediction monocrystaline silicon solar cell of monocrystaline silicon solar cell therein.
In some embodiments, defect information generation unit is further configured to: obtaining at least one training in advance
The current load information of defect classification model；Current load information according at least one defect classification model trained in advance is true
Make target defect disaggregated model；Electroluminescent image is input to target defect disaggregated model, obtains defect information.
In some embodiments, defect classification model be include convolutional layer, pond layer, full articulamentum and sorter network
Depth convolutional neural networks model.
In some embodiments, defect classification model is trained in the following way obtains: training sample set is obtained,
Wherein, training sample includes the electroluminescent image and defect classification of monocrystaline silicon solar cell；Utilize the side of machine learning
Method, using the electroluminescent image of the monocrystaline silicon solar cell in the training sample in training sample set as initial imperfection point
The input of class model, defect classification that the electroluminescent image with the monocrystaline silicon solar cell of input is corresponding are lacked as initial
The desired output of disaggregated model is fallen into, training obtains defect classification model.
In some embodiments, which further includes alarm unit, and alarm unit is configured to: in response to the monocrystalline silicon sun
Defect classification corresponding to energy battery meets preset condition, triggering warning device alarm.
In some embodiments, defect classification model updates in the following way: obtaining user and is held according to alarm
Capable response operation；The defect information that indicated defect classification updates monocrystaline silicon solar cell is operated according to response；It is based on
The defect information of updated monocrystaline silicon solar cell adjusts defect classification model.
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 detecting monocrystaline silicon solar cell defect, by obtain to
Then electroluminescent image is input to defect trained in advance point by the electroluminescent image of the monocrystaline silicon solar cell of detection
Class model obtains defect information.It can be mentioned on the basis of the defect of the monocrystaline silicon solar cell of real-time detection online production
The accuracy rate of height identification monocrystaline silicon solar cell defect.
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 the method for detecting monocrystaline silicon solar cell defect of one embodiment of the application can be applied to
Exemplary system architecture figure therein；
Fig. 2 is the process according to one embodiment of the method for detecting monocrystaline silicon solar cell defect of the application
Figure；
Fig. 3 is the flow chart according to one embodiment of the training defect classification model of the application；
Fig. 4 is showing for application scenarios of the method according to the application for detecting monocrystaline silicon solar cell defect
It is intended to；
Fig. 5 is the stream according to another embodiment of the method for detecting monocrystaline silicon solar cell defect of the application
Cheng Tu；
Fig. 6 is the structure according to one embodiment of the device for detecting monocrystaline silicon solar cell defect of the application
Schematic diagram；
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.
The method for detecting monocrystaline silicon solar cell defect that Fig. 1 shows one embodiment of the application can answer
For exemplary system architecture 100 therein.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105,
106.Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104
It may include various connection types, such as wired, wireless communication link or fiber optic cables etc..
Terminal device 101,102,103 can be interacted by network 104 with server 105,106, be disappeared with receiving or sending
Breath etc..Various client applications can be installed, such as the application of image taking class, search are drawn on terminal device 101,102,103
Hold up class application, instant messaging tools, mailbox client, video playback class application etc..
Terminal device 101,102,103 can be hardware, be also possible to software.When terminal device 101,102,103 is hard
It can be dedicated image collecting device or other various electronic equipments interacted with server when part, including but not
It is limited to camera, video camera, smart phone, tablet computer, pocket computer on knee and desktop computer etc..When terminal is set
Standby 101,102,103 when being software, may be mounted in above-mentioned cited electronic equipment.Its may be implemented into multiple softwares or
Software module (such as providing the software of Distributed Services or software module), also may be implemented into single software or software mould
Block.It is not specifically limited herein.
Server 105,106 can provide various services, such as carry out to the data that terminal device 101,102,103 is sent
The processing such as analysis, storage or calculating.
It should be noted that for detecting the method one of monocrystaline silicon solar cell defect provided by the embodiment of the present application
As by server 105,106 execute, correspondingly, the device for detecting monocrystaline silicon solar cell defect is generally positioned at service
In device 105,106.
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 the software of Distributed Services or software module), also may be implemented
At single software or software module.It is not specifically limited herein.
It should be understood that the number of terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
With continued reference to Fig. 2, it illustrates according to the method for detecting monocrystaline silicon solar cell defect of the application
The process 200 of one embodiment.The method for being used to detect monocrystaline silicon solar cell defect, comprising the following steps:
Step 201, the electroluminescent image of monocrystaline silicon solar cell to be detected is obtained.
In the present embodiment, for detecting the executing subject of the method for monocrystaline silicon solar cell defect (such as shown in Fig. 1
Server) the available monocrystalline silicon sun to be detected uploaded from image collecting device (figure terminal device) as indicated with 1
The electroluminescent image of energy battery.
The defect of monocrystaline silicon solar cell is generally divided into latent defect and external defect.Latent defect for example can be position
Mistake, tomography etc..External defect for example may include crack, fragment, disconnected grid etc..
