Pub Date : 2024-06-24DOI: 10.1007/s11663-024-03184-1
Chunyang Shi, Yikun Wang, Jianjun Hu, Lei Zhang, Peilin Tao
For the control of the wear amount of work rolls and replacement moment in finishing rolling, most of the traditional models are unable to accurately predict the optimal finishing wear amount and replacement moment of work roll in advance, which may lead to the disruption of the production rhythm, and even cause product quality defects. This research describes a Lévy's improved arithmetic optimization algorithm twin support vector regression (LAOA-TSVR) prediction model for wear amount of work roll and replacement moment in a finishing mill. Firstly, the research group initially employed real production data from a hot strip finishing mill to identify influential factors of wear amount of work roll through correlation analysis using SPSS. Subsequently, to validate its predictive performance, the model was compared against three classical algorithms: Back Propagation (BP), Radial Basis Function (RBF), and Support Vector Machine (SVM), confirming LAOA-TSVR's superior accuracy. Finally, the model underwent practical production testing with a dataset totaling 200 sets. The findings reveal that the model attains a 95.2 pct hit rate for predicting wear amount of work roll within ± 0.5 pct. Likewise, it achieves a 98.3 pct hit rate for predicting the replacement moment of work roll for finishing mill.
{"title":"Prediction Model of Wear Amount of Work Roll and Replacement Moment in Finishing Rolling Based on Lévy's Improved Arithmetic Optimization Algorithm Twin Support Vector Regression","authors":"Chunyang Shi, Yikun Wang, Jianjun Hu, Lei Zhang, Peilin Tao","doi":"10.1007/s11663-024-03184-1","DOIUrl":"https://doi.org/10.1007/s11663-024-03184-1","url":null,"abstract":"<p>For the control of the wear amount of work rolls and replacement moment in finishing rolling, most of the traditional models are unable to accurately predict the optimal finishing wear amount and replacement moment of work roll in advance, which may lead to the disruption of the production rhythm, and even cause product quality defects. This research describes a Lévy's improved arithmetic optimization algorithm twin support vector regression (LAOA-TSVR) prediction model for wear amount of work roll and replacement moment in a finishing mill. Firstly, the research group initially employed real production data from a hot strip finishing mill to identify influential factors of wear amount of work roll through correlation analysis using SPSS. Subsequently, to validate its predictive performance, the model was compared against three classical algorithms: Back Propagation (BP), Radial Basis Function (RBF), and Support Vector Machine (SVM), confirming LAOA-TSVR's superior accuracy. Finally, the model underwent practical production testing with a dataset totaling 200 sets. The findings reveal that the model attains a 95.2 pct hit rate for predicting wear amount of work roll within ± 0.5 pct. Likewise, it achieves a 98.3 pct hit rate for predicting the replacement moment of work roll for finishing mill.</p>","PeriodicalId":18613,"journal":{"name":"Metallurgical and Materials Transactions B","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141516276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The influence of magnesium treatment on cleanliness and microstructure characteristics of as-cast high-nitrogen stainless bearing steel (HNSBS) was systematically investigated. Results manifested that as the magnesium content increased from 0.0003 to 0.0054 wt pct, the oxygen and sulfur contents in steel, along with the number density and average size of inclusions significantly decreased due to the strong thermodynamic affinity and the removal of inclusions. Meanwhile, the inclusion evolution processes were Al2O3 → MgO·Al2O3 → MgO and MnS → MgS + Mg3N2, and the magnesium content in HNSBS should not exceed 0.0047 wt pct to prevent the formation of deleterious Mg3N2 inclusion. Additionally, the secondary dendrite spacing and the area fraction of precipitates (M23(C, N)6 and M2(C, N)) at the 1/2 radius of ingots decreased form 83 ± 25 μm and 17 pct to 63 ± 16 μm and 12 pct, respectively. The dendrite structure was refined owing to the increase in effective nucleation sites for γ-Fe provided by MgO·Al2O3 and MgS inclusions, as well as the enrichment of magnesium in the liquid phase at solidifying front. The area fraction and size of precipitates were reduced due to the decrease of chromium activity. The finer and more dispersed precipitates was attributed to the reduction of growth space and increase in effective nucleation sites. This work provides theoretical guidance for preventing the formation of deleterious inclusions (especially for nitrides) in high-nitrogen alloy systems and refining the microstructure of alloy systems containing M23(C, N)6 and M2(C, N) precipitates.
