CN110532924A - A kind of identifying processing method and device of high heat resistance steel - Google Patents
A kind of identifying processing method and device of high heat resistance steel Download PDFInfo
- Publication number
- CN110532924A CN110532924A CN201910777644.4A CN201910777644A CN110532924A CN 110532924 A CN110532924 A CN 110532924A CN 201910777644 A CN201910777644 A CN 201910777644A CN 110532924 A CN110532924 A CN 110532924A
- Authority
- CN
- China
- Prior art keywords
- photo
- heat resisting
- resisting steel
- identifier information
- steel
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of identifying processing method and devices of high heat resistance steel, are related to metallurgical technology field, which comprises obtain the photo of heat resisting steel;It will be in the photo input model of the heat resisting steel, wherein, the model show that every group of data in the multi-group data include: heat resisting steel photo, the first identifier information for identifying the heat resisting steel corrosion resistance rank and for identifying the second identifier information of the heat resisting steel inoxidizability rank by machine learning training using multi-group data;In the case that first identifier information and second identifier information in the photo are all satisfied pre-set level, the label of qualified products is stamped for the heat resisting steel, solves the criterion of identification disunity to anticorrosive oxidation resistant heat resisting steel, not stringent in the prior art, the quality of product can not be effectively ensured, and the technical issues of artificial treatment low efficiency, reach intelligence degree height, it is easy to operate, recognition efficiency is high, guarantee the technical effect of the quality of product.
Description
Technical field
The present invention relates to metallurgical technology field more particularly to a kind of identifying processing method and devices of high heat resistance steel.
Background technique
Heat resisting steel refers to the steel alloy of intensity with higher and good chemical stability at high temperature.It includes antioxygen
Change steel (or high temperature non-scaling steel) and two class of refractory steel.Oxidation resistant steel generally requires preferable chemical stability, but bear
Load is lower.Refractory steel then more demanding elevated temperature strength and corresponding inoxidizability.Heat resisting steel is usually used in manufacturing boiler, steamer
The components to work at high temperature in the industrial departments such as machine, dynamic power machine, industrial furnace and aviation, petrochemical industry.These components remove
It is required that outside elevated temperature strength and high temperature oxidation corrosion resistance, it is different depending on the application also to require have enough toughness, good machinability
And weldability and certain structure stability.
But present inventor during inventive technique scheme, has found above-mentioned technology extremely in realizing the embodiment of the present application
It has the following technical problems less:
In the prior art, to the criterion of identification disunity of anticorrosive oxidation resistant heat resisting steel, it is not stringent, lead to product quality
Stability difference is big, and the quality of product, and artificial treatment low efficiency can not be effectively ensured.
Summary of the invention
The embodiment of the present invention solves in the prior art by providing a kind of identifying processing method and device of high heat resistance steel
To the criterion of identification disunity of anticorrosive oxidation resistant heat resisting steel, it is not stringent, cause stable product quality sex differernce big, can not
The quality of product is effectively ensured, and the technical issues of artificial treatment low efficiency, has reached intelligence degree height, easy to operate, knowledge
It is not high-efficient, guarantee the technical effect of the quality of product.
In view of the above problems, the embodiment of the present application is proposed in order to provide the identifying processing method and dress of a kind of high heat resistance steel
It sets.
In a first aspect, the present invention provides a kind of identifying processing methods of high heat resistance steel, which comprises obtain heat-resisting
The photo of steel;It will be in the photo input model of the heat resisting steel, wherein the model is to pass through machine learning using multi-group data
Training obtains, every group of data in the multi-group data include: heat resisting steel photo, anticorrosive for identifying the heat resisting steel
The first identifier information of property rank and for identifying the second identifier information of the heat resisting steel inoxidizability rank;In the photograph
In the case that first identifier information and second identifier information in piece are all satisfied pre-set level, qualified production is stamped for the heat resisting steel
The label of product.
Preferably, the photo for obtaining heat resisting steel, comprising: when the photo of the heat resisting steel is complete photo, then
Color pretreatment is carried out to the photo of the heat resisting steel;Profile processing is carried out to the picture after color pretreatment, is avoided
Pixel interference outside photo range;According to described by profile treated photo, the photo of the heat resisting steel is obtained.
Preferably, when the photo of the heat resisting steel is incomplete photo, the photo is rejected.
Preferably, every group of data in the multi-group data include for identifying the heat resisting steel corrosion resistance rank
First identifier information, comprising: obtain the corrosion resistance class criteria of heat resisting steel;According to the determining corrosion resistance rank mark
Standard obtains first identifier information;Using the first identifier information as the first standardized data, it is input to each group of training
In data.
Preferably, every group of data in the multi-group data include for identifying the heat resisting steel inoxidizability rank
Second identifier information, comprising: obtain the inoxidizability class criteria of heat resisting steel;According to the determining inoxidizability rank mark
Standard obtains second identifier information;Using the second identifier information as the second standardized data, it is input to each group of training
In data.
