CN108921841A - Continuous casting of iron and steel base quality determining method, device, equipment and storage medium - Google Patents
Continuous casting of iron and steel base quality determining method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN108921841A CN108921841A CN201810710536.0A CN201810710536A CN108921841A CN 108921841 A CN108921841 A CN 108921841A CN 201810710536 A CN201810710536 A CN 201810710536A CN 108921841 A CN108921841 A CN 108921841A
- Authority
- CN
- China
- Prior art keywords
- iron
- continuous casting
- steel base
- quality
- 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
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 title claims abstract description 370
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 193
- 239000010959 steel Substances 0.000 title claims abstract description 193
- 238000009749 continuous casting Methods 0.000 title claims abstract description 187
- 229910052742 iron Inorganic materials 0.000 title claims abstract description 185
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 230000007547 defect Effects 0.000 claims abstract description 79
- 238000013145 classification model Methods 0.000 claims abstract description 47
- 238000004519 manufacturing process Methods 0.000 claims abstract description 45
- 238000005259 measurement Methods 0.000 claims abstract description 43
- 238000001514 detection method Methods 0.000 claims abstract description 27
- 238000012372 quality testing Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims description 36
- 238000003062 neural network model Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- General Factory Administration (AREA)
Abstract
The embodiment of the present invention provides a kind of continuous casting of iron and steel base quality determining method, device, equipment and storage medium.This method includes：Obtain the image information of at least one continuous casting of iron and steel base；Image recognition is carried out using image information of the default defect classification model at least one continuous casting of iron and steel base, is detected with the quality to each continuous casting of iron and steel base at least one described continuous casting of iron and steel base；The quality measurements of the continuous casting of iron and steel base are sent to the production line of the continuous casting of iron and steel base.The embodiment of the present invention saves the workload of artificial detection continuous casting of iron and steel base, improves the efficiency of continuous casting of iron and steel base quality testing, in addition, can avoid failing to judge and judging by accident caused by human factor.
Description
Technical field
The present embodiments relate to technical field of image processing more particularly to a kind of continuous casting of iron and steel base quality determining method,
Device, equipment and storage medium.
Background technique
In steel and iron manufacturing industry, the quality testing of continuous casting of iron and steel base is the key link in production procedure.Traditional steel
The quality testing of continuous casting billet is usually artificial detection, is detected by surface of the testing staff to continuous casting of iron and steel base, to judge steel
Iron continuous casting billet whether there is flaw and defect.
But it is lower by the efficiency of the quality of artificial detection continuous casting of iron and steel base, and be easy to appear and fail to judge and judge by accident.
Summary of the invention
The embodiment of the present invention provides a kind of continuous casting of iron and steel base quality determining method, device, equipment and storage medium, to improve
The efficiency of continuous casting of iron and steel base quality testing, in addition, avoiding failing to judge and judging by accident caused by human factor.
In a first aspect, the embodiment of the present invention provides a kind of continuous casting of iron and steel base quality determining method, including：
Obtain the image information of at least one continuous casting of iron and steel base；
Image recognition is carried out using image information of the default defect classification model at least one continuous casting of iron and steel base, with
The quality of each continuous casting of iron and steel base at least one described continuous casting of iron and steel base is detected；
The quality measurements of the continuous casting of iron and steel base are sent to the production line of the continuous casting of iron and steel base.
Optionally, the image information for obtaining at least one continuous casting of iron and steel base；
It receives and is believed by the image of the continuous casting of iron and steel base of the capture apparatus acquisition on the production line of the continuous casting of iron and steel base
Breath.
Optionally, the method also includes：
Record the quality measurements of the continuous casting of iron and steel base；
The instruction for training the default defect classification model is updated according to the quality measurements of the continuous casting of iron and steel base
Practice database；
Defect classification model is preset according to the updated tranining database re -training.
Optionally, the quality measurements include defect classification logotype information.
Optionally, the default defect classification model includes deep neural network model.
Optionally, the method also includes：
According to the image information of the production line of the continuous casting of iron and steel base and at least one continuous casting of iron and steel base, determine described in
The structure of deep neural network model.