After accessing forward current between the two poles of the earth of monocrystaline silicon solar cell, near infrared light can be issued.Mono-crystalline silicon solar
It is also related with the density of defect other than the size of electric current of the luminous intensity of battery in addition to being proportional to input.The few part of defect,
Luminous intensity is also stronger；The more part of defect, luminous intensity are weaker.It therefore can be from the electroluminescent of monocrystaline silicon solar cell
The defects of monocrystaline silicon solar cell is with the presence or absence of dislocation, tomography, crack, fragment, disconnected grid are observed in luminescent image.
Image collecting device in the present embodiment can be the various electronic equipments with image camera function, such as various
Camera, mobile terminal etc..Further, above-mentioned image collecting device can be configured with infrared camera.
In the present embodiment, image collecting device can be by the electroluminescent of monocrystaline silicon solar cell to be detected collected
Luminescent image is uploaded in presetting database.Above-mentioned executing subject can read above-mentioned monocrystalline to be detected from presetting database
The electroluminescent image of silicon solar cell.In addition, image collecting device can be by acquired mono-crystalline silicon solar to be detected
The electroluminescent image of battery is uploaded to above-mentioned executing subject by network.Above-mentioned execution master can be above-mentioned to be checked from local reading
The electroluminescent image of the monocrystaline silicon solar cell of survey.
In application scenes, above-mentioned executing subject can be to the mono-crystalline silicon solar of above-mentioned image collecting device upload
The electroluminescent image of battery is pre-processed, such as is filtered out in the electroluminescent of image acquisition device monocrystaline silicon solar cell
During luminescent image, due to background, temperature etc. influence and the noise etc. that introduces.
Step 202, electroluminescent image is input to defect classification model trained in advance, obtains defect information, defect
Information is used to indicate the defect classification of defect included by monocrystaline silicon solar cell.
In the present embodiment, the electroluminescent graph based on step 201 monocrystaline silicon solar cell to be detected collected
The electroluminescent image of above-mentioned monocrystaline silicon solar cell can be input to defect trained in advance point by picture, above-mentioned executing subject
In class model, to obtain defect information.Drawbacks described above information is used to indicate defect included by monocrystaline silicon solar cell
Defect classification.Wherein defect classification for example may include: dislocation, tomography, crack, fragment, disconnected grid etc..Drawbacks described above information can be with
Mark including defect classification.As an example, the mark of defect classification can be numerical value, and such as: " 1 " is the mark for indicating dislocation
Know, " 2 " indicate the mark of tomography, and " 3 " indicate the mark of crack, and " 4 " indicate the mark of fragment, the mark of " 5 " expression " disconnected grid "
Deng.In addition, mark can also be the combination etc. of text, character or symbol.In addition, if above-mentioned monocrystaline silicon solar cell does not lack
It falls into, not having the defect classification of defective monocrystaline silicon solar cell can be non-defective unit.The mark of non-defective unit classification, such as can be
"0".It is understood that the mark of drawbacks described above classification can according to need and be set, herein without limiting.
In the present embodiment, drawbacks described above disaggregated model is used for according to the electricity for being input to monocrystaline silicon solar cell therein
The defect classification of defect included by photoluminescence image prediction monocrystaline silicon solar cell.
In the present embodiment, drawbacks described above disaggregated model can be various machine learning models, such as the closest (k- of k
Nearest Neighbor, KNN) model, support vector machines (Support Vector Machine, SVM) model, artificial neuron
Network (Artificial Neural Network, ANN) model etc..
It should be noted that the closest model of above-mentioned k, supporting vector machine model, artificial nerve network model are wide at present
The well-known technique of general research and application, details are not described herein.
In some optional implementations of the present embodiment, drawbacks described above disaggregated model can be include convolutional layer, pond
Change the depth convolutional neural networks model of layer, full articulamentum and sorter network.Include in depth convolutional neural networks model
At least one convolutional layer, at least one pond layer, at least one full articulamentum and a sorter network.Wherein each convolution
Layer may include multiple convolution kernels.Convolutional layer is using the different convolution kernel of weight to the electroluminescent graph of monocrystaline silicon solar cell
Picture or characteristic pattern are scanned convolution, obtain the characteristic pattern of the electroluminescent image of monocrystaline silicon solar cell.Characteristic pattern can be with
The feature of electroluminescent image different dimensions including monocrystaline silicon solar cell.What pond layer was used to export above-mentioned convolutional layer
Characteristic pattern carries out dimensionality reduction operation, the main feature in keeping characteristics figure.Above-mentioned full articulamentum may include multiple nodes.Full connection
Each node of layer is connected with all nodes that pond layer exports.The characteristic synthetic that full articulamentum is used to pond layer to export
Get up.Full articulamentum can integrate the local message with class discrimination of pond layer different node output.
This deep neural network model with convolutional layer, pond layer, too to monocrystalline silicon taken on production line
The robustness with higher such as deformation, the fuzzy, illumination variation of positive energy battery electroluminescence image, have more classification task
High can generalization.
