In this study, a new model using artificial neural networks is proposed to improve the thickness error between the plates, which occurs when the rolling conditions change a lot during the thick rolling. The model was developed by using Python, and the input values are the change in the finish rolling temperature between the plates, the change in target tensile strength, the change in target thickness, and the change in rolling force. The new model is 31.76% better than the existing model based on the standard deviation value of the thickness error. This result is expected to reduce quality costs when applied to online models at actual production sites in the future.

AA1050/AA6061/AA1050 layered sheet was fabricated by cold roll-bonding process and subsequently T4 and T6 aging-treated. Two commercial AA1050 sheets of 1 mm thickness and one AA6061 sheet of 2 mm thickness were stacked up so that an AA6061 sheet was located between two AA1050 sheets. After surface treatments such as degreasing and wire brushing, they were then roll-bonded to a thickness of 2 mm by cold rolling. The roll-bonded Al sheets were then processed by natural aging (T4) and artificial aging (T6) treatments. The as roll-bonded Al sheets showed a typical deformation structure, where the grains are elongated in the rolling direction. However, after the T4 and T6 aging treatments, the Al sheets had a recrystallized structure consisting of coarse grains in both the AA5052 and AA6061 regions with different grain sizes in each. In addition, the sheets showed an inhomogeneous hardness distribution in the thickness direction, with higher hardness in AA6061 than in AA1050 after the T4 and T6 age treatments. The tensile strength of the T6-treated specimen was higher than that of the T4-treated one. However, the strength-ductility balance was much better in the T4-treated specimen than the T6-treated one. The tensile properties of the Al sheets fabricated in the present study were compared with those in a previous study.

The purpose of this study was to analyze microstructural changes and evaluate the mechanical properties of TWIP steel subjected to variations in heat treatment, in order to identify optimal process conditions for enhancing the performance of TWIP steel. For this purpose, a homogenization heat treatment was conducted at 1,200 °C for 2 h, followed by hot rolling at temperature exceeding 1,100 °C and cold rolling. Annealing heat treatment is achieved using a muffle furnace in the range of 600 °C to 1,000 °C. The microstructure characterization was performed with an optical microscope and X-ray diffraction. Mechanical properties are evaluated using micro Vickers hardness, tensile test, and ECO index (UTS × Elongation). The specimens annealed at 900 °C and 1,000 °C experienced a significant decrease in hardness and strength due to decarburization. Consequently, the decarburization phenomenon is closely related to the heat treatment process and mechanical properties of TWIP steel, and the effect of the microstructure change during annealing heat treatment.

Hexagonal bolt, nut, fittings, and high-pressure valves with special alloy play an important role in many industrial products, for instance, such as semiconductor facilities, hydrogen stations and fuel cell electric vehicles. The purpose of this study is to investigate the structural stability of turning wheel using the reaction force of roller in variable hexagonal rolling die. As the results, the bearing groove had the possibility of damage in turning wheel, especially, in case of Bottom condition. Furthermore, the turning wheel showed structural instability by using safety factor but structural stability using strength, respectively, as a safety criterion.

Hexagonal bolt, nut, fittings, and high-pressure valves with special alloy play an important role in many industrial products, for instance, such as semiconductor facilities, hydrogen stations and fuel cell electric vehicles. The purpose of this study is to predict the reaction force of roller in drawing system. Numerical analysis was conducted to obtain data for designing the turning wheel, which is key parts in drawing system, using the reaction force of roller. As the results, the reaction force of X axis direction was about 9~20 times larger than that of Z axis direction and the reaction force of Y axis direction was negligible. The maximum reaction force of roller was the case of 4 stage and the numerical results in this study could be helped for designing the mechanical parts of variable hexagonal rolling die.

Hydrogen infrastructure, for instance, such as hydrogen stations, supply chain network, is important in society of hydrogen economy. Special alloy are frequently used to prevent the hydrogen embrittlement in hydrogen vehicles, semiconductor factories and so on. Because special alloy including Monel material has high strength and high hardness, it is known as the hard-to-cut or roll material. This paper aims to investigate the characteristics and safety on bearing and shaft, which consist of key parts of rolling unit, through structural analysis. As the results, it showed that the bearing was weaker than shaft. Further the bearing was safe up to 20.4 ton, which was about 2 times of maximum of roller reaction force in case of considering as static load. However, the bearing was safe up to 10.2 ton in case of considering as repeated load.