Second aspect, the embodiment of the present invention provide a kind of continuous casting of iron and steel base quality detection device, including：
Module is obtained, for obtaining the image information of at least one continuous casting of iron and steel base；
Detection module, for using default defect classification model to the image information of at least one continuous casting of iron and steel base into
Row image recognition is detected with the quality to each continuous casting of iron and steel base at least one described continuous casting of iron and steel base；
Sending module, for the quality measurements of the continuous casting of iron and steel base to be sent to the production of the continuous casting of iron and steel base
Line.
Optionally, the acquisition module is specifically used for receiving and be adopted by the capture apparatus on the production line of the continuous casting of iron and steel base
The image information of the continuous casting of iron and steel base of collection.
Optionally, continuous casting of iron and steel base quality detection device further includes：
Logging modle, for recording the quality measurements of the continuous casting of iron and steel base；
Update module, for being updated according to the quality measurements of the continuous casting of iron and steel base for training the default defect
The tranining database of disaggregated model；
Model training module, for presetting defect classification mould according to the updated tranining database re -training
Type.
Optionally, the quality measurements include defect classification logotype information.
Optionally, the default defect classification model includes deep neural network model.
Optionally, continuous casting of iron and steel base quality detection device further includes：
Determining module, for according to the production line of the continuous casting of iron and steel base and the image of at least one continuous casting of iron and steel base
Information determines the structure of the deep neural network model.
The third aspect, the embodiment of the present invention provide a kind of server, including：
Memory；
Processor；And
Computer program；
Wherein, the computer program stores in the memory, and is configured as being executed by the processor with reality
Method described in existing first aspect.
Fourth aspect, the embodiment of the present invention provide a kind of computer readable storage medium, are stored thereon with computer program,
The computer program is executed by processor to realize method described in first aspect.
Continuous casting of iron and steel base quality determining method, device, equipment and storage medium provided in an embodiment of the present invention, pass through service
Device obtains the image information of at least one continuous casting of iron and steel base, using default defect classification model at least one described continuous casting of iron and steel
The image information of base carries out image recognition, is carried out with the quality to each continuous casting of iron and steel base at least one described continuous casting of iron and steel base
It detects, and the quality measurements of the continuous casting of iron and steel base is sent to the production line of the continuous casting of iron and steel base, save artificial
The workload for detecting continuous casting of iron and steel base, improves the efficiency of continuous casting of iron and steel base quality testing, in addition, can avoid human factor causes
Fail to judge and judge by accident.
Detailed description of the invention
Fig. 1 is a kind of schematic diagram of application scenarios provided in an embodiment of the present invention；
Fig. 2 is the schematic diagram of another application scenarios provided in an embodiment of the present invention；
Fig. 3 is continuous casting of iron and steel base quality determining method flow chart provided in an embodiment of the present invention；
Fig. 4 be another embodiment of the present invention provides continuous casting of iron and steel base quality determining method flow chart；
Fig. 5 is the structural schematic diagram of continuous casting of iron and steel base quality detection device provided in an embodiment of the present invention；
Fig. 6 is the structural schematic diagram of server provided in an embodiment of the present invention.
Through the above attached drawings, it has been shown that the specific embodiment of the disclosure will be hereinafter described in more detail.These attached drawings
It is not intended to limit the scope of this disclosure concept by any means with verbal description, but is by referring to specific embodiments
Those skilled in the art illustrate the concept of the disclosure.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all implementations consistent with this disclosure.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the disclosure.
