CN116682505B - HRB400E steel mechanical property prediction method based on quantile regression forest - Google Patents
HRB400E steel mechanical property prediction method based on quantile regression forest Download PDFInfo
- Publication number
- CN116682505B CN116682505B CN202310707256.5A CN202310707256A CN116682505B CN 116682505 B CN116682505 B CN 116682505B CN 202310707256 A CN202310707256 A CN 202310707256A CN 116682505 B CN116682505 B CN 116682505B
- Authority
- CN
- China
- Prior art keywords
- data
- model
- quantile regression
- hrb400e
- hrb400e 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.)
- Active
Links
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 54
- 239000010959 steel Substances 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 16
- 238000005457 optimization Methods 0.000 claims abstract description 9
- 238000012360 testing method Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 6
- 238000012216 screening Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 abstract description 7
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000007637 random forest analysis Methods 0.000 abstract description 2
- 238000011161 development Methods 0.000 description 5
- 239000000463 material Substances 0.000 description 5
- 230000000052 comparative effect Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 238000005096 rolling process Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Crystallography & Structural Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Investigating Strength Of Materials By Application Of Mechanical Stress (AREA)
- Investigating And Analyzing Materials By Characteristic Methods (AREA)
Abstract
The invention discloses a HRB400E steel mechanical property prediction method based on quantile regression forest, and data sample selection; data processing; dividing data: dividing an actual data set into a training set and a testing set according to a data dividing strategy; constructing a quantile regression forest model: calculating training data by using a quantile regression forest model, and determining the optimal super-parameter combination of the model by combining a Bayesian optimization method so as to obtain a final prediction model; mechanical property prediction of HRB400E steel: and calculating the data to be predicted by using the final prediction model to obtain the mechanical property prediction value of the HRB400E steel to be predicted. According to the invention, the steps are adopted, the interval prediction is realized by introducing quantile regression into the random forest model, and the optimal parameter combination is determined by combining Bayesian optimization, so that the optimal prediction model is obtained, the production process parameters can be reversely optimized and guided, and the beneficial effect of improving the product quality is achieved.
Description
Technical Field
The invention relates to the technical field of material performance prediction, in particular to a method for predicting the mechanical properties of HRB400E steel based on quantile regression forest.
Background
Along with the continuous development of the bar, the bar is widely applied to the industrial fields of buildings, machinery, automobiles, ships and the like, wherein 70% of the bar is used as the building, and the other bar is used as various shafts, nuts and springs, so that the bar has great significance for the development of the steel industry. At present, the development of bars in China has made a great progress, not only is the production scale and the production process broken through continuously, but also the production quality of the bars in China is improved remarkably compared with the former quality, and the requirements of the bars are more and more increased along with the development of industry in China, and the requirements of the bars on the performance are more and more strict.
Compared with the common bar, the HRB400E steel mainly improves the strength and the elongation of the steel to a certain extent on the technical index, thereby enhancing the shock resistance of the steel, ensuring that the structural member has good ductility under the action of earthquake force, and establishing a mechanical property prediction model of the HRB400E steel based on the historical production data of the structural member is beneficial to optimizing the production process of the structural member and has important significance for improving the product quality.
A large number of researches show that the traditional method mainly obtains the mechanical properties of the material through experimental means, and a large amount of labor cost, time cost and the like are required. With the continuous development of machine learning, a mechanical property prediction model is established based on data, however, the conventional algorithms such as a neural network have insufficient model robustness due to unstable data during modeling, and the model precision cannot meet the requirements, so that a new method is needed for predicting the mechanical property of the model rapidly and reasonably.
Disclosure of Invention
The invention aims to provide a method for predicting the mechanical properties of HRB400E steel based on quantile regression forest, and the production process parameters can be reversely optimized and guided by accurately predicting the mechanical properties of the HRB400E steel, so that the product quality is improved.
In order to achieve the purpose, the invention provides a HRB400E steel mechanical property prediction method based on quantile regression forest, which comprises the following steps of S1, selecting a data sample: selecting HRB400E steels with the same series and different intensities, and collecting input parameters and output parameters;
s2, data processing: screening the parameter data collected in the S1, and removing abnormal values of the data in the S1 by using a Laida criterion to obtain an actual data set;
s3, data division: dividing the actual data set in the S2 into a training set and a testing set according to a data dividing strategy;
s4, constructing a quantile regression forest model: calculating training data by using a quantile regression forest model, and determining the optimal super-parameter combination of the model by combining a Bayesian optimization method so as to obtain a final prediction model of the HRB400E steel to be predicted;
s5, predicting the mechanical properties of HRB400E steel: and calculating the data to be predicted by using the final prediction model to obtain the mechanical property prediction value of the HRB400E steel to be predicted.
