Machine learning(ML) models provide great opportunities to accelerate novel material development, offering a virtual alternative to laborious and resource-intensive empirical methods. In this work, the second of a two...Machine learning(ML) models provide great opportunities to accelerate novel material development, offering a virtual alternative to laborious and resource-intensive empirical methods. In this work, the second of a two-part study, an ML approach is presented that offers accelerated digital design of Mg alloys. A systematic evaluation of four ML regression algorithms was explored to rationalise the complex relationships in Mg-alloy data and to capture the composition-processing-property patterns. Cross-validation and hold-out set validation techniques were utilised for unbiased estimation of model performance. Using atomic and thermodynamic properties of the alloys, feature augmentation was examined to define the most descriptive representation spaces for the alloy data. Additionally, a graphical user interface(GUI) webtool was developed to facilitate the use of the proposed models in predicting the mechanical properties of new Mg alloys. The results demonstrate that random forest regression model and neural network are robust models for predicting the ultimate tensile strength and ductility of Mg alloys, with accuracies of ~80% and 70% respectively. The developed models in this work are a step towards high-throughput screening of novel candidates for target mechanical properties and provide ML-guided alloy design.展开更多
Typically, magnesium alloys have been designed using a so-called hill-climbing approach, with rather incremental advances over the past century. Iterative and incremental alloy design is slow and expensive, but more i...Typically, magnesium alloys have been designed using a so-called hill-climbing approach, with rather incremental advances over the past century. Iterative and incremental alloy design is slow and expensive, but more importantly it does not harness all the data that exists in the field. In this work, a new approach is proposed that utilises data science and provides a detailed understanding of the data that exists in the field of Mg-alloy design to date. In this approach, first a consolidated alloy database that incorporates 916 datapoints was developed from the literature and experimental work. To analyse the characteristics of the database, alloying and thermomechanical processing effects on mechanical properties were explored via composition-process-property matrices. An unsupervised machine learning(ML) method of clustering was also implemented, using unlabelled data, with the aim of revealing potentially useful information for an alloy representation space of low dimensionality. In addition, the alloy database was correlated to thermodynamically stable secondary phases to further understand the relationships between microstructure and mechanical properties. This work not only introduces an invaluable open-source database, but it also provides, for the first-time data, insights that enable future accelerated digital Mg-alloy design.展开更多
This article provides a report on the effect of multiaxial deformation(MAD) on the structure, texture, mechanical characteristics, and corrosion resistance of the Mg-0.8(wt.)% Ca alloy. MAD was carried out on the allo...This article provides a report on the effect of multiaxial deformation(MAD) on the structure, texture, mechanical characteristics, and corrosion resistance of the Mg-0.8(wt.)% Ca alloy. MAD was carried out on the alloy in the as-cast and the annealed states in multiple passes, with a stepwise decrease in the deformation temperature from 450 to 250 ℃ in 50 ℃ steps. The cumulative true strain at the end of the process was 22.5. In the case of the as-cast alloy, this resulted in a refined microstructure characterized by an average grain size of 2.7 μm and a fraction of high-angle boundaries(HABs) of 57.6%. The corresponding values for the annealed alloy were 2.1 μm and 68.2%. The predominant mechanism of structure formation was associated with discontinuous and continuous dynamic recrystallization acting in concert. MAD was also shown to lead to the formation of a rather sharp prismatic texture in the as-cast alloy, whilst in the case of the annealed one the texture was weakened. A displacement of the basal poles {00.4} from the periphery to the center of a pole figure was observed. These changes in the microstructure and texture gave rise to a significant improvement of the mechanical characteristics of the alloy. This included an increase of the ultimate tensile strength reaching 308 MPa for annealed material and 264 MPa for the as-cast one in conjunction with a twofold increase in ductility. A further important result of the MAD processing was a reduction of the rate of electrochemical corrosion, as indicated by a significant decrease in the corrosion current density in both microstructural states of the alloy studied.展开更多
Multi-principal element alloys(MPEAs),inclusive of high entropy alloys(HEAs),continue to attract significant research attention owing to their potentially desirable properties.Although MPEAs remain under extensive res...Multi-principal element alloys(MPEAs),inclusive of high entropy alloys(HEAs),continue to attract significant research attention owing to their potentially desirable properties.Although MPEAs remain under extensive research,traditional(i.e.empirical)alloy production and testing are both costly and timeconsuming,partly due to the inefficiency of the early discovery process which involves experiments on a large number of alloy compositions.It is intuitive to apply machine learning in the discovery of this novel class of materials,of which only a small number of potential alloys have been probed to date.In this work,a proof-of-concept is proposed,combining generative adversarial networks(GANs)with discriminative neural networks(NNs),to accelerate the exploration of novel MPEAs.By applying the GAN model herein,it was possible to directly generate novel compositions for MPEAs,and to predict their phases.To verify the predictability of the model,alloys designed by the model are presented and a candidate produced-as validation.This suggests that the model herein offers an approach that can significantly enhance the capacity and efficiency of development of novel MPEAs.展开更多
基金the support of the Monash-IITB Academy Scholarshipthe Australian Research Council for funding the present research (DP190103592)。
文摘Machine learning(ML) models provide great opportunities to accelerate novel material development, offering a virtual alternative to laborious and resource-intensive empirical methods. In this work, the second of a two-part study, an ML approach is presented that offers accelerated digital design of Mg alloys. A systematic evaluation of four ML regression algorithms was explored to rationalise the complex relationships in Mg-alloy data and to capture the composition-processing-property patterns. Cross-validation and hold-out set validation techniques were utilised for unbiased estimation of model performance. Using atomic and thermodynamic properties of the alloys, feature augmentation was examined to define the most descriptive representation spaces for the alloy data. Additionally, a graphical user interface(GUI) webtool was developed to facilitate the use of the proposed models in predicting the mechanical properties of new Mg alloys. The results demonstrate that random forest regression model and neural network are robust models for predicting the ultimate tensile strength and ductility of Mg alloys, with accuracies of ~80% and 70% respectively. The developed models in this work are a step towards high-throughput screening of novel candidates for target mechanical properties and provide ML-guided alloy design.