Continuous casting of iron and steel base quality determining method provided by the invention, can be adapted for communication system shown in FIG. 1.Such as Fig. 1
Shown, which includes：Capture apparatus, console, server, the production line of continuous casting of iron and steel base, control module, production number
According to library.Specifically, the production line in continuous casting of iron and steel base specifically can be set in capture apparatus, which shoots continuous casting of iron and steel base
Image information.The image information is sent to console by the capture apparatus, which is sent to operation for the image information
The server of defective disaggregated model.Optionally, console can be integrated in capture apparatus, or be integrated in the server, or
Person's console is and the capture apparatus and the mutually independent equipment of server.The console can be with the capture apparatus and service
Device communication.The defect classification model run on the server can be preparatory trained model, which is used for
Image recognition is carried out to the image information of continuous casting of iron and steel base, is detected with the quality to the continuous casting of iron and steel base, and export quality
The quality measurements are sent to control module by testing result, the server, if the quality measurements identify the steel
Continuous casting billet existing defects, then the control module can make corresponding response according to business demand, such as issue prompt information, this reality
Apply example and do not limit the prompting mode of prompt information, for example, can be in screen display reminding information, buzzer issues prompt tone,
Vibrator generates vibration etc..If the defect of the continuous casting of iron and steel base is more serious, which can also control and carry this
The continuous casting of iron and steel base is transmitted to specified collection site by the conveyer belt of continuous casting of iron and steel base；Alternatively, the control module can also be controlled
The continuous casting of iron and steel base is picked up and is put into specified collection site by mechanical arm processed.The control module can integrate in conveyer belt or machine
In tool arm, it is also possible to the equipment independently of conveyer belt or mechanical arm, which can control conveyer belt or mechanical arm.In addition,
The control module can also be using the quality measurements that defect classification model exports and the response that the control module is made as line
Upper production log storage is into Production database, and optionally, which includes：The figure of defective continuous casting of iron and steel base
As the defect classification logotype information of information and the continuous casting of iron and steel base.
Optionally, in the initial state, what is stored in tranining database is history labeled data, and training engine is according to training
History labeled data training in database obtains the defect classification model.Classify when constantly storing the defect in Production database
When the quality measurements of model output, tranining database can also be updated according to the quality measurements in the Production database
In training data, training engine sends request of data to the tranining database, so that the tranining database is by updated instruction
Practice data and be sent to trained engine, this is lacked the training engine according to training data re -training updated in the tranining database
Disaggregated model is fallen into, and obtains updated defect classification model.
Optionally, tranining database and training engine can integrate in the server, in some embodiments, training number
It can also be not integrated into the server and be individually present according to library and training engine.
As another feasible implementation, when defect classification model exports quality measurements, which can
Directly using the quality measurements as log storage is produced on line into Production database, without passing through control module for matter
Testing result storage is measured to Production database, detailed process is as shown in Figure 2.
In addition, as depicted in figs. 1 and 2, when console receives the image information of the continuous casting of iron and steel base of capture apparatus shooting
When, which can also store the image information of the continuous casting of iron and steel base into Production database.
Continuous casting of iron and steel base quality determining method provided by the invention, it is intended to solve the technical problem as above of the prior art.
How to be solved with technical solution of the specifically embodiment to technical solution of the present invention and the application below above-mentioned
Technical problem is described in detail.These specific embodiments can be combined with each other below, for the same or similar concept
Or process may repeat no more in certain embodiments.Below in conjunction with attached drawing, the embodiment of the present invention is described.
Fig. 3 is continuous casting of iron and steel base quality determining method flow chart provided in an embodiment of the present invention.The embodiment of the present invention is directed to
The technical problem as above of the prior art provides continuous casting of iron and steel base quality determining method, and specific step is as follows for this method：
Step 301, the image information for obtaining at least one continuous casting of iron and steel base.
Optionally, the image information for obtaining at least one continuous casting of iron and steel base；Receive the life by the continuous casting of iron and steel base
The image information of the continuous casting of iron and steel base of capture apparatus acquisition in producing line.
In the present embodiment, it is provided at least one capture apparatus on the production line of continuous casting of iron and steel base, at least one bat
It takes the photograph equipment and constitutes image capturing system, it will be understood that in the image capturing system other than capture apparatus, it is also possible to there are other to set
It is standby, such as be used for transmission the transmission device of image, the controller for controlling capture apparatus shooting etc., the controller is controllable to be clapped
Take the photograph the shooting angle, shooting time, shooting posture etc. of equipment.The capture apparatus is used to acquire the continuous casting of iron and steel base on the production line
Image information, the present embodiment do not limit the number of continuous casting of iron and steel base on the production line.