In the present embodiment, drawbacks described above disaggregated model, which can be, is obtained by different training method training.
As an example, it can store and be based on to a large amount of monocrystalline silicon too in the executing subject of training defect classification model
It is positive can battery electroluminescent image and respectively corresponding defect classification is counted and the mapping table that generates, and should
Mapping table is as defect classification model.The electroluminescent graph of monocrystaline silicon solar cell is stored in above-mentioned mapping table
The corresponding relationship of picture and corresponding defect classification.In this way, above-mentioned executing subject can be by mono-crystalline silicon solar electricity to be detected
The electroluminescent image in pond is compared with the electroluminescent image of multiple monocrystaline silicon solar cells in the mapping table,
If the electroluminescent image of a monocrystaline silicon solar cell in the mapping table and mono-crystalline silicon solar to be detected electricity
The electroluminescent image in pond is same or similar, then by the electroluminescent image of the monocrystaline silicon solar cell in the mapping table
Defect classification of the corresponding defect classification as defect possessed by monocrystaline silicon solar cell to be detected.
It should be noted that the executing subject of training defect classification model can with for detecting monocrystaline silicon solar cell
The executing subject of the method for defect is identical, can also be different.If identical, train the executing subject of defect classification model can be with
After statistics obtains above-mentioned mapping table, above-mentioned mapping table is stored in local.If it is different, then training defect point
The executing subject of class model can send above-mentioned mapping table by network after statistics obtains above-mentioned mapping table
To the executing subject of the method for detecting monocrystaline silicon solar cell defect.
In some optional implementations of the present embodiment, drawbacks described above disaggregated model be can be by shown in Fig. 3
Training step training obtains.
Referring to FIG. 3, Fig. 3 shows the process 300 of one embodiment of the training defect classification model according to the application.
As shown in figure 3, training defect classification model may include such as step:
Step 301, training sample set is obtained, wherein training sample includes the electroluminescent of monocrystaline silicon solar cell
Image and defect classification.
In these optional implementations, the executing subject of training defect classification model can obtain training sample from local
This set, or can realize that the devices in remote electronic of communication connection is obtained from the executing subject with training defect classification model and instruct
Practice sample set.It include multiple training samples in training sample set.Wherein, each training sample includes mono-crystalline silicon solar electricity
The defect classification of defect possessed by the electroluminescent image in pond and the electroluminescent image of the monocrystaline silicon solar cell.It can
With understanding, defect classification here can be identified with numerical value, text, character or symbol, can also with numerical value, text,
The combination of character and symbol etc. identifies.
Step 302, using the method for machine learning, by the mono-crystalline silicon solar in the training sample in training sample set
Input of the electroluminescent image of battery as initial imperfection disaggregated model, by the electroluminescent of the monocrystaline silicon solar cell with input
Desired output of the corresponding defect classification of luminescent image as initial imperfection disaggregated model, training obtain defect classification model.
In these optional implementations, the executing subject of training defect classification model can determine loss letter first
Number.Loss function for example can be with are as follows: logarithm loss function, quadratic loss function, figure penalties function, Hinge loss function etc..
Then it is calculated using above-mentioned loss function and sample is input to the defect classification and training sample that initial imperfection disaggregated model is exported
Difference in this set between the corresponding defect classification of the training sample.Later, it can be based on calculating using above-mentioned loss function
Resulting difference adjusts the parameter of initial imperfection disaggregated model.Circulation executes above-mentioned training step, until above-mentioned training meets in advance
If training termination condition, terminate training.For example, the training termination condition here preset at can include but is not limited to it is following at least
One: the training time is more than preset duration；Frequency of training is more than preset times；It calculates resulting difference and is less than default difference threshold
Value.
In these optional implementations, if defect classification model is depth convolutional neural networks model, it can use
The defect class of the training sample in defect classification of the various implementations based on training sample generated and training sample set
The parameter of each layer of the initial convolutional neural networks of discrepancy adjustment between not.For example, can using BP (Back Propagation,
Backpropagation) algorithm or SGD (Stochastic Gradient Descent, stochastic gradient descent) algorithm be initial to adjust
The parameter of neural network.
It should be noted that the executing subject of above-mentioned trained defect classification model can with for detecting mono-crystalline silicon solar
The executing subject of the method for battery defect is identical, can also be different.If identical, the executing subject of defect classification model is trained
The parameter value of trained defect classification model can be stored in local after training obtains defect classification model.If no
Together, then trained defect can be classified after training obtains defect classification model by training the executing subject of defect classification model
The parameter value of model is sent to the executing subject of the method for detecting monocrystaline silicon solar cell defect by network.
