CN111861041A - Method for predicting dynamic recrystallization type flowing stress of Nb microalloyed steel - Google Patents
Method for predicting dynamic recrystallization type flowing stress of Nb microalloyed steel Download PDFInfo
- Publication number
- CN111861041A CN111861041A CN202010767229.3A CN202010767229A CN111861041A CN 111861041 A CN111861041 A CN 111861041A CN 202010767229 A CN202010767229 A CN 202010767229A CN 111861041 A CN111861041 A CN 111861041A
- Authority
- CN
- China
- Prior art keywords
- stress
- strain
- rheological
- dynamic recrystallization
- curve
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Investigating Strength Of Materials By Application Of Mechanical Stress (AREA)
Abstract
A method for predicting dynamic recrystallization type flowing stress of Nb microalloyed steel belongs to the cross technical field of steel research and machine learning. The method is based on dynamic recrystallization type rheological stress curves of series Nb microalloyed steel and experimental data of steel type information, a genetic algorithm is adopted to learn parameters in a mathematical model corresponding to each rheological stress curve, a Bayesian regularized BP neural network is used to establish a network relation model between the steel type information and the rheological stress curve characteristics, and then dynamic recrystallization type rheological stress is predicted by combining the mathematical model corresponding to the rheological stress curves. The model established by the method can predict the rheological stress curve of the series of steel under various components and process conditions with high precision, obviously reduce the workload of a single-pass compression experiment, and improve the prediction efficiency and precision of the dynamic recrystallization rheological stress curve.
Description
Technical Field
The invention belongs to the cross technical field of steel research and machine learning, and particularly relates to a method for predicting dynamic recrystallization type flow allergy of Nb microalloyed steel.
Background
Nb microalloying high strength steel is widely applied to the aspects of pipelines, bridge buildings and the like. The Nb microalloying high strength steel requires high strength and good toughness. The fine grain strengthening can simultaneously improve the toughness of the steel, the dynamic recrystallization is taken as one of important ways for refining the grain size of austenite, and the final mechanical property of the Nb microalloyed high-strength steel is greatly influenced. At present, two methods are mainly used for researching the austenite dynamic recrystallization type rheological stress, one method is to adopt a single-pass compression experiment to directly obtain the rheological stress curve of experimental steel; and the other method is to establish a mathematical model according to the existing rheological stress curve. Although the rheological stress curve can be obtained according to the single-pass compression experiment, the experimental workload is large. The dynamic recrystallization type rheological stress curve can be predicted according to a rheological stress mathematical model established by the existing rheological stress curve, but the dynamic recrystallization type rheological stress curve is only suitable for single steel grade and process conditions, and the precision is also to be improved. The machine learning theory and the method can automatically learn the characteristics of data set according to large-scale data, have the characteristics of strong universality and high precision, and have been applied to many aspects of material science at present, such as prediction of novel solid materials, calculation of material performance and the like. Aiming at the problems of accuracy and generalization of dynamic recrystallization type rheological stress prediction, machine learning can be well solved, so that the development of the work in the aspect has important significance.
By searching a national intellectual property office database and an SOOPAT database, no relevant patent aiming at the dynamic recrystallization rheological stress of the Nb microalloyed steel is published at present; the prediction of the dynamic recrystallization rheological stress in the related literature is only performed on a single steel grade or under a single process condition, and has low precision and limited application range. For example, Abarghoei et al establishes a machine learning model for the Steady-State rheological stress in the Hot deformation process of X70 Steel, and predicts the Steady-State rheological stress, but the literature does not only relate to the influence of chemical components on the rheological stress, but also cannot predict the rheological stress curve of the whole deformation process [ Abarghoei H, Arabi H, Seyedein S H, et al. 471 and 477.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a method for predicting dynamic recrystallization type rheological stress, which is suitable for series Nb microalloyed steel, has higher precision and applicability on the premise of ensuring the traditional physical metallurgy rule, consumes shorter time and is suitable for predicting the dynamic recrystallization type rheological stress of any steel or alloy by taking a mathematical model as guidance and establishing a model for predicting the dynamic recrystallization type rheological stress of the Nb microalloyed steel by adopting a machine learning method.
