连铸
 
             Home | About Journal | Editorial Board | Instruction for Authors | Subscriptions | Advertisement | Contacts Us | Chinese
 
 

Office Online

 
   Author Center
   Peer Review
   Editor Work
   Office Work
   Editor-in-chief
 

Journal Online

 
   Forthcoming Articles
   Current Issue
   Archive
   Read Articles
   Download Articles
   Email Alert
   
 
Quick Search  
  Advanced Search
 
2022 Vol.  41 No.  6
Published: 2022-12-18

CONTINUOUS CASTING
Strand Quality
Continuous Casting Equipment
Technology Exchange
1 ZHANG Li-qiang, LI Yi-hong
Preface
2022 Vol. 41 (6): 1-1 [Abstract] ( 91 ) [HTML 1KB] [PDF 293KB] ( 448 )
Continuous Casting
2 ZHANG Kai-tian, ZHENG Zhong, ZHU Ming-mei, LIN Hong-yu, JIANG Kun-chi
Co-optimization method of casting speed-cooling water in an unsteady continuous casting process
Aiming at the problem that abnormal cooling intensity in unsteady continuous casting is easy to lead to defects in slab quality, an improved genetic algorithm was proposed to optimize the casting speed and cooling water from the perspective of system cooling. Based on the analysis of the industrial continuous casting data of a Chinese steel plant for three months, it was found that the unsteady continuous casting, such as the beginning casting, ending casting, change the nozzle, and change the tundish, due to the poor coordination between the casting speed and cooling water, leads to insufficient cooling intensity, which affects the quality of slab and continuous casting efficiency. The genetic algorithm was improved from the aspects of optimization objective and selection operator, so as to improve the convergence speed and optimization ability of the model while generating feasible solutions. The results show that the model optimization scheme met the industrial process rules, and the average heat release of the unsteady continuous casting system was increased from 45.87% to 49.05%, which is within a reasonable range, by appropriately increasing the secondary cooling water flow rate. This optimization method could guide the production control for the continuous casting system.
2022 Vol. 41 (6): 2-7 [Abstract] ( 108 ) [HTML 1KB] [PDF 1395KB] ( 373 )
8 LIU Tian, LI Yao-guang, SUN Yan-hui, LI Wen-shuang, YU Fei
Development and application of prediction model for solidification structure and segregation of 82B billet
Based on a domestic factory 82B small billet continuous casting production process, the ProCAST software was used to build 82B small billet slab macrosegregation in cross-section model, the temperature field, shell thickness and solidification organization three aspects to verify the correctness of the model, through the model the continuous casting parameters (casting speed, cooling water flows and superheat) on the cross-section of slab macrosegregation. The simulation results show that the center segregation of 82B continuous casting billet increases with the increase of casting speed and superheat, but the cooling water flows amount has little effect on the center segregation. The key to reduce the carbon segregation in the center of the billet is to control the casting speed and superheat. Therefore, in order to ensure that the carbon segregation in the center of the billet is not more than 1.10, the casting speed should be controlled below 2.64 m/min and the superheat should not be more than 10 ℃.
2022 Vol. 41 (6): 8-15 [Abstract] ( 180 ) [HTML 0KB] [PDF 4855KB] ( 80 )
Strand Quality
16 YANG Li-an, MI Jin-zhou, LI Tao, CONG Jun-qiang, DENG Ai-jun
Intelligent customization method for prediction model of longitudinal surface crack on continuously casting slab
In the process of steel products manufacturing, online prediction of the location of casting billet quality defects and timely offline cleaning of the defective billet are helpful to improve the production stability of continuous casting and rolling, and realize energy saving, emission reduction and green production of iron and steel enterprises.However, the continuous casting process has the characteristics of multivariable, time-varying and polymorphism. Only by combining the characteristics of equipment, steel grade and defects, and customizing the slab quality defect prediction model, can the slab quality defects be accurately predicted.Therefore, combining data communication technology, artificial intelligence technology, C# and Matlab hybrid programming technology, the intelligent online judgment system for continuous casting slab is established, the intelligent customization method of slab quality prediction model is studied, and the customization process is introduced by taking slab longitudinal crack prediction model as an example. The results show that this method can assist process engineers to intelligently customize the prediction model for steel grades and defects, reduce the difficulty of model development and optimization, and improve the reliability of slab quality prediction model.