It is answering for the method according to the present embodiment for detecting monocrystaline silicon solar cell defect with continued reference to Fig. 4, Fig. 4
With a schematic diagram 400 of scene.In the application scenarios shown in Fig. 4, the captured in real-time mono-crystalline silicon solar first of camera 401
The electroluminescent image of battery 402.Later, electronic equipment 403 can obtain list to be detected from above-mentioned electroluminescent image
The electroluminescent image 404 of crystal silicon solar batteries 402.Later, above-mentioned electronic equipment 403 can be by monocrystalline silicon to be detected too
The electroluminescent image of positive energy battery and multiple monocrystalline silicon sun in the mapping table being stored in above-mentioned electronic equipment 403
The electroluminescent image of energy battery is compared 405.Wherein, monocrystaline silicon solar cell is stored in above-mentioned mapping table
Electroluminescent image and corresponding defect classification corresponding relationship.According to comparison result, it is right to obtain monocrystaline silicon solar cell institute
The defect classification 406 answered.
The electroluminescent hair that the method provided by the above embodiment of the application passes through acquisition monocrystaline silicon solar cell to be detected
Then the electroluminescent image of monocrystaline silicon solar cell is input to defect classification model trained in advance, obtained by light image
Defect information.Identification monocrystalline can be improved on the basis of the defect of the monocrystaline silicon solar cell of real-time detection online production
The accuracy rate of silicon solar cell defect.
With further reference to Fig. 5, it illustrates another implementations of the method for detecting monocrystaline silicon solar cell defect
The process 500 of example.This is used to detect the process 500 of the method for monocrystaline silicon solar cell defect, comprising the following steps:
Step 501, the electroluminescent image of monocrystaline silicon solar cell to be detected is obtained.
In the present embodiment, step 501 is identical as the step 201 of embodiment illustrated in fig. 2, does not repeat herein.
Step 502, the current load information for the defect classification model that at least one is trained in advance is obtained.
In the present embodiment, it can be set in the executing subject of the method for detecting monocrystaline silicon solar cell defect
At least one defect classification model trained in advance.For example, if executing subject is the server cluster of multiple servers composition, it can
A defect classification model trained in advance to be arranged on each server.It, can be with if executing subject is individual server
At least one defect classification model trained in advance is set on that server.
Above-mentioned executing subject can distribute the electricity of at least one monocrystaline silicon solar cell for each defect classification model
Photoluminescence image is analyzed and processed.The electroluminescent image of each monocrystaline silicon solar cell to be processed can be used as this
One load of defect classification model.Here the current load information of each defect classification model can be to be used to indicate this
The information of the current quantity of the electroluminescent image of untreated monocrystaline silicon solar cell of defect classification model.If a defect
Disaggregated model is currently without the electroluminescent image of untreated monocrystaline silicon solar cell, the then load of the defect classification model
Load number indicated by information is 0.
The defects of the present embodiment disaggregated model can be identical as the defects of embodiment illustrated in fig. 2 disaggregated model, herein
It does not repeat.
The training method of the defects of the present embodiment disaggregated model can also be with the defects of embodiment illustrated in fig. 2 classification mould
The training method of type is identical, does not repeat herein.
Step 503, determine that target lacks according to the current load information of at least one defect classification model trained in advance
Fall into disaggregated model.
In the present embodiment, the current of at least one defect classification model trained in advance obtained based on step 502 is born
Information carrying breath, above-mentioned executing subject can determine target defect disaggregated model according to preset rules.For example, above-mentioned executing subject can
To choose a defect classification model of the minimum number of the electroluminescent image of current untreated monocrystaline silicon solar cell
As target defect disaggregated model.In another example above-mentioned executing subject can be from the corresponding current untreated monocrystalline silicon sun
The quantity of the electroluminescent image of energy battery, which is less than in the defect classification model of preset threshold, randomly selects a defect classification mould
Type is as target defect disaggregated model.
Step 504, electroluminescent image is input to target defect disaggregated model, obtains defect information.
In the present embodiment, step 504 can be identical as the step 202 in embodiment illustrated in fig. 2, does not repeat herein.
Step 505, meet preset condition, triggering alarm dress in response to defect classification corresponding to monocrystaline silicon solar cell
Set alarm.
In the present embodiment, above-mentioned executing subject can be full in response to the defect classification corresponding to monocrystaline silicon solar cell
Sufficient preset condition issues dependent instruction to trigger warning device alarm.
Here preset condition for example can be a pre-set categories.In addition, preset condition can also be according to specifically answering
It is set with scene, herein without limitation.
In the present embodiment, warning device can be used to detect monocrystaline silicon solar cell defect by network with above-mentioned
The executing subject of method is communicatively coupled.
Here, the alarm of triggering warning device is to prompt producers' monocrystaline silicon solar cell to have defect.One
In a little application scenarios, which needs manual confirmation and releases.
