Prediction and optimization of stretch flangeability of advanced high strength steels utilizing machine learning approaches

Advanced high strength steels (AHSS) exhibit diverse mechanical properties due to their complex chemical compositions and microstructures. Existing machine learning (ML) studies often focus on specific steel grades, limiting generalizability in predicting and optimizing AHSS properties. Here, an ML framework was presented to predict and optimize the stretch-flangeability of AHSS based on composition-microstructure-property correlations, using datasets from 212 steel conditions. Support vector machine, symbolic regression, and extreme gradient boosting models accurately predicted hole expansion ratio (HER), ultimate tensile strength (UTS), and total elongation (TE). Shapley additive explanations revealed the importance of bainite volume fraction (VB), carbon content (C), and chromium content (Cr) for HER, UTS, and TE, respectively. Multi-objective optimization generated 252 optimized conditions with improved comprehensive mechanical properties. The best optimized chemical compositions (0.12wt.% C-1.10Mn-0.15Si-0.47Cr) along with the carbon equivalent (CE) of 0.44 wt.%, and microstructural features (7.2% ferrite, 44.5% bainite, 40.5% martensite, and 7.8% tempered martensite) yielded HER of 119.8%, UTS of 1013.5 MPa, and TE of 22.7%. This systematic framework enables efficient prediction and optimization of material properties (especially HER), with potential applications across various fields of materials science.

Effects of Microstructural Properties on Damage Evolution and Edge Crack Sensitivity of DP1000 Steels

In the present work, the microstructural damage behavior of two DP1000 steel test subjects through various stress states was studied to thoroughly learn the interaction between microstructure, damage evolution, and edge stretchability. In addition, microstructural changes at the fracture sites and fracture surfaces were observed using a scanning electron microscope. The distinctive mechanical and damage behaviors of the materials were revealed. However, the steels were slightly different in chemical composition, microstructural characteristics, and yield stress. The results showed that when microstructural and mechanical properties of phases were more similar, i.e., the microstructure was more homogenous, the damage was initiated by cracking at ferrite-martensite interfaces, and it propagated along the loading direction. This allowed the material to represent high local formability and significant necking. In contrast, by increasing the dissimilarity between ferrite and martensite phases, damage propagated by the shear linking of the voids hindered local deformation of the material and led it to sudden fracture after negligible necking. These distinct damage evolutions noticeably influenced the materials’ edge stretchability. Since higher local formability favors the edges with higher resistance to cracking, the hole expansion ratio increases, as clearly observed throughout the current study.

Structures and Mechanical Properties of Some Dual-Phase Steels with Low Manganese Content

In recent years, to reduce cars costs, research has been conducted on dual-phase steels with low manganese content (below 1.0%). This study investigated the influence of technological parameters of heat treatment (heating temperature and cooling medium) on such steels’ structures and mechanical properties. The ferrite-martensitic structures, specific for dual-phase steels, were obtained by intercritical quenching: heating of samples (made of alloys with 0.511% Mn, respectively 0.529% Mn) to temperatures located between critical points Ac1 and Ac3, followed by cooling in water without mechanical agitation and in water activated with ultrasounds at the frequency of 59 kHz. Through metallographic analyses and tensile tests, it was possible to determine the volume fraction of martensite, the ferrite microhardness, the ultimate tensile strength, the total elongation, and with the obtained data, their variations with the heating temperature and the cooling medium were established. Raising the heating temperature (between 760 °C and 820 °C) and using ultrasounds at cooling increased the volume fraction of martensite and the ferrite microhardness. This fact has increased the mechanical strength and reduced the deformability of the studied dual-phase steels. Intercritical quenching in water activated with ultrasounds provided values of structural characteristics and mechanical properties very close to those obtained by quenching in water without mechanical agitation, but was accomplished using a higher-temperature heating. The results obtained were compared with those determined in previous research, performed on dual-phase steel with 1.90% Mn.

Optimal Design of Hot-Dip Galvanized DP Steels via Artificial Neural Networks and Multi-Objective Genetic Optimization

This modeling and optimization study applies a non-linear back-propagation artificial neural network, commonly denoted as BPNN, to model the most important mechanical properties such as yield strength (YS), ultimate tensile strength (UTS) and elongation at fracture (EL) during the experimental processing of hot-dip galvanized dual-phase (GDP) steels. Once the non-linear BPNN is properly trained, the most important variables of the continuous galvanizing process, including initial/first cooling rate (CR1), holding time at the galvanizing temperature of 460 °C (tg) and the final/second cooling rate (CR2), are obtained in an optimal way using an evolutionary approach. The experimental development of GDP steels in continuous processing lines with outstanding mechanical properties (550 < YS < 750 MPa, 1100 MPa < UTS and 10% < EL) is possible by using a combined hybrid approach based in BPNN and multi-objective genetic algorithm (GA). The proposed computational method is applied to the specific design of an actual manufacturing process for the first time.

