CN111933221B - Method for predicting dynamic recrystallization fraction of Nb microalloyed steel - Google Patents
Method for predicting dynamic recrystallization fraction of Nb microalloyed steel Download PDFInfo
- Publication number
- CN111933221B CN111933221B CN202010766776.XA CN202010766776A CN111933221B CN 111933221 B CN111933221 B CN 111933221B CN 202010766776 A CN202010766776 A CN 202010766776A CN 111933221 B CN111933221 B CN 111933221B
- Authority
- CN
- China
- Prior art keywords
- strain
- dynamic recrystallization
- epsilon
- rheological stress
- model
- 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.)
- Active
Links
- 238000001953 recrystallisation Methods 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 55
- 229910000742 Microalloyed steel Inorganic materials 0.000 title claims abstract description 25
- 238000013178 mathematical model Methods 0.000 claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims abstract description 12
- 239000000126 substance Substances 0.000 claims abstract description 9
- 238000012216 screening Methods 0.000 claims description 15
- 238000005482 strain hardening Methods 0.000 claims description 9
- 238000010438 heat treatment Methods 0.000 claims description 8
- 238000005272 metallurgy Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 abstract description 10
- 238000010801 machine learning Methods 0.000 abstract description 9
- 238000010791 quenching Methods 0.000 abstract description 8
- 230000000171 quenching effect Effects 0.000 abstract description 7
- 229910000831 Steel Inorganic materials 0.000 abstract description 6
- 230000006399 behavior Effects 0.000 abstract description 6
- 239000010959 steel Substances 0.000 abstract description 6
- 238000007906 compression Methods 0.000 abstract description 4
- 230000006835 compression Effects 0.000 abstract description 4
- 238000011160 research Methods 0.000 abstract description 3
- 230000007547 defect Effects 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 229910001566 austenite Inorganic materials 0.000 description 3
- 229910045601 alloy Inorganic materials 0.000 description 1
- 239000000956 alloy Substances 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/30—Prediction of properties of chemical compounds, compositions or mixtures
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C10/00—Computational theoretical chemistry, i.e. ICT specially adapted for theoretical aspects of quantum chemistry, molecular mechanics, molecular dynamics or the like
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
Abstract
The invention discloses a method for predicting dynamic recrystallization fraction of Nb microalloyed steel, belonging to the technical field of steel research and machine learning intersection; according to the method, a data set of dynamic recrystallization behavior of the Nb microalloy steel is constructed by experimental data of dynamic recrystallization type rheological stress of the existing C-Mn-Nb microalloy steel, a model between chemical components, process parameters and rheological stress curve characteristics is built by using a BP neural network based on Bayesian regularization, and the dynamic recrystallization score mathematical model is used for realizing high-precision prediction of the dynamic recrystallization score, so that the workload of single compression experiments and quenching experiments is obviously reduced, and the efficiency of predicting the dynamic recrystallization score is improved.
Description
Technical Field
The invention belongs to the technical field of steel research and machine learning, and particularly relates to a method for predicting dynamic recrystallization fraction of Nb microalloyed steel.
Background
The austenite dynamic recrystallization during the high-temperature deformation of the Nb microalloyed steel has great influence on the transformation behavior and the final performance of the subsequent austenite, and the research on the dynamic recrystallization behavior can provide basis for formulating the optimal controlled rolling process. At present, two main methods exist for researching the dynamic recrystallization fraction of austenite, one is to adopt a single-pass thermal compression experiment to quench at different deformation, and directly carry out metallographic observation to count the recrystallization fraction; the other is a mathematical model based on the recrystallization score. Recrystallization behavior can be described according to quenching experiments, but the experimental effort is large. The recrystallization fraction at different deformation levels can be predicted from a mathematical model of the recrystallization fraction, but the model has various forms and model parameters are only applicable to specific components and process conditions. And the machine learning can learn the characteristics in the data set according to the existing data set, and has the advantages of high precision and strong universality. However, in terms of dynamic recrystallization score prediction, machine learning has not been applied yet, and development of work of machine learning in terms of dynamic recrystallization score prediction has a very important meaning.
