CN113627469A - Hot-rolled strip steel plate shape convexity prediction method based on fuzzy inference algorithm - Google Patents
Hot-rolled strip steel plate shape convexity prediction method based on fuzzy inference algorithm Download PDFInfo
- Publication number
- CN113627469A CN113627469A CN202110746849.3A CN202110746849A CN113627469A CN 113627469 A CN113627469 A CN 113627469A CN 202110746849 A CN202110746849 A CN 202110746849A CN 113627469 A CN113627469 A CN 113627469A
- Authority
- CN
- China
- Prior art keywords
- hot
- strip steel
- rolled strip
- data set
- convexity
- 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
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 51
- 239000010959 steel Substances 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 27
- 238000004519 manufacturing process Methods 0.000 claims abstract description 11
- 238000007637 random forest analysis Methods 0.000 claims abstract description 7
- 238000012216 screening Methods 0.000 claims abstract description 4
- 230000014509 gene expression Effects 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000005070 sampling Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000003066 decision tree Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000013138 pruning Methods 0.000 claims description 3
- 238000007621 cluster analysis Methods 0.000 claims description 2
- 238000005096 rolling process Methods 0.000 description 10
- 230000007246 mechanism Effects 0.000 description 9
- 238000013000 roll bending Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 3
- 238000011144 upstream manufacturing Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- 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)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Control Of Metal Rolling (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a hot-rolled strip steel plate shape convexity prediction method based on a fuzzy inference algorithm, which comprises the following steps of: s1, collecting data recorded in the production process of the hot-rolled strip steel, determining parameters influencing the strip shape convexity of the hot-rolled strip steel in the data, and constructing an original data set; s2, screening key data characteristics influencing the strip shape convexity of the hot-rolled strip steel in the original data set by using a random forest algorithm, and constructing a characteristic data set based on the key data characteristics; s3, clustering the characteristic data set by using an FCM algorithm to construct an initial fuzzy rule; s4, obtaining the prediction result of the strip shape convexity of the hot-rolled strip steel by using a Mamdani fuzzy reasoning method. The invention is convenient for practical application to industrial field to guide field production, and improves the stability and consistency of the quality of steel products.
Description
Technical Field
The invention relates to the technical field of hot-rolled strip steel production, in particular to a hot-rolled strip steel plate shape convexity prediction method based on a fuzzy reasoning algorithm.
Background
The strip shape convexity of the hot-rolled strip steel is an important factor influencing the quality of strip steel products, the online prediction of the strip shape convexity can effectively improve the quality of the hot-rolled strip steel products, and the research on a strip shape convexity prediction model has wide application prospect. Currently, methods applied to plate convexity prediction are roughly divided into two categories, namely convexity prediction based on a mechanism model and convexity prediction based on data driving.
The convexity prediction based on the mechanism model is a prediction model for obtaining convexity based on the balance relation of the principle, momentum, quality, energy and the like of steel rolling, the convexity prediction value obtained according to the model is relatively accurate, but the solving equation of the convexity to obtain the accurate convexity in the rolling process of steel production is very difficult, so that the convexity prediction method based on the mechanism model is difficult to be widely adopted in the steel rolling process.
The convexity prediction based on data driving is that a convexity prediction model is built according to field industrial data and an intelligent algorithm in the steel rolling process, and compared with a prediction method based on a mechanism model, the convexity prediction method does not need to build the mechanism model, only needs to use industrial data as model input, and outputs a corresponding convexity prediction value.
However, the data-driven convexity prediction method establishes a black box model, and field workers are difficult to correspondingly improve the rolling process according to the model, so that the quality of steel products is improved. Therefore, the convexity prediction method is not suitable for guiding field production and has limitation in popularization and application.
Disclosure of Invention
The invention aims to provide a hot-rolled strip steel plate shape convexity prediction method based on a fuzzy reasoning algorithm, and aims to solve the problems that the existing convexity prediction method is not suitable for guiding field production and has limitation in popularization and application.
In order to achieve the purpose, the invention provides the following technical scheme:
a hot-rolled strip steel plate shape convexity prediction method based on a fuzzy inference algorithm comprises the following steps:
s1, collecting data recorded in the production process of the hot-rolled strip steel, determining parameters influencing the strip shape convexity of the hot-rolled strip steel in the data, and constructing an original data set;
s2, screening key data characteristics influencing the strip shape convexity of the hot-rolled strip steel in the original data set by using a random forest algorithm, and constructing a characteristic data set based on the key data characteristics;
s3, clustering the characteristic data set by using an FCM algorithm to construct an initial fuzzy rule;
s4, obtaining the prediction result of the strip shape convexity of the hot-rolled strip steel by using a Mamdani fuzzy reasoning method.
