Intelligent prediction method of quality for continuous casting process

Zhao, Liping; Dou, Rushan; Yin, Junjun; Yao, Yiyong

doi:10.1109/imcec.2016.7867521

Cited by 12 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Focusing on conventional machine-learning-based approaches, Matsko et al [ 12 ] provided an outline for the application of an adaptive fuzzy decision tree for the automatic process control of the CCP. Zhao et al [ 13 ] proposed an iPSO-LSSVM-based model for the prediction of the intermixing length in the steel-grade transition casting process. The proposed method reached the lowest prediction errors among linear regression, nonlinear regression, and iPSO-LSSVM methods.…”

Section: Introductionmentioning

confidence: 99%

Machine-Learning Algorithms for Process Condition Data-Based Inclusion Prediction in Continuous-Casting Process: A Case Study

Zhang

Gao

Sun

et al. 2023

Sensors

View full text Add to dashboard Cite

Quality-related prediction in the continuous-casting process is important for the quality and process control of casting slabs. As intelligent manufacturing technologies continue to evolve, numerous data-driven techniques have been available for industrial applications. This case study was aimed at developing a machine-learning algorithm, capable of predicting slag inclusion defects in continuous-casting slabs, based on process condition sensor data. A large dataset consisting of sensor data from nearly 7300 casting samples has been analyzed, with the empirical mode decomposition (EMD) algorithm utilized to process the multi-modal time series. The following machine-learning algorithms have been examined: K-Nearest neighbors, support vector classifier (linear and nonlinear kernels), decision trees, random forests, AdaBoost, and Artificial Neural Networks. Four over-sampling or under-sampling algorithms have been adopted to solve imbalanced data distribution. In the experiment, the optimized random forest outperformed other machine-learning algorithms in terms of recall and ROC AUC, which could provide valuable insights for quality control.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine-Learning Algorithms for Process Condition Data-Based Inclusion Prediction in Continuous-Casting Process: A Case Study

Zhang

Gao

Sun

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Continuous casting machines (CCM) are among the main equipment used in steel casting [1][2][3][4][5]. In order to create a layer of slag to prevent the contact of the metal with the air, a mold flux (MF) is applied to the surface of the molten metal [6][7][8].…”

Section: Introductionmentioning

confidence: 99%

“…In order to create a layer of slag to prevent the contact of the metal with the air, a mold flux (MF) is applied to the surface of the molten metal [6][7][8]. The flux assimilates non-metallic inclusions, lubricates the crystallizer walls, and protects against oxidation and metal losses in the tundish ladle and the crystallizer [9,10]. A three-component system of CaO-SiO 2 -Al 2 O 3 forms the basis of almost all known MFs [6].…”

Section: Introductionmentioning

confidence: 99%

“…In order to ensure the required properties, fluxing additives containing CaF 2 , Na 2 O, K 2 O, MgO, MnO, B 2 O 3 , Li 2 O, BaO, free carbon, and carbonates are introduced into the flux [6,7,[9][10][11].…”

Section: Introductionmentioning

confidence: 99%

“…If the layer is too thick, some of the slag will harden and pieces will enter the billet area. As a result, the sliding resistance of the billet and the level of metal damage will increase [6,8,10,11]. An uneven layer leads to excessive consumption of the MF and extra costs.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A model of automated mold flux feeding into the crystallizer of a continuous casting machine

Litsin,

Baskov,

Morkovnik

2023

cisisr

View full text Add to dashboard Cite

This paper describes a model of automatic mold flux (MF) feeding into the crystallizer of a continuous casting machine (CCM). The MF is used to protect metal from secondary oxidation, to lubricate the billet crust and the mold wall, and to fulfill some other functions. Most Russian steel plants use imported MF due to their higher quality and the use of imported CCMs. The effective consumption of MF is essential due to its high cost.Obtaining preliminary data from the model with the introduction of new equipment and expanding the range of steel in steel making shops is an urgent task. Therefore, a model of automated MF feeding has been developed, which can be modified by changing casting parameters. A detailed description of the model developed in Matlab Simulink software is provided. The distinctive features of the model include the relationships between the metal and slag temperature difference, slag layer thickness, and screw feeder flow rate. Mathematical expressions for these relationships are derived and a description of the structural automation diagram and the functional diagram of the model is presented. Model-based equipment settings (electric drive parameters and sensor parameters) and the introduction of the proposed control algorithm reduces flux consumption by up to 13 % while reducing the manufacturing costs of the final product by up to 6 %.

show abstract

Development of a System Based on an Artificial Vision to Determine the Length of Billets in the Cutting Process in Steel Mills

Sánchez-Pozo

Larco

2023

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Intelligent prediction method of quality for continuous casting process

Cited by 12 publications

References 2 publications

Machine-Learning Algorithms for Process Condition Data-Based Inclusion Prediction in Continuous-Casting Process: A Case Study

Machine-Learning Algorithms for Process Condition Data-Based Inclusion Prediction in Continuous-Casting Process: A Case Study

A model of automated mold flux feeding into the crystallizer of a continuous casting machine

Development of a System Based on an Artificial Vision to Determine the Length of Billets in the Cutting Process in Steel Mills

Contact Info

Product

Resources

About