Specifically, console as shown in the figures 1 and 2 obtains at least one continuous casting of iron and steel base of image capturing system acquisition
Image information, and send server for the image information of at least one continuous casting of iron and steel base, which can be remotely
Server is also possible to local server.Server operation has preparatory trained defect classification model.
In some embodiments, multiple server operations there can be the defect classification model, which can be according to negative
Equalization algorithm is carried, selects a more idle server from multiple server, and by least one continuous casting of iron and steel base
Image information be sent to the more idle server；Alternatively, the console can according to load-balancing algorithm, by this at least one
The image information of a continuous casting of iron and steel base is distributed on several different servers.
Step 302 carries out figure using image information of the default defect classification model at least one continuous casting of iron and steel base
As identification, detected with the quality to each continuous casting of iron and steel base at least one described continuous casting of iron and steel base.
After server receives the image information of at least one continuous casting of iron and steel base of console transmission, using preparatory training
Good defect classification model carries out image recognition to the image information of at least one continuous casting of iron and steel base, specifically, the defect point
Class model pre-processes image information, and carries out classified calculating, and classified calculating herein is connected to steel in different images
The defect of slab is classified, to detect to the quality of each continuous casting of iron and steel base at least one continuous casting of iron and steel base.
The defect classification model exports the corresponding defect classification logotype information of each image information, if the corresponding steel of the image information
Continuous casting billet does not have defect, then the corresponding defect classification logotype information of the image information can be 0.In addition, the defect classification model
Can also export 1,2 ... the numerical value such as n are for identifying the different defect of n kind.
Step 303, the production line that the quality measurements of the continuous casting of iron and steel base are sent to the continuous casting of iron and steel base.
As depicted in figs. 1 and 2, the quality measurements that defect classification model exports are sent to control module by server,
Control information is sent from the control module to the production line of continuous casting of iron and steel base, for example, control module control carries the steel
The continuous casting of iron and steel base is transmitted to specified collection site by the conveyer belt of continuous casting billet；Alternatively, the control module can also control machine
The continuous casting of iron and steel base is picked up and is put into specified collection site by tool arm.Optionally, the quality measurements include defect class
Other identification information, such as represent the numerical value of n kind difference defect and represent flawless 0 value.That is, the defect classification model
Input be continuous casting of iron and steel base image information, the output of the defect classification model is the defect classification logotype of the continuous casting of iron and steel base
Information.It is appreciated that the quality measurements are not limited to include defect classification logotype information, it can also include the defect classification mark
Know the corresponding image information of information.
Optionally, the default defect classification model includes deep neural network model.The deep neural network model packet
It includes convolutional layer, pond layer, connect layer etc. entirely, wherein convolution operation is scanned original image using the different convolution kernel of weight
Convolution, the feature for therefrom extracting various meanings obtain characteristic pattern.Pondization operation then carries out dimensionality reduction operation to this feature figure, and retaining should
Main feature in characteristic pattern.It, can be to the original on production line using the deep neural network model with convolution, pondization operation
The defect of continuous casting of iron and steel base distinguishes in the deformation of beginning image, fuzzy, illumination variation and the original image, avoids due to original
The deformation of image, fuzzy, illumination variation, cause the deep neural network model to judge the defect of continuous casting of iron and steel base by accident.
On the basis of the present embodiment, the method also includes：According to the production line of the continuous casting of iron and steel base and it is described extremely
The image information of a few continuous casting of iron and steel base, determines the structure of the deep neural network model.Specifically, server can basis
The image information of the production line of continuous casting of iron and steel base and at least one continuous casting of iron and steel base determines convolution in the deep neural network model
Layer, pond layer connect the number of plies of layer entirely, convolutional layer, pond layer, the full permutation and combination method for connecting layer and convolutional layer, pond layer,
Connect the parameter in layer entirely.For different iron and steel enterprises, the production line of continuous casting of iron and steel base is different, in addition, different steels
The device parameter of enterprise, the capture apparatus installed on production line may also be different, therefore, can be according to each iron and steel enterprise
Concrete condition determine the structure of the deep neural network model.