From figure 5 it can be seen that being used to detect the monocrystalline silicon sun in the present embodiment compared with the corresponding embodiment of Fig. 2
The process 500 of the method for energy battery defect is highlighted determines that target is lacked from the defect classification model that at least one is trained in advance
The step of falling into disaggregated model, and highlight the step of preset condition triggering alarm is met according to defect classification.This implementation as a result,
On-line analysis monocrystalline silicon can be improved according to load balancing come selection target defect classification model in the scheme of example description
The efficiency of the defect of solar battery.In addition, can prompt producers in time to the list with defect using warning device alarm
Crystal silicon solar batteries are handled.
In some optional implementations of the present embodiment, defect classification model can be updated in the following way:
First, it obtains user and is operated according to the performed response of alarm.
If defect classification corresponding to monocrystaline silicon solar cell meets preset condition, above-mentioned for detecting the monocrystalline silicon sun
Command adapted thereto triggering warning device alarm can be generated in the executing subject of the method for energy battery defect, and user can be according to above-mentioned report
It is alert to execute corresponding response operation.Here user can on monocrystaline silicon solar cell production line related personnel (such as
Quality testing personnel).
Here response operation can be electroluminescent of the user to monocrystaline silicon solar cell indicated by above-mentioned alarm
It is made after image confirmation.Such as user confirms the electroluminescent image of monocrystaline silicon solar cell indicated by above-mentioned alarm
Afterwards, determine that the monocrystaline silicon solar cell is non-defective unit, then above-mentioned response operation can be used to indicate the monocrystalline silicon sun for input
Energy battery is the operation of the information of non-defective unit.In another example user is to the electroluminescent of monocrystaline silicon solar cell indicated by above-mentioned alarm
After luminescent image confirmation, determine that the monocrystaline silicon solar cell does not have the method for detecting monocrystaline silicon solar cell defect
The determined classification of executing subject defect, but the defect with other classifications, then above-mentioned response operation can be used for input
In the operation for indicating that the monocrystaline silicon solar cell has the information of the defect of other classifications.
If updating the executing subject and the above-mentioned method for detecting monocrystaline silicon solar cell defect of defect classification model
Executing subject it is identical, then the executing subject for updating defect classification model can be from the local above-mentioned response operation for obtaining user.
If updating the executing subject and the above-mentioned method for detecting monocrystaline silicon solar cell defect of defect classification model
Executing subject it is not identical, then the executing subject for updating defect classification model can be by network from for detecting mono-crystalline silicon solar
The executing subject of the method for battery defect obtains the response operation of above-mentioned user.
Second, the defect information that indicated defect classification updates monocrystaline silicon solar cell is operated according to response.
The executing subject for updating defect classification model can operate indicated defect classification according to response and carry out more new single-crystal
The defect information of silicon solar cell, such as update defect classification corresponding to monocrystaline silicon solar cell.
Third, the defect information based on updated monocrystaline silicon solar cell adjust defect classification model.
In these optional implementations, the executing subject for updating defect classification model can be by the above-mentioned monocrystalline silicon sun
The electroluminescent image of energy battery is input in defect classification model, to lack after update corresponding to the monocrystaline silicon solar cell
Classification is fallen into as desired output, to adjust the parameter of defect classification model, to realize the adjustment to defect classification model.
In these optional implementations, defect classification model is updated due to using aforesaid way, so that
Drawbacks described above disaggregated model can be continuously available in use it is perfect, so as to further increase identification to monocrystalline silicon too
The accuracy rate of positive energy battery defect.
With further reference to Fig. 6, as the realization to method shown in above-mentioned each figure, this application provides one kind for detecting list
One embodiment of the device of crystal silicon solar batteries defect, the Installation practice is corresponding with embodiment of the method shown in Fig. 2,
The device specifically can be applied in various electronic equipments.
As shown in fig. 6, the device 600 for detecting monocrystaline silicon solar cell defect of the present embodiment includes: to obtain list
First 601, defect information generation unit 602.Wherein, acquiring unit 601 are configured to obtain mono-crystalline silicon solar electricity to be detected
The electroluminescent image in pond；Defect information generation unit 602 is configured to for electroluminescent image being input to lacking for training in advance
Disaggregated model is fallen into, defect information is obtained, defect information is used to indicate the classification of defect included by monocrystaline silicon solar cell,
Middle defect classification model is used to predict monocrystalline silicon too according to the electroluminescent image for being input to monocrystaline silicon solar cell therein
The classification of defect included by positive energy battery.
In the present embodiment, for detecting acquiring unit 601, the defect of the device 600 of monocrystaline silicon solar cell defect
The specific processing of information generating unit 602 and its brought technical effect can be respectively with reference to steps 201 in Fig. 2 corresponding embodiment
With the related description of step 202, details are not described herein.
In some optional implementations of the present embodiment, defect information generation unit 602 is further configured to: being obtained
The current load information for the defect classification model for taking at least one to train in advance；The defect classification trained in advance according at least one
The current load information of model determines target defect disaggregated model；Electroluminescent image is input to target defect classification mould
Type obtains defect information.
In some optional implementations of the present embodiment, defect classification model be include convolutional layer, pond layer, Quan Lian
Connect the depth convolutional neural networks model of layer and sorter network.