Preferably, the first identifier information and second identifier information in the photo is all satisfied the feelings of pre-set level
Under condition, the label of qualified products is stamped for the heat resisting steel, comprising: obtain the first pre-set level;Judge corresponding in the photo
First identifier information whether meet first pre-set level;Described in meeting when first identifier information corresponding in the photo
When the first pre-set level, then the second pre-set level is obtained;Judge whether corresponding second identifier information meets institute in the photo
State the second pre-set level;It is then described when second identifier information corresponding in the photo meets second pre-set level
Heat resisting steel stamps the label of qualified products.
Preferably, further includes: when first identifier information corresponding in the photo is unsatisfactory for first pre-set level,
Then the photo is rejected, and stamps the label of substandard product for the heat resisting steel;When the second mark corresponding in the photo
When knowledge information is unsatisfactory for second pre-set level, then the photo is rejected, and stamps substandard product for the heat resisting steel
Label.
Second aspect, the present invention provides a kind of recognition process unit of high heat resistance steel, described device includes: the first acquisition
Unit, the first acquisition unit are used to obtain the photo of heat resisting steel;First input unit, first input unit is used for will
In the photo input model of the heat resisting steel, wherein the model is trained by machine learning using multi-group data and is obtained,
Every group of data in the multi-group data include: heat resisting steel photo, for identify the heat resisting steel corrosion resistance rank
One identification information and for identifying the second identifier information of the heat resisting steel inoxidizability rank;First execution unit, it is described
The case where first identifier information and second identifier information that first execution unit is used in the photo are all satisfied pre-set level
Under, the label of qualified products is stamped for the heat resisting steel.
Preferably, described device further include:
First processing units, the first processing units are used for when the photo of the heat resisting steel is complete photo, then
Color pretreatment is carried out to the photo of the heat resisting steel;
The second processing unit, described the second processing unit are used to carry out at profile the picture after color pretreatment
Reason, avoids the pixel interference outside photo range;
First obtains unit, the first obtains unit are used to obtain institute by profile treated photo according to described
State the photo of heat resisting steel.
Preferably, described device further include:
Third processing unit, the third processing unit are used for when the photo of the heat resisting steel is incomplete photo,
The photo is rejected.
Preferably, described device further include:
Second obtaining unit, second obtaining unit are used to obtain the corrosion resistance class criteria of heat resisting steel;
Third obtaining unit, the third obtaining unit are used to be obtained according to the determining corrosion resistance class criteria
First identifier information;
Second input unit, second input unit are used for using the first identifier information as the first normalized number
According to being input in each group of training data.
Preferably, described device further include:
4th obtaining unit, the 4th obtaining unit are used to obtain the inoxidizability class criteria of heat resisting steel;
5th obtaining unit, the 5th obtaining unit are used to be obtained according to the determining inoxidizability class criteria
Second identifier information;
Third input unit, the third input unit are used for using the second identifier information as the second normalized number
According to being input in each group of training data.
Preferably, described device further include:
6th obtaining unit, the 6th obtaining unit is for obtaining the first pre-set level;
First judging unit, first judging unit is for judging in the photo whether is corresponding first identifier information
Meet first pre-set level;
7th obtaining unit, the 7th obtaining unit are used for when corresponding first identifier information meets institute in the photo
When stating the first pre-set level, then the second pre-set level is obtained;
Second judgment unit, the second judgment unit is for judging in the photo whether is corresponding second identifier information
Meet second pre-set level;
Second execution unit, second execution unit are used for when corresponding second identifier information meets institute in the photo
When stating the second pre-set level, then the label of qualified products is stamped for the heat resisting steel.
Preferably, described device further include:
Third execution unit, the third execution unit are used for when corresponding first identifier information is unsatisfactory in the photo
When first pre-set level, then the photo is rejected, and stamps the label of substandard product for the heat resisting steel;
4th execution unit, the 4th execution unit are used for when corresponding second identifier information is unsatisfactory in the photo
When second pre-set level, then the photo is rejected, and stamps the label of substandard product for the heat resisting steel.
The third aspect, the present invention provides a kind of computer readable storage mediums, are stored thereon with computer program, the journey
The photo for obtaining heat resisting steel is performed the steps of when sequence is executed by processor;By in the photo input model of the heat resisting steel,
In, the model show that every group of data in the multi-group data are wrapped by machine learning training using multi-group data
It includes: heat resisting steel photo, the first identifier information for identifying the heat resisting steel corrosion resistance rank and described resistance to for identifying
The second identifier information of hot steel inoxidizability rank;First identifier information and second identifier information in the photo are all satisfied
In the case where pre-set level, the label of qualified products is stamped for the heat resisting steel.