基金the support of the Monash-IITB Academy Scholarshipfunded in part by the Australian Research Council (DP190103592)。
文摘Typically, magnesium alloys have been designed using a so-called hill-climbing approach, with rather incremental advances over the past century. Iterative and incremental alloy design is slow and expensive, but more importantly it does not harness all the data that exists in the field. In this work, a new approach is proposed that utilises data science and provides a detailed understanding of the data that exists in the field of Mg-alloy design to date. In this approach, first a consolidated alloy database that incorporates 916 datapoints was developed from the literature and experimental work. To analyse the characteristics of the database, alloying and thermomechanical processing effects on mechanical properties were explored via composition-process-property matrices. An unsupervised machine learning(ML) method of clustering was also implemented, using unlabelled data, with the aim of revealing potentially useful information for an alloy representation space of low dimensionality. In addition, the alloy database was correlated to thermodynamically stable secondary phases to further understand the relationships between microstructure and mechanical properties. This work not only introduces an invaluable open-source database, but it also provides, for the first-time data, insights that enable future accelerated digital Mg-alloy design.
基金supported by the Russian Science Foundation(Grant No.18-45-06010)and within the framework of state task No.075-00328-21-00(texture study)。
文摘This article provides a report on the effect of multiaxial deformation(MAD) on the structure, texture, mechanical characteristics, and corrosion resistance of the Mg-0.8(wt.)% Ca alloy. MAD was carried out on the alloy in the as-cast and the annealed states in multiple passes, with a stepwise decrease in the deformation temperature from 450 to 250 ℃ in 50 ℃ steps. The cumulative true strain at the end of the process was 22.5. In the case of the as-cast alloy, this resulted in a refined microstructure characterized by an average grain size of 2.7 μm and a fraction of high-angle boundaries(HABs) of 57.6%. The corresponding values for the annealed alloy were 2.1 μm and 68.2%. The predominant mechanism of structure formation was associated with discontinuous and continuous dynamic recrystallization acting in concert. MAD was also shown to lead to the formation of a rather sharp prismatic texture in the as-cast alloy, whilst in the case of the annealed one the texture was weakened. A displacement of the basal poles {00.4} from the periphery to the center of a pole figure was observed. These changes in the microstructure and texture gave rise to a significant improvement of the mechanical characteristics of the alloy. This included an increase of the ultimate tensile strength reaching 308 MPa for annealed material and 264 MPa for the as-cast one in conjunction with a twofold increase in ductility. A further important result of the MAD processing was a reduction of the rate of electrochemical corrosion, as indicated by a significant decrease in the corrosion current density in both microstructural states of the alloy studied.
文摘Multi-principal element alloys(MPEAs),inclusive of high entropy alloys(HEAs),continue to attract significant research attention owing to their potentially desirable properties.Although MPEAs remain under extensive research,traditional(i.e.empirical)alloy production and testing are both costly and timeconsuming,partly due to the inefficiency of the early discovery process which involves experiments on a large number of alloy compositions.It is intuitive to apply machine learning in the discovery of this novel class of materials,of which only a small number of potential alloys have been probed to date.In this work,a proof-of-concept is proposed,combining generative adversarial networks(GANs)with discriminative neural networks(NNs),to accelerate the exploration of novel MPEAs.By applying the GAN model herein,it was possible to directly generate novel compositions for MPEAs,and to predict their phases.To verify the predictability of the model,alloys designed by the model are presented and a candidate produced-as validation.This suggests that the model herein offers an approach that can significantly enhance the capacity and efficiency of development of novel MPEAs.