A method of predicting Nb microalloyed steel dynamic recrystallization flow allergy, comprising the steps of:
step 1, constructing an initial data set based on the experimental data of the dynamic recrystallization type rheological stress curve, steel type information and process parameters of the existing Nb microalloyed steel, wherein: the steel grade information comprises: c content, Mn content, and Nb content; the technological parameters comprise: heating temperature, deformation temperature, maximum strain amount and strain rate;
step 3, determining the allergy of each flow in the screening data set according to the flow allergy curve of the screening data setMeasured peak strain of force curvepPeak stress σpSteady state strainsAnd steady state stress σs;
And 4, determining a mathematical model form of the dynamic recrystallization type rheological stress curve, which comprises the following specific steps:
step 4-1, dividing the rheological stress into two parts, namely one part before the peak stress and one part after the peak stress;
step 4-2, selecting a mathematical model A suitable for the rheological stress before the peak stress, and selecting a mathematical model B suitable for the peak stress to the steady stress, wherein:
the mathematical model form of the dynamic recrystallization type rheological stress curve is as follows:
where σ is stress, strain, σpIn order to be the peak stress,pis the peak strain, σsFor steady state stress, C and C1Is a constant;
step 5, according to the dynamic recrystallization type rheological stress mathematical model form determined in the step 4, respectively learning parameters in the mathematical model A and the mathematical model B according to an actually measured rheological stress curve by adopting a genetic algorithm;
step 6, establishing a nonlinear mapping network relation model between steel type information and dynamic recrystallization type rheological stress characteristics by adopting a Bayesian regularized BP neural network, and then performing model training to obtain a trained BP neural network model;
step 7, selecting at least one group of components and processes according to the trained BP neural network model, and predicting the dynamic recrystallization rheological stress characteristics;
and 8, combining the dynamic recrystallization rheological stress characteristics predicted in the step 7 with the rheological stress mathematical model A and the rheological stress mathematical model B determined in the step 4 to obtain a dynamic recrystallization rheological stress curve.
In step 3, determining the peak strain of each rheological stress curve in the screening data setpPeak stress σpSteady state strainsAnd steady state stress σsThe specific process comprises the following steps:
determination of peak strain from peaks on the rheological stress curve (i.e. stress sigma-strain curve)pAnd peak stress σp(ii) a Definition of the Strain hardening Rate(delta sigma is a stress increment, delta is a strain increment), and the strain at which theta is first restored to a value of 0 is regarded as a steady-state strain from a strain hardening rate theta-strain curvesSteady state stress σsDetermined from the stress sigma-strain curve.
In the step 5, parameters in the mathematical model A and the mathematical model B are learned according to the actually measured rheological stress curve by adopting a genetic algorithm according to the rheological stress mathematical model form determined in the step 4, and the specific process is as follows:
setting parameters such as cross rate, variation rate and maximum iteration number during genetic algorithm learning according to the actually measured rheological stress curve and the mathematical model form determined in step 4, and learning parameters C and C in the mathematical model corresponding to each rheological stress curve1。
In the step 6, a Bayesian regularized BP neural network is adopted to establish a nonlinear mapping network relation model among steel grade information, process parameters and dynamic recrystallization type rheological stress characteristics, and then model training is carried out, wherein the specific process is as follows:
establishing a three-layer neural network model 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, maximum strain and strain rate; the output parameters of the output layer are peak strain, peak stress, steady state strain, steady state stress, C and C1(ii) a The hidden layer is 5 neurons; and then training the neural network.