Fourth aspect, the present invention provides the recognition process unit of another high heat resistance steel, including memory, processor and
The computer program that can be run on a memory and on a processor is stored, the processor is realized following when executing described program
Step: the photo of heat resisting steel is obtained;It will be in the photo input model of the heat resisting steel, wherein the model is to use multiple groups number
According to what is obtained by machine learning training, every group of data in the multi-group data include: heat resisting steel photo, for identifying
State the first identifier information of heat resisting steel corrosion resistance rank and for identifying the second of the heat resisting steel inoxidizability rank the mark
Know information;It is described in the case that first identifier information and second identifier information in the photo are all satisfied pre-set level
Heat resisting steel stamps the label of qualified products.
Said one or multiple technical solutions in the embodiment of the present application at least have following one or more technology effects
Fruit:
The embodiment of the present application provides a kind of identifying processing processing method and processing device of high heat resistance steel, which comprises
Obtain the photo of heat resisting steel;It will be in the photo input model of the heat resisting steel, wherein the model is to be passed through using multi-group data
Machine learning training obtains, every group of data in the multi-group data include: heat resisting steel photo, described heat-resisting for identifying
The first identifier information of steel corrosion resistance rank and for identifying the second identifier information of the heat resisting steel inoxidizability rank;
Then first identifier information and second identifier information and pre-set level are compared, judges first identifier information and the second mark in photo
Know whether information meets pre-set level, the first identifier information and second identifier information in the photo meet default grade simultaneously
In other situation, the label of qualified products is stamped for the heat resisting steel, to solve in the prior art to anticorrosive anti-oxidant
Heat resisting steel criterion of identification disunity, not stringent, cause stable product quality sex differernce big, product can not be effectively ensured
Quality, and the technical issues of artificial treatment low efficiency, has reached intelligence degree height, easy to operate, recognition efficiency is high, guarantees to produce
The technical effect of the quality of product.
The above description is only an overview of the technical scheme of the present invention, in order to better understand the technical means of the present invention,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, the followings are specific embodiments of the present invention.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of the identifying processing method of high heat resistance steel in the embodiment of the present invention;
Fig. 2 is a kind of structural schematic diagram of the recognition process unit of high heat resistance steel in the embodiment of the present invention;
Fig. 3 is the structural schematic diagram of the recognition process unit of another high heat resistance steel in the embodiment of the present invention.
Drawing reference numeral explanation: bus 300, receiver 301, processor 302, transmitter 303, memory 304, bus interface
306。
Specific embodiment
The embodiment of the present application provides a kind of identifying processing method and device of high heat resistance steel, which comprises obtains
The photo of heat resisting steel;It will be in the photo input model of the heat resisting steel, wherein the model is to pass through machine using multi-group data
What learning training obtained, every group of data in the multi-group data include: heat resisting steel photo, anti-for identifying the heat resisting steel
The first identifier information of corrosivity rank and for identifying the second identifier information of the heat resisting steel inoxidizability rank;Institute
It states in the case that first identifier information and second identifier information in photo is all satisfied pre-set level, stamps conjunction for the heat resisting steel
The label of lattice product, thus reached intelligence degree height, it is easy to operate, recognition efficiency is high, guarantee the technology of the quality of product
Effect.
Technical solution of the present invention is described in detail below by attached drawing and specific embodiment, it should be understood that the application
Specific features in embodiment and embodiment are the detailed description to technical scheme, rather than to present techniques
The restriction of scheme, in the absence of conflict, the technical characteristic in the embodiment of the present application and embodiment can be combined with each other.
Embodiment one
Fig. 1 is a kind of flow diagram of the identifying processing method of high heat resistance steel of the embodiment of the present invention, as shown in Figure 1, institute
The method of stating includes:
Step 110: obtaining the photo of heat resisting steel.
Further, the photo for obtaining heat resisting steel, comprising: when the photo of the heat resisting steel is complete photo,
Color pretreatment then is carried out to the photo of the heat resisting steel;Profile processing is carried out to the picture after color pretreatment, is kept away
Exempt from the pixel interference outside photo range;According to described by profile treated photo, the photo of the heat resisting steel is obtained.Into one
Step, when the photo of the heat resisting steel is incomplete photo, the photo is rejected.
