Online Detection of Laser Welding Penetration Depth Based on Multi-Sensor Features
The accurate online detection of laser welding penetration depth has been a critical problem to which the industry has paid the most attention. Aiming at the laser welding process of TC4 titanium alloy, a multi-sensor monitoring system that obtained the keyhole/molten pool images and laser-induced p...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Materials |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1944/17/7/1580 |
| _version_ | 1797212322195832832 |
|---|---|
| author | Kun She Donghui Li Kaisong Yang Mingyu Li Beile Wu Lijun Yang Yiming Huang |
| author_facet | Kun She Donghui Li Kaisong Yang Mingyu Li Beile Wu Lijun Yang Yiming Huang |
| author_sort | Kun She |
| collection | DOAJ |
| description | The accurate online detection of laser welding penetration depth has been a critical problem to which the industry has paid the most attention. Aiming at the laser welding process of TC4 titanium alloy, a multi-sensor monitoring system that obtained the keyhole/molten pool images and laser-induced plasma spectrum was built. The influences of laser power on the keyhole/molten pool morphologies and plasma thermo-mechanical characteristics were investigated. The results showed that there were significant correlations among the variations of the keyhole–molten pool, plasma spectrum, and penetration depth. The image features and spectral features were extracted by image processing and dimension-reduction methods, respectively. Moreover, several penetration depth prediction models based on single-sensor features and multi-sensor features were established. The mean square error of the neural network model built by multi-sensor features was 0.0162, which was smaller than that of the model built by single-sensor features. The established high-precision model provided a theoretical basis for real-time feedback control of the penetration depth in the laser welding process. |
| first_indexed | 2024-04-24T10:40:32Z |
| format | Article |
| id | doaj.art-d1638fae772d46ac821373fca43fd6d6 |
| institution | Directory Open Access Journal |
| issn | 1996-1944 |
| language | English |
| last_indexed | 2024-04-24T10:40:32Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Materials |
| spelling | doaj.art-d1638fae772d46ac821373fca43fd6d62024-04-12T13:22:03ZengMDPI AGMaterials1996-19442024-03-01177158010.3390/ma17071580Online Detection of Laser Welding Penetration Depth Based on Multi-Sensor FeaturesKun She0Donghui Li1Kaisong Yang2Mingyu Li3Beile Wu4Lijun Yang5Yiming Huang6School of Electrical and Information Engineering, Tianjin 300350, ChinaSchool of Electrical and Information Engineering, Tianjin 300350, ChinaTianjin Key Laboratory of Advanced Joining Technology, School of Materials Science and Engineering, Tianjin University, Tianjin 300350, ChinaTianjin Key Laboratory of Advanced Joining Technology, School of Materials Science and Engineering, Tianjin University, Tianjin 300350, ChinaTianjin Key Laboratory of Advanced Joining Technology, School of Materials Science and Engineering, Tianjin University, Tianjin 300350, ChinaTianjin Key Laboratory of Advanced Joining Technology, School of Materials Science and Engineering, Tianjin University, Tianjin 300350, ChinaTianjin Key Laboratory of Advanced Joining Technology, School of Materials Science and Engineering, Tianjin University, Tianjin 300350, ChinaThe accurate online detection of laser welding penetration depth has been a critical problem to which the industry has paid the most attention. Aiming at the laser welding process of TC4 titanium alloy, a multi-sensor monitoring system that obtained the keyhole/molten pool images and laser-induced plasma spectrum was built. The influences of laser power on the keyhole/molten pool morphologies and plasma thermo-mechanical characteristics were investigated. The results showed that there were significant correlations among the variations of the keyhole–molten pool, plasma spectrum, and penetration depth. The image features and spectral features were extracted by image processing and dimension-reduction methods, respectively. Moreover, several penetration depth prediction models based on single-sensor features and multi-sensor features were established. The mean square error of the neural network model built by multi-sensor features was 0.0162, which was smaller than that of the model built by single-sensor features. The established high-precision model provided a theoretical basis for real-time feedback control of the penetration depth in the laser welding process.https://www.mdpi.com/1996-1944/17/7/1580laser weldingspectral analysisimage processingpenetration depthonline monitoring |
| spellingShingle | Kun She Donghui Li Kaisong Yang Mingyu Li Beile Wu Lijun Yang Yiming Huang Online Detection of Laser Welding Penetration Depth Based on Multi-Sensor Features Materials laser welding spectral analysis image processing penetration depth online monitoring |
| title | Online Detection of Laser Welding Penetration Depth Based on Multi-Sensor Features |
| title_full | Online Detection of Laser Welding Penetration Depth Based on Multi-Sensor Features |
| title_fullStr | Online Detection of Laser Welding Penetration Depth Based on Multi-Sensor Features |
| title_full_unstemmed | Online Detection of Laser Welding Penetration Depth Based on Multi-Sensor Features |
| title_short | Online Detection of Laser Welding Penetration Depth Based on Multi-Sensor Features |
| title_sort | online detection of laser welding penetration depth based on multi sensor features |
| topic | laser welding spectral analysis image processing penetration depth online monitoring |
| url | https://www.mdpi.com/1996-1944/17/7/1580 |
| work_keys_str_mv | AT kunshe onlinedetectionoflaserweldingpenetrationdepthbasedonmultisensorfeatures AT donghuili onlinedetectionoflaserweldingpenetrationdepthbasedonmultisensorfeatures AT kaisongyang onlinedetectionoflaserweldingpenetrationdepthbasedonmultisensorfeatures AT mingyuli onlinedetectionoflaserweldingpenetrationdepthbasedonmultisensorfeatures AT beilewu onlinedetectionoflaserweldingpenetrationdepthbasedonmultisensorfeatures AT lijunyang onlinedetectionoflaserweldingpenetrationdepthbasedonmultisensorfeatures AT yiminghuang onlinedetectionoflaserweldingpenetrationdepthbasedonmultisensorfeatures |