Further, in the step S2, a random forest algorithm is used to screen key data characteristics of the original data set that affect the strip shape crown of the hot-rolled strip steel, specifically:
s21, performing replaced random sampling on the original data set to form a plurality of training sets;
s22, randomly sampling M from M data features of training set1A data feature, wherein M1<M；
S23, constructing a cart decision tree without pruning;
s24, voting by a plurality of weak learners to obtain final output, and sorting the importance of the data features;
and S25, selecting the first 15 data features as key data features.
Further, in step S3, performing cluster analysis on the feature data set by using an FCM algorithm, specifically:
s31, determining the initial clustering number C and the parameter m, and initializing the clustering center
S32, calculating an initial membership matrix U;
s33, updating the clustering center
And a membership matrix U;
s34, when max (epsilon) is less than or equal to epsilon0When the target function is updated, the updating is stopped to obtain a minimized target function;
s35, dividing the data points into a class with the maximum membership degree;
wherein max (epsilon) is the maximum difference between the membership function value of the current stage and the membership function value of the previous iteration, and epsilon0Is an error threshold.
Further, the method can be used for preparing a novel materialIn step S31, the initial cluster number C and the parameter m are determined, and the cluster center is initialized
The method specifically comprises the following steps:
s311, dividing the characteristic data set into S grids, and calculating grid density values and average densities;
s312, selecting a parameter a, leaving grids meeting the grid density value larger than a times of the average density value, and deleting other grids;
s313, selecting the grid center with the maximum density value from the left grids as a first clustering center, and calculating the density values and the average density values of the remaining grids;
s314, selecting a parameter b, selecting grids meeting the requirement that the grid density value is larger than b times of the average density value, and selecting a grid center farthest to a clustering point from the grids as a second clustering center;
s315, looping the steps S312-S314 until all grids in the grid S set are selected;
s316, determining the initial clustering number C and the parameter m, and initializing the clustering center
Compared with the prior art, the invention has the following beneficial effects:
the invention combines the advantages of a mechanism model and a data-driven convexity prediction method, and solves the contradiction between complexity and accuracy. On one hand, the fuzzy reasoning extracts rules from industrial data and constructs a reasoning system with high accuracy, the reasoning system can approach any continuous nonlinear mapping function with any precision, and output prediction data with higher precision can be obtained according to input data without mastering an accurate mechanism model of the system. On the other hand, the fuzzy reasoning introduces expert experience, fuzzy rules (if-then rules) with the same form expression as the expert rules are automatically generated from industrial data, the fuzzy reasoning system has strong interpretability relative to a black box model, the fuzzy rule mode is easy to understand by operators, managers can also effectively make decision support according to the fuzzy rule mode, and the black box model generated by data driving has stronger interpretability compared with the black box model generated by data driving.
Therefore, the method provided by the invention has the advantages that the process parameters influencing the plate shape convexity of the hot-rolled strip steel are collected, the characteristic value extraction pretreatment is carried out on the data, the initialization rule is generated through fuzzy C clustering, and finally the strip steel outlet convexity is predicted through Mamdani fuzzy reasoning, so that the method is convenient to be actually applied to industrial fields to guide field production, and the stability and the consistency of the quality of steel products are improved.
Drawings
FIG. 1 is a flow chart of a hot-rolled strip shape crown prediction method based on a fuzzy inference algorithm according to an embodiment of the present invention;
FIG. 2 is a data characteristic importance degree ranking diagram influencing the strip shape convexity of the hot-rolled strip steel provided by the embodiment of the invention;
FIG. 3 is a graph of Gaussian membership function for a fuzzy rule according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of an error of a convexity prediction result according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an error of a convexity prediction result according to an embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the following figures and embodiments:
as shown in fig. 1, a method for predicting the convexity of a hot-rolled strip shape based on a fuzzy inference algorithm comprises the following steps:
s1, collecting data recorded in the production process of the hot-rolled strip steel, determining parameters influencing the strip shape convexity of the hot-rolled strip steel in the data, and constructing an original data set;
s2, screening key data characteristics influencing the strip shape convexity of the hot-rolled strip steel in the original data set by using a random forest algorithm, and constructing a characteristic data set based on the key data characteristics;
the step S2 includes:
s21, performing replaced random sampling on the original data set to form a plurality of training sets;
s22, randomly sampling M from M data features of training set1A data feature, wherein M1<M；
S23, constructing a cart decision tree without pruning;
s24, voting by a plurality of weak learners to obtain final output, and sorting the importance of the data features;
and S25, selecting the first 15 data features as key data features.