A cold roll-bonding process is applied to fabricate an AA6061/AA5052/AA6061/AA5052 layered sheet. Two AA6061 and one AA5052 sheets of 2mm thickness, 40mm width and 300mm length are alternately stacked, then reduced to a thickness of 2.0 mm by multi-pass cold rolling after surface treatment such as degreasing and wire brushing. The rolling is performed at ambient temperature without lubricant using a 2-high mill with a roll diameter of 400 mm at a rolling speed of 6.0 m/sec. The roll-bonded AA6061/AA5052/AA6061/AA5052 layered sheet is then hardened by natural aging (T4) and artificial aging (T6) treatments. The microstructure of the as-roll bonded and the age-hardened Al sheets was revealed by SEM observation; the mechanical properties were investigated by tensile testing and hardness testing. After T4 and T6 aging treatment, the specimens had a recrystallization structure consisting of coarse equiaxed grains in both AA5052 and AA6061 regions. The as-roll-bonded specimen showed a clad structure in which the hardness of AA5052 regions was higher than that of AA6061 regions. However, after T4 and T6 aging treatment, specimens exhibited different structures, with hardness of AA6061 regions higher than that of AA5052 regions. Strengths of T6 and T4 age-treated specimens were found to increase by 1.55 and 1.36 times, respectively, compared to the value of the starting material.

This article suggests the machine learning model, i.e., classifier, for predicting the production quality of free-machining 303-series stainless steel(STS303) small rolling wire rods according to the operating condition of the manufacturing process. For the development of the classifier, manufacturing data for 37 operating variables were collected from the manufacturing execution system(MES) of Company S, and the 12 types of derived variables were generated based on literature review and interviews with field experts. This research was performed with data preprocessing, exploratory data analysis, feature selection, machine learning modeling, and the evaluation of alternative models. In the preprocessing stage, missing values and outliers are removed, and oversampling using SMOTE(Synthetic oversampling technique) to resolve data imbalance. Features are selected by variable importance of LASSO(Least absolute shrinkage and selection operator) regression, extreme gradient boosting(XGBoost), and random forest models. Finally, logistic regression, support vector machine(SVM), random forest, and XGBoost are developed as a classifier to predict the adequate or defective products with new operating conditions. The optimal hyper-parameters for each model are investigated by the grid search and random search methods based on k-fold cross-validation. As a result of the experiment, XGBoost showed relatively high predictive performance compared to other models with an accuracy of 0.9929, specificity of 0.9372, F1-score of 0.9963, and logarithmic loss of 0.0209. The classifier developed in this study is expected to improve productivity by enabling effective management of the manufacturing process for the STS303 small rolling wire rods.

This study suggests a machine learning model for predicting the production quality of free-machining 303-series stainless steel small rolling wire rods according to the manufacturing process's operation condition. The operation condition involves 37 features such as sulfur, manganese, carbon content, rolling time, and rolling temperature. The study procedure includes data preprocessing (integration and refinement), exploratory data analysis, feature selection, machine learning modeling. In the preprocessing stage, missing values and outlier are removed, and variables for the interaction between processes and quality influencing factors identified in existing studies are added. Features are selected by variable importance index of lasso regression, extreme gradient boosting (XGBoost), and random forest models. Finally, logistic regression, support vector machine, random forest, and XGBoost is developed as a classifier to predict good or defective products with new operating condition. The hyper-parameters for each model are optimized using k-fold cross validation. As a result of the experiment, XGBoost showed relatively high predictive performance compared to other models with accuracy of 0.9929, specificity of 0.9372, F1-score of 0.9963 and logarithmic loss of 0.0209. In this study, the quality prediction model is expected to be able to efficiently perform quality management by predicting the production quality of small rolling wire rods in advance.

The annealing characteristics of cold-rolled Al-6.5Mg-1.5Zn-0.5Fe-0.5Mn alloy, newly designed as an automobile material, are investigated in detail, and compared with those of other aluminum alloys. Using multi-pass rolling at room temperature, the ingot aluminum alloy is cut to a thickness of 4 mm, width of 30 mm, and length of 100 mm to reduce the thickness to 1 mm (r = 75 %). Annealing after rolling is performed at various temperatures ranging from 200 to 500 oC for 1 hour. The specimens annealed at temperatures up to 300 oC show a deformation structure; however, from 350 oC they have a recrystallization structure consisting of almost equiaxed grains. The hardness distribution in the thickness direction of the annealed specimens is homogeneous at all annealing temperatures, and their average hardness decreases with increasing annealing temperature. The tensile strength of the as-rolled specimen shows a high value of 496 MPa; however, this value decreases with increasing annealing temperature and becomes 338MPa after annealing at 400 oC. These mechanical properties of the specimens are compared with those of other aluminum alloys, including commercial 5xxx system alloys.