In some optional implementations of the present embodiment, defect classification model is trained in the following way obtains
: obtain training sample set, wherein training sample includes the electroluminescent image and defect class of monocrystaline silicon solar cell
Not；Using the method for machine learning, by the electroluminescent hair of the monocrystaline silicon solar cell in the training sample in training sample set
Input of the light image as initial imperfection disaggregated model, the electroluminescent image with the monocrystaline silicon solar cell of input is corresponding
Desired output of the defect classification as initial imperfection disaggregated model, training obtains defect classification model.
In some optional implementations of the present embodiment, for detecting the device of monocrystaline silicon solar cell defect
600 further include alarm unit 603, and alarm unit 603 is configured to: in response to defect class corresponding to monocrystaline silicon solar cell
Do not meet preset condition, triggering warning device alarm.
In some optional implementations of the present embodiment, defect classification model updates in the following way: obtaining
Family is taken to be operated according to the performed response of alarm；Indicated defect classification is operated according to response updates mono-crystalline silicon solar electricity
The defect information in pond；Defect information based on updated monocrystaline silicon solar cell adjusts defect classification model.
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, Central Processing Unit)
701, it can be according to the program being stored in read-only memory (ROM, Read Only Memory) 702 or from storage section
708 programs being loaded into random access storage device (RAM, Random Access Memory) 703 and execute various appropriate
Movement 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 is connected with each other by bus 704.Input/output (I/O, Input/Output) interface 705 is also connected to
Bus 704.
I/O interface 705 is connected to lower component: the importation 706 including keyboard, mouse etc.；It is penetrated including such as cathode
Spool (CRT, Cathode Ray Tube), liquid crystal display (LCD, Liquid Crystal Display) etc. and loudspeaker
Deng output par, c 707；Storage section 708 including hard disk etc.；And including such as LAN (local area network, Local Area
Network) the communications portion 709 of the network interface card of card, modem etc..Communications portion 709 is via such as internet
Network 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 from the calculating read thereon
Machine program is 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, programming language include object oriented program language-such as Java, Smalltalk, C++, also
Including conventional procedural programming language-such as " C " language or similar programming language.Program code can be complete
It executes, partly executed on the user computer on the user computer entirely, being executed as an independent software package, part
Part executes on the remote computer or executes on a remote computer or server completely on the user computer.It is relating to
And in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or extensively
Domain net (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as provided using Internet service
Quotient 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 and defect information generation 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 electroluminescent of monocrystaline silicon solar cell to be detected
The unit of image ".
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 electroluminescent image of monocrystaline silicon solar cell to be detected is obtained；Electroluminescent image is input to preparatory training
Defect classification model, obtain defect information, defect information is used to indicate the class of defect included by monocrystaline silicon solar cell
Not, wherein defect classification model is used for according to the electroluminescent image prediction monocrystalline for being input to monocrystaline silicon solar cell therein
The classification of defect included by silicon solar cell.
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 (14)
1. a kind of method for detecting monocrystaline silicon solar cell defect, comprising:
Obtain the electroluminescent image of monocrystaline silicon solar cell to be detected；
The electroluminescent image is input to defect classification model trained in advance, obtains defect information, the defect information
It is used to indicate the defect classification of defect included by the monocrystaline silicon solar cell, wherein the defect classification model is used for root
Defect included by monocrystaline silicon solar cell is predicted according to the electroluminescent image for being input to monocrystaline silicon solar cell therein
Defect classification.
2. described that the electroluminescent image is input to defect trained in advance according to the method described in claim 1, wherein
Disaggregated model obtains defect information, comprising:
Obtain the current load information for the defect classification model that at least one is trained in advance；
Target defect classification mould is determined according to the current load information of at least one defect classification model trained in advance
Type；
The electroluminescent image is input to the target defect disaggregated model, obtains the defect information.
3. according to the method described in claim 1, wherein, the defect classification model be include convolutional layer, pond layer, full connection
The depth convolutional neural networks model of layer and sorter network.
4. method according to claim 1 or 3, wherein the defect classification model is trained in the following way obtains
:
Obtain training sample set, wherein training sample includes the electroluminescent image and defect of monocrystaline silicon solar cell
Classification；
Using the method for machine learning, by the electricity of the monocrystaline silicon solar cell in the training sample in the training sample set
Input of the photoluminescence image as the initial imperfection disaggregated model, by the electroluminescent of the monocrystaline silicon solar cell with input
Desired output of the corresponding defect classification of image as the initial imperfection disaggregated model, training obtain the defect classification mould
Type.
5. according to the method described in claim 1, wherein, the method also includes:
Meet preset condition, triggering warning device alarm in response to defect classification corresponding to the monocrystaline silicon solar cell.
6. according to the method described in claim 5, wherein, the defect classification model updates in the following way:
Obtain user's response according to performed by alarm operation；
The defect information of the monocrystaline silicon solar cell is updated according to the indicated defect classification of the response operation；
Defect information based on updated monocrystaline silicon solar cell adjusts the defect classification model.