S3, clustering the characteristic data set by using an FCM algorithm to construct an initial fuzzy rule;
in the step S3, the specific steps are:
s31, determining the initial clustering number C and the parameter m, and initializing the clustering center
In the step S31, the specific steps are:
s311, dividing the characteristic data set into S grids, and calculating grid density values and average densities;
s312, selecting a parameter a, leaving grids meeting the grid density value larger than a times of the average density value, and deleting other grids;
s313, selecting the grid center with the maximum density value from the left grids as a first clustering center, and calculating the density values and the average density values of the remaining grids;
s314, selecting a parameter b, selecting grids meeting the requirement that the grid density value is larger than b times of the average density value, and selecting a grid center farthest to a clustering point from the grids as a second clustering center;
s315, looping the steps S312-S314 until all grids in the grid S set are selected;
s316, determining the initial clustering number C and the parameter m, and initializing the clustering center
In the above step S316, the cluster center
The calculation formula of (2) is as follows:
wherein, ciIs the ith cluster center, niNumber of data points in the ith cluster, NiIs the ith cluster.
S32, calculating an initial membership matrix U;
s33, updating the clustering center
And a membership matrix U;
in the above step S33, the cluster center
And the update formula of the membership matrix U is as follows:
wherein x isjFor the j-th data point in cluster i, uijThe membership degree of the jth data point in the cluster i is defined, and the parameter m is a fuzzy index; c is the number of clustering centers, dijIs the data point xjDistance to the ith cluster center, dij＝||xj-ci||；dkjIs the distance of the data point to the kth cluster center, dkj＝||xj-ck||。
S34, when max (epsilon) is less than or equal to epsilon0When the target function is updated, the updating is stopped to obtain a minimized target function;
in the above step S34, the expression for max (∈) is:
max(ε)＝max(uij k+1-uij k) (4)
wherein max (epsilon) is the maximum difference between the membership function value of the current stage and the membership function value of the previous iteration, and epsilon0Is an error threshold.
The expression minimizing the objective function is:
s35, dividing the data points into a class with the maximum membership degree;
in step S3, an initial fuzzy rule is constructed, specifically:
wherein A is1 iIs the data point x1Corresponding fuzzy subset, A2 iIs the data point x2Corresponding fuzzy subset, siThen is the fuzzy output of the corresponding ith fuzzy rule;
the membership function value of each attribute of each rule can be solved according to a gaussian membership function, two important parameters of the gaussian membership function need to be determined according to classification conditions, namely a central value and a variance value, the central value is a clustering central value, the variance value is determined by mean square error of each data point in a cluster and the clustering center, namely the expression of the gaussian membership function is as follows:
wherein the variance value
S4, obtaining a prediction result of the plate shape convexity of the hot-rolled strip steel by using a Mamdani fuzzy reasoning method;
in step S4, the expression of the Mamdani fuzzy inference process is:
the fuzzy implication is as follows:
example one
In the embodiment, the data which influence the strip shape convexity of the hot-rolled strip and are recorded in the production process of the hot-rolled strip are collected, and 450 groups of 64-dimensional data are used for constructing an original data set.
And (3) constructing a random forest algorithm, performing feature selection on the obtained 450 groups of 64-dimensional data, completing importance ranking of each data feature, selecting the top 15 data features from output results as key data features, and constructing a feature data set based on the key data features, wherein the result is shown in fig. 2. From the results, the first 15 key factors influencing the crown are respectively a target crown, an F4 roll shifting value, an F7 roll bending force, an F1 roll shifting value, an F7 rolling speed, an F4 roll bending force, an F3 roll shifting value, an F6 outlet thickness, an F2 roll shifting value, an F6 roll shifting value, a strip steel width, an intermediate blank crown, an F6 rolling speed, an F3 roll bending force and an F6 roll bending force, the importance degree of the data features of the first 15 dimensions is accumulated to reach 66.1126% (more than 65%), and the data features can be determined as key features.