The embodiment of the present invention obtains the image information of at least one continuous casting of iron and steel base by server, using default defect point
Class model carries out image recognition to the image information of at least one continuous casting of iron and steel base, at least one described continuous casting of iron and steel
The quality of each continuous casting of iron and steel base is detected in base, and the quality measurements of the continuous casting of iron and steel base are sent to the steel
The production line of iron continuous casting billet saves the workload of artificial detection continuous casting of iron and steel base, improves continuous casting of iron and steel base quality testing
Efficiency, in addition, can avoid failing to judge and judging by accident caused by human factor.
Fig. 4 be another embodiment of the present invention provides continuous casting of iron and steel base quality determining method flow chart.In above-described embodiment
On the basis of, continuous casting of iron and steel base quality determining method provided in this embodiment further includes following steps：
Step 401, the quality measurements for recording the continuous casting of iron and steel base.
As shown in Fig. 2, after server obtains the quality measurements of continuous casting of iron and steel base using defect classification model, the clothes
Being engaged in device can be directly using the quality measurements as production log storage on line into Production database.In the present embodiment, should
Quality measurements include the defect classification logotype information of image information continuous casting of iron and steel base corresponding with the image information.It is optional
, Production database can integrate in the server, can also exist independently of the server.
Step 402 is updated according to the quality measurements of the continuous casting of iron and steel base for training the default defect to classify
The tranining database of model.
For example, since the accuracy of defect classification model is mentioned during the defect classification model constantly updates iteration
High, therefore, the initial stage of image classification is carried out using the defect classification model in server, the defect classification model is in image
Continuous casting of iron and steel base carry out quality testing accuracy may not be high, at this point, testing staff can be to the matter in the Production database
Amount testing result is detected, and is modified to the result of defect classification model detection mistake.Further, according to modified
The quality measurements of continuous casting of iron and steel base update the tranining database for training the defect classification model, that is to say, that will repair
Sample of the quality measurements of continuous casting of iron and steel base after just as the re -training defect classification model.For example, as detection people
After member can be modified the quality measurements in the Production database, which can be by its revised steel
The quality measurements of continuous casting billet are synchronized to the tranining database.
Step 403 presets defect classification model according to the updated tranining database re -training.
As depicted in figs. 1 and 2, training engine sends request of data to the tranining database, so that the tranining database will
Updated training data is sent to trained engine, and the training engine is according to training data weight updated in the tranining database
The defect classification model is newly trained, and obtains updated defect classification model.Server is using the updated defect classification
Model continues to identify the image information of the collected continuous casting of iron and steel base of capture apparatus, defect classification.
The embodiment of the present invention is modified by the quality measurements of the continuous casting of iron and steel base exported to defect classification model,
And using revised quality measurements as the new samples of the training defect classification model, to improve defect classification mould
The accuracy of type improves the accuracy that quality testing is carried out to continuous casting of iron and steel base.
Fig. 5 is the structural schematic diagram of continuous casting of iron and steel base quality detection device provided in an embodiment of the present invention.The continuous casting of iron and steel
Base quality detection device specifically can be the component of server or the server in above-described embodiment.The embodiment of the present invention mentions
The continuous casting of iron and steel base quality detection device of confession can execute the process flow of continuous casting of iron and steel base quality determining method embodiment offer,
As shown in figure 5, continuous casting of iron and steel base quality detection device 50 includes：Obtain module 51, detection module 52 and sending module 53；Its
In, obtain the image information that module 51 is used to obtain at least one continuous casting of iron and steel base；Detection module 52 is used for using default defect
Disaggregated model carries out image recognition to the image information of at least one continuous casting of iron and steel base, to connect at least one described steel
The quality of each continuous casting of iron and steel base is detected in slab；Sending module 53 is used for the quality testing knot of the continuous casting of iron and steel base
Fruit is sent to the production line of the continuous casting of iron and steel base.
Optionally, module 51 is obtained to be specifically used for receiving the capture apparatus acquisition by the production line of the continuous casting of iron and steel base
The continuous casting of iron and steel base image information.