Specifically, the photo of heat resisting steel is to carry out obtained photo of taking pictures to heat resisting steel, can be shown on photo
The relevant information of corresponding heat resisting steel, for example, heat resisting steel number, at grading information.After the photo for obtaining heat resisting steel, also
It needs to carry out corresponding examination processing to photo, that is, judges whether the photo of the heat resisting steel is satisfactory photo, In
In the case where undesirable, which is rejected.It is specific: when the photo of obtained steel is complete photo,
Then further the photo can be performed corresponding processing, i.e., by carrying out the operation such as color pretreatment to the photo, guarantee the photograph
Piece can satisfy standard when identification, after colors countenance is completed, then continue to handle the profile of the photo, in this way
It can guarantee not will receive the interference outside photo range when follow-up work, further ensure the accuracy of identifying processing, pass through
Requirement when profile treated photo can meet identifying processing, can be obtained the heat resisting steel of the condition of satisfaction by aforesaid operations
Photo;Further, when the photo of obtained steel is incomplete photo, that is to say, that the photo is in the presence of certain
Flaw, shown information will be not comprehensive enough and accurate on photo, can work subsequent identifying processing generate one in this way
Fixed influence causes result not accurate enough, so, it needs to reject in the incomplete photo.
Step 120: will be in the photo input model of the heat resisting steel, wherein the model is to be passed through using multi-group data
Machine learning training obtains, every group of data in the multi-group data include: heat resisting steel photo, described heat-resisting for identifying
The first identifier information of steel corrosion resistance rank and for identifying the second identifier information of the heat resisting steel inoxidizability rank.
Specifically, then the photo of heat resisting steel can be input to instruction after the photo for obtaining satisfactory heat resisting steel
Practice in model, which is to be trained by multi-group data by machine learning, wherein machine learning is to realize
A kind of approach of artificial intelligence, it and data mining have certain similitude and a multi-field cross discipline, are related to probability
By, statistics, Approximation Theory, convextiry analysis, the multiple subjects such as computational complexity theory.It is looked in contrast to data mining between big data
For mutual characteristic, the design of algorithm is more focused in machine learning, allow computer can it is white " study " is regular from data dynamicly,
And assimilated equations predict unknown data.Further, each group of data in the multi-group data of input include: resistance to
Hot steel photo, the first identifier information for identifying heat resisting steel corrosion resistance rank and for identifying heat resisting steel inoxidizability grade
Other second identifier information, that is, the first identification information includes the corrosion resistance information of corresponding heat resisting steel, the second identification information packet
Inoxidizability information containing corresponding heat resisting steel, after photographic intelligence, the first identification information, the input of the second identification information, i.e.,
Corresponding output information can be further obtained according to target requirement.
Further, every group of data in the multi-group data include for identifying the heat resisting steel corrosion resistance rank
First identifier information, comprising: obtain the corrosion resistance class criteria of heat resisting steel;According to the determining corrosion resistance rank mark
Standard obtains first identifier information;Using the first identifier information as the first standardized data, it is input to each group of training
In data.
Specifically, first identifier information represents the corrosion resistance information of corresponding heat resisting steel, heat resisting steel is being obtained
When first identifier information, specific operating procedure are as follows: firstly the need of the standard of corrosion resistance rank is obtained, which can be state
Family's standard, is also possible to international standard, this is not specifically limited in this embodiment, therefore, also needs to tie in actual use
The correlative factors such as the specifically used environment of the heat-resisting steel grade are closed specifically to be determined;After obtaining corrosion resistance class criteria,
Can the corrosion resistance rank further to corresponding heat resisting steel determine, that is to say, that according to corrosion resistance rank mark
The first identifier information of corresponding steel can be obtained in standard, then can be using the first identifier information as the first standardized data, input
Foundation into each group of training data, as identifying processing.
Further, every group of data in the multi-group data include for identifying the heat resisting steel inoxidizability rank
Second identifier information, comprising: obtain the inoxidizability class criteria of heat resisting steel;According to the determining inoxidizability rank mark
Standard obtains second identifier information;Using the second identifier information as the second standardized data, it is input to each group of training
In data.
Specifically, second identifier information represents the inoxidizability information of corresponding heat resisting steel, heat resisting steel is being obtained
When second identifier information, specific operating procedure are as follows: firstly the need of the standard of inoxidizability rank is obtained, which can be state
Family's standard, is also possible to international standard, this is not specifically limited in this embodiment, therefore, also needs to tie in actual use
The correlative factors such as the specifically used environment of the heat-resisting steel grade are closed specifically to be determined;After obtaining inoxidizability class criteria,
Can the inoxidizability rank further to corresponding heat resisting steel determine, that is to say, that according to inoxidizability rank mark
The second identifier information of corresponding steel can be obtained in standard, then can be using the second identifier information as the second standardized data, input
Into each group of training data, as the foundation of identifying processing, subsequent combinable first identifier information and second identifier information
Specifically judged.
Step 130: the case where first identifier information and second identifier information in the photo are all satisfied pre-set level
Under, the label of qualified products is stamped for the heat resisting steel.