In the step 7, at least one group of components and processes are selected according to the trained BP neural network model, and the dynamic recrystallization rheological stress characteristics are predicted, wherein the specific process is as follows:
for each component and the process thereof, predicting peak stress, peak strain, steady state stress, C and C under the component and the process condition by the trained BP neural network model1。
Compared with the prior art, the invention has the advantages that:
(1) the applicability is wide. The method collects more than 300 Nb microalloyed steel dynamic recrystallization type rheological stress curves, constructs a data set, and the data set contains more comprehensive Nb microalloyed steel components and process parameter information, avoids the defect of less rheological stress information under a single steel type or process condition, and simultaneously ensures that the selected mathematical model has the characteristic of conforming to the physical metallurgical law, so that the comprehensive model has wider applicability;
(2) the precision is higher. The method adopts a machine learning method to learn the information in the flow stress curve and adopts the machine learning method to construct the network model between the steel grade information and the flow stress characteristics, thereby making up the defect of low precision of the traditional physical metallurgy mathematical model and having the characteristic of higher precision;
(3) can predict the rheological stress of various components and process conditions. The invention can predict the rheological stress characteristics in any range and under process conditions by adopting the network model established by machine learning, and draw a rheological stress curve according to the rheological stress mathematical model, thereby greatly reducing the workload of single-pass compression experiments and improving the efficiency and the precision of predicting the dynamic recrystallization rheological stress.
Drawings
FIG. 1 is a flow chart of a method of predicting Nb microalloyed steel dynamic recrystallization flow susceptibility in accordance with example 1 of the invention;
FIG. 2 is a graph comparing predicted and measured flow stress curves for example 1 of the present invention, wherein:
FIG. 2(a) is a comparison graph of a predicted dynamic recrystallization type rheological stress curve and an actually measured curve under the component A process;
FIG. 2(B) is a comparison graph of a predicted dynamic recrystallization type rheological stress curve and an actually measured curve in a B component process;
FIG. 3 is a graph of the comparison of the accuracy of the predicted and measured flow stress curves of example 1 of the present invention, wherein:
FIG. 3(a) is a graph of the comparison of the predicted dynamic recrystallization rheological stress curve and the measured curve in the A component process;
FIG. 3(B) is a graph of the comparison of the predicted dynamic recrystallization rheological stress curve and the measured curve in the B component process.
Detailed Description
The embodiments of the present invention will be further described with reference to the accompanying drawings.
Example 1
A method for predicting Nb microalloyed steel dynamic recrystallization flow stress, a flow chart is shown in figure 1, and the method comprises the following steps:
step 1, constructing an initial data set based on the existing experimental data of 500 Nb microalloyed steel dynamic recrystallization type rheological stress curves, steel type information and process parameter information, wherein the steel type information comprises: c content, Mn content, and Nb content; the technological parameters comprise: heating temperature, deformation temperature, maximum strain amount and strain rate;
TABLE 1 screened Steel grades and Process parameter information
Step 3, determining the actually measured peak value strain of each curve in the data set according to the rheological stress curve in the screened data setpPeak stress σpSteady state strainsAnd steady state stress σs;
In the embodiment of the invention, the peak strain is determined according to the peak value on the rheological stress curve (namely the stress sigma-strain curve)pAnd peak stress σp(ii) a Definition of the Strain hardening Rate(delta sigma is a stress increment, delta is a strain increment), and the strain at which theta is first restored to a value of 0 is regarded as a steady-state strain from a strain hardening rate theta-strain curvesSteady state stress σsDetermining from the stress sigma-strain curve; table 2 contains information for the determined rheological stresses.
TABLE 2 information contained in the rheological stress
And 4, determining the mathematical model form of the dynamic recrystallization type rheological stress curve as follows:
where σ is stress, strain, σpIn order to be the peak stress,pis the peak strain, σsFor steady state stress, C and C1Is a constant.