Optionally, continuous casting of iron and steel base quality detection device 50 further includes：Logging modle 54, update module 55, model training
Module 56；Logging modle 54 is used to record the quality measurements of the continuous casting of iron and steel base；Update module 55 is used for according to
The quality measurements of continuous casting of iron and steel base update the tranining database for training the default defect classification model；Model training
Module 56 is used to preset defect classification model according to the updated tranining database re -training.
Optionally, the quality measurements include defect classification logotype information.
Optionally, the default defect classification model includes deep neural network model.
Optionally, continuous casting of iron and steel base quality detection device 50 further includes：Determining module 57；The determining module 57 is used for basis
The image information of the production line of the continuous casting of iron and steel base and at least one continuous casting of iron and steel base, determines the deep neural network
The structure of model.
The continuous casting of iron and steel base quality detection device of embodiment illustrated in fig. 5 can be used for executing the technical side of above method embodiment
Case, it is similar that the realization principle and technical effect are similar, and details are not described herein again.
Fig. 6 is the structural schematic diagram of server provided in an embodiment of the present invention.Server provided in an embodiment of the present invention can
To execute the process flow of continuous casting of iron and steel base quality determining method embodiment offer, as shown in fig. 6, server 60 includes memory
61, processor 62, computer program and communication interface 63；Wherein, computer program is stored in memory 61, and is configured as
Continuous casting of iron and steel base quality determining method described in above embodiments is executed as processor 62.
The server of embodiment illustrated in fig. 6 can be used for executing the technical solution of above method embodiment, realization principle and
Technical effect is similar, and details are not described herein again.
In addition, the present embodiment also provides a kind of computer readable storage medium, it is stored thereon with computer program, the meter
Calculation machine program is executed by processor to realize continuous casting of iron and steel base quality determining method described in above-described embodiment.
In several embodiments provided by the present invention, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be tied
Another system is closed or is desirably integrated into, or some features can be ignored or not executed.Another point, it is shown or discussed
Mutual coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or logical of device or unit
Letter connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit being realized in the form of SFU software functional unit can store and computer-readable deposit at one
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are used so that a computer
It is each that equipment (can be personal computer, server or the network equipment etc.) or processor (processor) execute the present invention
The part steps of embodiment the method.And storage medium above-mentioned includes：USB flash disk, mobile hard disk, read-only memory (Read-
Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. it is various
It can store the medium of program code.
Those skilled in the art can be understood that, for convenience and simplicity of description, only with above-mentioned each functional module
Division progress for example, in practical application, can according to need and above-mentioned function distribution is complete by different functional modules
At the internal structure of device being divided into different functional modules, to complete all or part of the functions described above.On
The specific work process for stating the device of description, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
Finally it should be noted that：The above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Present invention has been described in detail with reference to the aforementioned embodiments for pipe, those skilled in the art should understand that：Its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (14)
1. a kind of continuous casting of iron and steel base quality determining method, which is characterized in that including：
Obtain the image information of at least one continuous casting of iron and steel base；
Image recognition is carried out using image information of the default defect classification model at least one continuous casting of iron and steel base, to institute
The quality for stating each continuous casting of iron and steel base at least one continuous casting of iron and steel base is detected；
The quality measurements of the continuous casting of iron and steel base are sent to the production line of the continuous casting of iron and steel base.
2. the method according to claim 1, wherein the image letter for obtaining at least one continuous casting of iron and steel base
Breath；
Receive the image information of the continuous casting of iron and steel base by the capture apparatus acquisition on the production line of the continuous casting of iron and steel base.
3. the method according to claim 1, wherein the method also includes：
Record the quality measurements of the continuous casting of iron and steel base；
The training number for training the default defect classification model is updated according to the quality measurements of the continuous casting of iron and steel base
According to library；
Defect classification model is preset according to the updated tranining database re -training.
4. method according to claim 1-3, which is characterized in that the quality measurements include defect classification
Identification information.
5. according to the method described in claim 4, it is characterized in that, the default defect classification model includes deep neural network
Model.
6. according to the method described in claim 5, it is characterized in that, the method also includes：
According to the image information of the production line of the continuous casting of iron and steel base and at least one continuous casting of iron and steel base, the depth is determined
The structure of neural network model.
