CN114329940A - Continuous casting billet quality prediction method based on extreme learning machine - Google Patents
Continuous casting billet quality prediction method based on extreme learning machine Download PDFInfo
- Publication number
- CN114329940A CN114329940A CN202111588992.0A CN202111588992A CN114329940A CN 114329940 A CN114329940 A CN 114329940A CN 202111588992 A CN202111588992 A CN 202111588992A CN 114329940 A CN114329940 A CN 114329940A
- Authority
- CN
- China
- Prior art keywords
- continuous casting
- casting billet
- learning machine
- extreme learning
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- 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
- 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
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Continuous Casting (AREA)
Abstract
The invention provides a continuous casting billet quality prediction method based on an extreme learning machine, and belongs to the technical field of ferrous metallurgy. The method comprises the steps of firstly collecting data related to actual production of the continuous casting billet, finding out influencing factors influencing the quality of the continuous casting billet, then preprocessing selected sample data, determining the number of input nodes and the number of output nodes counted by the extreme learning machine according to the data, then inputting a training data set into the extreme learning machine to finish training of the extreme learning machine, and finally inputting residual sample data to finish defect grade classification of the quality of the continuous casting billet. The method has the advantages of high training speed, high prediction precision and better adaptability, and the prediction precision and the operation speed of the continuous casting billet quality prediction model based on a statistical method, an expert system, a BP neural network and the like are obviously improved, so that the quality of the continuous casting billet can be timely and accurately judged.
Description
The application is a divisional application of a patent application named as 'a continuous casting billet quality prediction method based on an extreme learning machine', the application date of the original application is 2018, 02 and 05, and the application number is 201810109564.7.
Technical Field
The invention relates to the technical field of ferrous metallurgy, in particular to a continuous casting billet quality prediction method based on an extreme learning machine.
Background
In recent decades, with the rapid development of steel enterprises, the hot charging and hot delivery of continuous casting billets and the direct rolling technology make continuous casting steel become the most active research field of the steel enterprises, and the development of the technology not only greatly reduces the production cost and the investment of equipment of steel, but also improves the competitiveness of products. However, the current continuous casting technology cannot completely eliminate the defects, so that the defects are inevitably generated in the subsequent hot charging, hot feeding and direct rolling processes, thereby affecting the quality of steel products. If the continuous casting billets with the defects can be judged in time and sorted off line, the quality of the continuous casting billets/products can be improved, and the continuous production in the continuous casting-continuous rolling process is facilitated. How to accurately forecast and detect the quality of a casting blank in time is an important problem to be solved urgently in the sustainable development process of iron and steel enterprises.
At present, methods for predicting the quality of continuous casting slabs mainly comprise statistical methods and non-statistical methods, wherein the statistical methods comprise the following steps: linear regression, non-linear regression, etc., and non-statistical methods include: expert systems, BP neural networks, etc. In the production process of the continuous casting blank, molten steel undergoes a series of complex physical and chemical changes such as solidification, crystallization, phase change and the like, the related production equipment and parameters are numerous, and each influencing factor and the continuous casting blank defect show a strong nonlinear relationship. The continuous casting billet quality prediction model established based on the statistical method has weak adaptability and generalization capability, and has certain limitation on the continuous casting billet quality prediction of the current steel enterprises in multiple steel grades and small-batch production modes; the continuous casting quality prediction model based on the non-statistical method has strong adaptability and generalization capability, and due to the fact that the influence on the continuous casting quality is numerous, and strong nonlinear relations exist between various influencing factors and the continuous casting defects, the problem can be well solved through strong nonlinear approximation capability of the artificial neural network, and the BP neural network is one of the most widely applied neural networks at present. Similarly, the method is also successfully applied to the continuous casting billet quality prediction in the field of steel. However, the model established based on the method needs to consume a lot of time in the training process, is easy to fall into a local optimal value, needs to set a lot of network training parameters in the training process, has low prediction precision, is difficult to rapidly and timely judge the quality of the continuous casting billet of the iron and steel enterprise, and is not beneficial to the high-efficiency production of the high-quality steel of the iron and steel enterprise. Therefore, the method for predicting the quality of the continuous casting billet, which has strong adaptability, high operation rate and high prediction accuracy, is developed, and has important significance for improving the automatic control level of the narrow window of the quality of the continuous casting billet in the steelmaking-continuous casting process.