Step 5, according to the dynamic recrystallization type rheological stress mathematical model form determined in the step 4, respectively learning parameters C and C in the mathematical model according to the actually measured rheological stress curve by adopting a genetic algorithm1;
In the embodiment of the invention, a genetic algorithm is adopted, and parameters C and C in a mathematical model A and a mathematical model B corresponding to each rheological stress curve are respectively learned according to actually measured rheological stress curves1For 0 to peak strain, i.e., the parameter to be learned in mathematical model a is C; for peak to steady state strain, the parameter to be learned in the mathematical model B is C1(ii) a The population number of the genetic algorithm is set to be 50, the maximum evolutionary algebra is 100, a roulette mode is selected for operation, a single-point cross algorithm is adopted for cross operation, the cross probability is set to be 0.85, random uniform variation is adopted for variation operation, the variation probability is set to be 0.01, and the maximum iteration is 5000 times.
When parameter C is learned, the parameter range is set to be 0.2-2.0, and the fitness function is as follows:
in the formula (I), the compound is shown in the specification,andrespectively the ith strainiCalculated and measured stress values, sigma, corresponding to timepIn order to be the peak stress,pis the peak strain. Obtaining optimal parameter C-enable FUN by genetic algorithm optimizationstress1The minimum value is obtained.
② learning parameter C1When the parameter range is set to be 1.0-250, the fitness function is as follows:
in the formula (I), the compound is shown in the specification,andrespectively the ith strainiCalculated and measured stress values, sigma, corresponding to timesFor steady state stress, σpIn order to be the peak stress,pis the peak strain. Obtaining optimal parameter C by genetic algorithm optimization1Make FUNstress2The minimum value is obtained.
Optimizing the resulting C and C1Respectively substituting into mathematical models A and B until the correlation coefficient R of optimized rheological stress and measured rheological stress is greater than 0.9, and the mean square error RMSE is less than 10MPa2(the calculation methods of the correlation coefficient R and the mean square error RMSE are respectively shown in the formulas (5) and (6)), and the correspondingly obtained learning parameters are the model parameters C and C after the genetic algorithm learning1The model parameter ranges after the genetic algorithm learning are listed in table 3;
in the formula, MiIs the ith strainiCorresponding measured value of the flow stress, PiIs the ith strainiThe corresponding predicted value of the rheological stress model,is the average of the measured values of the rheological stress,the average value of the predicted values of the rheological stress is shown, and N is the total amount of strain corresponding to each rheological stress curve;
TABLE 3 model parameter ranges after genetic Algorithm learning
Step 6, establishing a nonlinear mapping network relation model among steel grade information, process parameter information and dynamic recrystallization type rheological stress characteristics by adopting a Bayesian regularized BP neural network, and then performing model training;
in the embodiment of the invention, the specific process of model training is as follows: establishing a three-layer neural network model 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, maximum strain and strain rate; the output parameters of the output layer are peak strain, peak stress, steady state strain, steady state stress, C and C1; the hidden layer is 5 neurons. And (3) processing 310 pieces of data information in the screening data set according to the following steps of 8: 2, 80% for training and 20% for testing; and then training the neural network to obtain a trained BP neural network model.