Specifically, then may be used after the first identifier information and second identifier information for obtaining the heat resisting steel in photo
Specifically judged in conjunction with first identifier information and second identifier information, corresponding to first identifier information and second identifier information
Levels of information when be all satisfied preset requirement, then illustrate that corresponding heat resisting steel is satisfactory, at this point, heat-resisting to this
Steel stamps the label of qualified products.For example, when the first identifier information in photo is the first estate, second identifier letter
Breath is the second grade, and the preset corrosion resistance rank met the requirements and inoxidizability rank are both needed to be greater than or equal to the third level
It not, that is, include third level, second level, first level, therefore, the heat resisting steel corresponding to the photo is to meet preset requirement
, it is qualified products.
Further, the first identifier information and second identifier information in the photo is all satisfied pre-set level
In the case of, the label of qualified products is stamped for the heat resisting steel, comprising: obtain the first pre-set level;It is right in the photo to judge
Whether the first identifier information answered meets first pre-set level;When first identifier information corresponding in the photo meets institute
When stating the first pre-set level, then the second pre-set level is obtained;Judge whether corresponding second identifier information meets in the photo
Second pre-set level;It is then institute when second identifier information corresponding in the photo meets second pre-set level
State the label that heat resisting steel stamps qualified products.
Further, further includes: when first identifier information corresponding in the photo is unsatisfactory for first pre-set level
When, then the photo is rejected, and the label of substandard product is stamped for the heat resisting steel;When in the photo corresponding second
When identification information is unsatisfactory for second pre-set level, then the photo is rejected, and stamps unqualified production for the heat resisting steel
The label of product.
Specifically, when judging whether first identifier information in photo and second identifier information meet pre-set level,
Specific decision logic are as follows: firstly, it is necessary to the default corrosion resistance rank of the heat resisting steel met the requirements, i.e., the first default grade
Not, the first identifier information and the first pre-set level in photo are then compared, it is pre- to judge whether first identifier information meets first
If rank, when meeting, the default inoxidizability rank of heat resisting steel is then obtained, i.e. the second pre-set level is then right again
According to the second identifier information and the second pre-set level in piece, judge whether second identifier information meets the second pre-set level, when
When second identifier information meets the second pre-set level, then illustrates corresponding heat resisting steel while meeting the first pre-set level and second
Pre-set level, that is, the heat resisting steel are qualified products, and therefore, it is necessary to the label of qualified products is stamped to the heat resisting steel.
Further, when comparing the first identifier information and the first pre-set level in photo, first identifier information cannot
When enough meeting the first pre-set level, then illustrate that the corrosion resistance of heat resisting steel corresponding to the photo is unsatisfactory for preset requirement,
It does not need further to judge inoxidizability at this time yet, directly rejects the photo, while stamping and not conforming to for the heat resisting steel
The label of lattice product;When comparing the second identifier information and the second pre-set level in photo, second identifier information can not expire
When the second pre-set level of foot, then illustrate that the corrosion resistance of heat resisting steel corresponding to the photo is met the requirements, but inoxidizability is not
Meet preset requirement, then further reject the photo, while stamping the label of substandard product for the heat resisting steel.It lifts
For example, when the first predetermined level is equal to or higher than third level, i.e., including first level, second level, third level;The
Two predetermined levels are similarly equal to or higher than third level, that is, include first level, second level, third level, when in photo
The corresponding grade of first identifier information be first level, the corresponding grade of second identifier information be second level, then explanation should
Heat resisting steel corresponding to photo is satisfactory product, as qualified products;When the first identifier information in photo is corresponding
When grade is fourth level, then illustrate that heat resisting steel corresponding to the photo is undesirable product, as substandard product;
When the corresponding grade of first identifier information in photo is first level, the corresponding grade of second identifier information is fourth level,
Then illustrate that heat resisting steel corresponding to the photo is undesirable product, as substandard product.
Embodiment two
Based on inventive concept same as the identifying processing method of high heat resistance steel a kind of in previous embodiment, the present invention is also mentioned
For a kind of recognition process unit of high heat resistance steel, as shown in Fig. 2, described device includes:
First acquisition unit 11, the first acquisition unit 11 are used to obtain the photo of heat resisting steel.
First input unit 12, first input unit 12 are used in the photo input model of the heat resisting steel,
In, the model show that every group of data in the multi-group data are wrapped by machine learning training using multi-group data
It includes: heat resisting steel photo, the first identifier information for identifying the heat resisting steel corrosion resistance rank and described resistance to for identifying
The second identifier information of hot steel inoxidizability rank.
First execution unit 13, first execution unit 13 is for the first identifier information and second in the photo
In the case that identification information is all satisfied pre-set level, the label of qualified products is stamped for the heat resisting steel.
Further, described device further include:
First processing units, the first processing units are used for when the photo of the heat resisting steel is complete photo, then
Color pretreatment is carried out to the photo of the heat resisting steel.
The second processing unit, described the second processing unit are used to carry out at profile the picture after color pretreatment
Reason, avoids the pixel interference outside photo range.
First obtains unit, the first obtains unit are used to obtain institute by profile treated photo according to described
State the photo of heat resisting steel.