According to the sequencing of the importance degrees, the outlet convexity of the strip steel is closely related to the set target convexity when the strip steel is required to reach the set target convexity, the roll shifting value of an upstream rack and the high correlation between the roll bending force and the outlet convexity are determined by the mechanism realized by the upstream rack through convexity control, and the strip steel width and thickness are also important factors influencing the outlet convexity according to the convexity theory. Thus, the importance ranking map and the convexity mechanism are consistent.
The C-means cluster centers were blurred as shown in table 1.
TABLE 1
From the results, it was found that there were 56 group data belonging to the first category, 20 group data belonging to the second category, 64 group data belonging to the third category, 5 group data belonging to the fourth category, 35 group data belonging to the fifth category, 19 group data belonging to the sixth category, 60 group data belonging to the seventh category, 58 group data belonging to the eighth category, 24 group data belonging to the ninth category, 62 group data belonging to the tenth category, 4 group data belonging to the tenth category, and 43 group data belonging to the twelfth category.
In the present embodiment, each class has 16 membership functions, and a total of 192 membership functions, i.e., F1-1-F1-16、F2-1-F2-16、……、F12-1-F12-16. The first class of 16 membership function expressions is listed as follows:
the final fuzzy Rule number is also 12 according to 12 clusters, that is, each category corresponds to a fuzzy Rule, which is Rule1, Rule2, …, and Rule 12. The form is as follows:
IF x1 is A1 and x2 is A2…and x15 is A15,then y is B1
wherein x1 is a target crown, x2 is an F4 roll shifting value, x3 is an F7 roll bending force, x4 is an F1 roll shifting value, x5 is an F7 rolling speed, x6 is an F4 roll bending force, x7 is an F3 roll shifting value, x8 is an F6 outlet crown, x9 is an F2 roll shifting value, x10 is an F6 roll shifting value, x11 is a strip steel width, x12 is an intermediate billet crown, x13 is an F6 rolling speed, x14 is an F3 roll bending force, x15 is an F6 roll bending force, and y is an outlet crown. A1, A2, A15 and B1 are fuzzy subsets, represented by means of Gaussian membership function curves, as shown in FIG. 3.
And (3) obtaining a predicted value according to the Mamdani fuzzy reasoning, comparing the actual value and the predicted value of the strip steel outlet convexity in order to verify the obtained prediction precision, and obtaining the corresponding prediction precision result in the figures 4 and 5. In the figure, the horizontal axis is the actual value of the strip steel outlet convexity C40, the vertical axis is the value obtained by reasoning, the middle line is an angular bisector, and the two side lines are threshold lines of plus or minus 10 percent (figure 4) and plus or minus 5 percent (figure 5) respectively. According to results, the plate shape convexity prediction method based on the Mamdani fuzzy inference has feasibility, and prediction accuracy can meet the prediction accuracy requirement of a steel rolling industry field.
The foregoing is merely an example of the present invention and common general knowledge in the art of designing and/or characterizing particular aspects and/or features is not described in any greater detail herein. It should be noted that, for those skilled in the art, without departing from the technical solution of the present invention, several variations and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent. The scope of the claims of the present application shall be determined by the contents of the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.
Claims (5)
1. A hot-rolled strip steel plate shape convexity prediction method based on a fuzzy inference algorithm is characterized by comprising the following steps:
s1, collecting data recorded in the production process of the hot-rolled strip steel, determining parameters influencing the strip shape convexity of the hot-rolled strip steel in the data, and constructing an original data set;
s2, screening key data characteristics influencing the strip shape convexity of the hot-rolled strip steel in the original data set by using a random forest algorithm, and constructing a characteristic data set based on the key data characteristics;
s3, clustering the characteristic data set by using an FCM algorithm to construct an initial fuzzy rule;
s4, obtaining the prediction result of the strip shape convexity of the hot-rolled strip steel by using a Mamdani fuzzy reasoning method.
2. The method for predicting the strip shape convexity of the hot-rolled strip steel based on the fuzzy inference algorithm as claimed in claim 1, wherein in the step S2, the key data characteristics influencing the strip shape convexity of the hot-rolled strip steel in the original data set are screened by using a random forest algorithm, and specifically the method comprises the following steps:
s21, performing replaced random sampling on the original data set to form a plurality of training sets;
s22, randomly sampling M from M data features of training set1A data feature, wherein M1<M；
S23, constructing a cart decision tree without pruning;
s24, voting by a plurality of weak learners to obtain final output, and sorting the importance of the data features;
and S25, selecting the first 15 data features as key data features.