Step 7, selecting at least one group of components and processes according to the trained BP neural network model, and predicting the dynamic recrystallization rheological stress characteristics;
in the embodiment of the invention, the specific prediction process is as follows: two groups of components are respectively selected, including:
component A: 0.1C-1.42Mn-0.035 Nb;
and B component: 0.104C-0.4Mn-0.05 Nb;
the corresponding process comprises the following steps:
a process: deformation temperature 1100 deg.C, strain rate 0.2s-1Heating temperature of 1400 ℃ and maximum dependent variable3.0;
And the process B comprises the following steps: deformation temperature 1000 ℃ and strain rate 1s-1The heating temperature is 1200 ℃, and the maximum strain is 1.0;
aiming at each component and the process thereof, predicting the dynamic recrystallization rheological stress characteristics of the component and the process under the condition of the trained BP neural network model, which specifically comprises the following steps: peak stress sigmapPeak strainpSteady state stress σsC and C1The result is:
the component A process comprises the following steps:p=0.6211,σp=89.2581,σs=72.7970,C=0.6443,C1=3.1211;
the component B process comprises the following steps:p=0.3998,σp=161.686,σs=147.7749,C=0.5825,C1=21.2994。
step 8, combining the dynamic recrystallization rheological stress characteristics predicted in the step 7 with the rheological stress curve mathematical model A and the mathematical model B determined in the step 4 to obtain a dynamic recrystallization rheological stress curve, wherein a comparison graph of the predicted dynamic recrystallization rheological stress curve and an actually measured curve in the component A process is shown in a figure 2(a), and a comparison graph of the predicted dynamic recrystallization rheological stress curve and the actually measured curve in the component B process is shown in a figure 2 (B); in this example, the precision comparison graphs of the predicted dynamic recrystallization type rheological stress curves and the respective actually measured curves in the component a process and the component B process are shown in fig. 3(a) and 3(B), respectively.
Claims (5)
1. A method for predicting the dynamic recrystallization flow stress of Nb microalloyed steel, which is characterized by comprising the following steps:
step 1, constructing an initial data set based on the experimental data of the dynamic recrystallization type rheological stress curve, steel type information and process parameters of the existing Nb microalloyed steel, wherein: the steel grade information comprises: c content, Mn content, and Nb content; the technological parameters comprise: heating temperature, deformation temperature, maximum strain amount and strain rate;
step 2, judging whether the flow stress curve in the initial data set conforms to the physical metallurgy rule or not, and reserving the flow stress curve conforming to the physical metallurgy rule to form a screening data set;
step 3, determining the actually measured peak value strain of each rheological stress curve in the screening data set according to the rheological stress curve in the screening data setpPeak stress σpSteady state strainsAnd steady state stress σs;
And 4, determining a mathematical model form of the dynamic recrystallization type rheological stress curve, which comprises the following specific steps:
step 4-1, dividing the rheological stress into two parts, namely one part before the peak stress and one part after the peak stress;
step 4-2, selecting a mathematical model A suitable for the rheological stress before the peak stress, and selecting a mathematical model B suitable for the peak stress to the steady stress, wherein:
the mathematical model form of the dynamic recrystallization type rheological stress curve is as follows:
where σ is stress, strain, σpIn order to be the peak stress,pis the peak strain, σsFor steady state stress, C and C1Is a constant;
step 5, according to the dynamic recrystallization type rheological stress mathematical model form determined in the step 4, respectively learning parameters in the mathematical model A and the mathematical model B according to an actually measured rheological stress curve by adopting a genetic algorithm;
step 6, establishing a nonlinear mapping network relation model between steel type information and dynamic recrystallization type rheological stress characteristics by adopting a Bayesian regularized BP neural network, and then performing model training to obtain a trained BP neural network model;
step 7, selecting at least one group of components and processes according to the trained BP neural network model, and predicting the dynamic recrystallization rheological stress characteristics;
and 8, combining the dynamic recrystallization rheological stress characteristics predicted in the step 7 with the rheological stress mathematical model A and the rheological stress mathematical model B determined in the step 4 to obtain a dynamic recrystallization rheological stress curve.
2. The method of predicting dynamic recrystallization flow stress of Nb microalloyed steel as claimed in claim 1, wherein in step 3, the peak strain of each flow stress curve in the screening dataset is determinedpPeak stress σpSteady state strainsAnd steady state stress σsThe specific process comprises the following steps:
determining peak strain from peaks on the rheological stress curvepAnd peak stress σp(ii) a Definition of the Strain hardening RateWherein, delta sigma is stress increment, and delta is strain increment; according to the strain hardening rate theta-strain curve, the strain when theta is recovered to 0 value for the first time is taken as the steady state strainsSteady state stress σsDetermined from the stress sigma-strain curve.
