Evaluation of thin film material properties using a deep nanoindentation and ANN
Due to the substrate effect, there are several difficulties to evaluate the material properties of thin films via nanoindentation. In this study, an inverse analysis method based on an artificial neural network (ANN) is proposed to obtain free-volume-model (FVM) parameters of thin film metallic glas...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-09-01
|
| Series: | Materials & Design |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0264127522006220 |
| _version_ | 1798037074450841600 |
|---|---|
| author | Giyeol Han Karuppasamy Pandian Marimuthu Hyungyil Lee |
| author_facet | Giyeol Han Karuppasamy Pandian Marimuthu Hyungyil Lee |
| author_sort | Giyeol Han |
| collection | DOAJ |
| description | Due to the substrate effect, there are several difficulties to evaluate the material properties of thin films via nanoindentation. In this study, an inverse analysis method based on an artificial neural network (ANN) is proposed to obtain free-volume-model (FVM) parameters of thin film metallic glass (TFMG) via nanoindentation. Unlike conventional nanoindentation procedures for thin films, a deeper indentation depth (≈ 30% of film thickness) is adopted to accurately identify the film properties even with significant substrate deformations. Both sphero-conical and Berkovich tips are employed to ensure unique solutions. A complex mapping function of inverse analysis is replaced by establishing ANN between nanoindentation (features) and material (targets) parameters. The established ANN model is trained with the database generated via systematic finite element analyses (FEA). The trained ANN model is experimentally validated by estimating the material properties of Zr55Cu30Ag15 TFMG deposited on two different substrates (Si and soda lime glass). The maximum difference of plastic indentation energy between experiments and FEA values using the estimated film material properties was within 3%. |
| first_indexed | 2024-04-11T21:21:42Z |
| format | Article |
| id | doaj.art-deb686f7a6d240fbb27070645c331a83 |
| institution | Directory Open Access Journal |
| issn | 0264-1275 |
| language | English |
| last_indexed | 2024-04-11T21:21:42Z |
| publishDate | 2022-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Materials & Design |
| spelling | doaj.art-deb686f7a6d240fbb27070645c331a832022-12-22T04:02:36ZengElsevierMaterials & Design0264-12752022-09-01221111000Evaluation of thin film material properties using a deep nanoindentation and ANNGiyeol Han0Karuppasamy Pandian Marimuthu1Hyungyil Lee2Department of Mechanical Engineering, Sogang University, Seoul 04107, Republic of KoreaDepartment of Mechanical Engineering, Sogang University, Seoul 04107, Republic of KoreaCorresponding author.; Department of Mechanical Engineering, Sogang University, Seoul 04107, Republic of KoreaDue to the substrate effect, there are several difficulties to evaluate the material properties of thin films via nanoindentation. In this study, an inverse analysis method based on an artificial neural network (ANN) is proposed to obtain free-volume-model (FVM) parameters of thin film metallic glass (TFMG) via nanoindentation. Unlike conventional nanoindentation procedures for thin films, a deeper indentation depth (≈ 30% of film thickness) is adopted to accurately identify the film properties even with significant substrate deformations. Both sphero-conical and Berkovich tips are employed to ensure unique solutions. A complex mapping function of inverse analysis is replaced by establishing ANN between nanoindentation (features) and material (targets) parameters. The established ANN model is trained with the database generated via systematic finite element analyses (FEA). The trained ANN model is experimentally validated by estimating the material properties of Zr55Cu30Ag15 TFMG deposited on two different substrates (Si and soda lime glass). The maximum difference of plastic indentation energy between experiments and FEA values using the estimated film material properties was within 3%.http://www.sciencedirect.com/science/article/pii/S0264127522006220NanoindentationThin film metallic glassMaterial propertyFEAPlastic energy |
| spellingShingle | Giyeol Han Karuppasamy Pandian Marimuthu Hyungyil Lee Evaluation of thin film material properties using a deep nanoindentation and ANN Materials & Design Nanoindentation Thin film metallic glass Material property FEA Plastic energy |
| title | Evaluation of thin film material properties using a deep nanoindentation and ANN |
| title_full | Evaluation of thin film material properties using a deep nanoindentation and ANN |
| title_fullStr | Evaluation of thin film material properties using a deep nanoindentation and ANN |
| title_full_unstemmed | Evaluation of thin film material properties using a deep nanoindentation and ANN |
| title_short | Evaluation of thin film material properties using a deep nanoindentation and ANN |
| title_sort | evaluation of thin film material properties using a deep nanoindentation and ann |
| topic | Nanoindentation Thin film metallic glass Material property FEA Plastic energy |
| url | http://www.sciencedirect.com/science/article/pii/S0264127522006220 |
| work_keys_str_mv | AT giyeolhan evaluationofthinfilmmaterialpropertiesusingadeepnanoindentationandann AT karuppasamypandianmarimuthu evaluationofthinfilmmaterialpropertiesusingadeepnanoindentationandann AT hyungyillee evaluationofthinfilmmaterialpropertiesusingadeepnanoindentationandann |