3. The method for predicting the crown of the hot-rolled strip steel plate based on the fuzzy inference algorithm as claimed in claim 2, wherein in the step S3, the FCM algorithm is used for performing cluster analysis on the characteristic data set, specifically:
s31, determining the initial clustering number C and the parameter m, and initializing the clustering center
S32, calculating an initial membership matrix U;
s33, updating the clustering center
And a membership matrix U;
s34, when max (epsilon) is less than or equal to epsilon0When the target function is updated, the updating is stopped to obtain a minimized target function;
s35, dividing the data points into a class with the maximum membership degree;
wherein max (epsilon) is the maximum difference between the membership function value of the current stage and the membership function value of the previous iteration, and epsilon0Is an error threshold.
4. The method for predicting the crown of the hot-rolled strip steel plate based on the fuzzy inference algorithm as claimed in claim 3, wherein in the step S31, the initial cluster number C and the parameter m are determined, and the cluster center C is initialized, specifically:
s311, dividing the characteristic data set into S grids, and calculating grid density values and average densities;
s312, selecting a parameter a, leaving grids meeting the grid density value larger than a times of the average density value, and deleting other grids;
s313, selecting the grid center with the maximum density value from the left grids as a first clustering center, and calculating the density values and the average density values of the remaining grids;
s314, selecting a parameter b, selecting grids meeting the requirement that the grid density value is larger than b times of the average density value, and selecting a grid center farthest to a clustering point from the grids as a second clustering center;
s315, looping the steps S312-S314 until all grids in the grid S set are selected;
s316, determining the initial clustering number C and the parameter m, and initializing the clustering center
5. The method for predicting the crown of the hot-rolled strip steel plate based on the fuzzy inference algorithm as claimed in claim 1, wherein in the step S4, the expression of the Mamdani fuzzy inference process is as follows:
the fuzzy implication is as follows:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110746849.3A CN113627469B (en) | 2021-07-01 | 2021-07-01 | Hot rolled strip steel plate convexity prediction method based on fuzzy reasoning algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110746849.3A CN113627469B (en) | 2021-07-01 | 2021-07-01 | Hot rolled strip steel plate convexity prediction method based on fuzzy reasoning algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113627469A true CN113627469A (en) | 2021-11-09 |
| CN113627469B CN113627469B (en) | 2024-02-09 |
Family
ID=78378947
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110746849.3A Active CN113627469B (en) | 2021-07-01 | 2021-07-01 | Hot rolled strip steel plate convexity prediction method based on fuzzy reasoning algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113627469B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06142729A (en) * | 1992-10-30 | 1994-05-24 | Toshiba Corp | Plate crown controller for rolled stock |
| EP0901053A1 (en) * | 1997-09-04 | 1999-03-10 | Rijksuniversiteit te Groningen | Method for modelling and/or controlling a production process using a neural network and controller for a production process |
| US20030005258A1 (en) * | 2001-03-22 | 2003-01-02 | Modha Dharmendra Shantilal | Feature weighting in k-means clustering |
| US20040024750A1 (en) * | 2002-07-31 | 2004-02-05 | Ulyanov Sergei V. | Intelligent mechatronic control suspension system based on quantum soft computing |
| CN102069094A (en) * | 2010-11-16 | 2011-05-25 | 北京首钢自动化信息技术有限公司 | Data mining-based plate shape control key process parameter optimization system |
| WO2012000648A1 (en) * | 2010-06-28 | 2012-01-05 | Precitec Kg | Method for closed-loop controlling a laser processing operation and laser material processing head using the same |
| CN108268979A (en) * | 2018-02-01 | 2018-07-10 | 北京科技大学 | A kind of cut deal qualitative forecasting method based on evolution fuzzy association rules |
| CN108637020A (en) * | 2018-05-09 | 2018-10-12 | 北京科技大学 | A kind of TSP question PSO-BP neural networks strip profile prediction technique |
| CN110929347A (en) * | 2019-10-25 | 2020-03-27 | 东北大学 | Hot continuous rolling strip steel convexity prediction method based on gradient lifting tree model |
-
2021
- 2021-07-01 CN CN202110746849.3A patent/CN113627469B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06142729A (en) * | 1992-10-30 | 1994-05-24 | Toshiba Corp | Plate crown controller for rolled stock |