3. The method for predicting the dynamic recrystallization flow stress of the Nb microalloyed steel according to claim 1, wherein in the step 5, parameters in the mathematical model A and the mathematical model B are learned according to the measured flow stress curve by adopting a genetic algorithm according to the form of the flow stress mathematical model determined in the step 4, and the specific process is as follows:
setting parameters such as cross rate, variation rate and maximum iteration number during genetic algorithm learning according to the actually measured rheological stress curve and the mathematical model form determined in step 4, and learning parameters C and C in the mathematical model corresponding to each rheological stress curve1。
4. The method for predicting the dynamic recrystallization type rheological stress of the Nb microalloyed steel according to claim 1, wherein in the step 6, a Bayesian regularized BP neural network is adopted to establish a nonlinear mapping network relation model among steel type information, process parameters and the dynamic recrystallization type rheological stress characteristics, and then model training is carried out, and the specific process is as follows:
establishing a three-layer neural network model 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, maximum strain and strain rate; the output parameters of the output layer are peak strain, peak stress, steady state strain, steady state stress, C and C1(ii) a The hidden layer is 5 neurons; and then training the neural network.
5. The method for predicting the dynamic recrystallization rheological stress of the Nb microalloyed steel according to the claim 1, wherein in the step 7, at least one group of components and processes are selected according to a trained BP neural network model to predict the dynamic recrystallization rheological stress characteristics, and the specific process is as follows:
for each component and the process thereof, predicting peak stress, peak strain, steady state stress, C and C under the component and the process condition by the trained BP neural network model1。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010767229.3A CN111861041B (en) | 2020-08-03 | 2020-08-03 | Method for predicting dynamic recrystallization type rheological stress of Nb microalloyed steel |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010767229.3A CN111861041B (en) | 2020-08-03 | 2020-08-03 | Method for predicting dynamic recrystallization type rheological stress of Nb microalloyed steel |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111861041A true CN111861041A (en) | 2020-10-30 |
CN111861041B CN111861041B (en) | 2023-09-05 |
Family
ID=72952790
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010767229.3A Active CN111861041B (en) | 2020-08-03 | 2020-08-03 | Method for predicting dynamic recrystallization type rheological stress of Nb microalloyed steel |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111861041B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112507542A (en) * | 2020-12-02 | 2021-03-16 | 中南大学 | Method for accurately predicting stress relaxation behavior under tensile stress and compressive stress states |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102339344A (en) * | 2011-05-25 | 2012-02-01 | 深圳大学 | Back analysis identification method for parameters of dynamic re-crystallizing model |
CN105652666A (en) * | 2016-03-09 | 2016-06-08 | 中南大学 | Large die forging press beam feeding speed predictive control method based on BP neural networks |
CN111079309A (en) * | 2019-12-30 | 2020-04-28 | 湖北汽车工业学院 | Multi-pass compression rheological stress model establishment method for coupled recrystallization dynamics |
US20200210826A1 (en) * | 2018-12-29 | 2020-07-02 | Northeastern University | Intelligent analysis system using magnetic flux leakage data in pipeline inner inspection |
-
2020
- 2020-08-03 CN CN202010767229.3A patent/CN111861041B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102339344A (en) * | 2011-05-25 | 2012-02-01 | 深圳大学 | Back analysis identification method for parameters of dynamic re-crystallizing model |
CN105652666A (en) * | 2016-03-09 | 2016-06-08 | 中南大学 | Large die forging press beam feeding speed predictive control method based on BP neural networks |