2022 Vol. 41 (6): 16-20 [Abstract] ( 162 ) [HTML 0KB] [PDF 2133KB] ( 100 )
21 ZHANG He, DUAN Hai-yang, WANG Xu-dong, YAO Man
Longitudinal crack prediction method of continuous cast slab based on random forest and clustering
Longitudinal crack is a common surface defect of casting slab. Accurate prediction of longitudinal cracking on slab surface is of great significance for improving the quality of casting slab. Aiming at the temporal and spatial variation trends of the temperature of the mold thermocouple during the formation and propagation of longitudinal cracks, this paper captures and extracts the typical variation features of the thermocouple temperature in time series, and the Random Forest(RF) algorithm is used to reduce the dimension of the captured features, and the features closely related to longitudinal cracks are extracted. On this basis, a longitudinal crack detection model based on K-means(K Means) clustering was established. The results show that the proposed longitudinal crack prediction model based on temperature-time series features and clustering algorithm can correctly distinguish and identify samples with longitudinal cracks from samples under normal conditions, which provides feasible way for introducing machine learning methods into abnormal monitoring of continuous casting process.
2022 Vol. 41 (6): 21-28 [Abstract] ( 119 ) [HTML 0KB] [PDF 5029KB] ( 90 )
29 HOU Zi-bing, PENG Zhi-qiang, GUO Kun-hui, LIU Qian, ZENG Zi-hang, GUO Dong-wei
Quality prediction model of hot rolled coil based on big data of continuous casting process
Hot charging or continuous casting and rolling technology of slabs have been gradually adopted by more and more steel enterprises, but its further development is restricted by the quality of slab. Therefore, the effective judgment of continuous casting slab defects can prevent the slab with quality problems from entering the rolling process, so as to reduce the extra energy consumption. Based on the difficulty of online quality detection for slabs, the quality prediction models of hot rolling coil of slabs were established from the perspective of big data production. Firstly, according to the highly unbalanced data of normal and defective products, the data preprocessing method combining correlation analysis, random classification of unbalanced data and dimensionality reduction with principal component analysis was proposed. Then, the GA-BP neural network algorithm was selected to construct the hot rolled coil quality prediction models for low carbon steel, peritectic steel and medium carbon steel, respectively. The results showed that the prediction model has a high accuracy, and the overall prediction accuracy of the low carbon steel model reaches 94.7%, and the defect prediction accuracy is 82.8%. The overall prediction accuracy of the peritectic steel model is 93.3%, and the defect prediction accuracy is 87.5%. The overall prediction accuracy of medium carbon steel model was 85.4%, and the defect prediction accuracy was 87.3%. Furthermore, an online prediction software for hot rolled coil quality was designed based on Python language, which could predict the quality of hot rolled coil in real time and trace the causes of defects conveniently and quickly.
2022 Vol. 41 (6): 29-37 [Abstract] ( 118 ) [HTML 0KB] [PDF 5826KB] ( 132 )
38 HAN Zhan-guang, ZHOU Gan-shui, XIE Chang-chuan
Defect detection of billet macrostructure based on machine learning
Aiming at the problem of low magnification defect rating of continuous casting billets, a system solution based on deep learning framework was established. Based on the defect target detection algorithm of YOLO V4, the detection and recognition of defects of detection class are carried out. The standard Average Precision (AP) index is used as the evaluation index. The AP of “central pipe”, “central porosity”, “nonmetallic inclusion”, “subsurface blowhole” and “central segregation” reached 82.19%, 97.63%, 54.27%, 66.20% and 29.29% respectively. The defect instance segmentation algorithm based on MASK RCNN was used to detect and identify segmented defects. Taking the standard AP(0.5-0.95) as the evaluation index, the AP(0.5-0.95) for detecting and segmentation of four types of defects, namely, “central crack”, “corner crack”, “middle crack” and “subcutaneous crack”, reached 0.78. In particular, From the perspective of production and application, AP(0.5) reaches 0.96, which can better meet the needs of defect detection.