7. a kind of for detecting the device of monocrystaline silicon solar cell defect, comprising:
Acquiring unit is configured to obtain the electroluminescent image of monocrystaline silicon solar cell to be detected；
Defect information generation unit is configured to for the electroluminescent image being input to defect classification model trained in advance,
Defect information is obtained, the defect information is used to indicate the classification of defect included by the monocrystaline silicon solar cell, wherein
The defect classification model is used for according to the electroluminescent image prediction monocrystalline silicon for being input to monocrystaline silicon solar cell therein
The classification of defect included by solar battery.
8. device according to claim 7, wherein the defect information generation unit is further configured to:
Obtain the current load information for the defect classification model that at least one is trained in advance；
Target defect classification mould is determined according to the current load information of at least one defect classification model trained in advance
Type；
The electroluminescent image is input to the target defect disaggregated model, obtains the defect information.
9. device according to claim 7, wherein the defect classification model be include convolutional layer, pond layer, full connection
The depth convolutional neural networks model of layer and sorter network.
10. the device according to claim 7 or 9, wherein the defect classification model is trained in the following way obtains
:
Obtain training sample set, wherein training sample includes the electroluminescent image and defect of monocrystaline silicon solar cell
Classification；
Using the method for machine learning, by the electricity of the monocrystaline silicon solar cell in the training sample in the training sample set
Input of the photoluminescence image as the initial imperfection disaggregated model, by the electroluminescent of the monocrystaline silicon solar cell with input
Desired output of the corresponding defect classification of image as the initial imperfection disaggregated model, training obtain the defect classification mould
Type.
11. device according to claim 7, wherein described device further includes alarm unit, and the alarm unit is configured
At:
Meet preset condition, triggering warning device alarm in response to defect classification corresponding to the monocrystaline silicon solar cell.
12. device according to claim 11, wherein the defect classification model updates in the following way:
Obtain user's response according to performed by alarm operation；
The defect information of the monocrystaline silicon solar cell is updated according to the indicated defect classification of the response operation；
Defect information based on updated monocrystaline silicon solar cell adjusts the defect classification model.
13. a kind of electronic equipment, 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 6.
14. a kind of computer-readable medium, is stored thereon with computer program, wherein the realization when program is executed by processor
Such as method as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810907537.4A CN109086827A (en) | 2018-08-10 | 2018-08-10 | Method and apparatus for detecting monocrystaline silicon solar cell defect |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810907537.4A CN109086827A (en) | 2018-08-10 | 2018-08-10 | Method and apparatus for detecting monocrystaline silicon solar cell defect |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109086827A true CN109086827A (en) | 2018-12-25 |
Family
ID=64834517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810907537.4A Pending CN109086827A (en) | 2018-08-10 | 2018-08-10 | Method and apparatus for detecting monocrystaline silicon solar cell defect |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109086827A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109828545A (en) * | 2019-02-28 | 2019-05-31 | 武汉三工智能装备制造有限公司 | AI intelligent process anomalous identification closed loop control method, host and change system |
| CN110487802A (en) * | 2019-08-15 | 2019-11-22 | 苏州热工研究院有限公司 | The identification device of on-site test photovoltaic module defect |
| CN111260617A (en) * | 2020-01-11 | 2020-06-09 | 上海应用技术大学 | Solar cell panel defect detection method based on deep learning |
| CN111860987A (en) * | 2020-07-08 | 2020-10-30 | 江苏科慧半导体研究院有限公司 | Mixed fluorescent material emission spectrum prediction method and device |
| CN113145553A (en) * | 2021-02-07 | 2021-07-23 | 福建新峰二维材料科技有限公司 | Classifying method for cast monocrystalline silicon wafers |
| CN113314433A (en) * | 2021-05-27 | 2021-08-27 | 深圳市泰晶太阳能科技有限公司 | Monocrystalline silicon solar cell reliability screening method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101796398A (en) * | 2007-08-31 | 2010-08-04 | Icos视觉系统股份有限公司 | Apparatus and method for detecting semiconductor substrate anomalies |
| CN102472791A (en) * | 2009-08-04 | 2012-05-23 | 国立大学法人奈良先端科学技术大学院大学 | Solar cell evaluation method, evaluation device, maintenance method, maintenance system, and method of manufacturing solar cell module |
