Machine Learning Model for Thickness Evolution of Oxide Scale During Hot Strip Rolling of Steels

Cui, Chunyuan; Wang, Hao; Gao, Xinyu; Cao, Guangming; Liu, Zhenyu

doi:10.1007/s11661-021-06368-5

Cited by 17 publications

(8 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the MIV can be obtained by Equation (7). [ 42 ]

\text{MIV} = \left|\right. \frac{P_{1} - P_{2}}{N} \left|\right.

where N is the number of training data.…”

Section: Resultsmentioning

confidence: 99%

“…: SVM was used to establish the relationships of the optimized parameters in the P s and P f models with compositions and processing parameters due to its advantage in dealing with nonlinear small data problems. [15,42] Because the number of inputs affects the performance of ML, it is necessary to filter them before training the SVM model. [43] In our work, the Pearson correlation coefficient analysis [43] was carried out to determine the linear correlations between independent and dependent variables by normalizing all data to be in the range from 0 to 1.…”

Section: The Theoretically Guided ML For P S and P Fmentioning

confidence: 99%

See 1 more Smart Citation

Physical Metallurgy Guided Machine Learning for Strain‐Induced Precipitation of Nb (C, N) Based on the Orthogonalized Small Data

Jiang

Cui

et al. 2023

steel research int.

Self Cite

View full text Add to dashboard Cite

Strain‐induced precipitation (SIP) plays an important role in controlling the microstructure and properties of micro‐alloyed steels during hot rolling. However, due to lack of systematic experiments, the existing precipitation data are scarce and insufficient for accurate modeling of SIP behavior with good extrapolation. Herein, the data space of Niobium Carbonitride (Nb(C,N)) SIP kinetics is analyzed based on principle of orthogonal design, and the missing points in the orthogonal space are identified and supplemented in addition to the available data. The parameters in models for precipitation start and finish times are optimized by using the precipitation–time–temperature curves through genetic algorithm, and their relationships with compositions and processing conditions are established by support vector machine. Based on the orthogonally modified dataset, the machine learning (ML) models outperform the classical and ML models with the original data in terms of accuracy and are in good agreement with theoretical expectations. By using the new ML modeling, the evolution behavior of Nb (C, N) during hot deformation is predicted and verified with transmission electron microscope, and the influences of Nb content in steel, strain, strain rate, and the sensitivity of compositions and processing conditions on precipitation kinetics are quantitatively analyzed.

show abstract

“…Then, the MIV can be obtained by Equation (7). [ 42 ]

\text{MIV} = \left|\right. \frac{P_{1} - P_{2}}{N} \left|\right.

where N is the number of training data.…”

Section: Resultsmentioning

confidence: 99%

Section: The Theoretically Guided ML For P S and P Fmentioning

confidence: 99%

Physical Metallurgy Guided Machine Learning for Strain‐Induced Precipitation of Nb (C, N) Based on the Orthogonalized Small Data

Jiang

Cui

et al. 2023

steel research int.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The integration of data‐driven methodologies and AI throughout the entire life cycle of steel materials can substantially enhance the efficiency of steel material R&D and foster engineering applications. In the steel industry, ML can not only carry out the R&D of high‐performance steel materials, but also it can be applied in the quality control of steel materials to realize the prediction and optimization of steel product quality [58,61,99] . By enabling real‐time monitoring and analysis, ML contributes to a reduction in defect rates, improving overall product quality.…”

Section: Discussionmentioning

confidence: 99%

“…Consequently, data mining using an industrial manufacturing dataset with high dimensions and small fluctuation of change presents a significant challenge [55] . To enhance the accuracy of modeling with industrial manufacturing datasets, three effective strategies have been developed: combining the ML model with multiscale calculation, [56] integrating the ML model with PM variables, [57,58] and expanding industrial data with literature data [59–61] …”

Section: Ai Technology In Steel Materials Design and Discoverymentioning

confidence: 99%

Data‐driven and artificial intelligence accelerated steel material research and intelligent manufacturing technology