A powder-in-sheath rolling method is applied to the fabrication of a carbon nano tube (CNT) reinforced copper composite. A copper tube with outer diameter of 30 mm and wall thickness of 2 mm is used as sheath material. A mixture of pure copper powder and CNTs with a volume content of 3 % is filled in a tube by tap filling and then processed to an 93.3 % reduction using multi-pass rolling after heating for 0.5 h at 400 oC. The specimen is then sintered for 1h at 500 oC. The relative density of the 3 vol%CNT/Cu composite fabricated using powder in sheath rolling is 98 %, while that of the Cu powder compact is 99 %. The microstructure is somewhat heterogeneous in width direction in the composite, but is relatively homogeneous in the Cu powder compact. The hardness distribution is also ununiform in the width direction for the composite. The average hardness of the composites is higher by 8Hv than that of Cu powder compact. The tensile strength of the composite is 280 MPa, which is 20 MPa higher than that of the Cu powder compact. It is concluded that the powder in sheath rolling method is an effective process for fabrication of sound CNT reinforced Cu matrix composites.

In order to analyze the effect of hot asymmetric rolling on the microstructure and texture of aluminum alloy and to investigate the effect of the texture on the formability and plastic anisotropy of aluminum alloy, aluminum 6061 alloy is asymmetrically rolled at room temperature, 200 ℃, 350 ℃, and 500 ℃, and the results are compared with symmetrically rolled results. In the case of asymmetric rolling, the equivalent strain (εeq) is greatest in the upper roll part where the rotational speed of the roll is high and increases with increasing rolling temperature. The increase rate of the mean misorientation angle with increasing temperature is larger than that during symmetrical rolling, and dynamic recrystallization occurs the most when asymmetrical rolling is performed at 500 ℃. In the case of hot symmetric rolling, the {001}<110> rotated cube orientation mainly develops, but in the case of hot asymmetric rolling, the {111}<110> orientation develops along with the {001}<100> cube orientation. The hot asymmetric rolling improves the formability (r) of the aluminum 6061 alloy to 0.9 and reduces the plastic anisotropy (Δr) to near zero due to the {111}<110> shear orientation that develops by asymmetric rolling.

A cold roll-bonding process is applied to fabricate an AA6061/AA5052/AA6061 three-layer clad sheet. Two AA6061 and one AA5052 sheets of 2 mm thickness, 40 mm width, and 300 mm length are stacked, with the AA5052 sheet located in the center. After surface treatment such as degreasing and wire brushing, sample is reduced to a thickness of 1.5 mm by multi-pass cold rolling. The rolling is performed at ambient temperature without lubricant using a 2-high mill with a roll diameter of 400 mm at rolling speed of 6.0 m/sec. The roll bonded AA6061/AA5052/AA6061 complex sheet is then hardened by natural aging(T4) and artificial aging(T6) treatments. The microstructures of the as-roll bonded and age-hardened Al complex sheets are revealed by optical microscopy; the mechanical properties are investigated by tensile testing and hardness testing. After rolling, the roll-bonded AA6061/AA5052/AA6061 sheets show a typical deformation structure in which grains are elongated in the rolling direction. However, after T4 and T6 aging treatment, there is a recrystallization structure consisting of coarse equiaxed grains in both AA5052 and AA6061 sheets. The as roll-bonded specimen shows a sandwich structure in which an AA5052 sheet is inserted into two AA6061 sheets with higher hardness. However, after T4 and T6 aging treatment, there is a different sandwich structure in which the hardness of the upper and lower layers of the AA6061 sheets is higher than that of the center of the AA5052 sheet. The strength values of the T4 and T6 age-treated specimens are found to increase by 1.3 and 1.4 times, respectively, compared to that value of the starting material.

SUS hexagonal bar have been widely used to manufacture the hexagonal bolt/nut, adapter and fittings. Raw SUS circular bar is used to make SUS hexagonal bar using drawing system. The purpose of this study is to investigate the characteristics, for instance, such as stress, strain and reduction ratio of area for bar. As the results, it was confirmed that the maximum stresses were occurred at edge of hexagonal bar, thus it could be worked as residual stress of hexagonal bar. The phenomenon of spring back was almost no found in all parts of hexagonal bar. Furthermore it showed that the reduction ratios of area were about mean 26% when SUS circular bar was changed to SUS hexagonal bar in this study.