7. a kind of continuous casting of iron and steel base quality detection device, which is characterized in that including：
Module is obtained, for obtaining the image information of at least one continuous casting of iron and steel base；
Detection module, for carrying out figure to the image information of at least one continuous casting of iron and steel base using default defect classification model
As identification, detected with the quality to each continuous casting of iron and steel base at least one described continuous casting of iron and steel base；
Sending module, for the quality measurements of the continuous casting of iron and steel base to be sent to the production line of the continuous casting of iron and steel base.
8. continuous casting of iron and steel base quality detection device according to claim 7, which is characterized in that the acquisition module is specifically used
In the image information for the continuous casting of iron and steel base for receiving the capture apparatus acquisition on the production line by the continuous casting of iron and steel base.
9. continuous casting of iron and steel base quality detection device according to claim 7, which is characterized in that further include：
Logging modle, for recording the quality measurements of the continuous casting of iron and steel base；
Update module, for being updated according to the quality measurements of the continuous casting of iron and steel base for training the default defect to classify
The tranining database of model；
Model training module, for presetting defect classification model according to the updated tranining database re -training.
10. according to the described in any item continuous casting of iron and steel base quality detection devices of claim 7-9, which is characterized in that the quality
Testing result includes defect classification logotype information.
11. continuous casting of iron and steel base quality detection device according to claim 10, which is characterized in that the default defect classification
Model includes deep neural network model.
12. continuous casting of iron and steel base quality detection device according to claim 11, which is characterized in that further include：
Determining module, for being believed according to the production line of the continuous casting of iron and steel base and the image of at least one continuous casting of iron and steel base
Breath, determines the structure of the deep neural network model.
13. a kind of server, which is characterized in that including：
Memory；
Processor；And
Computer program；
Wherein, the computer program stores in the memory, and is configured as being executed by the processor to realize such as
Method described in any one of claims 1-6.
14. a kind of computer readable storage medium, which is characterized in that be stored thereon with computer program, the computer program
It is executed by processor to realize as the method according to claim 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810710536.0A CN108921841A (en) | 2018-07-02 | 2018-07-02 | Continuous casting of iron and steel base quality determining method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810710536.0A CN108921841A (en) | 2018-07-02 | 2018-07-02 | Continuous casting of iron and steel base quality determining method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108921841A true CN108921841A (en) | 2018-11-30 |
Family
ID=64423753
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810710536.0A Pending CN108921841A (en) | 2018-07-02 | 2018-07-02 | Continuous casting of iron and steel base quality determining method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108921841A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109919925A (en) * | 2019-03-04 | 2019-06-21 | 联觉(深圳)科技有限公司 | Printed circuit board intelligent detecting method, system, electronic device and storage medium |
| CN110517240A (en) * | 2019-08-22 | 2019-11-29 | 联峰钢铁（张家港）有限公司 | A kind of conticaster state judging method and device |
| CN110533191A (en) * | 2019-08-22 | 2019-12-03 | 江苏联峰实业有限公司 | A kind of method and device handling narrow composition alloy steel |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101871895A (en) * | 2010-05-10 | 2010-10-27 | 重庆大学 | Laser scanning imaging non-destructive testing method for surface defects of continuous casting hot slabs |
| CN201974388U (en) * | 2010-12-15 | 2011-09-14 | 河北汉光重工有限责任公司 | Monitoring device for surface quality of steel product |
| CN102519981A (en) * | 2011-12-16 | 2012-06-27 | 湖南工业大学 | Online detection system for PVC (polyvinyl chloride) building material surface quality |
| CN102954966A (en) * | 2011-08-19 | 2013-03-06 | 天津市三特电子有限公司 | Hot continuous cast billet surface quality detection system |