Geng,

Wang,

et al. 2023

Materials Genome Engineering Advances

View full text Add to dashboard Cite

With the development of new information technology, big data technology and artificial intelligence (AI) have accelerated material research and development and industrial manufacturing, which have become the key technology driving a new wave of global technological revolution and industrial transformation. This review introduces the data resources and databases related to steel materials. It then examines the fundamental strategies and applications of machine learning (ML) in the design and discovery of steel materials, including ML models based on experimental data, industrial manufacturing data, and simulation data, respectively. Given the advancements in big data, AI/ML, and new communication technologies, an intelligent manufacturing mode featuring digital twins is deemed critical in guiding the next industrial revolution. Consequently, the application of intelligence manufacturing with digital twins in the iron and steel industry is reviewed and discussed. Furthermore, the applications of ML in service performance prediction of steel products are addressed. Finally, the future development trends for data‐driven and AI approaches throughout the entire life cycle of steel materials are prospected. Overall, this work presents an in‐depth examination of the integration of data‐driven and AI technologies in the steel industry, highlighting their potential and future directions.

show abstract

“…Almost all steel products have to be subjected to hot rolling, during which the steel thickness is reduced through rolling in the range of temperatures from above 1 100°C through to 700°C or even lower. 1) As the hot rolling process of steel is usually carried out in an oxidizing atmosphere, a thick oxide scale is inevitably oxidized on its surface, which will not only cause material loss but also affect the surface state of steel in the hot rolling process. 2) According to the different stages of hot rolled strip oxide scale formation, it can be divided into four types, namely primary oxide, secondary oxide, tertiary oxide, and quaternary oxide.…”

Section: Introductionmentioning

confidence: 99%

Isothermal Structure Transformation and Kinetics Behavior of Oxide Scale on Low Carbon Steel

et al. 2023

Self Cite

View full text Add to dashboard Cite

The phase transformation of the oxide scale that forms on hot-rolled steel strips during cooling is one of the most important phenomena, which determines the surface quality of the strips, because the properties of the oxide scale, such as spallation resistance, crack initiation, and propagation, and pickling behavior, are strongly dependent on the oxide scale microstructure. To obtain steel strips with high surface quality, it is crucial to understand the microstructural development of the oxide scale. In this paper, a thermogravimetric analyzer was used to study the isothermal structure transformation behavior of FeO formed at high temperature in an inert gas (Ar) at 300-550°C for 1 000-15 000 s. Meanwhile, the isothermal dynamic model of FeO eutectoid transformation was established based on the JMAK equation combined with experimental data. The experimental results show that the oxide scale structure of the sample after pre-oxidation is composed of Fe 2 O 3 , Fe 3 O 4 , and FeO. At 300°C and 550°C, only the pro-eutectoid structure is formed in the oxide scale, but no eutectoid structure is formed. When the isothermal temperature is in the range of 350-500°C, both pro-eutectoid structure and eutectoid structure are formed in the oxide scale. With the extension of isothermal time, the eutectoid reaction continues until the complete decomposition of FeO. In addition, the FeO eutectoid transformation isothermal dynamics model was used to predict the eutectoid structure content of FeO eutectoid decomposition under different isothermal conditions, and the experimental data were compared with the predicted results, which verified the high prediction accuracy of the model.

show abstract

Machine Learning Model for Thickness Evolution of Oxide Scale During Hot Strip Rolling of Steels

Cited by 17 publications

References 33 publications

Physical Metallurgy Guided Machine Learning for Strain‐Induced Precipitation of Nb (C, N) Based on the Orthogonalized Small Data

Physical Metallurgy Guided Machine Learning for Strain‐Induced Precipitation of Nb (C, N) Based on the Orthogonalized Small Data

Data‐driven and artificial intelligence accelerated steel material research and intelligent manufacturing technology

Isothermal Structure Transformation and Kinetics Behavior of Oxide Scale on Low Carbon Steel

Contact Info

Product

Resources

About