2022 Vol. 41 (6): 38-44 [Abstract] ( 266 ) [HTML 0KB] [PDF 2992KB] ( 108 )
45 XIAO Min, HU Tao, ZHANG Wei, DING Cheng-yan, SHAO Jian, CHEN Dan
On-line prediction for surface longitudinal crack of continuous casting slab on length direction based on PSO-PNN
Surface longitudinal crack is one of the most common surface defects on continuous casting slabs. Due to environmental factors, the on-line detection accuracy of longitudinal cracks on the surface of casting slab is not high, and the quality inspection of casting slab in major steel mills still depends on manual work. Therefore, a method of predicting longitudinal cracks on the surface of casting slab based on particle swarm optimization probabilistic neural network PNN is proposed. Firstly, continuous casting production process tracking and data time-space transformation was established to match the production process data with the slab on length direction. The Bayes minimum risk criterion of PNN was used for supervised feature learning, and the optimization algorithm PSO was used to optimize the selection of key parameters of PNN, and the final model PSO-PNN was obtained. Finally, the quality defect data and production process data of continuous casting line in a steel mill are used for experimental verification. The results show that the classification accuracy of the method is 97.5% for the whole slab and precision and recall for surface longitudinal crack of slab on length direction are above 92%, which can effectively realize the prediction of the longitudinal cracks on the surface of the full length of the slab, and provide a reference for on-site quality inspection personnel.
2022 Vol. 41 (6): 45-53 [Abstract] ( 149 ) [HTML 0KB] [PDF 4835KB] ( 83 )
54 ZHAO Ji-min, HE Yang, LIU Jian-hua, ZHENG Zhong, YOU Da-li
Predictive method of casting slab quality based on just-in-time learning algorithm
Traditional models for the prediction of casting slab quality were mostly built using the global modeling method, which had poor self-adaptive ability and unsteady prediction accuracy. In this study, a new method based on the just-in-time learning algorithm was proposed for the prediction of casting slab quality. The main feathers of the method included the local model based on the just-in-time learning algorithm was built to replace the traditional global model, and the just-in-time modeling method make the prediction model more adapted to the continuous casting process with complex production scenarios and various working conditions. According to the time-varying characteristics of continuous casting production data, the time weighting factor was introduced into the similarity calculation to strengthen the correlation between the sample data and the data to be predicted, which was more beneficial to increasing the model accuracy for the prediction of casting slab quality. Taking the triangular crack of No.65 high-carbon steel slab in a steel plant as an example, the application of just-in-time learning algorithm in the construction of local model for casting slab quality prediction is illustrated, and the prediction results are compared with the global model for casting slab quality prediction. The results showed that the performance of the local model was better than that of the global model based on the assessment indexes. The prediction accuracy of the global model was 65%, while that of the local model was increased to 90%. The effectiveness of the local model for the prediction of casting slab quality was confirmed by comparing the prediction results.
2022 Vol. 41 (6): 54-60 [Abstract] ( 113 ) [HTML 0KB] [PDF 3167KB] ( 116 )
61 HUANG Jun, WANG Bao-feng, ZHANG Xue-yuan, TENG Fei, DING Guo
Development and application of on line detection technology for surface defects of high temperature billets
With the improvement of the requirements of intellectualization in the iron and steel industry, iron and steel enterprises are no longer satisfied with the traditional manual surface defect sampling method after high-temperature slab cooling. In order to realize the non-destructive online detection and quality judgment of slab surface defects in the process of continuous casting, based on the theory of machine vision non-destructive detection, a method of real-time detection of slab defect contour based on CCD and laser scanning is developed in this project. The three-dimensional digital reconstruction of slab surface defect morphology is carried out by using machine vision and graphic processing methods, which effectively realizes the recognition and classification of defect images. Combined with laboratory calibration and field application, the results show that 16 CCD can meet the requirements of full width circumferential detection of high-temperature slab, and defect size detection resolution reaches millimeter level. Through digitization and accurate positioning of the location and depth of defects, it can meet the online detection and monitoring of high-temperature slab defects, and provide a strong support for the traceability of slab product quality.