Further, described device further include:
Third processing unit, the third processing unit are used for when the photo of the heat resisting steel is incomplete photo,
The photo is rejected.
Further, described device further include:
Second obtaining unit, second obtaining unit are used to obtain the corrosion resistance class criteria of heat resisting steel.
Third obtaining unit, the third obtaining unit are used to be obtained according to the determining corrosion resistance class criteria
First identifier information.
Second input unit, second input unit are used for using the first identifier information as the first normalized number
According to being input in each group of training data.
Further, described device further include:
4th obtaining unit, the 4th obtaining unit are used to obtain the inoxidizability class criteria of heat resisting steel.
5th obtaining unit, the 5th obtaining unit are used to be obtained according to the determining inoxidizability class criteria
Second identifier information.
Third input unit, the third input unit are used for using the second identifier information as the second normalized number
According to being input in each group of training data.
Further, described device further include:
6th obtaining unit, the 6th obtaining unit is for obtaining the first pre-set level.
First judging unit, first judging unit is for judging in the photo whether is corresponding first identifier information
Meet first pre-set level.
7th obtaining unit, the 7th obtaining unit are used for when corresponding first identifier information meets institute in the photo
When stating the first pre-set level, then the second pre-set level is obtained.
Second judgment unit, the second judgment unit is for judging in the photo whether is corresponding second identifier information
Meet second pre-set level.
Second execution unit, second execution unit are used for when corresponding second identifier information meets institute in the photo
When stating the second pre-set level, then the label of qualified products is stamped for the heat resisting steel.
Further, described device further include:
Third execution unit, the third execution unit are used for when corresponding first identifier information is unsatisfactory in the photo
When first pre-set level, then the photo is rejected, and stamps the label of substandard product for the heat resisting steel.
4th execution unit, the 4th execution unit are used for when corresponding second identifier information is unsatisfactory in the photo
When second pre-set level, then the photo is rejected, and stamps the label of substandard product for the heat resisting steel.
The various change mode and specific example of one of 1 embodiment 1 of the earlier figures identifying processing method of high heat resistance steel
It is equally applicable to a kind of recognition process unit of high heat resistance steel of the present embodiment, at a kind of aforementioned identification to high heat resistance steel
The detailed description of reason method, those skilled in the art are clear that a kind of identifying processing of high heat resistance steel in the present embodiment
The implementation method of device, so this will not be detailed here in order to illustrate the succinct of book.
Embodiment three
Based on inventive concept same as the identifying processing method of high heat resistance steel a kind of in previous embodiment, the present invention is also mentioned
For another computer readable storage medium, it is stored thereon with computer program, is realized above when which is executed by processor
A kind of the step of either the identifying processing method of high heat resistance steel method.
Wherein, in Fig. 3, bus architecture (is represented) with bus 300, and bus 300 may include any number of interconnection
Bus and bridge, bus 300 will include the one or more processors represented by processor 302 and what memory 304 represented deposits
The various circuits of reservoir link together.Bus 300 can also will peripheral equipment, voltage-stablizer and management circuit etc. it
Various other circuits of class link together, and these are all it is known in the art, therefore, no longer carry out further to it herein
Description.Bus interface 306 provides interface between bus 300 and receiver 301 and transmitter 303.Receiver 301 and transmitter
303 can be the same element, i.e. transceiver, provide the unit for communicating over a transmission medium with various other devices.
Processor 302 is responsible for management bus 300 and common processing, and memory 304 can be used for storage processor
302 when executing operation used data.
Said one or multiple technical solutions in the embodiment of the present application at least have following one or more technology effects
Fruit:
The embodiment of the present application provides a kind of identifying processing processing method and processing device of high heat resistance steel, which comprises
Obtain the photo of heat resisting steel;It will be in the photo input model of the heat resisting steel, wherein the model is to be passed through using multi-group data
Machine learning training obtains, every group of data in the multi-group data include: heat resisting steel photo, described heat-resisting for identifying
The first identifier information of steel corrosion resistance rank and for identifying the second identifier information of the heat resisting steel inoxidizability rank;
Then first identifier information and second identifier information and pre-set level are compared, judges first identifier information and the second mark in photo
Know whether information meets pre-set level, the first identifier information and second identifier information in the photo meet default grade simultaneously
In other situation, the label of qualified products is stamped for the heat resisting steel, to solve in the prior art to anticorrosive anti-oxidant
Heat resisting steel criterion of identification disunity, not stringent, cause stable product quality sex differernce big, product can not be effectively ensured
Quality, and the technical issues of artificial treatment low efficiency, has reached intelligence degree height, easy to operate, recognition efficiency is high, guarantees to produce
The technical effect of the quality of product.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (10)
1. a kind of identifying processing method of high heat resistance steel, which is characterized in that the described method includes:
Obtain the photo of heat resisting steel;
It will be in the photo input model of the heat resisting steel, wherein the model is to pass through machine learning training using multi-group data
It obtains, every group of data in the multi-group data include: heat resisting steel photo, for identifying the heat resisting steel corrosion resistance grade
Other first identifier information and for identifying the second identifier information of the heat resisting steel inoxidizability rank;
It is described heat-resisting in the case that first identifier information and second identifier information in the photo are all satisfied pre-set level
Steel stamps the label of qualified products.