By searching the national intellectual property office database and the SOOPAT database, the patent CN106053754B authorizes a method for predicting the dynamic recrystallization fraction of the high alloyed material under the time-varying working condition, a metallographic microstructure is obtained through a large number of thermal simulation experiments and quenching experiments, and a traditional dynamic recrystallization dynamics model is improved into a new model capable of predicting the dynamic recrystallization fraction under the time-varying working condition, but the patent has two defects: (1) it requires a large number of thermal modeling and quenching experiments, (2) the recrystallization fraction model is only applicable to specific components and process conditions. Patent CN110068507a discloses a method for correcting a traditional recrystallization model, which obtains samples under different deformation conditions through a large number of physical simulation tests, calculates the recrystallization fraction of a core, and obtains the true strain of the core of the sample by using numerical simulation software; obtaining model parameters by adopting a fitting method, and fitting the obtained model parameters with the Zener-Hollomon parameters to obtain recrystallization model parameters under other conditions, wherein the method has the defects: (1) the model parameters obtained by fitting have low precision, and (2) a large number of thermal deformation experiments and numerical simulation experiments are needed, so that the cost is high and the simulation time is long.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides a method for predicting the dynamic recrystallization fraction of Nb microalloyed steel. The method combines a mathematical model and machine learning to predict the dynamic recrystallization fraction of the Nb microalloy steel, has higher precision, wide application range and short consumption time, can obviously reduce a large amount of quenching experiment workload, and is suitable for predicting the dynamic recrystallization fraction of any steel grade or alloy.
A method of predicting the dynamic recrystallization fraction of Nb microalloyed steel comprising the steps of:
step 1, constructing an initial data set of dynamic recrystallization behavior of Nb microalloyed steel by experimental data of dynamic recrystallization type rheological stress of the existing C-Mn-Nb microalloyed steel, wherein the data set comprises: C. mn and Nb contents, heating temperature, deformation temperature, strain rate and maximum strain amount;
step 2, screening a rheological stress curve conforming to a physical metallurgy law to obtain a screening data set;
step 3, selecting a dynamic recrystallization fraction mathematical model form, wherein the dynamic recrystallization fraction mathematical model is as follows:
wherein f dyn For the dynamic recrystallization fraction, t is time,
for strain rate, b (ε) and n (ε) are variables related to strain ε.
Assume that: (1) reaching critical strain ε c When the dynamic recrystallization fraction was 0.5%; (2) reaching steady state strain ε s The dynamic recrystallization fraction was 99%. Formulae (2) and (3) can be obtained:
obtainable by the formulae (2) and (3),
wherein (1)>
t c To achieve critical strain epsilon c Time t of (2) s To achieve steady state strain ε s Time of epsilon c For critical strain, ε p For peak strain, ε s Is steady state strain, k is a constant;
step 4, determining the actual measurement critical strain epsilon of each rheological stress curve in the data set according to the rheological stress curves in the screening data set c Peak strain epsilon p And steady state strain ε s ；
Step 5, according to critical strain epsilon c And peak strain epsilon p Relation epsilon of (2) c ＝kε p Calculating the k value of each rheological stress curve;
step 6, establishing a nonlinear mapping network relation model between chemical components, technological parameters and dynamic recrystallization type rheological stress characteristics by using a BP neural network based on Bayesian regularization, and training the model to obtain a trained network model;
step 7, selecting at least one group of components and processes according to the trained network relation model, and predicting rheological stress characteristics;
and step 8, predicting the dynamic recrystallization fraction according to the rheological stress characteristics predicted in the step 7 and the dynamic recrystallization fraction mathematical model selected in the step 3.
In the step 4, the critical strain epsilon of each rheological stress curve is determined c Peak strain epsilon p Steady state strain ε s The specific process is as follows: determining peak strain epsilon from peaks on a rheological stress curve (i.e., stress sigma-strain epsilon curve) p The method comprises the steps of carrying out a first treatment on the surface of the Definition of Strain hardening Rate
(Δσ is the stress increment, Δε is the strain increment), and the strain when θ is recovered to 0 value for the first time is defined as the steady state strain ε from the strain hardening rate θ -strain ε curve s The method comprises the steps of carrying out a first treatment on the surface of the Deriving the strain hardening rate θ from the stress σ to obtain +.>
According to
Peak determination of critical stress sigma of curve c Critical strain epsilon c Determined from the stress sigma-strain epsilon curve.
In the step 6, a non-linear mapping network relation model between chemical components, technological parameters and dynamic recrystallization type rheological stress characteristics is established by adopting a BP neural network based on Bayesian regularization, and training of the model is carried out, wherein the specific process is as follows: establishing a three-layer neural network relation by adopting a BP neural network based on Bayesian regularization, wherein input parameters of an input layer are C content, mn content, nb content, heating temperature, deformation temperature, strain rate and maximum strain; the output parameter of the output layer is peak strain epsilon p Steady state strain ε s And k; the number of hidden layer neurons is 5.