US20200210826A1 (en) * | 2018-12-29 | 2020-07-02 | Northeastern University | Intelligent analysis system using magnetic flux leakage data in pipeline inner inspection |
CN111079309A (en) * | 2019-12-30 | 2020-04-28 | 湖北汽车工业学院 | Multi-pass compression rheological stress model establishment method for coupled recrystallization dynamics |
Non-Patent Citations (3)
Title |
---|
SIWEI WU等: "Comparisons of Different Data-Driven Modeling Techniques for Predicting Tensile Strength of X70 Pipeline Steels", 《TRANS INDIAN INST MET》, vol. 72, no. 5, pages 1277, XP036757521, DOI: 10.1007/s12666-019-01624-0 * |
杨浩: "超快冷条件下含Nb高强船板钢的组织性能调控", 《中国博士学位论文全文数据库 工 程科技Ⅰ辑》, no. 07, pages 022 - 24 * |
肖宝亮等: "高铌微合金钢高温变形流变应力预测模型", 《钢铁研究学报》, vol. 20, no. 9, pages 28 - 31 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112507542A (en) * | 2020-12-02 | 2021-03-16 | 中南大学 | Method for accurately predicting stress relaxation behavior under tensile stress and compressive stress states |
CN112507542B (en) * | 2020-12-02 | 2022-04-26 | 中南大学 | Method for accurately predicting stress relaxation behavior under tensile stress and compressive stress states |
Also Published As
Publication number | Publication date |
---|---|
CN111861041B (en) | 2023-09-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114611844B (en) | Method and system for determining alloy addition amount in converter tapping process | |
CN111310348A (en) | Material constitutive model prediction method based on PSO-LSSVM | |
GB2600213A (en) | Plate performance prediction method and apparatus | |
CN112036081B (en) | Method for determining addition amount of silicon-manganese alloy in converter tapping based on yield prediction | |
CN112651562B (en) | Laser cladding process optimization method based on signal-to-noise ratio and improved gray correlation degree | |
CN113033105B (en) | Method for predicting fatigue performance of steel material based on mechanical theory guiding transfer learning | |
CN114897227A (en) | Multi-steel-grade mechanical property forecasting method based on improved random forest algorithm | |
CN114638164B (en) | Method for predicting high-temperature creep life of power station pressure pipeline | |
CN111639820A (en) | Energy consumption parameter optimization method and system for cement kiln production | |
CN116611348A (en) | Unified parameter-free fatigue life prediction method for metal materials based on machine learning | |
CN116882585A (en) | Genetic algorithm and neural network coupled aluminum alloy hub low-pressure casting process optimization method | |
CN115146529B (en) | Method for predicting cold shot blasting reinforcement residual stress of automobile suspension spring | |
CN117494531B (en) | Medium carbon steel decarburization depth prediction method based on finite element and XGBoost algorithm | |
CN116484745A (en) | Design method of hot-rolled low-alloy steel for physical metallurgy guidance industry big data mining | |
CN111933221A (en) | Method for predicting dynamic recrystallization fraction of Nb microalloyed steel | |
CN108062583A (en) | A kind of heating furnace technique parameter optimization method towards energy-saving and emission-reduction | |
CN111861041B (en) | Method for predicting dynamic recrystallization type rheological stress of Nb microalloyed steel | |
CN112418522B (en) | Industrial heating furnace steel temperature prediction method based on three-branch integrated prediction model | |
CN116825253B (en) | Method for establishing hot rolled strip steel mechanical property prediction model based on feature selection | |
CN115394381B (en) | High-entropy alloy hardness prediction method and device based on machine learning and two-step data expansion | |
Wei et al. | High-cycle fatigue SN curve prediction of steels based on a transfer learning-guided convolutional neural network | |
CN114783540A (en) | Multi-element alloy performance prediction method based on particle swarm optimization BP neural network | |
CN115034370B (en) | BP network model-based method for predicting hearth activity of blast furnace | |
CN115081301A (en) | Dynamic carbon emission evolution method based on mixed PSO-MKPLS | |
CN117669255A (en) | Rolling bearing reliability assessment method with dynamic covariates |
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 |