Disclosure of Invention
The invention aims to provide a continuous casting billet quality prediction method based on an extreme learning machine.
In order to achieve the aim, the invention provides a continuous casting billet quality prediction method based on an extreme learning machine, which comprises the following specific steps:
step 1: selecting input variables of the extreme learning machine: according to the influence factors of the continuous casting billet quality and the continuous casting billet defects, correlation analysis is carried out by using Pearson correlation coefficients, and the influence factors influencing the continuous casting billet quality are determined; the defects of the continuous casting slab comprise center porosity, center segregation and shrinkage cavity;
step 2: acquiring influence factor data of the quality of the continuous casting billet, preprocessing the influence factor data, determining the number of input nodes and the number of output nodes of an extreme learning machine, determining a used sample data set, and establishing a model;
and step 3: normalizing the input data of the extreme learning machine, creating a classification label for the defect grade of the continuous casting billet corresponding to the sample, and selecting two thirds of the collected sample data to input into the extreme learning machine to finish training of the extreme learning machine;
and 4, step 4: inputting the remaining one third of sample data to the extreme learning machine, verifying the accuracy of the model, and setting reasonable hidden layer node number and hidden layer activation function based on the training fitting degree and the defect grade judgment accuracy of the extreme learning machine so as to ensure the optimization of the network structure and complete the defect grade classification of the continuous casting billet quality;
the process operation time for judging the defect grade by the method is 0.1 s;
the data preprocessing method in the step 2 is to preprocess abnormal data through the technology of elimination and data smoothing;
selecting the historical data in the step 3 to randomly select two thirds of sample data;
the method utilizes an industrial control computer and a process database to realize the real-time forecast of the quality of the continuous casting billet; the industrial control computer is used for judging and feeding back the quality of the continuous casting billet in real time; the process database is connected with the industrial control computer and used for collecting and recording the production process data of the continuous casting billet in real time and providing data support for the operation of the industrial control computer.
Optionally, the normalization processing selection range of the data in the step 3 is [0.1, 0.9], the classification accuracy of the extreme learning machine on the defect level of the continuous casting billet is influenced due to the large difference of the order of magnitude among the variable data, and the normalization range of the data is [0.1, 0.9], so that the influence of the large difference of the order of magnitude of the data on the prediction accuracy of the continuous casting billet quality prediction model based on the extreme learning machine can be avoided, and the original information of the variable data can be maintained.
Optionally, the process database collects and records the casting time information in real time after the pouring of the molten steel in the tundish is started; the casting frequency information comprises: tundish molten steel composition, crystallizer equipment and process parameters, and molten steel temperature.
Optionally, the building of the whole model in step 2 includes: model training, model verification and model parameter selection.
Optionally, the method further comprises:
and 5: predicting a classification result based on an extreme learning machine, and sorting and offline the defective continuous casting billet in time if the defective continuous casting billet is judged; if judge that continuous casting billet quality is normal continuous casting billet, the continuous casting billet can directly get into next process.
The method utilizes an industrial control computer and a process database to realize the real-time forecast of the quality of the continuous casting billet, wherein the industrial control computer is used for judging and feeding back the quality of the continuous casting billet in real time; the process database is connected with the industrial control computer and is used for collecting and recording the production process data of the continuous casting billet in real time and providing data support for the operation of the industrial control computer.
The technical scheme of the invention has the following beneficial effects:
in the scheme, the problems that a continuous casting billet quality prediction model based on a statistical method, an expert system, a BP neural network and the like is poor in adaptability, long in training time and prone to falling into a local optimal value can be avoided, a large number of neural network parameters and optimal network structure parameters are not required to be set in the training process, and the classification precision and the operation rate of the continuous casting billet quality judgment model are obviously improved.
