Designing cold rolled IF steel sheets with optimized tensile properties using ANN and GA

Mohanty, Itishree; Bhattacharjee, D.; Datta, Someswar

doi:10.1016/j.commatsci.2011.03.007

Cited by 58 publications

(19 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…the grain size, in a complex non-linear manner, so ANN is an effective tool to handle such complexity as it can bring out the input-output non-linear relationships in materials systems [24][25][26][27]. Sensitivity analysis [28,29] is performed on the trained ANN models to bring out the input variables contributing positively or negatively to the final output. The results from rough set analyses and from ANN models are compared.…”

Section: Introductionmentioning

confidence: 99%

An Informatics Based Approach to Reduce the Grain Size of Cast Hadfield Steel

Dey

Pathak²,

Sheoran³

et al. 2015

J. Inst. Eng. India Ser. D

Self Cite

View full text Add to dashboard Cite

Materials Informatics concept using computational intelligence based approaches are employed to bring out the significant alloying additions to achieve grain refinement in cast Hadfield steel. Castings of Hadfield steels used for railway crossings, requires fine grained austenitic structure. Maintaining proper grain size of this component is very crucial in order to achieve the desired properties and service life. This work studies the important variables affecting the grain size of such steels which includes the compositional and processing variables. The computational findings and prior knowledge is used to design the alloy, which is subjected to a few trials to validate the findings.

show abstract

Section: Introductionmentioning

confidence: 99%

An Informatics Based Approach to Reduce the Grain Size of Cast Hadfield Steel

Dey

Pathak²,

Sheoran³

et al. 2015

J. Inst. Eng. India Ser. D

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although ML essentially correlates input parameters with output target properties for the composition range covered in the data set and has no design function itself, under certain conditions it can be applied to discover new systems in combination with a proper search algorithm [41e46]. For example, an ANN model coupling composition/ processing variable with various mechanical properties was established and combined with a GA to design new micro-alloyed pipeline steel and cold rolled IF steels [41,43]. Large amounts of design results are usually obtained in a ML design process, so how to quickly identify quality of design results is also a key issue.…”

Section: Introductionmentioning

confidence: 99%

Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel

et al. 2019

View full text Add to dashboard Cite

With the development of the materials genome philosophy and data mining methodologies, machine learning (ML) has been widely applied for discovering new materials in various systems including highend steels with improved performance. Although recently, some attempts have been made to incorporate physical features in the ML process, its effects have not been demonstrated and systematically analysed nor experimentally validated with prototype alloys. To address this issue, a physical metallurgy (PM) -guided ML model was developed, wherein intermediate parameters were generated based on original inputs and PM principles, e.g., equilibrium volume fraction (V f ) and driving force (D f ) for precipitation, and these were added to the original dataset vectors as extra dimensions to participate in and guide the ML process. As a result, the ML process becomes more robust when dealing with small datasets by improving the data quality and enriching data information. Therefore, a new material design method is proposed combining PM-guided ML regression, ML classifier and a genetic algorithm (GA). The model was successfully applied to the design of advanced ultrahigh-strength stainless steels using only a small database extracted from the literature. The proposed prototype alloy with a leaner chemistry but better mechanical properties has been produced experimentally and an excellent agreement was obtained for the predicted optimal parameter settings and the final properties. In addition, the present work also clearly demonstrated that implementation of PM parameters can improve the design accuracy and efficiency by eliminating intermediate solutions not obeying PM principles in the ML process. Furthermore, various important factors influencing the generalizability of the ML model are discussed in detail.

show abstract

“…Here computational intelligence techniques come into picture as it has the ability to handle problems non-linear, complex systems as in cases of metals and alloys [4]. Genetic algorithm (GA) [5,6] has been successfully employed for designing novel materials [7][8][9][10]. In this work multi-objective GA [11,12] is used to search for solutions, i.e.…”

Section: Introductionmentioning

confidence: 99%

In silico Design of High Strength Aluminium Alloy Using Multi-objective GA

Dey

Ganguly

Datta

2015

Swarm, Evolutionary, and Memetic Computing

Self Cite

View full text Add to dashboard Cite

Abstract. Multi-objective optimization is employed using genetic algorithm, for designing novel age-hardenable aluminium alloy with improved properties. Data on the mechanical properties of age-hardenable aluminium alloys is considered together for modeling the mechanical properties using artificial neural network. The models are used as objective functions to get the optimized combination of input parameters for the objectives, viz. high strength and ductility. The significance analyses of the variables on the ANN models gave a primary insight on the role of the variables. The Pareto solutions emerged from the GA based multi-objective optimization is found suitable for effective design of aluminium alloys with tailored properties. An in depth study of the role of the variables in the non-dominated solutions clearly describes the guideline for developing an alloy with improved mechanical properties.

show abstract

Designing cold rolled IF steel sheets with optimized tensile properties using ANN and GA

Cited by 58 publications

References 10 publications

An Informatics Based Approach to Reduce the Grain Size of Cast Hadfield Steel

An Informatics Based Approach to Reduce the Grain Size of Cast Hadfield Steel

Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel

In silico Design of High Strength Aluminium Alloy Using Multi-objective GA

Contact Info

Product

Resources

About