An artificial neural network (ANN) model was developed to predict the tensile properties as a function of alloying element and microstructural factor of ferrite-pearlite steels. The input parameters of the model were composed of alloying elements (Mn, Si, Al, Nb, Ti, and V) and microstructural factors (pearlite fraction, ferrite grain size, interlamellar spacing, and cementite thickness), while the output parameters of the model were yield strength and tensile strength. Although the ferrite-pearlite steels have complex relationships among the alloying elements, microstructural factors, and tensile properties, the ANN model predictions were found to be more accurate with experimental results than the existing equation model. In the present study the individual effect of input parameters on the tensile properties was quantitatively estimated with the help of the average index of the relative importance for alloying elements as well as microstructural factors. The ANN model attempted from the metallurgical points of view is expected to be useful for designing new steels having required mechanical properties.

Artificial Neural Network for Modeling the Tensile Properties of Ferrite-Pearlite Steels: Relative Importance of Alloying Elements and Microstructural Factors

In this work, actual production data from a rolling mill has been analyzed through the concept of Self Organizing Maps (SOM) for understanding various correlations and patterns in the production data set. SOM is an unsupervised machine learning approach, thus all the process parameters and desired properties can be analyzed simultaneously. Yield Strength (YS), Ultimate tensile strength (UTS) and elongation percent properties have been chosen as the metrics on the basis of which the coil can be utilized for a specific application. This production data contains many missing parameters. Additionally, parameters like different carbon equivalents (CE) and grain size of ferrite GS are dependent of other input parameters (composition of the coils, processing temperature, etc). Therefore, it is important to understand correlations between compositions, processing parameters, structure (GS), and macroscopic properties. Through SOM approach, several correlations have been determined in the production data set which are in accordance with the findings reported in the open literature. SOM predictions have been tabulated. These predictions will be helpful in achieving the optimum properties for various AHSS grades in the industry. 

AHSS applications in Industry 4.0: Determination of optimum processing parameters during coiling process through unsupervised machine learning approach

The variation of the morphology and distribution of cementite particles in different prior structures with spheroidizing annealing process has been proceeded in this paper. It is found that the dissolution and coarsening progresses of various initial structures in spheroidizing annealing process are quite asynchronous due to the different interlamellar spacing. The dissolution rate of degenerated pearlite (D-P) with finer interlamellar spacing is faster. The granular cementite in the spheroidized microstructure is fine, uniform and dense. The mean diameter of spherical cementite is refined to 233 nm. However, the initial structure of degenerated pearlite (D-P) is highly sensitive to the austenitization temperature. The cementite is easy to be coarsened under high austenitizing temperature. The coarsening is accompanied by the gradual increase of the Cr content in the cementite, which increases the stability of the cementite. Therefore, the optimal austenitizing temperature for degenerated pearlite (D-P) is suggested to be 770 °C. The dissolution rates of cementite in spheroidized structures are related to the initial pearlite interlamellar spacing and the austenitizing temperature. A detailed experimental research and analysis are needed on the evolution of different initial structures during spheroidizing annealing treatment.

Effect of Prior Microstructures on Cementite Dissolution Behavior During Subcritical Annealing of High Carbon Steels

We determined the effects of alloying elements and heat treatment temperature on the graphitization behavior of a medium-carbon high-silicon steel (Fe-0.55C-2.3Si, wt%). Trace amounts (  B-bearing steel > base steel, which is attributed to the numerous grain boundaries in the Ti-bearing steel and presence of BN particles in the B-bearing steel because the grain boundaries and BN particles act as major graphite nucleation sites. A higher abundance of nucleation sites for graphitization in the initial microstructure leads to higher graphite density but reduced average graphite size. For all three steels, higher heat treatment temperature promoted both cementite decomposition and graphite formation by accelerated carbon diffusion, which reduced the graphitization completion time, decreased the graphite number density, and increased the graphite size. Fine and uniformly distributed graphite forms within a short time (1 h) in the Ti-bearing steel treated at 750 °C, which significantly decreased its strength and improved its ductility.

Effects of B and Ti addition and heat treatment temperature on graphitization behavior of Fe-0.55C-2.3Si steel

Yield strength and yield-point (YP) phenomenon are regarded as crucial properties to be assured in practical applications such as line-pipe forming. In this work, the impacts of microstructural constituents on YP and yield ratio were explored in four API X65 line-pipe steel plates fabricated by altering the start or finish rolling temperature and plate thickness. The four steel plates were predominantly made up of granular bainite (GB) and polygonal ferrite (PF), along with the greater volume proportion of PF in the case of the lower start and finish rolling temperatures and the thicker plate thickness. According to the skin-pass rolling to reduce the YP elongation, the increased amount of mobile dislocations was greater in the PF than in the GB, indicating that the PF was more responsible for the YP alleviation than the GB because the more mobile dislocations were formed in the PF than in the GB. Thus, the decreasing rate of YP elongation was faster for the thicker plate and the low start or finish rolling temperature. On the other hand, the lower yield ratio was preferred for the thicker plates as they exhibited the shorter YP elongation and the higher strain-hardening rate, thereby leading to the rapid enhancement of yield strength in the YP range and consequently to the continuous increase in yield ratio. Thus, this work would be favorably utilized for designing optimal microstructural and TMCP parameters for securing the yield-strength guarantee in line-pipe steels. 

Effects of granular bainite and polygonal ferrite on yield point phenomenon in API X65 line-pipe steels

Oil country tubular goods (OCTG) steels with a low yield ratio (yield strength/tensile strength) and excellent impact toughness have recently been demanded to ensure mining performance and safety. From this viewpoint, the optimization of the manufacturing conditions is important because they influence the microstructure and mechanical properties of the steels; in particular, in the case of OCTG steels with carbon contents greater than 0.2 wt%, the finishing mill temperature (FMT) and coiling temperature (CT) strongly affect the microstructure of the final products, which are generally composed of ferrite and pearlite phases. In this study, 0.39C-0.23Si-1.56Mn-0.11Cr steel plates were fabricated under various FMT and CT conditions and their yield strength, tensile strength, and impact energy were investigated. In addition, pipes with diameters of 244 and 508 mm were manufactured via an electric resistance welding method using two of these strips fabricated under two different optimized conditions [(1) FMT = 880 °C and CT = 630 °C and (2) FMT = 800 °C and CT = 690 °C] to analyze the change in mechanical properties induced by the work-hardening effect during the piping process. The results revealed that the FMT and CT are closely related to the volume fraction of the ferrite phase, the grain size and lamellar spacing of the pearlite phase, and the tensile and impact properties of the steel strips; the variations in the microstructure and mechanical properties with the FMT and CT were also discussed in detail.

Sung Hwan Bang

Papers

Effect of Rolling and Coiling Temperatures on Microstructure and Mechanical Properties of Medium-Carbon Pipeline Steel