2. the method as described in claim 1, which is characterized in that the photo for obtaining heat resisting steel, comprising:
When the photo of the heat resisting steel is complete photo, then color pretreatment is carried out to the photo of the heat resisting steel;
Profile processing is carried out to the picture after color pretreatment, avoids the pixel interference outside photo range;
According to described by profile treated photo, the photo of the heat resisting steel is obtained.
3. method according to claim 2, which is characterized in that, will when the photo of the heat resisting steel is incomplete photo
The photo is rejected.
4. the method as described in claim 1, which is characterized in that every group of data in the multi-group data include for identifying
The first identifier information of the heat resisting steel corrosion resistance rank, comprising:
Obtain the corrosion resistance class criteria of heat resisting steel;
According to the determining corrosion resistance class criteria, first identifier information is obtained;
Using the first identifier information as the first standardized data, it is input in each group of training data.
5. the method as described in claim 1, which is characterized in that every group of data in the multi-group data include for identifying
The second identifier information of the heat resisting steel inoxidizability rank, comprising:
Obtain the inoxidizability class criteria of heat resisting steel;
According to the determining inoxidizability class criteria, second identifier information is obtained;
Using the second identifier information as the second standardized data, it is input in each group of training data.
6. the method as described in claim 1, which is characterized in that the first identifier information and the second mark in the photo
In the case that knowledge information is all satisfied pre-set level, the label of qualified products is stamped for the heat resisting steel, comprising:
Obtain the first pre-set level;
Judge whether corresponding first identifier information meets first pre-set level in the photo;
When first identifier information corresponding in the photo meets first pre-set level, then the second pre-set level is obtained;
Judge whether corresponding second identifier information meets second pre-set level in the photo;
When second identifier information corresponding in the photo meets second pre-set level, then conjunction is stamped for the heat resisting steel
The label of lattice product.
7. method as claimed in claim 6, which is characterized in that further include:
When first identifier information corresponding in the photo is unsatisfactory for first pre-set level, then the photo is rejected,
And the label of substandard product is stamped for the heat resisting steel;
When second identifier information corresponding in the photo is unsatisfactory for second pre-set level, then the photo is rejected,
And the label of substandard product is stamped for the heat resisting steel.
8. a kind of recognition process unit of high heat resistance steel, which is characterized in that described device includes:
First acquisition unit, the first acquisition unit are used to obtain the photo of heat resisting steel;
First input unit, first input unit is used for will be in the photo input model of the heat resisting steel, wherein the mould
Type show that every group of data in the multi-group data include: heat resisting steel by machine learning training using multi-group data
Photo, the first identifier information for identifying the heat resisting steel corrosion resistance rank and anti-oxidant for identifying the heat resisting steel
The second identifier information of property rank;
First execution unit, first execution unit is for the first identifier information and second identifier information in the photo
In the case where being all satisfied pre-set level, the label of qualified products is stamped for the heat resisting steel.
9. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
It is performed the steps of when row
Obtain the photo of heat resisting steel;
It will be in the photo input model of the heat resisting steel, wherein the model is to pass through machine learning training using multi-group data
It obtains, every group of data in the multi-group data include: heat resisting steel photo, for identifying the heat resisting steel corrosion resistance grade
Other first identifier information and for identifying the second identifier information of the heat resisting steel inoxidizability rank;
It is described heat-resisting in the case that first identifier information and second identifier information in the photo are all satisfied pre-set level
Steel stamps the label of qualified products.