The method classifies the defect levels of the continuous casting billets through the extreme learning machine, only needs to set the number of nodes of the hidden layer of the network without adjusting the input weight of the network and the bias of the hidden layer in the training process to generate a unique optimal solution, and the model has the advantages of high training speed, high prediction precision and better adaptability.
Drawings
FIG. 1 is a schematic diagram showing the construction of a continuous casting billet quality prediction method based on an extreme learning machine according to the present invention;
FIG. 2 is a flow chart of the calculation of each operation module of the industrial control computer according to the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantages of the present invention more apparent, the following detailed description is given with reference to the accompanying drawings and specific embodiments.
The invention provides a continuous casting billet quality prediction method based on an extreme learning machine, which is a schematic composition diagram of the method as shown in figure 1.
As shown in fig. 2, the method comprises the following specific steps:
(1) selecting input variables of the extreme learning machine: according to the influence factors of the continuous casting billet quality and the continuous casting billet defects, correlation analysis is carried out by using Pearson correlation coefficients, and the influence factors influencing the continuous casting billet quality are found;
(2) acquiring influence factor data of the quality of the continuous casting billet, preprocessing the data, determining the number of input nodes and the number of output nodes of an extreme learning machine, determining used sample data, and establishing a model;
(3) normalizing the input data of the extreme learning machine, and selecting two thirds of the collected sample data to input into the extreme learning machine to finish training the extreme learning machine;
(4) and inputting the remaining one third of sample data into the extreme learning machine, verifying the accuracy of the model, and finishing the defect grade classification of the quality of the continuous casting billet.
In specific application, the effectiveness of the model is verified mainly through three typical defects (center porosity, center segregation and shrinkage cavity) of the 180mm x 180mm continuous casting square billet 60Si2Mn spring steel of a certain domestic special steel mill. Firstly, carrying out prediction processing and correlation analysis on collected sample data to determine required data of the model; secondly, using two thirds of data samples to establish a continuous casting billet quality prediction model based on an extreme learning machine, and then using the established model to process one third of data samples to be classified; and finally, judging the recognition result according to the output of the model, comparing the recognition result with the actual result to obtain a conclusion, and counting the time required by the model operation. In the training process, a large number of neural network structure parameters are not required to be set, the optimal solution of the model can be obtained only by selecting and determining the appropriate number of the hidden layer nodes, and the operation speed and the classification accuracy of the model are greatly improved.
The specific application process is as follows:
(1) Firstly, producing a continuous casting billet 60Si with the thickness of 180mm multiplied by 180mm for a certain domestic special steel mill2And collecting historical data of the Mn spring steel, and determining an influence factor set influencing the quality of the continuous casting billet. The invention takes three typical defects of center porosity, center segregation and shrinkage cavity defects of a continuous casting slab as examples, and determines the number of input variables of a model by applying Pearson correlation coefficients to acquired data to perform correlation analysis and inductive summary of professor Chuisekoni.
(2) And preprocessing the data of the factors influencing the quality of the continuous casting billet, preprocessing the abnormal data and determining a final sample data set.
(3) And (3) carrying out normalization processing on the obtained data sample set, wherein the data normalization range is [0.1, 0.9], and meanwhile, establishing a classification label for the continuous casting blank defect grade corresponding to the sample.
(4) And (3) constructing an extreme learning machine, randomly selecting two thirds of data to train the model according to the data processed in the step (3), verifying the effectiveness of the model by the remaining one third of data, and setting a reasonable number of hidden layer nodes and a hidden layer activation function by comprehensively considering the training fitting degree and the defect grade judgment accuracy of the extreme learning machine.
(5) After pouring of the molten steel in the tundish is started, a database system collects and records pouring time information (molten steel composition of the tundish, crystallizer equipment and process parameters, molten steel temperature data and the like) in real time, normalization processing is carried out on the obtained data, the data processing range is [0.1, 0.9], and an industrial control computer inputs the data into a well-established continuous casting billet quality prediction model based on an extreme learning machine according to the data provided by the process database system to carry out real-time judgment and classification on three typical defects (center porosity, center segregation and shrinkage cavity)) of spring steel produced on site.