In the step 7, at least one group of components and processes are selected according to the trained network relation model, and rheological stress characteristics are predicted, wherein the specific process is as follows: for the components to be predicted and their processes, the rheological stress characteristics are predicted: peak strain epsilon p Steady state strain ε s And k.
Compared with the prior art, the invention has the advantages that:
(1) The applicability is wide. The invention collects more than 280 dynamic recrystallization type rheological stress curves of the C-Mn-Nb microalloy steel, constructs a C-Mn-Nb microalloy steel data set, and the data set contains comprehensive chemical components and technological parameter information of the Nb microalloy steel, thereby avoiding the defect of information deficiency under single steel grade or technological condition and leading a machine learning model to have wider applicability;
(2) The precision is higher. The invention adopts a machine learning method to construct a network relation model among chemical components, process parameters and rheological stress characteristics, overcomes the defect of low precision of the traditional dynamic recrystallization fraction mathematical model, and has the advantage of high precision;
(3) A large number of single-pass compression and subsequent quenching experiments can be reduced. According to the invention, a network relation model among chemical components, process parameters and rheological stress characteristics of the Nb microalloy steel series is established by adopting a machine learning algorithm, so that the rheological stress characteristics of different components and under process conditions can be predicted, meanwhile, the dynamic recrystallization fraction is predicted by using a recrystallization fraction mathematical model, the workload of single-pass compression and quenching experiments is greatly reduced, and the prediction efficiency of the dynamic recrystallization fraction is improved.
Drawings
FIG. 1 is a flow chart of a method for predicting the dynamic recrystallization fraction of Nb microalloyed steel in accordance with example 1 of the present invention;
FIG. 2 is a graph comparing predicted dynamic recrystallization fraction to measured dynamic recrystallization fraction for example 1 of the present invention, wherein:
fig. 2 (a) is a graph comparing the predicted dynamic recrystallization fraction with the measured dynamic recrystallization fraction in the a-component process, and fig. 2 (B) is a graph comparing the predicted dynamic recrystallization fraction with the measured dynamic recrystallization fraction in the B-component process.
Detailed Description
Embodiments of the present invention are further described below with reference to the accompanying drawings.
Example 1
A method for predicting the dynamic recrystallization fraction of Nb microalloyed steel, the flow chart of which is shown in fig. 1, comprising the steps of:
step 1, constructing an initial data set of dynamic recrystallization behavior of Nb microalloyed steel by experimental data of the existing 410 dynamic recrystallization rheological stress curves of the C-Mn-Nb microalloyed steel, wherein the data set comprises: C. mn and Nb contents, heating temperature, deformation temperature, strain rate and maximum strain amount;
step 2, screening a rheological stress curve conforming to a physical metallurgy law, wherein the screening standard is as follows: (1) judging whether the rheological stress curve accords with the physical metallurgy law under the same component and different deformation conditions. If the deformation temperature is reduced under the condition of different deformation temperatures of the same component, the rheological stress is gradually increased under the same strain quantity; under the condition of different strain rates of the same component, as the strain rate increases, the rheological stress gradually increases at the same strain quantity; (2) and judging whether the rheological stress curve accords with the physical metallurgy law or not when different components are in the same deformation condition. If the same deformation condition is different in Nb content, the rheological stress is gradually increased with the increase of the Nb content at the same strain amount; when the same deformation condition has different Mn contents, the rheological stress gradually increases with the increase of the Mn content and the same strain quantity; when the same deformation condition is different in C content, the rheological stress gradually decreases with the increase of the C content at the same strain amount. After screening by a physical metallurgy principle, a screening data set is obtained, wherein 280 rheological stress curves are included in the screening data set, and table 1 shows the screened steel grade and process information;
table 1 steel grade and process information after physical metallurgical principle screening
Step 3, selecting a dynamic recrystallization fraction mathematical model form;
in the embodiment of the invention, a dynamic recrystallization score mathematical model form is selected, and is as follows:
wherein f dyn For the dynamic recrystallization fraction, t is time,
for strain rate, b (ε) and n (ε) are variables related to strain ε.
Assume that: (1) reaching critical strain ε c When the dynamic recrystallization fraction was 0.5%;(2) reaching steady state strain ε s The dynamic recrystallization fraction was 99%. Formulae (2) and (3) can be obtained:
obtainable by the formulae (2) and (3),
wherein (1)>
t c For the time to reach critical strain, t s For the time to reach steady state strain ε c For critical strain, ε p For peak strain, ε s Is steady state strain k is constant.