| CN103399016A (en) * | 2013-07-26 | 2013-11-20 | 齐鲁工业大学 | Online detection system for surface defects of coldly-rolled aluminum plate and detection method of online detection system |
| CN108230318A (en) * | 2018-01-09 | 2018-06-29 | 北京百度网讯科技有限公司 | Ladle defects detection sorting technique, device, equipment and computer-readable medium |
| 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
- 2018-07-02 CN CN201810710536.0A patent/CN108921841A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101871895A (en) * | 2010-05-10 | 2010-10-27 | 重庆大学 | Laser scanning imaging non-destructive testing method for surface defects of continuous casting hot slabs |
| CN201974388U (en) * | 2010-12-15 | 2011-09-14 | 河北汉光重工有限责任公司 | Monitoring device for surface quality of steel product |
| CN102954966A (en) * | 2011-08-19 | 2013-03-06 | 天津市三特电子有限公司 | Hot continuous cast billet surface quality detection system |
| CN102519981A (en) * | 2011-12-16 | 2012-06-27 | 湖南工业大学 | Online detection system for PVC (polyvinyl chloride) building material surface quality |
| CN103399016A (en) * | 2013-07-26 | 2013-11-20 | 齐鲁工业大学 | Online detection system for surface defects of coldly-rolled aluminum plate and detection method of online detection system |
| CN108230318A (en) * | 2018-01-09 | 2018-06-29 | 北京百度网讯科技有限公司 | Ladle defects detection sorting technique, device, equipment and computer-readable medium |
| 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 |
|---|---|---|---|---|
| CN109919925A (en) * | 2019-03-04 | 2019-06-21 | 联觉(深圳)科技有限公司 | Printed circuit board intelligent detecting method, system, electronic device and storage medium |
| CN110517240A (en) * | 2019-08-22 | 2019-11-29 | 联峰钢铁（张家港）有限公司 | A kind of conticaster state judging method and device |
| CN110533191A (en) * | 2019-08-22 | 2019-12-03 | 江苏联峰实业有限公司 | A kind of method and device handling narrow composition alloy steel |
| CN110517240B (en) * | 2019-08-22 | 2022-06-03 | 联峰钢铁（张家港）有限公司 | Method and device for judging continuous casting machine state |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109993734A (en) | Method and apparatus for output information | |
| CN110009614A (en) | Method and apparatus for output information | |
| CN108921841A (en) | Continuous casting of iron and steel base quality determining method, device, equipment and storage medium | |
| JP2015172576A5 (en) | Method and system for inspection of complex item | |
| CN114862832B (en) | Optimization method, device, equipment and storage medium for defect detection model | |
| JP6844564B2 (en) | Inspection system, identification system, and learning data generator | |
| TW202004574A (en) | Artificial intelligence recheck system and method thereof | |
| CN108921840A (en) | Display screen peripheral circuit detection method, device, electronic equipment and storage medium | |
| CN108764456A (en) | Airborne target identification model construction platform, airborne target recognition methods and equipment | |
| CN118310970A (en) | Mechanical equipment surface defect detection method and system | |
| JP7311455B2 (en) | Scrap grade determination system, scrap grade determination method, estimation device, learning device, learned model generation method, and program | |
| CN109087281A (en) | Display screen peripheral circuit detection method, device, electronic equipment and storage medium | |
| JP2019158684A (en) | Inspection system, identification system, and discriminator evaluation device | |
| CN118409447A (en) | LCD display screen display fault judging method and system | |
| CN117862068A (en) | A defective product sorting program verification method, device and storage medium | |
| JP2019075078A (en) | Construction site image determination device and construction site image determination program | |
| KR102760440B1 (en) | Artificial intelligence-based radiographic inspection system | |
| CN119023181B (en) | Random vibration testing method and system | |
| CN115526859A (en) | Method for identifying production defects, distributed processing platform, equipment, and storage medium | |
| CN110175985A (en) | Carbon fiber composite core wire damage detecting method, device and computer storage medium | |
| JP6341550B1 (en) | Construction site image determination device and construction site image determination program | |
| CN118644469A (en) | A method for concrete surface defect detection and management based on deep learning and augmented reality | |
| CN108268899A (en) | A kind of detection method of electronic component, device and equipment | |
| CN114324382A (en) | Panel terminal cleanliness detection method and panel terminal cleanliness detection device | |
| CN111259494B (en) | Health monitoring and analyzing method for heavy machine equipment |
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 |