(6) And predicting a classification result according to the extreme learning machine. If the defect continuous casting billet is judged, sorting the defective continuous casting billet in time and unloading the defective continuous casting billet; if the judged quality of the continuous casting billet is normal, the continuous casting billet can directly enter the next procedure; not only provide auxiliary information for operating personnel control continuous casting billet quality, can provide the basis for operating personnel's continuous casting billet quality judgement simultaneously.
The invention provides a continuous casting billet quality prediction model based on an extreme learning machine, which is applied to 60Si of a certain domestic steel mill2The grade classification and quality evaluation of the defects of the Mn spring steel continuous casting billet with the thickness of 180mm multiplied by 180mm are carried out, the typical defect grade defects in three types of center porosity, center segregation and shrinkage cavity of the continuous casting billet in the steel mill are judged as examples to illustrate the test effect of the invention, the test results after the implementation of the invention are shown in table 1, and the results show that: compared with a continuous casting billet quality prediction model based on a statistical method, an expert system and a BP neural network, the continuous casting billet quality prediction model based on the extreme learning machine further improves the classification accuracy and the operation rate of three defects of center porosity, center segregation and shrinkage cavity, the classification accuracy of three typical defects of center porosity, center segregation and shrinkage cavity of the continuous casting billet can respectively reach 85%, 82.5% and 70%, and the operation speed of the method in the process of judging the defect grade is very high and only needs 0.1 s. The method provided by the invention can be used for rapidly and efficiently judging the quality of the continuous casting billet, so that an operator is assisted to accurately control the quality of the continuous casting billet, and the control level of the quality of the continuous casting billet is continuously improved.
Table 1 test results after the practice of the invention:
note: because the extreme learning machine needs to set a classification label, the '1' in the table is a normal continuous casting billet, the '2' in the table is a continuous casting billet defect grade of 0.5, the '3' in the table is a continuous casting billet defect grade of 1.0, the '4' in the table is a continuous casting billet defect grade of 1.5, and the '5' in the table is a continuous casting billet defect grade of 2.0. The defect grade of the continuous casting billet is increased from small to large, which indicates that the defect grade is more and more serious.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (5)
1. A continuous casting billet quality prediction method based on an extreme learning machine is characterized by comprising the following specific steps:
step 1: selecting input variables of the extreme learning machine: according to the influence factors of the continuous casting billet quality and the continuous casting billet defects, correlation analysis is carried out by using Pearson correlation coefficients, and the influence factors influencing the continuous casting billet quality are determined; the defects of the continuous casting slab comprise center porosity, center segregation and shrinkage cavity;
step 2: acquiring influence factor data of the quality of the continuous casting billet, preprocessing the influence factor data, determining the number of input nodes and the number of output nodes of an extreme learning machine, determining a used sample data set, and establishing a model;
and step 3: normalizing the input data of the extreme learning machine, creating a classification label for the defect grade of the continuous casting billet corresponding to the sample, and selecting two thirds of the collected sample data to input into the extreme learning machine to finish training of the extreme learning machine;
and 4, step 4: inputting the remaining one third of sample data to the extreme learning machine, verifying the accuracy of the model, and setting reasonable hidden layer node number and hidden layer activation function based on the training fitting degree and the defect grade judgment accuracy of the extreme learning machine so as to ensure the optimization of the network structure and complete the defect grade classification of the continuous casting billet quality;
the process operation time for judging the defect grade by the method is 0.1 s;
the data preprocessing method in the step 2 is to preprocess abnormal data through the technology of elimination and data smoothing;
selecting the historical data in the step 3 to randomly select two thirds of sample data;
the method utilizes an industrial control computer and a process database to realize the real-time forecast of the quality of the continuous casting billet; the industrial control computer is used for judging and feeding back the quality of the continuous casting billet in real time; the process database is connected with the industrial control computer and used for collecting and recording the production process data of the continuous casting billet in real time and providing data support for the operation of the industrial control computer.
2. The extreme learning machine-based continuous casting billet quality prediction method according to claim 1, wherein the normalization processing of the data in the step 3 is selected within a range of [0.1, 0.9] so as to avoid the influence of large difference of data magnitude on the prediction accuracy of the extreme learning machine-based continuous casting billet quality prediction model, and maintain the original information of each variable data.