| EP0901053A1 (en) * | 1997-09-04 | 1999-03-10 | Rijksuniversiteit te Groningen | Method for modelling and/or controlling a production process using a neural network and controller for a production process |
| US20030005258A1 (en) * | 2001-03-22 | 2003-01-02 | Modha Dharmendra Shantilal | Feature weighting in k-means clustering |
| US20040024750A1 (en) * | 2002-07-31 | 2004-02-05 | Ulyanov Sergei V. | Intelligent mechatronic control suspension system based on quantum soft computing |
| WO2012000648A1 (en) * | 2010-06-28 | 2012-01-05 | Precitec Kg | Method for closed-loop controlling a laser processing operation and laser material processing head using the same |
| CN102069094A (en) * | 2010-11-16 | 2011-05-25 | 北京首钢自动化信息技术有限公司 | Data mining-based plate shape control key process parameter optimization system |
| CN108268979A (en) * | 2018-02-01 | 2018-07-10 | 北京科技大学 | A kind of cut deal qualitative forecasting method based on evolution fuzzy association rules |
| CN108637020A (en) * | 2018-05-09 | 2018-10-12 | 北京科技大学 | A kind of TSP question PSO-BP neural networks strip profile prediction technique |
| CN110929347A (en) * | 2019-10-25 | 2020-03-27 | 东北大学 | Hot continuous rolling strip steel convexity prediction method based on gradient lifting tree model |
Non-Patent Citations (3)
| Title |
|---|
| JOSÉ ANGEL BARRIOS等: "Fuzzy C-means Rule Generation for Fuzzy Entry Temperature Prediction in a Hot Strip Mill", 《JOURNAL OF IRON AND STEEL RESEARCH INTERNATIONAL VOLUME 》, vol. 23, pages 116 - 123, XP029412528, DOI: 10.1016/S1006-706X(16)30022-X * |
| 孙智勇: "基于模糊控制的中厚板轧辊凸度控制研究与设计", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》, no. 7, pages 140 - 335 * |
| 陈胜利等: "一个轧制单元内实时辊系综合凸度预测及应用", 《机械工程学报》, vol. 53, no. 2, pages 61 - 66 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113627469B (en) | 2024-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sun et al. | Prediction of stock index futures prices based on fuzzy sets and multivariate fuzzy time series | |
| Chang et al. | Intelligent control for modeling of real‐time reservoir operation, part II: artificial neural network with operating rule curves | |
| CN106779087A (en) | A kind of general-purpose machinery learning data analysis platform | |
| CN105976049A (en) | Chaotic neural network-based inventory prediction model and construction method thereof | |
| CN106355192A (en) | Support vector machine method based on chaos and grey wolf optimization | |
| Qiu et al. | A new approach for multiple attribute group decision making with interval-valued intuitionistic fuzzy information | |
| CN101599138A (en) | Land evaluation method based on artificial neural network | |
| CN105976070A (en) | Key-element-based matrix decomposition and fine tuning method | |
| CN106529818A (en) | Water quality evaluation prediction method based on fuzzy wavelet neural network | |
| CN106845012A (en) | A kind of blast furnace gas system model membership function based on multiple target Density Clustering determines method | |
| CN111461921B (en) | Load modeling typical user database updating method based on machine learning | |
| CN106778838A (en) | A kind of method for predicting air quality | |
| CN113128124B (en) | Multi-grade C-Mn steel mechanical property prediction method based on improved neural network | |
| CN109697566A (en) | Electronic product processing technology evaluation system and its evaluation method | |
| CN105404142B (en) | Aluminium electroloysis multi parameters control method based on BP neural network Yu MBFO algorithms | |
| Chou et al. | Takagi-Sugeno-Kang type collaborative fuzzy rule based system | |
| CN109085752A (en) | Aluminium electroloysis preference multi-objective optimization algorithm based on angle dominance relation | |
| Wang et al. | A new approach of obtaining reservoir operation rules: Artificial immune recognition system | |
| Van Tinh et al. | A new hybrid fuzzy time series forecasting model based on combining fuzzy c-means clustering and particle swam optimization | |
| Saleh et al. | Implementation of equal width interval discretization on smarter method for selecting computer laboratory assistant | |
| CN113627469A (en) | Hot-rolled strip steel plate shape convexity prediction method based on fuzzy inference algorithm | |
| CN111401638B (en) | Spatial load prediction method based on extreme learning machine and load density index method | |
| CN109086469A (en) | Aluminium electroloysis modeling and optimization method based on recurrent neural network and preference information | |
| dos Santos et al. | Decision support systems in multicriteria groups: An approach based on fuzzy rules | |
| CN113158389B (en) | Medium-voltage distribution network feeder line classification method based on machine learning algorithm |
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 |