Step 4, determining the actual measurement critical strain epsilon of each rheological stress curve in the data set according to the rheological stress curves in the screening data set c Peak strain epsilon p And steady state strain ε s ；
In the embodiment of the invention, the peak strain epsilon is determined according to the peak value on the rheological stress curve (namely the stress sigma-strain epsilon curve) p The method comprises the steps of carrying out a first treatment on the surface of the Definition of Strain hardening Rate
(Δσ is the stress increment, Δε is the strain increment), and the strain when θ is recovered to 0 value for the first time is defined as the steady state strain ε from the strain hardening rate θ -strain ε curve s The method comprises the steps of carrying out a first treatment on the surface of the Deriving the strain hardening rate θ from the stress σ to obtain +.>
According to->
Peak determination of critical stress sigma of curve c Critical strain epsilon c Determined from the stress sigma-strain epsilon curve.
Step 5, according to critical strain epsilon c And peak strain epsilon p Relation epsilon of (2) c ＝kε p Calculating the k value of each rheological stress curve, wherein table 2 is the determined rheological stress characteristic information;
table 2 screening rheological stress characterization information in data set
Step 6, establishing a nonlinear mapping network relation model between chemical components, technological parameters and dynamic recrystallization type rheological stress characteristics by using a BP neural network based on Bayesian regularization, and training the model to obtain a trained network model;
in the embodiment of the invention, the specific process of training the model is as follows: establishing a three-layer neural network relation by adopting a BP neural network based on Bayesian regularization, wherein input parameters of an input layer are C content, mn content, nb content, heating temperature, deformation temperature, strain rate and maximum strain; the output parameter of the output layer is peak strain epsilon p Steady state strain ε s And k; the number of hidden layer neurons is 5. And then training the model to obtain a trained network relation model.
Step 7, selecting at least one group of components and processes according to the trained network relation model, and predicting rheological stress characteristics;
in the embodiment of the invention, rheological stress characteristic prediction is carried out, and the specific process is as follows: two groups of components are selected respectively, including:
component A: 0.1C-1.42Mn-0.035Nb;
and the component B comprises the following components: 0.117C-1.21Mn-0.041Nb;
the corresponding process is as follows:
a process: deformation temperature 1100 ℃ and strain rate of 0.2s -1 Heating at 1400 deg.c to maximum strain of 3.0;
and B, technology: deformation ofAt 1050℃and strain rate of 0.1s -1 The heating temperature is 1200 ℃, and the maximum strain is 0.8.
For the components to be predicted and their processes, the rheological stress characteristics are predicted: peak strain epsilon p Steady state strain ε s And k, as a result of
The component A comprises the following processes: epsilon p ＝0.6211，ε s ＝2.3629，k＝0.8048；
The component B comprises the following processes: epsilon p ＝0.2471，ε s ＝0.5968，k＝0.8464。
And 8, predicting dynamic recrystallization fraction according to the rheological stress characteristics predicted in the step 7 and the dynamic recrystallization fraction mathematical model selected in the step 3, wherein a comparison chart of the predicted dynamic recrystallization fraction and the actual dynamic recrystallization fraction in the A component process is shown in fig. 2 (a), and a comparison chart of the predicted dynamic recrystallization fraction and the actual dynamic recrystallization fraction in the B component process is shown in fig. 2 (B).