3. The extreme learning machine-based continuous casting billet quality prediction method according to claim 1, characterized in that the process database collects and records the casting time information in real time after the pouring of the molten steel in the tundish is started; the casting frequency information comprises: tundish molten steel composition, crystallizer equipment and process parameters, and molten steel temperature.
4. The extreme learning machine-based slab quality prediction method according to claim 1, wherein the establishment of the whole model in the step 2 comprises: model training, model verification and parameter selection of the model.
5. The extreme learning machine-based slab quality prediction method according to claim 1, further comprising:
and 5: predicting a classification result based on an extreme learning machine, and sorting and offline the defective continuous casting billet in time if the defective continuous casting billet is judged; if judge that continuous casting billet quality is normal continuous casting billet, the continuous casting billet can directly get into next process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111588992.0A CN114329940A (en) | 2018-02-05 | 2018-02-05 | Continuous casting billet quality prediction method based on extreme learning machine |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810109564.7A CN108256260A (en) | 2018-02-05 | 2018-02-05 | A kind of continuous casting billet quality Forecasting Methodology based on extreme learning machine |
| CN202111588992.0A CN114329940A (en) | 2018-02-05 | 2018-02-05 | Continuous casting billet quality prediction method based on extreme learning machine |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810109564.7A Division CN108256260A (en) | 2018-02-05 | 2018-02-05 | A kind of continuous casting billet quality Forecasting Methodology based on extreme learning machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114329940A true CN114329940A (en) | 2022-04-12 |
Family
ID=62743703
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111588992.0A Pending CN114329940A (en) | 2018-02-05 | 2018-02-05 | Continuous casting billet quality prediction method based on extreme learning machine |
| CN201810109564.7A Pending CN108256260A (en) | 2018-02-05 | 2018-02-05 | A kind of continuous casting billet quality Forecasting Methodology based on extreme learning machine |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810109564.7A Pending CN108256260A (en) | 2018-02-05 | 2018-02-05 | A kind of continuous casting billet quality Forecasting Methodology based on extreme learning machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN114329940A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116449788A (en) * | 2023-05-30 | 2023-07-18 | 湖南科技大学 | Fault detection and productivity optimization method for casting blank production process of steel mill |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109240929A (en) * | 2018-09-18 | 2019-01-18 | 百度在线网络技术（北京）有限公司 | Software quality prediction method, apparatus, terminal and computer readable storage medium |
| CN109234491A (en) * | 2018-11-20 | 2019-01-18 | 北京科技大学 | A kind of BOF Steelmaking Endpoint manganese content prediction technique based on extreme learning machine |
| CN109252009A (en) * | 2018-11-20 | 2019-01-22 | 北京科技大学 | BOF Steelmaking Endpoint manganese content prediction technique based on regularization extreme learning machine |
| CN109359723A (en) * | 2018-11-20 | 2019-02-19 | 北京科技大学 | Based on the converter terminal manganese content prediction technique for improving regularization extreme learning machine |
| CN110930065A (en) * | 2019-12-09 | 2020-03-27 | 马鞍山钢铁股份有限公司 | Casting blank quality determination method and system |
| CN110991916A (en) * | 2019-12-10 | 2020-04-10 | 马鞍山钢铁股份有限公司 | Casting blank quality judgment system and method |
| CN112418538A (en) * | 2020-11-30 | 2021-02-26 | 武汉科技大学 | Continuous casting billet inclusion prediction method based on random forest classification |
| CN112862331A (en) * | 2021-02-20 | 2021-05-28 | 同济大学 | Semiconductor manufacturing system feeding control method and system based on attribute selection |
| CN113705101A (en) * | 2021-08-31 | 2021-11-26 | 南京工业大学 | Aluminum alloy speed reducer shell casting parameter design method based on extreme learning machine |
| CN116186936B (en) * | 2023-03-01 | 2024-03-22 | 华院计算技术(上海)股份有限公司 | Method, system, equipment and medium for determining continuous casting process parameters |