2022 Vol. 41 (6): 61-67 [Abstract] ( 176 ) [HTML 0KB] [PDF 4032KB] ( 100 )
Continuous Casting Equipment
68 LIU Yang, ZHU Guo-sen, ZHU Zhi-yuan, WANG Guo-lian, TIAN Zhi-hong, LIU Peng-tao
Development of equipment and technology for hot charging pretreatment basing on casting segment of slab
As an important technology of steel rolling interface, hot charging and hot delivery of continuous casting slab plays a key role in green carbon reduction, improving yield and shortening production cycle. The limiting link for the continuous improvement of the hot charging temperature and proportion of microalloyed steel continuous casting slab is the hot charging crack defect on the surface of the steel plate. In view of this problem, Shougang independently designed and developed a complete set of technology, equipment and control system for the hot charging pretreatment of slab based on the caster sector, which realized the refinement and toughening of the surface structure of high-temperature slab, and eliminated the “red feeding crack” defect on the surface of high-temperature hot charging rolled products. The problems such as bending deformation and cooling uniformity of high-temperature slab under rapid cooling conditions are solved, the internal temperature of high-temperature slab is retained to the maximum, and the overall hot charging temperature is increased. Compared with similar technologies, it has better economy and replicability.
2022 Vol. 41 (6): 68-73 [Abstract] ( 106 ) [HTML 0KB] [PDF 3591KB] ( 86 )
Technology Exchange
74 LI Xiang-kui, LIU Yan-qiang, LIU Hong-ming, TIAN Gui-chang, QIAO Huan-shan, LI Xin-xin
Development and application of intelligent quality evaluation system for slab caster of Shougang
In order to insolve the low automation and intelligenc, inaccurate slab abnormal information matching and delivering, inefficient judging of the slab quality evaluation system during the low cost and efficient production of high-level automotive steel product, SGJT steelmaking plant upgraded the old automatic process control and information system. Based on the metallurgic knowledge rule database of relationship between the automotive steel defect and process parameters, intelligent quality evaluation system with 123 abnormal events and parameters was developed. This system can evaluate slab quality and give the disposal instructions of the abnormal slab automatically by tracking of abnormal slab information on line. The results show that slab quality evaluation system has the functions of atuomatic rapid judging of the slab quality, on-line monitoring process abnormality and tracing the product quality informations.
2022 Vol. 41 (6): 74-79 [Abstract] ( 104 ) [HTML 0KB] [PDF 2193KB] ( 89 )
80 DENG Bi-tao, HAN Zhi-wei, LIU Qiang, KONG Yi-wen, LONG Mu-jun
Development and application of CISDI continuous casting online quality prediction system
In order to predict slab quality in real time and guide continuous casting production, MCC CCID has studied the rule-based slab quality online prediction system (CISDI Continuous Casting Quality Expert, CQE). The system includes the functions of whole process data tracking, real-time quality prediction, flexible rule editing, accurate rule analysis and high-density data query, Convert the on-site production rules into the on-site quality prediction by computer experts. The system has been put into operation in a domestic steel plant for one year. During this period, the quality of 21 656 slabs is predicted, and the prediction accuracy reaches 90.2%. It can accurately predict the slab quality. It provides great help for slab cutting optimization, quality objection analysis and quality improvement, and has remarkable economic benefits.
2022 Vol. 41 (6): 80-87 [Abstract] ( 225 ) [HTML 0KB] [PDF 3848KB] ( 124 )
连铸
 

News

 
 
· Indexed-in
·
·
·
·
                  More 
 

Author Center

 
   Instruction for Authors
   Template
   Copyright Agreement
 

Links

 
· Links
·
·
·
·
·
                  More 
 
Copyright © CONTINUOUS CASTING 
Supported by: Beijing Magtech