Claims (3)
1. A method for predicting the dynamic recrystallization fraction of Nb microalloyed steel comprising the steps of:
step 1, constructing an initial data set of dynamic recrystallization behavior of Nb microalloyed steel by experimental data of dynamic recrystallization type rheological stress of the existing C-Mn-Nb microalloyed steel, wherein the data set comprises: C. mn and Nb contents, heating temperature, deformation temperature, strain rate and maximum strain amount;
step 2, screening a rheological stress curve conforming to a physical metallurgy law to obtain a screening data set; the screening standard is to judge whether the rheological stress curve accords with the physical metallurgy law under the same component and different deformation conditions;
step 3, selecting a dynamic recrystallization fraction mathematical model form, wherein the dynamic recrystallization fraction mathematical model is as follows:
wherein f dyn For the dynamic recrystallization fraction, t is time,
b (epsilon) and n (epsilon) are variables related to strain epsilon for strain rate;
assume that: (1) reaching critical strain ε c When the dynamic recrystallization fraction was 0.5%; (2) reaching steady state strain ε s When the dynamic recrystallization fraction is 99%, formulae (2) and (3) can be obtained:
obtainable by the formulae (2) and (3),
wherein (1)>
t c To achieve critical strain epsilon c Time t of (2) s To achieve steady state strain ε s Time of epsilon c For critical strain, ε p For peak strain, ε s Is steady state strain, k is a constant;
step 4, determining the actual measurement critical strain epsilon of each rheological stress curve in the data set according to the rheological stress curves in the screening data set c Peak strain epsilon p And steady state strain ε s ；
Step 5, according to critical strain epsilon c And peak strain epsilon p Relation epsilon of (2) c ＝kε p Calculating the k value of each rheological stress curve;
step 6, establishing a nonlinear mapping network relation model between chemical components, technological parameters and dynamic recrystallization type rheological stress characteristics by using a BP neural network based on Bayesian regularization, and training the model to obtain a trained network model;
the BP neural network based on Bayesian regularization is adopted to establish a nonlinear mapping network relation model between chemical components, technological parameters and dynamic recrystallization type rheological stress characteristics, and training of the model is carried out, wherein the specific process is as follows: establishing a three-layer neural network relation by adopting a BP neural network based on Bayesian regularization, wherein input parameters of an input layer are C content, mn content, nb content, heating temperature, deformation temperature, strain rate and maximum strain; the output parameter of the output layer is peak strain epsilon p Steady state strain ε s And k; the number of hidden layer neurons is 5;
step 7, selecting at least one group of components and processes according to the trained network relation model, and predicting rheological stress characteristics;
and step 8, predicting the dynamic recrystallization fraction according to the rheological stress characteristics predicted in the step 7 and the dynamic recrystallization fraction mathematical model selected in the step 3.
2. The method for predicting dynamic recrystallization fraction of Nb microalloyed steel of claim 1, wherein in said step 4, critical strain ε of each rheological stress curve is determined c Peak strain epsilon p Steady state strain ε s The specific process is as follows: determining peak strain epsilon from peaks on a rheological stress curve p The method comprises the steps of carrying out a first treatment on the surface of the Definition of Strain hardening Rate
Wherein Δσ is the stress increment and Δε is the strain increment; the strain when θ is recovered to 0 value for the first time is regarded as steady state strain ε according to the θ -strain ε curve of strain hardening rate s The method comprises the steps of carrying out a first treatment on the surface of the Deriving the strain hardening rate θ from the stress σ to obtain +.>
According to->
Peak determination of critical stress sigma of curve c Critical strain epsilon c Determined from the stress sigma-strain epsilon curve.
3. The method for predicting dynamic recrystallization fraction of Nb microalloyed steel according to claim 1, wherein in step 7, at least one set of components and processes are selected according to a trained network relationship model, and the predicted rheological stress characteristics are as follows: for the components to be predicted and their processes, the rheological stress characteristics are predicted: peak strain epsilon p Steady state strain ε s And k.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010766776.XA CN111933221B (en) | 2020-08-03 | 2020-08-03 | Method for predicting dynamic recrystallization fraction of Nb microalloyed steel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010766776.XA CN111933221B (en) | 2020-08-03 | 2020-08-03 | Method for predicting dynamic recrystallization fraction of Nb microalloyed steel |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111933221A CN111933221A (en) | 2020-11-13 |
| CN111933221B true CN111933221B (en) | 2023-07-04 |
Family
ID=73306422
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010766776.XA Active CN111933221B (en) | 2020-08-03 | 2020-08-03 | Method for predicting dynamic recrystallization fraction of Nb microalloyed steel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111933221B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112786120B (en) * | 2021-01-26 | 2022-07-05 | 云南大学 | Method for synthesizing chemical material with assistance of neural network |