10. a kind of recognition process unit of high heat resistance steel, including memory, processor and storage on a memory and can handled
The computer program run on device, which is characterized in that the processor performs the steps of when executing described program
Obtain the photo of heat resisting steel;
It will be in the photo input model of the heat resisting steel, wherein the model is to pass through machine learning training using multi-group data
It obtains, every group of data in the multi-group data include: heat resisting steel photo, for identifying the heat resisting steel corrosion resistance grade
Other first identifier information and for identifying the second identifier information of the heat resisting steel inoxidizability rank;
It is described heat-resisting in the case that first identifier information and second identifier information in the photo are all satisfied pre-set level
Steel stamps the label of qualified products.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910777644.4A CN110532924A (en) | 2019-08-22 | 2019-08-22 | A kind of identifying processing method and device of high heat resistance steel |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910777644.4A CN110532924A (en) | 2019-08-22 | 2019-08-22 | A kind of identifying processing method and device of high heat resistance steel |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110532924A true CN110532924A (en) | 2019-12-03 |
Family
ID=68663974
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910777644.4A Pending CN110532924A (en) | 2019-08-22 | 2019-08-22 | A kind of identifying processing method and device of high heat resistance steel |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110532924A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111763814A (en) * | 2020-06-23 | 2020-10-13 | 江苏联峰实业有限公司 | Deformed steel bar heat treatment device |
CN113976665A (en) * | 2021-09-30 | 2022-01-28 | 江苏联峰实业有限公司 | Material tracking system and method for straightening process of medium and small rods |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110150326A1 (en) * | 2007-09-03 | 2011-06-23 | Korea Expressway Corporation | Steel bridge coating inspection system using image processing and the processing method for the same |
CN102692429A (en) * | 2011-03-24 | 2012-09-26 | 中国科学院沈阳自动化研究所 | Method for automatic identification and detection of defect in composite material |
CN109766939A (en) * | 2018-12-29 | 2019-05-17 | 佛山科学技术学院 | A kind of galvanized steel and mild steel classification method and device based on photo |
CN110009632A (en) * | 2019-04-17 | 2019-07-12 | 国网重庆市电力公司电力科学研究院 | A kind of appraisal procedure, device and the equipment of metal erosion state |
-
2019
- 2019-08-22 CN CN201910777644.4A patent/CN110532924A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110150326A1 (en) * | 2007-09-03 | 2011-06-23 | Korea Expressway Corporation | Steel bridge coating inspection system using image processing and the processing method for the same |
CN102692429A (en) * | 2011-03-24 | 2012-09-26 | 中国科学院沈阳自动化研究所 | Method for automatic identification and detection of defect in composite material |
CN109766939A (en) * | 2018-12-29 | 2019-05-17 | 佛山科学技术学院 | A kind of galvanized steel and mild steel classification method and device based on photo |
CN110009632A (en) * | 2019-04-17 | 2019-07-12 | 国网重庆市电力公司电力科学研究院 | A kind of appraisal procedure, device and the equipment of metal erosion state |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111763814A (en) * | 2020-06-23 | 2020-10-13 | 江苏联峰实业有限公司 | Deformed steel bar heat treatment device |
CN113976665A (en) * | 2021-09-30 | 2022-01-28 | 江苏联峰实业有限公司 | Material tracking system and method for straightening process of medium and small rods |
CN113976665B (en) * | 2021-09-30 | 2024-06-11 | 江苏联峰实业有限公司 | Material tracking system and method for middle and small rod straightening process |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113822951B (en) | Image processing method, device, electronic equipment and storage medium | |
CN110532924A (en) | A kind of identifying processing method and device of high heat resistance steel | |
Cemernek et al. | Big data as a promoter of industry 4.0: Lessons of the semiconductor industry | |
CN110222629A (en) | Bale No. recognition methods and Bale No. identifying system under a kind of steel scene | |
CN110490862A (en) | A kind of method and device improving continuous casting flaw detection qualification rate | |
CN112214707A (en) | Webpage content characterization method, classification method, device and equipment | |
CN110472695A (en) | A kind of the unusual service condition detection and classification method of industrial processes | |
CN109657792A (en) | Construct the method, apparatus and computer-readable medium of neural network | |
CN111881948A (en) | Training method and device of neural network model, and data classification method and device | |
CN117077085A (en) | Multi-mode harmful social media content identification method combining large model with two-way memory | |
Singh et al. | Introduce quality processes through DOE: a case study in die casting foundry | |
CN110111311B (en) | Image quality evaluation method and device | |
Muncsan et al. | Transferability of fast gradient sign method | |
US20180114173A1 (en) | Cognitive service request dispatching | |
CN109086737A (en) | Shipping cargo monitoring video frequency identifying method and system based on convolutional neural networks | |
CN108764248A (en) | Image feature point extraction method and device | |
CN109063732B (en) | Image ranking method and system based on feature interaction and multi-task learning | |
CN115830397A (en) | Semi-supervised part defect detection method based on countermeasure mechanism | |
CN110400560A (en) | Data processing method and device, storage medium, electronic device | |
CN111860357B (en) | Attendance rate calculating method and device based on living body identification, terminal and storage medium | |
CN113792751A (en) | Cross-domain behavior identification method, device, equipment and readable storage medium | |
CN110533191A (en) | A kind of method and device handling narrow composition alloy steel | |
CN108846421B (en) | Image classification method based on deep learning | |
CN110490260A (en) | A kind of method and apparatus identifying iron packet sky packet temperature drop | |
Deng et al. | Knowledge Distillation-Guided Cost-Sensitive Ensemble Learning Framework for Imbalanced Fault Diagnosis |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191203 |