Preferably, in S1, the input parameters are component content and process parameters, and the output parameters are yield strength, tensile strength and elongation.
Preferably, in S2, the whole HRB400E steel data with missing input parameters is removed during screening, and otherwise, the whole HRB400E steel data is reserved.
Preferably, in S3, the dividing strategy is random arrangement or hierarchical sampling according to the performance index, and the actual data set is divided into a training set and a test set according to the ratio of 3:1.
Preferably, in S4, quantile regression is introduced to realize interval prediction,
Y θ ＝Xβ θ +ε θ
where θ is the quantile, β is the coefficient, and ε is the error.
Preferably, in S5, the binary regression forest model is trained periodically, so that the iterative optimization of the binary regression forest model maintains higher prediction accuracy.
Therefore, the HRB400E steel mechanical property prediction method based on quantile regression forest has the beneficial effects that:
1. the interval prediction is realized by introducing quantile regression into the random forest model, and the super parameters of the model are optimized in two stages by combining Bayesian optimization, so that an optimal final prediction model is obtained, and the overall view of the condition distribution of the explained variables can be more comprehensively described by introducing quantile regression, so that a reliability reference is provided for the prediction result of the final prediction model;
2. the mechanical property of the HRB400E steel can be accurately predicted by limited data quantity, the method has the advantages of high precision and quick prediction, and the quantile regression forest model can be regularly trained, so that the higher prediction precision is always kept;
3. by selecting HRB400E steel data with different component contents and technological parameters, the actual data set contains more comprehensive information of the component contents and the technological parameters, so that the established final prediction model can reflect more objective prediction rules of the mechanical properties of the HRB400E steel, and the final prediction model has wider applicability;
4. through the accurate prediction of the mechanical properties of the HRB400E steel, the input parameters can be reversely optimized and guided, so that the product quality is improved;
5. and eliminating the abnormal value of the data in the input parameters by utilizing the Laida criterion, so that the signal-to-noise ratio is improved, and the calculated amount of modeling is greatly reduced.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
FIG. 1 is a graph comparing predicted values and measured values of mechanical properties in a final prediction model and an RBF model;
FIG. 2 is a histogram of predicted and actual values correlation coefficients of a final prediction model and an RBF model;
fig. 3 is a histogram of the mean absolute error of the final prediction model and the RBF model.
Detailed Description
The technical scheme of the invention is further described below through the attached drawings and the embodiments.
Unless defined otherwise, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
Example 1
S1, selecting a data sample: and selecting the HRB400E steels with the same series and different intensities, and collecting the input parameters and the output parameters.
The input parameters are component content and technological parameters, wherein the component content specifically comprises C content, si content, mn content, P content, S content, cu content, ni content, cr content, nb content, V content, ti content, mo content, als content and the like.
The technological parameters include thickness, tapping temperature, finishing rolling temperature, finishing machine frame temperature, cooling bed head temperature, finishing rolling speed, etc.
The output parameters are yield strength YS, tensile strength TS and elongation EL.
By selecting HRB400E steel data with different component contents and technological parameters, the data samples contain more comprehensive component content and technological parameter information, so that the established model can reflect more objective HRB400E steel mechanical property prediction rules, and the model has wider applicability.
S2, data processing: and (3) screening the parameter data collected in the step (S1), removing the whole HRB400E steel data with missing input parameters during screening, and otherwise, reserving.
The rolling thickness in the initial data set is kept unchanged, the abnormal value of the data in the S1 is removed by using the Laida criterion with the rest components and the process parameters, the signal to noise ratio is improved, and the actual data set is obtained until the data quantity is not reduced any more.
S3, data division: and (3) dividing the actual data set in the step (S2) into a training set and a testing set according to a data dividing strategy, wherein the dividing strategy is randomly arranged or is sampled in a layered mode according to the performance index, and the actual data set is divided into the training set and the testing set according to the ratio of 3:1.
S4, constructing a quantile regression forest model: and calculating training data by using a quantile regression forest model, and determining the optimal super-parameter combination of the model by combining a Bayesian optimization method, so as to obtain a final prediction model of the HRB400E steel to be predicted.
The quantile regression is introduced to realize the interval prediction,
Y θ ＝Xβ θ +ε θ
where θ is the quantile, β is the coefficient, and ε is the error.
S5, predicting the mechanical properties of HRB400E steel: and calculating the data to be predicted by using the final prediction model to obtain the mechanical property prediction value of the HRB400E steel to be predicted.
Judging whether the HRB400E steel obtained under the input parameters is a qualified product or not according to the mechanical property predicted value obtained by the final prediction model, and if the mechanical property predicted value is not in the qualified range, reversely adjusting the input parameters by the final prediction model to improve the qualification rate of the finished product of the HRB400E steel.
Example 2
Complete data 3046 groups are obtained after data processing, the training set after division is 2284 groups, and the prediction set is 762 groups. Calculating training data by using a quantile regression forest model, determining the optimal super-parameter combination of the model by combining a Bayesian optimization method, analyzing input parameters of the training data, and determining the optimal coefficient of a final model to be predicted according to the mechanical property corresponding to the parameters of the input parameters, thereby obtaining the final prediction model of the HRB400E steel to be predicted.
Comparative example 1
And after data processing, obtaining complete data 3046 groups, dividing the complete data into 2284 groups as training sets and 762 groups as prediction sets, and predicting the same mechanical properties by using an RBF neural network model.
Example 3
The final prediction models obtained in example 2 and comparative example 1 were evaluated from several angles of prediction accuracy, correlation coefficient, and average absolute percentage error:
3.1 evaluation of prediction accuracy
As shown in fig. 1, in example 1, the prediction accuracy of the relative error between the predicted value and the measured value of the yield strength of the HRB400E steel to be predicted obtained by the final prediction model is up to 95.8%, the prediction accuracy of the relative error between the predicted value and the measured value of the tensile strength is up to 99.2%, and the prediction accuracy of the absolute error between the predicted value and the measured value of the elongation is up to 100% within ±4%.
As shown in fig. 1, in comparative example 1, the prediction accuracy of the relative error between the predicted value and the measured value of the yield strength of HRB400E steel to be predicted obtained by the RBF model is 89.8%, the prediction accuracy of the relative error between the predicted value and the measured value of the tensile strength is 92.8% and the prediction accuracy of the absolute error between the predicted value and the measured value of the elongation is 97% within ±6%.
3.2 evaluation of correlation coefficient
Cov(X，Y)＝E[(X-μ x )(Y-μ y )]
Wherein sigma X Standard deviation of X, sigma Y Standard deviation of Y, mu x Mean value of X, mu y And is the average value of Y, E being the desire.
As shown in fig. 2, in example 1, the correlation coefficient between the input parameter obtained by the final prediction model and the yield strength of the HRB400E steel material may reach 0.58, the correlation coefficient between the input parameter and the tensile strength of the HRB400E steel material may reach 0.32, and the correlation coefficient between the input parameter and the elongation of the HRB400E steel material may reach 0.87.
As shown in fig. 2, in comparative example 1, the correlation coefficient of the input parameter obtained by the RBF model and the yield strength of the HRB400E steel could be 0.30, the correlation coefficient with the tensile strength of the HRB400E steel could be 0.16, and the correlation coefficient with the elongation of the HRB400E steel could be 0.34.
By comparing the correlation coefficients of the two models, it can be seen that the yield strength, tensile strength and elongation of the final predicted model are more correlated with the input parameters than the RBF model.
3.3 average absolute percent error evaluation
As shown in fig. 3, the mean square error of the mechanical properties obtained by the final prediction model is: the yield strength mean square error was 0.022, the tensile strength mean square error was 0.018, and the elongation mean square error was 0.024.
As shown in fig. 3, the mean square error of the mechanical properties obtained by the RBF model is: the yield strength mean square error is 0.031, the tensile strength mean square error is 0.025, and the elongation mean square error is 0.047.
By comparing the mean square errors of the two models, it can be seen that the mean square error of the final prediction model is smaller than that of the RBF model.
In summary, the final prediction model and the RBF model can be seen that the prediction effect of the final prediction model on the mechanical properties of HRB400E steel is better than that of the RBF model.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention and not for limiting it, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that: the technical scheme of the invention can be modified or replaced by the same, and the modified technical scheme cannot deviate from the spirit and scope of the technical scheme of the invention.
Claims (5)
1. A HRB400E steel mechanical property prediction method based on quantile regression forest is characterized in that: s1, selecting a data sample: selecting HRB400E steels with the same series and different intensities, and collecting input parameters and output parameters;
s2, data processing: screening the parameter data collected in the S1, and removing abnormal values of the data in the S1 by using a Laida criterion to obtain an actual data set;
s3, data division: dividing the actual data set in the S2 into a training set and a testing set according to a data dividing strategy;
s4, constructing a quantile regression forest model: calculating training data by using a quantile regression forest model, and determining the optimal super-parameter combination of the model by combining a Bayesian optimization method so as to obtain a final prediction model of the HRB400E steel to be predicted;
s4, introducing quantile regression to realize interval prediction,
Y θ ＝Xβ θ +ε θ
wherein θ is a quantile, β is a coefficient, ε is an error;
s5, predicting the mechanical properties of HRB400E steel: and calculating the data to be predicted by using the final prediction model to obtain the mechanical property prediction value of the HRB400E steel to be predicted.
2. The method for predicting the mechanical properties of the HRB400E steel based on quantile regression forest of claim 1, which is characterized by comprising the following steps: in S1, input parameters are component content and technological parameters, and output parameters are yield strength, tensile strength and elongation.
3. The method for predicting the mechanical properties of the HRB400E steel based on quantile regression forest of claim 1, which is characterized by comprising the following steps: and S2, eliminating the whole HRB400E steel data with missing input parameters during screening, and otherwise, reserving.
4. The method for predicting the mechanical properties of the HRB400E steel based on quantile regression forest of claim 1, which is characterized by comprising the following steps: and S3, the dividing strategy is randomly arranged or is sampled in a layered mode according to the performance indexes, and the actual data set is divided into a training set and a testing set according to the ratio of 3:1.
5. The method for predicting the mechanical properties of the HRB400E steel based on quantile regression forest of claim 1, which is characterized by comprising the following steps: and S5, training the quantile regression forest model periodically to enable the model to keep higher prediction precision after iterative optimization.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310707256.5A CN116682505B (en) | 2023-06-14 | 2023-06-14 | HRB400E steel mechanical property prediction method based on quantile regression forest |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310707256.5A CN116682505B (en) | 2023-06-14 | 2023-06-14 | HRB400E steel mechanical property prediction method based on quantile regression forest |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116682505A CN116682505A (en) | 2023-09-01 |
| CN116682505B true CN116682505B (en) | 2023-11-21 |
Family
ID=87778927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310707256.5A Active CN116682505B (en) | 2023-06-14 | 2023-06-14 | HRB400E steel mechanical property prediction method based on quantile regression forest |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116682505B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014038595A (en) * | 2012-07-20 | 2014-02-27 | Jfe Steel Corp | Material prediction device and material control method for steel material |
| KR20170035118A (en) * | 2015-09-22 | 2017-03-30 | 현대제철 주식회사 | Predicting method of mechanical properties of steel material |
| CN111429979A (en) * | 2020-03-23 | 2020-07-17 | 武汉科技大学 | Steel mechanical property prediction method based on support vector machine quantile regression |
| AU2020101854A4 (en) * | 2020-08-17 | 2020-09-24 | China Communications Construction Co., Ltd. | A method for predicting concrete durability based on data mining and artificial intelligence algorithm |
| CN111985796A (en) * | 2020-08-07 | 2020-11-24 | 华中科技大学 | Method for predicting concrete structure durability based on random forest and intelligent algorithm |
| CN112100745A (en) * | 2020-09-15 | 2020-12-18 | 东北大学 | Automobile girder steel mechanical property prediction method based on LDA theory |
| CN114897227A (en) * | 2022-04-26 | 2022-08-12 | 东北大学 | Multi-steel-grade mechanical property forecasting method based on improved random forest algorithm |
| CN115081749A (en) * | 2022-07-28 | 2022-09-20 | 华中科技大学 | Bayesian optimization LSTM-based shield tunneling load advanced prediction method and system |
| CN115618751A (en) * | 2022-12-16 | 2023-01-17 | 江苏金恒信息科技股份有限公司 | Steel plate mechanical property prediction method |
| WO2023040512A1 (en) * | 2021-09-16 | 2023-03-23 | 广东辛孚科技有限公司 | Catalytic cracking unit simulation and prediction method based on molecular-level mechanism model and big data technology |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846517B (en) * | 2018-06-12 | 2021-03-16 | 清华大学 | Integration method for predicating quantile probabilistic short-term power load |
| US11436395B2 (en) * | 2018-06-27 | 2022-09-06 | Dalian University Of Technology | Method for prediction of key performance parameter of an aero-engine transition state acceleration process based on space reconstruction |
-
2023
- 2023-06-14 CN CN202310707256.5A patent/CN116682505B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014038595A (en) * | 2012-07-20 | 2014-02-27 | Jfe Steel Corp | Material prediction device and material control method for steel material |
| KR20170035118A (en) * | 2015-09-22 | 2017-03-30 | 현대제철 주식회사 | Predicting method of mechanical properties of steel material |
| CN111429979A (en) * | 2020-03-23 | 2020-07-17 | 武汉科技大学 | Steel mechanical property prediction method based on support vector machine quantile regression |
| CN111985796A (en) * | 2020-08-07 | 2020-11-24 | 华中科技大学 | Method for predicting concrete structure durability based on random forest and intelligent algorithm |
| AU2020101854A4 (en) * | 2020-08-17 | 2020-09-24 | China Communications Construction Co., Ltd. | A method for predicting concrete durability based on data mining and artificial intelligence algorithm |
| CN112100745A (en) * | 2020-09-15 | 2020-12-18 | 东北大学 | Automobile girder steel mechanical property prediction method based on LDA theory |
| WO2023040512A1 (en) * | 2021-09-16 | 2023-03-23 | 广东辛孚科技有限公司 | Catalytic cracking unit simulation and prediction method based on molecular-level mechanism model and big data technology |
| CN114897227A (en) * | 2022-04-26 | 2022-08-12 | 东北大学 | Multi-steel-grade mechanical property forecasting method based on improved random forest algorithm |
| CN115081749A (en) * | 2022-07-28 | 2022-09-20 | 华中科技大学 | Bayesian optimization LSTM-based shield tunneling load advanced prediction method and system |
| CN115618751A (en) * | 2022-12-16 | 2023-01-17 | 江苏金恒信息科技股份有限公司 | Steel plate mechanical property prediction method |
Non-Patent Citations (3)
| Title |
|---|
| 基于灰色关联分析与随机森林回归模型的短期负荷预测;张冰;周步祥;石敏;魏金萧;;水电能源科学(04);全文 * |
| 基于随机森林算法预测减压馏分油中噻吩硫化物的组成分布;任小甜;褚小立;田松柏;;石油学报(石油加工)(05);全文 * |
| 热镀锌钢卷力学性能GBDT预报模型;王伟;匡祯辉;谢少捷;白振华;;福州大学学报(自然科学版)(05);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116682505A (en) | 2023-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11475317B2 (en) | Microalloyed steel mechanical property prediction method based on globally additive model | |
| CN116501003A (en) | Processing control method and system for smelting special steel | |
| CN110929347A (en) | Hot continuous rolling strip steel convexity prediction method based on gradient lifting tree model | |
| JP2005315703A (en) | Method for predicting material in steel material | |
| CN114897227A (en) | Multi-steel-grade mechanical property forecasting method based on improved random forest algorithm | |
| CN111790762B (en) | Hot rolled strip steel rolling force setting method based on random forest | |
| CN110569566A (en) | Method for predicting mechanical property of plate strip | |
| CN111105082A (en) | Workpiece quality prediction model construction method and prediction method based on machine learning | |
| CN111563686A (en) | Cold-rolled silicon steel quality judgment method based on full-process data | |
| CN111709181B (en) | Method for predicting fault of polyester filament yarn industrial production process based on principal component analysis | |
| CN117312816B (en) | Special steel smelting effect evaluation method and system | |
| CN104376201B (en) | A kind of determination method of the key process parameter of influence alloy material mechanical property | |
| Liu et al. | Machine learning for extending capability of mechanical characterization to improve springback prediction of a quenching and partitioning steel | |
| CN116682505B (en) | HRB400E steel mechanical property prediction method based on quantile regression forest | |
| CN1625721A (en) | Method for controlling an industrial process | |
| CN116825253B (en) | Method for establishing hot rolled strip steel mechanical property prediction model based on feature selection | |
| CN108763637B (en) | Calculation and prejudgment method for tensile strength of hot-rolled wire | |
| CN112434927A (en) | Thermal power plant full-factor competitiveness index evaluation method | |
| CN116484745A (en) | Design method of hot-rolled low-alloy steel for physical metallurgy guidance industry big data mining | |
| CN113780852B (en) | Diagnosis method for quality defects in plate and strip rolling process | |
| CN115985411A (en) | Soft measurement method for polymer melt index based on Gaussian process regression model | |
| JP4365536B2 (en) | Steel production process abnormality judgment device | |
| CN110442953B (en) | Q & P steel design method based on machine learning under guidance of physical metallurgy | |
| CN116822367A (en) | IF steel mechanical property prediction method based on LSTM model | |
| CN113887089A (en) | Wire rod mechanical property prediction method and computer readable storage medium |
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 |