| CN113702613B (en) * | 2021-08-19 | 2024-02-13 | 鞍钢股份有限公司 | Method for determining critical condition of dynamic recrystallization of material |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101591729A (en) * | 2009-06-19 | 2009-12-02 | 东北大学 | The method of structure evolution of austenite dynamic recrystallization in the prediction thermal deformation of plate-strip steel |
| CN102254057A (en) * | 2011-04-25 | 2011-11-23 | 天津职业技术师范大学 | Method for predicting rolling off-line mechanical property of thin plate |
| CN102339344A (en) * | 2011-05-25 | 2012-02-01 | 深圳大学 | Back analysis identification method for parameters of dynamic re-crystallizing model |
| CN106055844A (en) * | 2016-07-06 | 2016-10-26 | 中南大学 | Prediction and control method of nickel-base super alloy microstructure on the basis of BP (Back Propagation) neural network |
-
2020
- 2020-08-03 CN CN202010766776.XA patent/CN111933221B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101591729A (en) * | 2009-06-19 | 2009-12-02 | 东北大学 | The method of structure evolution of austenite dynamic recrystallization in the prediction thermal deformation of plate-strip steel |
| CN102254057A (en) * | 2011-04-25 | 2011-11-23 | 天津职业技术师范大学 | Method for predicting rolling off-line mechanical property of thin plate |
| CN102339344A (en) * | 2011-05-25 | 2012-02-01 | 深圳大学 | Back analysis identification method for parameters of dynamic re-crystallizing model |
| CN106055844A (en) * | 2016-07-06 | 2016-10-26 | 中南大学 | Prediction and control method of nickel-base super alloy microstructure on the basis of BP (Back Propagation) neural network |
Non-Patent Citations (4)
| Title |
|---|
| Characterization of hot flow behaviour and deformation stability of microalloyed steel using artificial neural networks and dynamic material model;Ignacio Alcelay等;《International Journal of Materials Research (formerly Zeitschrift fuer Metallkunde)》;第105卷(第8期);743-754 * |
| Dynamic recrystallization behavior of microalloyed forged steel;Jin WANG等;《JOURNAL OF RON AND STEEL RESEARCH, INTERNATIONAL.》;第15卷(第3期);78-81, 91 * |
| 低碳、Ti-V复合微合金化钢的流变应力模型;沈继程等;《东北大学学报(自然科学版)》;第37卷(第5期);638-641+667 * |
| 含Nb微合金钢动态再结晶行为;董毅等;《东北大学学报(自然科学版)》(第10期);1431-1434 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111933221A (en) | 2020-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jie et al. | Flow behavior of Al–6.2 Zn–0.70 Mg–0.30 Mn–0.17 Zr alloy during hot compressive deformation based on Arrhenius and ANN models | |
| CN111933221B (en) | Method for predicting dynamic recrystallization fraction of Nb microalloyed steel | |
| CN107220485B (en) | A kind of method for building up of constitutive model suitable for multiple tracks second compression | |
| Ji et al. | Optimization the working parameters of as-forged 42CrMo steel by constitutive equation-dynamic recrystallization equation and processing maps | |
| CN114611844B (en) | Method and system for determining alloy addition amount in converter tapping process | |
| CN104573278A (en) | Hot-rolled H profile steel mechanical property forecasting method based on multivariate linear regression analysis | |
| CN111310348A (en) | Material constitutive model prediction method based on PSO-LSSVM | |
| CN112949005B (en) | High-strength and high-toughness steel design method based on machine learning guidance | |
| CN110863169A (en) | Heat treatment optimization method for carburizing steel bearing ring | |
| CN112651562B (en) | Laser cladding process optimization method based on signal-to-noise ratio and improved gray correlation degree | |
| CN105677949A (en) | Method for predicting TC6 titanium alloy forging piece microstructural parameters | |
| Ping et al. | Neural network prediction of flow stress of Ti–15–3 alloy under hot compression | |
| CN104050380A (en) | LF furnace final temperature forecasting method based on Adaboost-PLS-ELM | |
| Qiao et al. | A comparative study on arrhenius equations and BP neural network models to predict hot deformation behaviors of a hypereutectoid steel | |
| CN1298458C (en) | Method for real-time estimating temperature of liquid steel in RH fining furnace | |
| CN110502781B (en) | Prior knowledge-based ferroalloy production ingredient optimization method | |
| CN111861041B (en) | Method for predicting dynamic recrystallization type rheological stress of Nb microalloyed steel | |
| Lin et al. | Prediction of metadynamic softening in a multi-pass hot deformed low alloy steel using artificial neural network | |
| Xu et al. | Prediction of static globularization of Ti-17 alloy with starting lamellar microstructure during heat treatment | |
| Colla et al. | Neural networks-based prediction of hardenability of high performance carburizing steels for automotive applications | |
| CN114864007A (en) | Method for establishing ultra-high strength steel high-temperature forming grain size evolution model | |
| Podgornik et al. | Tool steel heat treatment optimization using neural network modeling | |
| Thankachan et al. | Artificial neural network modeling to evaluate and predict the mechanical strength of duplex stainless steel during casting | |
| CN109614710B (en) | Method for predicting element segregation three-dimensional characteristics of continuous casting blank based on random mathematic principle | |
| CN110442953B (en) | Q & P steel design method based on machine learning under guidance of physical metallurgy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |