Enhanced processing map of Ti–6Al–2Sn–2Zr–2Mo–2Cr–0.15Si aided by extreme gradient boosting
A processing map is required for Ti alloys to find processing parameters securing a high formability. This study adopted the extreme gradient boosting (XGB) approach of machine learning to predict a flow curve and plot a processing map with less experiments for the first time. The optimum XGB model...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-10-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844022022794 |
| _version_ | 1811192451484876800 |
|---|---|
| author | Min Hwa Bae Minseob Kim Jinyeong Yu Min Sik Lee Sang Won Lee Taekyung Lee |
| author_facet | Min Hwa Bae Minseob Kim Jinyeong Yu Min Sik Lee Sang Won Lee Taekyung Lee |
| author_sort | Min Hwa Bae |
| collection | DOAJ |
| description | A processing map is required for Ti alloys to find processing parameters securing a high formability. This study adopted the extreme gradient boosting (XGB) approach of machine learning to predict a flow curve and plot a processing map with less experiments for the first time. The optimum XGB model predicted flow curves of Ti–6Al–2Sn–2Zr–2Mo–2Cr–0.15Si at 1073–1273 K and 10 s−1. The predicted data were used to plot a processing map, which showed a higher accuracy in the instability map as compared with the map without XGB. The XGB model also anticipated the power dissipation map at low strain rates. The low accuracy at high strain rates would be improved by alleviating the bias towards a flow hardening. This work has successfully proven the potential usefulness of XGB for plotting an enhanced processing map in light of a higher accuracy with less experiments. |
| first_indexed | 2024-04-11T23:52:49Z |
| format | Article |
| id | doaj.art-2c55315cdbf64339b4fd23a1088189a4 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-04-11T23:52:49Z |
| publishDate | 2022-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-2c55315cdbf64339b4fd23a1088189a42022-12-22T03:56:26ZengElsevierHeliyon2405-84402022-10-01810e10991Enhanced processing map of Ti–6Al–2Sn–2Zr–2Mo–2Cr–0.15Si aided by extreme gradient boostingMin Hwa Bae0Minseob Kim1Jinyeong Yu2Min Sik Lee3Sang Won Lee4Taekyung Lee5School of Mechanical Engineering, Pusan National University, Busan 46241, South KoreaSchool of Mechanical Engineering, Pusan National University, Busan 46241, South KoreaSchool of Mechanical Engineering, Pusan National University, Busan 46241, South KoreaSchool of Mechanical Engineering, Pusan National University, Busan 46241, South KoreaAdvanced Metals Division, Korea Institute of Materials Science, Changwon 51508, South KoreaSchool of Mechanical Engineering, Pusan National University, Busan 46241, South Korea; Corresponding author.A processing map is required for Ti alloys to find processing parameters securing a high formability. This study adopted the extreme gradient boosting (XGB) approach of machine learning to predict a flow curve and plot a processing map with less experiments for the first time. The optimum XGB model predicted flow curves of Ti–6Al–2Sn–2Zr–2Mo–2Cr–0.15Si at 1073–1273 K and 10 s−1. The predicted data were used to plot a processing map, which showed a higher accuracy in the instability map as compared with the map without XGB. The XGB model also anticipated the power dissipation map at low strain rates. The low accuracy at high strain rates would be improved by alleviating the bias towards a flow hardening. This work has successfully proven the potential usefulness of XGB for plotting an enhanced processing map in light of a higher accuracy with less experiments.http://www.sciencedirect.com/science/article/pii/S2405844022022794Metals forming and shapingMetals and alloysDeformation and fractureProcessing mapMachine learning |
| spellingShingle | Min Hwa Bae Minseob Kim Jinyeong Yu Min Sik Lee Sang Won Lee Taekyung Lee Enhanced processing map of Ti–6Al–2Sn–2Zr–2Mo–2Cr–0.15Si aided by extreme gradient boosting Heliyon Metals forming and shaping Metals and alloys Deformation and fracture Processing map Machine learning |
| title | Enhanced processing map of Ti–6Al–2Sn–2Zr–2Mo–2Cr–0.15Si aided by extreme gradient boosting |
| title_full | Enhanced processing map of Ti–6Al–2Sn–2Zr–2Mo–2Cr–0.15Si aided by extreme gradient boosting |
| title_fullStr | Enhanced processing map of Ti–6Al–2Sn–2Zr–2Mo–2Cr–0.15Si aided by extreme gradient boosting |
| title_full_unstemmed | Enhanced processing map of Ti–6Al–2Sn–2Zr–2Mo–2Cr–0.15Si aided by extreme gradient boosting |
| title_short | Enhanced processing map of Ti–6Al–2Sn–2Zr–2Mo–2Cr–0.15Si aided by extreme gradient boosting |
| title_sort | enhanced processing map of ti 6al 2sn 2zr 2mo 2cr 0 15si aided by extreme gradient boosting |
| topic | Metals forming and shaping Metals and alloys Deformation and fracture Processing map Machine learning |
| url | http://www.sciencedirect.com/science/article/pii/S2405844022022794 |
| work_keys_str_mv | AT minhwabae enhancedprocessingmapofti6al2sn2zr2mo2cr015siaidedbyextremegradientboosting AT minseobkim enhancedprocessingmapofti6al2sn2zr2mo2cr015siaidedbyextremegradientboosting AT jinyeongyu enhancedprocessingmapofti6al2sn2zr2mo2cr015siaidedbyextremegradientboosting AT minsiklee enhancedprocessingmapofti6al2sn2zr2mo2cr015siaidedbyextremegradientboosting AT sangwonlee enhancedprocessingmapofti6al2sn2zr2mo2cr015siaidedbyextremegradientboosting AT taekyunglee enhancedprocessingmapofti6al2sn2zr2mo2cr015siaidedbyextremegradientboosting |