Quality Assessment Method Based on a Spectrometer in Laser Beam Welding Process
For the automation of a laser beam welding (LBW) process, the weld quality must be monitored without destructive testing, and the quality must be assessed. A deep neural network (DNN)-based quality assessment method in spectrometry-based LBW is presented in this study. A spectrometer with a response...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Metals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4701/10/6/839 |
| _version_ | 1797564248898928640 |
|---|---|
| author | Jiyoung Yu Huijun Lee Dong-Yoon Kim Munjin Kang Insung Hwang |
| author_facet | Jiyoung Yu Huijun Lee Dong-Yoon Kim Munjin Kang Insung Hwang |
| author_sort | Jiyoung Yu |
| collection | DOAJ |
| description | For the automation of a laser beam welding (LBW) process, the weld quality must be monitored without destructive testing, and the quality must be assessed. A deep neural network (DNN)-based quality assessment method in spectrometry-based LBW is presented in this study. A spectrometer with a response range of 225–975 nm is designed and fabricated to measure and analyze the light reflected from the welding area in the LBW process. The weld quality is classified through welding experiments, and the spectral data are thus analyzed using the spectrometer, according to the welding conditions and weld quality classes. The measured data are converted to RGB (red, green, blue) values to obtain standardized and simplified spectral data. The weld quality prediction model is designed based on DNN, and the DNN model is trained using the experimental data. It is seen that the developed model has a weld-quality prediction accuracy of approximately 90%. |
| first_indexed | 2024-03-10T18:54:42Z |
| format | Article |
| id | doaj.art-d0f8bd5ab5534c2f9a9a113419318824 |
| institution | Directory Open Access Journal |
| issn | 2075-4701 |
| language | English |
| last_indexed | 2024-03-10T18:54:42Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Metals |
| spelling | doaj.art-d0f8bd5ab5534c2f9a9a1134193188242023-11-20T04:52:16ZengMDPI AGMetals2075-47012020-06-0110683910.3390/met10060839Quality Assessment Method Based on a Spectrometer in Laser Beam Welding ProcessJiyoung Yu0Huijun Lee1Dong-Yoon Kim2Munjin Kang3Insung Hwang4Research institute, Monisys Co., Ltd., 775, Gyeongin-ro, Yeongdeungpo-Gu, Seoul 07299, KoreaResearch institute, Monisys Co., Ltd., 775, Gyeongin-ro, Yeongdeungpo-Gu, Seoul 07299, KoreaJoining R & D Group, Korea Institute of Industrial Technology, 156 Gaetbeol-ro, Yeonsu-Gu, Incheon 21999, KoreaJoining R & D Group, Korea Institute of Industrial Technology, 156 Gaetbeol-ro, Yeonsu-Gu, Incheon 21999, KoreaJoining R & D Group, Korea Institute of Industrial Technology, 156 Gaetbeol-ro, Yeonsu-Gu, Incheon 21999, KoreaFor the automation of a laser beam welding (LBW) process, the weld quality must be monitored without destructive testing, and the quality must be assessed. A deep neural network (DNN)-based quality assessment method in spectrometry-based LBW is presented in this study. A spectrometer with a response range of 225–975 nm is designed and fabricated to measure and analyze the light reflected from the welding area in the LBW process. The weld quality is classified through welding experiments, and the spectral data are thus analyzed using the spectrometer, according to the welding conditions and weld quality classes. The measured data are converted to RGB (red, green, blue) values to obtain standardized and simplified spectral data. The weld quality prediction model is designed based on DNN, and the DNN model is trained using the experimental data. It is seen that the developed model has a weld-quality prediction accuracy of approximately 90%.https://www.mdpi.com/2075-4701/10/6/839deep neural networkhigh strength steellaser beam weldingpenetrationquality assessmentspectrometer |
| spellingShingle | Jiyoung Yu Huijun Lee Dong-Yoon Kim Munjin Kang Insung Hwang Quality Assessment Method Based on a Spectrometer in Laser Beam Welding Process Metals deep neural network high strength steel laser beam welding penetration quality assessment spectrometer |
| title | Quality Assessment Method Based on a Spectrometer in Laser Beam Welding Process |
| title_full | Quality Assessment Method Based on a Spectrometer in Laser Beam Welding Process |
| title_fullStr | Quality Assessment Method Based on a Spectrometer in Laser Beam Welding Process |
| title_full_unstemmed | Quality Assessment Method Based on a Spectrometer in Laser Beam Welding Process |
| title_short | Quality Assessment Method Based on a Spectrometer in Laser Beam Welding Process |
| title_sort | quality assessment method based on a spectrometer in laser beam welding process |
| topic | deep neural network high strength steel laser beam welding penetration quality assessment spectrometer |
| url | https://www.mdpi.com/2075-4701/10/6/839 |
| work_keys_str_mv | AT jiyoungyu qualityassessmentmethodbasedonaspectrometerinlaserbeamweldingprocess AT huijunlee qualityassessmentmethodbasedonaspectrometerinlaserbeamweldingprocess AT dongyoonkim qualityassessmentmethodbasedonaspectrometerinlaserbeamweldingprocess AT munjinkang qualityassessmentmethodbasedonaspectrometerinlaserbeamweldingprocess AT insunghwang qualityassessmentmethodbasedonaspectrometerinlaserbeamweldingprocess |