{"title":"Cleanliness Improvement and Microstructure Refinement of As-Cast High-Nitrogen Stainless Bearing Steel by Magnesium Treatment","authors":"Peng-Chong Lu, Hao Feng, Hua-Bing Li, Peng-Fei Zhang, Hong-Chun Zhu, Zhuo-Wen Ni, Shu-Cai Zhang, Zhou-Hua Jiang","doi":"10.1007/s11663-024-03182-3","DOIUrl":"https://doi.org/10.1007/s11663-024-03182-3","url":null,"abstract":"<p>The influence of magnesium treatment on cleanliness and microstructure characteristics of as-cast high-nitrogen stainless bearing steel (HNSBS) was systematically investigated. Results manifested that as the magnesium content increased from 0.0003 to 0.0054 wt pct, the oxygen and sulfur contents in steel, along with the number density and average size of inclusions significantly decreased due to the strong thermodynamic affinity and the removal of inclusions. Meanwhile, the inclusion evolution processes were Al<sub>2</sub>O<sub>3</sub> → MgO·Al<sub>2</sub>O<sub>3</sub> → MgO and MnS → MgS + Mg<sub>3</sub>N<sub>2</sub>, and the magnesium content in HNSBS should not exceed 0.0047 wt pct to prevent the formation of deleterious Mg<sub>3</sub>N<sub>2</sub> inclusion. Additionally, the secondary dendrite spacing and the area fraction of precipitates (M<sub>23</sub>(C, N)<sub>6</sub> and M<sub>2</sub>(C, N)) at the 1/2 radius of ingots decreased form 83 ± 25 <i>μ</i>m and 17 pct to 63 ± 16 <i>μ</i>m and 12 pct, respectively. The dendrite structure was refined owing to the increase in effective nucleation sites for <i>γ</i>-Fe provided by MgO·Al<sub>2</sub>O<sub>3</sub> and MgS inclusions, as well as the enrichment of magnesium in the liquid phase at solidifying front. The area fraction and size of precipitates were reduced due to the decrease of chromium activity. The finer and more dispersed precipitates was attributed to the reduction of growth space and increase in effective nucleation sites. This work provides theoretical guidance for preventing the formation of deleterious inclusions (especially for nitrides) in high-nitrogen alloy systems and refining the microstructure of alloy systems containing M<sub>23</sub>(C, N)<sub>6</sub> and M<sub>2</sub>(C, N) precipitates.</p>","PeriodicalId":18613,"journal":{"name":"Metallurgical and Materials Transactions B","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141516274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-24DOI: 10.1007/s11663-024-03177-0
Jingzhou Lu, Weiming Pan, Wanlin Wang, Kun Dou
Thin slab casting and rolling (TSCR) is a near-net-shape manufacturing process and a key development technology in China's iron and steel industry. This study uses cross-scale calculations to analyze the complete process of thin slab casting. The focus is on simulating and predicting the final solidification structure by adjusting process parameters. The aim is to enable further investigation into material performance and establish a foundation for researching deformation and phase transformation. To achieve this, a coupled model has been developed to simulate the entire thin slab casting process, using hot stamping steel as the research subject. The model encompasses fluid flow, heat transfer, and solidification. The study identifies the optimal combination for flow field, temperature distribution, and equiaxed grain ratio within the specified parameter range at a casting speed of 4.0 m/min and a superheat of 40 °C. The aim of the study is to establish an integrated computational materials engineering (ICME) research system for near-net-shape automotive steel casting processes.