Determination of Decarburization Depth Base on Deep Learning Methods
In the heat treatment of steel, decarburization is a serious issue that leads to poor wear resistance and low fatigue life. At present, the decarburization depth was determined using a visual estimation by the human eye, and the software estimation was determined through traditional image analysis....
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Metals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4701/13/3/479 |
| _version_ | 1797610148951228416 |
|---|---|
| author | Huang-Chu Huang Ting-Kuang Hu Jen-Chun Lee Jao-Chuan Lin Chung-Hsien Chen Chiu-Chin Lin |
| author_facet | Huang-Chu Huang Ting-Kuang Hu Jen-Chun Lee Jao-Chuan Lin Chung-Hsien Chen Chiu-Chin Lin |
| author_sort | Huang-Chu Huang |
| collection | DOAJ |
| description | In the heat treatment of steel, decarburization is a serious issue that leads to poor wear resistance and low fatigue life. At present, the decarburization depth was determined using a visual estimation by the human eye, and the software estimation was determined through traditional image analysis. Therefore, decarburization depth analysis remains limited in experts and traditional algorithms. Artificial intelligence is a general-purpose technology that has a multitude of applications. This paper uses the concept of deep learning to propose a decarburization layer detector (DLD) that can determine the depth of decarburized layers. This DLD system boasts high performance, real-time, low learning, and computation costs. In addition, we used several kinds of decarburized layers images to compare the proposed method with other deep learning network architectures. The experimental results show that the proposed method yields a detection accuracy of 92.97%, which is higher than existing methods and boasts computational demands which are far lower than other network architectures. Therefore, we propose a novel system for automatic decarburization depth determination as an application for metallographic analysis. |
| first_indexed | 2024-03-11T06:11:26Z |
| format | Article |
| id | doaj.art-8d6c16f7c6a84bd1bb154072cd679c9e |
| institution | Directory Open Access Journal |
| issn | 2075-4701 |
| language | English |
| last_indexed | 2024-03-11T06:11:26Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Metals |
| spelling | doaj.art-8d6c16f7c6a84bd1bb154072cd679c9e2023-11-17T12:38:20ZengMDPI AGMetals2075-47012023-02-0113347910.3390/met13030479Determination of Decarburization Depth Base on Deep Learning MethodsHuang-Chu Huang0Ting-Kuang Hu1Jen-Chun Lee2Jao-Chuan Lin3Chung-Hsien Chen4Chiu-Chin Lin5Department of Telecommunication Engineering, National Kaohsiung University of Science and Technology, Kaohsiung City 811, TaiwanPh.D. Program in Maritime Science and Technology, National Kaohsiung University of Science and Technology, Kaohsiung City 811, TaiwanDepartment of Telecommunication Engineering, National Kaohsiung University of Science and Technology, Kaohsiung City 811, TaiwanDepartment of Marine Leisure Management, National Kaohsiung University of Science and Technology, Kaohsiung City 811, TaiwanMetal Industries Research & Development Centre (MIRDC), Taichung City 407, TaiwanTechnology Talent Bechelor’s Program in Intelligent Maritime, National Kaohsiung University of Science and Technology, Kaohsiung City 811, TaiwanIn the heat treatment of steel, decarburization is a serious issue that leads to poor wear resistance and low fatigue life. At present, the decarburization depth was determined using a visual estimation by the human eye, and the software estimation was determined through traditional image analysis. Therefore, decarburization depth analysis remains limited in experts and traditional algorithms. Artificial intelligence is a general-purpose technology that has a multitude of applications. This paper uses the concept of deep learning to propose a decarburization layer detector (DLD) that can determine the depth of decarburized layers. This DLD system boasts high performance, real-time, low learning, and computation costs. In addition, we used several kinds of decarburized layers images to compare the proposed method with other deep learning network architectures. The experimental results show that the proposed method yields a detection accuracy of 92.97%, which is higher than existing methods and boasts computational demands which are far lower than other network architectures. Therefore, we propose a novel system for automatic decarburization depth determination as an application for metallographic analysis.https://www.mdpi.com/2075-4701/13/3/479decarburization depthartificial intelligencedeep learningtarget detection |
| spellingShingle | Huang-Chu Huang Ting-Kuang Hu Jen-Chun Lee Jao-Chuan Lin Chung-Hsien Chen Chiu-Chin Lin Determination of Decarburization Depth Base on Deep Learning Methods Metals decarburization depth artificial intelligence deep learning target detection |
| title | Determination of Decarburization Depth Base on Deep Learning Methods |
| title_full | Determination of Decarburization Depth Base on Deep Learning Methods |
| title_fullStr | Determination of Decarburization Depth Base on Deep Learning Methods |
| title_full_unstemmed | Determination of Decarburization Depth Base on Deep Learning Methods |
| title_short | Determination of Decarburization Depth Base on Deep Learning Methods |
| title_sort | determination of decarburization depth base on deep learning methods |
| topic | decarburization depth artificial intelligence deep learning target detection |
| url | https://www.mdpi.com/2075-4701/13/3/479 |
| work_keys_str_mv | AT huangchuhuang determinationofdecarburizationdepthbaseondeeplearningmethods AT tingkuanghu determinationofdecarburizationdepthbaseondeeplearningmethods AT jenchunlee determinationofdecarburizationdepthbaseondeeplearningmethods AT jaochuanlin determinationofdecarburizationdepthbaseondeeplearningmethods AT chunghsienchen determinationofdecarburizationdepthbaseondeeplearningmethods AT chiuchinlin determinationofdecarburizationdepthbaseondeeplearningmethods |