The annealing characteristics of a cold rolled Al-6.5Mg-1.5Zn alloy newly designed as an automobile material is investigated in detail. The aluminum alloy in the ingot state is cut to a thickness of 4 mm, a total width of 30 mm and a length of 100 mm and then reduced to a thickness of 1 mm (reduction of 75%) by multi-pass rolling at room temperature. Annealing after rolling is performed at temperatures ranging from 200 to 400 ℃ for 1 hour. The tensile strength of the annealed material tends to decrease with the annealing temperature and shows a maximum tensile strength of 482MPa in the material annealed at 200 ℃. The tensile elongation of the annealed material increases with the annealing temperature, while the tensile strength does not, and reaches a maximum value of 26 % at the 350 ℃ annealed material. For the microstructure, recovery and recrystallization actively occur as the annealing temperature increases. The recrystallization begins to occur at 300 ℃ and is completed at 350 ℃, which results in the formation of a fine grained structure. After the rolling, the rolling texture of {112}<111>(Cu-Orientation) develops, but after the annealing a specific texture does not develop.

In this study, three kinds of steels are manufactured by varying the rolling conditions, and their microstructures are analyzed. Tensile and Charpy impact tests are performed at room temperature to investigate the correlation between microstructure and mechanical properties. In addition, heat affected zone(HAZ) specimens are fabricated through the simulation of the welding process, and the HAZ microstructure is analyzed. The Charpy impact test of the HAZ specimens is performed at -40 oC to investigate the low temperature HAZ toughness. The main microstructures of steels are quasi-polygonal ferrite and pearlite with fine grains. Because coarse granular bainite forms with an increasing finish rolling temperature, the strength decreases and elongation increases. In the steel with the lowest reduction ratio, coarse granular bainite forms. In the HAZ specimens, fine acicular ferrites are the main features of the microstructure. The volume fraction of coarse bainitic ferrite and granular bainite increases with an increasing finish rolling temperature. The Charpy impact energy at -40 oC decreases with an increasing volume fraction of bainitic ferrite and granular bainite. In the HAZ specimen with the lowest reduction ratio, coarse bainitic ferrite and granular bainite forms and the Charpy impact energy at -40 oC is the lowest.

In this paper, we investigated the change of sectional shape according to the tension when the reed wire was rolled. When rolling is performed, the tension acting on the reed wire acts in the opposite direction of the rolling progress and prevents twisting or bending phenomenon. The shape of the cross section was changed according to the tension acting on the reed wire, and the reed wire was rolled by continuously rolling the flat rolled wire and the tension was applied to the reed wire to control the simulation. As a result of the experiment, it was confirmed that the dimensions of the thickness and width after rolling can be adjusted through the tension acting on the lead wire. It was also confirmed that as the tension increased, the length of the lead wire increased and the residual stress increased.

Effects of annealing temperature on the microstructure and mechanical properties through thickness of a Cu-3.0Ni- 0.7Si alloy processed by differential speed rolling are investigated in detail. The copper alloy with a thickness of 3 mm is rolled to a 50 % reduction at ambient temperature without lubricant and subsequently annealed for 0.5 h at 200-900 oC. The microstructure of the copper alloy after annealing is different in the thickness direction depending on the amount of the shear and compressive strain introduced by the rolling; the recrystallization occurs first in the upper roll side and center regions which are largely shear-deformed. The complete recrystallization occurs at an annealing temperature of 800 oC. The grain size after the complete recrystallization is finer than that of the conventional rolling. The hardness distribution of the specimens annealed at 500-700 oC is not uniform in the thickness direction due to partial recrystallization. This ununiformity of hardness corresponds well to the amount of shear strain in the thickness direction. The average hardness and ultimate tensile strength has the maximum values of 250 Hv and 450 Mpa, respectively, in the specimen annealed at 400 oC. It is considered that the complex mode of strain introduced by rolling directly affects the microstructure and the mechanical properties of the annealed specimens.

Effects of annealing temperature on the microstructure and mechanical properties through thickness of a cold-rolled Cu-3.0Ni-0.7Si alloy were investigated in detail. The copper alloy with thickness of 3 mm was rolled to 50 % reduction at ambient temperature without lubricant and subsequently annealed for 0.5h at 200~900 oC. The microstructure of the copper alloy after annealing was different in thickness direction depending on an amount of the shear and compressive strain introduced by rolling; the recrystallization occurred first in surface regions shear-deformed largely. The hardness distribution of the specimens annealed at 500~700 oC was not uniform in thickness direction due to partial recrystallization. This ununiformity of hardness corresponded well with an amount of shear strain in thickness direction. The average hardness and ultimate tensile strength showed the maximum values of 250Hv and 450MPa in specimen annealed at 400 oC, respectively. It is considered that the complex mode of strain introduced by rolling effected directly on the microstructure and the mechanical properties of the annealed specimens.