| CN116579650B (en) * | 2023-04-28 | 2024-04-26 | 华院计算技术(上海)股份有限公司 | Continuous casting quality judging method and device, computer readable storage medium and terminal |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1936370A1 (en) * | 2006-12-22 | 2008-06-25 | Max-Planck-Gesellschaft zur Förderung der Wissenschaften e.V. | Determination and prediction of the expression of traits of plants from the metabolite profile as a biomarker |
| WO2009030870A1 (en) * | 2007-09-05 | 2009-03-12 | University Of Leeds | Multi phase flow measurement system |
| CN104651559B (en) * | 2015-01-30 | 2017-01-11 | 东北大学 | Blast furnace liquid iron quality online forecasting system and method based on multivariable online sequential extreme learning machine |
| CN104657602A (en) * | 2015-02-02 | 2015-05-27 | 北京科技大学 | Method and system for forecasting thickness of band steel in hot continuous rolling production process |
| CN107016454B (en) * | 2017-01-23 | 2018-06-01 | 中南大学 | A kind of heterogeneous ore deposit ball mill crushing distribution function Forecasting Methodology |
| CN107193055B (en) * | 2017-05-27 | 2019-10-18 | 中国地质大学（武汉） | A kind of complicated geological drilling process Double-layer intelligent drilling speed modeling |
-
2018
- 2018-02-05 CN CN202111588992.0A patent/CN114329940A/en active Pending
- 2018-02-05 CN CN201810109564.7A patent/CN108256260A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116449788A (en) * | 2023-05-30 | 2023-07-18 | 湖南科技大学 | Fault detection and productivity optimization method for casting blank production process of steel mill |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108256260A (en) | 2018-07-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114329940A (en) | Continuous casting billet quality prediction method based on extreme learning machine | |
| CN104751288B (en) | A kind of coil of strip segmentation online quality judging system and method for multidimensional | |
| Cemernek et al. | Machine learning in continuous casting of steel: A state-of-the-art survey | |
| CN107179749A (en) | Hot dip zinc product whole process method of quality control | |
| CN106345823A (en) | On-line real-time mechanical property prediction method based on hot rolled steel coil production processes | |
| CN111209967A (en) | Rolling process plate convexity prediction method based on support vector machine | |
| CN112418538A (en) | Continuous casting billet inclusion prediction method based on random forest classification | |
| CN116307289A (en) | Textile processing procedure parameter detection and prediction method, system and storage medium | |
| CN111676365A (en) | LSTM-based method for predicting annealing temperature set value of transition steel coil | |
| CN111950577A (en) | Point inspection method and device | |
| CN110287456A (en) | Bulk lots volume rolled surface defect analysis method based on data mining | |
| CN115169453A (en) | Hot continuous rolling width prediction method based on density clustering and depth residual error network | |
| CN115815345A (en) | Mechanism collaborative prediction method and system for predicting mechanical property of full-flow hot-rolled strip steel | |
| CN112418522B (en) | Industrial heating furnace steel temperature prediction method based on three-branch integrated prediction model | |
| CN114386679A (en) | Ball mill energy consumption state monitoring method based on ensemble learning | |
| CN112580951B (en) | Urban ground bus operation monitoring key index screening method based on passenger travel | |
| CN109920489A (en) | It is a kind of that model and method for building up are hydrocracked based on Lasso-CCF-CNN | |
| US20240002964A1 (en) | Method and system for determining converter tapping quantity | |
| CN108364095B (en) | Molten steel quality diagnosis method in steelmaking production process based on data mining | |
| NL2030465B1 (en) | Continuous casting slab quality predicting method based on extreme learning machine | |
| Rojek et al. | Methods of computational intelligence in the context of quality assurance in foundry products | |
| CN114971064A (en) | Hot-rolled strip steel surface defect prediction method based on NGboost algorithm | |
| CN106959668A (en) | A kind of mechanical production devices cutting state identification and data processing method method | |
| CN114266286A (en) | Online detection method and device for welding process information | |
| CN115034370B (en) | BP network model-based method for predicting hearth activity of blast furnace |
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 |