| CN108154508A (en) * | 2018-01-09 | 2018-06-12 | 北京百度网讯科技有限公司 | Method, apparatus, storage medium and the terminal device of product defects detection positioning |
| CN108257121A (en) * | 2018-01-09 | 2018-07-06 | 北京百度网讯科技有限公司 | The newer method, apparatus of product defects detection model, storage medium and terminal device |
| CN108320278A (en) * | 2018-01-09 | 2018-07-24 | 北京百度网讯科技有限公司 | Product defects detect localization method, device, equipment and computer-readable medium |
-
2018
- 2018-08-10 CN CN201810907537.4A patent/CN109086827A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101796398A (en) * | 2007-08-31 | 2010-08-04 | Icos视觉系统股份有限公司 | Apparatus and method for detecting semiconductor substrate anomalies |
| CN102472791A (en) * | 2009-08-04 | 2012-05-23 | 国立大学法人奈良先端科学技术大学院大学 | Solar cell evaluation method, evaluation device, maintenance method, maintenance system, and method of manufacturing solar cell module |
| CN108154508A (en) * | 2018-01-09 | 2018-06-12 | 北京百度网讯科技有限公司 | Method, apparatus, storage medium and the terminal device of product defects detection positioning |
| CN108257121A (en) * | 2018-01-09 | 2018-07-06 | 北京百度网讯科技有限公司 | The newer method, apparatus of product defects detection model, storage medium and terminal device |
| CN108320278A (en) * | 2018-01-09 | 2018-07-24 | 北京百度网讯科技有限公司 | Product defects detect localization method, device, equipment and computer-readable medium |
Non-Patent Citations (2)
| Title |
|---|
| 墨恺: "晶硅太阳电池电致发光成像缺陷检测及自动识别", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
| 陈文志: "基于电致发光成像的太阳能电池缺陷检测", 《万方数据知识服务平台》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109828545A (en) * | 2019-02-28 | 2019-05-31 | 武汉三工智能装备制造有限公司 | AI intelligent process anomalous identification closed loop control method, host and change system |
| CN109828545B (en) * | 2019-02-28 | 2020-09-11 | 武汉三工智能装备制造有限公司 | AI intelligent process anomaly identification closed-loop control method, host and equipment system |
| CN110487802A (en) * | 2019-08-15 | 2019-11-22 | 苏州热工研究院有限公司 | The identification device of on-site test photovoltaic module defect |
| CN111260617A (en) * | 2020-01-11 | 2020-06-09 | 上海应用技术大学 | Solar cell panel defect detection method based on deep learning |
| CN111860987A (en) * | 2020-07-08 | 2020-10-30 | 江苏科慧半导体研究院有限公司 | Mixed fluorescent material emission spectrum prediction method and device |
| CN111860987B (en) * | 2020-07-08 | 2024-05-31 | 江苏科慧半导体研究院有限公司 | Method and device for predicting emission spectrum of mixed fluorescent material |
| CN113145553A (en) * | 2021-02-07 | 2021-07-23 | 福建新峰二维材料科技有限公司 | Classifying method for cast monocrystalline silicon wafers |
| CN113314433A (en) * | 2021-05-27 | 2021-08-27 | 深圳市泰晶太阳能科技有限公司 | Monocrystalline silicon solar cell reliability screening method |
| CN113314433B (en) * | 2021-05-27 | 2022-12-06 | 深圳市泰晶太阳能科技有限公司 | Monocrystalline silicon solar cell reliability screening mode |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109086827A (en) | Method and apparatus for detecting monocrystaline silicon solar cell defect | |
| CN109145973A (en) | Method and apparatus for detecting monocrystaline silicon solar cell defect | |
| CN109344908A (en) | Method and apparatus for generating model | |
| CN109191453A (en) | Method and apparatus for generating image category detection model | |
| CN109949286A (en) | Method and apparatus for output information | |
| CN109145828A (en) | Method and apparatus for generating video classification detection model | |
| CN108776808A (en) | A kind of method and apparatus for detecting ladle corrosion defect | |
| CN111368980B (en) | State detection method, device, equipment and storage medium | |
| CN109492128A (en) | Method and apparatus for generating model | |
| CN110458107A (en) | Method and apparatus for image recognition | |
| CN109446990A (en) | Method and apparatus for generating information | |
| CN103941871B (en) | The method and apparatus for controlling the hardware running status of intelligent terminal | |
| CN109376267A (en) | Method and apparatus for generating model | |
| CN109359676A (en) | Method and apparatus for generating vehicle damage information | |
| CN108830837A (en) | A kind of method and apparatus for detecting ladle corrosion defect | |
| CN109495783A (en) | Video reviewing method, device, electronic equipment and medium | |
| CN108229485A (en) | For testing the method and apparatus of user interface | |
| CN109934242A (en) | Image identification method and device | |
| CN114757307B (en) | Artificial intelligence automatic training method, system, device and storage medium | |
| CN107784395A (en) | A kind of electric power line ice-covering thickness Forecasting Methodology based on LSTM artificial neural networks | |
| CN110263748A (en) | Method and apparatus for sending information | |
| CN109634833A (en) | A kind of Software Defects Predict Methods and device | |
| CN108961267A (en) | Image processing method, picture processing unit and terminal device | |
| CN108960110A (en) | Method and apparatus for generating information | |
| CN116453056A (en) | Target detection model construction method and transformer substation foreign matter intrusion detection method |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181225 |
|
| RJ01 | Rejection of invention patent application after publication |