Microstructure-Based Modeling of the Effect of Inclusion on the Bendability of Advanced High Strength Dual-Phase Steels

Advanced high strength dual-phase steels are one of the most widely sought-after structural materials for automotive applications. These high strength steels, however, are prone to fracture under bending-dominated manufacturing processes. Experimental observations suggest that the bendability of these steels is sensitive to the presence of subsurface non-metallic inclusions and the inclusions exhibit a rather discrete size effect on the bendability of these steels. Following this, we have carried out a series of microstructure-based finite element calculations of ductile fracture in an advanced high strength dual-phase steel under bending. In the calculations, both the dual-phase microstructure and inclusion are discretely modeled. To gain additional insight, we have also analyzed the effect of an inclusion on the bendability of a single-phase material. In line with the experimental observations, strong inclusion size effect on the bendability of the dual-phase steel naturally emerge in the calculations. Furthermore, supervised machine learning is used to quantify the effects of the multivariable input space associated with the dual-phase microstructure and inclusion on the bendability of the steel. The results of the supervised machine learning are then used to identify the contributions of individual features and isolate critical features that control the bendability of dual-phase steels.

Modeling the Mechanical Response of a Dual-Phase Steel Based on Individual-Phase Tensile Properties

In this work, the engineering stress–strain tensile curve and the force-deflection bending curve of two Dual-Phase (DP) steels are modeled, combining the mechanical data of fully ferritic and fully martensitic steels. The data is coupled by a modified law of mixture, which includes a partition parameter q that takes into account the strength and strain distributions in both martensite and ferrite phases. The resulting constitutive model is solved in the context of the finite element method assuming a modified mixture rule in which a new parameter q′ is defined in order to extend the capabilities of the model to deal with triaxial stresses and strains and thus achieve a good agreement between experimental results and numerical predictions. The model results show that the martensite only deforms elastically, while the ferrite deforms both elastically and plastically. Furthermore, the partition factor q′ is found to strongly depend on the ferritic strain level. Finally, it is possible to conclude that the maximum strength of the studied DP steels is moderately influenced by the maximum strength of martensite.

New Insights into the Microstructural Changes During the Processing of Dual-Phase Steels from Multiresolution Spherical Indentation Stress–Strain Protocols

In this study, recently established multiresolution spherical indentation stress–strain protocols have been employed to derive new insights into the microstructural changes that occur during the processing of dual-phase (DP) steels. This is accomplished by utilizing indenter tips of different radii such that the mechanical responses can be evaluated both at the macroscale (reflecting the bulk properties of the sample) and at the microscale (reflecting the properties of the constituent phases). More specifically, nine different thermo-mechanical processing conditions involving different combinations of intercritical annealing temperatures and bake hardening after different amounts of cold work were studied. In addition to demonstrating the tremendous benefits of the indentation protocols for evaluating the variations within each sample and between the samples at different material length scales in a high throughput manner, the measurements provided several new insights into the microstructural changes occurring in the alloys during their processing. In particular, the indentation measurements indicated that the strength of the martensite phase reduces by about 37% when quenched from 810 °C compared to being quenched from 750 °C, while the strength of the ferrite phase remains about the same. In addition, during the 10% thickness reduction and bake hardening steps, the strength of the martensite phase shows a small decrease due to tempering, while the strength of the ferrite increases by about 50% by static aging.

Plastic accommodation at homophase interfaces between nanotwinned and recrystallized grains in an austenitic duplex-microstructured steel

The plastic co-deformation behavior at the homophase interfaces between the hard nanotwinned grain inclusions and the soft recrystallized matrix grains in a duplex-microstructured AISI 316L austenitic stainless steel is examined through the analysis of long-range orientation gradients within the matrix grains by electron backscatter diffraction and transmission electron microcopy. Our analysis reveals that the mechanical accommodation of homophase interfaces until a macroscopic strain of 22% is realized within a small area of soft grains (about four grains) adjacent to the homophase interface. The activation of deformation twinning in the first two grain layers results in the occurrence of a 'hump' in the orientation gradient profile. We ascribe this effect to the role of deformation twinning on the generation of geometrically necessary dislocations. The smooth profile of the orientation gradient amplitude within the first 10 grain layers indicates a gradual plastic accommodation of the homophase interfaces upon straining. As a consequence, damage nucleation at such interfaces is impeded, resulting in an enhanced ductility of the single phase duplex-microstructured steel.