Optimization of the Weld Pool Boundary Calculated by the LSTM-Based Measurement Method in GTAW
The shape of the weld pool surface contains a lot of important features to reflect the quality of the weld. However, it is difficult to obtain the weld pool boundary precisely. In this paper, a boundary extension method is designed first to optimize the boundary profile of the interpolated weld pool...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Metals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4701/12/8/1321 |
| _version_ | 1827599029187379200 |
|---|---|
| author | Jinping Liu Shaojie Wu Yingchao Feng Guowei Pan Peng Chen Xiaodong Yang Cancan Yan |
| author_facet | Jinping Liu Shaojie Wu Yingchao Feng Guowei Pan Peng Chen Xiaodong Yang Cancan Yan |
| author_sort | Jinping Liu |
| collection | DOAJ |
| description | The shape of the weld pool surface contains a lot of important features to reflect the quality of the weld. However, it is difficult to obtain the weld pool boundary precisely. In this paper, a boundary extension method is designed first to optimize the boundary profile of the interpolated weld pool surface calculated by the long-short-term memory (LSTM)-based measurement method. Experimental results show that after boundary extension, the errors of the left and right part of the boundary of the weld pool are slightly improved. The weld width error in the X direction is reduced to 2.43%, and the weld width error in the Y direction is slightly increased to 8.68%. Then the robustness of the LSTM-based model is analyzed by studying the phenomena of missing points and more points. To solve the problem caused by the missing/adding the first few imaging points, a forward-reverse united reconstruction optimization method is then designed. After optimization by forward-reverse united reconstruction optimization method, the boundary error of the reconstructed weld pool surface is obviously reduced. The weld width error is reduced to 1.62% in the X direction and 3.94% in the Y direction. |
| first_indexed | 2024-03-09T04:05:22Z |
| format | Article |
| id | doaj.art-4b48dc6601e843a89273f07651d9c13b |
| institution | Directory Open Access Journal |
| issn | 2075-4701 |
| language | English |
| last_indexed | 2024-03-09T04:05:22Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Metals |
| spelling | doaj.art-4b48dc6601e843a89273f07651d9c13b2023-12-03T14:07:00ZengMDPI AGMetals2075-47012022-08-01128132110.3390/met12081321Optimization of the Weld Pool Boundary Calculated by the LSTM-Based Measurement Method in GTAWJinping Liu0Shaojie Wu1Yingchao Feng2Guowei Pan3Peng Chen4Xiaodong Yang5Cancan Yan6China Nuclear Industry 23 Construction Co., Ltd., Beijing 101300, ChinaState Key Laboratory of Advanced Welding and Joining, Harbin Institute of Technology, Harbin 150001, ChinaChina Nuclear Industry 23 Construction Co., Ltd., Beijing 101300, ChinaChina Nuclear Industry 23 Construction Co., Ltd., Beijing 101300, ChinaChina Nuclear Industry 23 Construction Co., Ltd., Beijing 101300, ChinaChina Nuclear Industry 23 Construction Co., Ltd., Beijing 101300, ChinaChina Nuclear Industry 23 Construction Co., Ltd., Beijing 101300, ChinaThe shape of the weld pool surface contains a lot of important features to reflect the quality of the weld. However, it is difficult to obtain the weld pool boundary precisely. In this paper, a boundary extension method is designed first to optimize the boundary profile of the interpolated weld pool surface calculated by the long-short-term memory (LSTM)-based measurement method. Experimental results show that after boundary extension, the errors of the left and right part of the boundary of the weld pool are slightly improved. The weld width error in the X direction is reduced to 2.43%, and the weld width error in the Y direction is slightly increased to 8.68%. Then the robustness of the LSTM-based model is analyzed by studying the phenomena of missing points and more points. To solve the problem caused by the missing/adding the first few imaging points, a forward-reverse united reconstruction optimization method is then designed. After optimization by forward-reverse united reconstruction optimization method, the boundary error of the reconstructed weld pool surface is obviously reduced. The weld width error is reduced to 1.62% in the X direction and 3.94% in the Y direction.https://www.mdpi.com/2075-4701/12/8/1321Gas Tungsten Arc Welding (GTAW)weld pool surfaceLSTM neural networkmeasurementreconstruction |
| spellingShingle | Jinping Liu Shaojie Wu Yingchao Feng Guowei Pan Peng Chen Xiaodong Yang Cancan Yan Optimization of the Weld Pool Boundary Calculated by the LSTM-Based Measurement Method in GTAW Metals Gas Tungsten Arc Welding (GTAW) weld pool surface LSTM neural network measurement reconstruction |
| title | Optimization of the Weld Pool Boundary Calculated by the LSTM-Based Measurement Method in GTAW |
| title_full | Optimization of the Weld Pool Boundary Calculated by the LSTM-Based Measurement Method in GTAW |
| title_fullStr | Optimization of the Weld Pool Boundary Calculated by the LSTM-Based Measurement Method in GTAW |
| title_full_unstemmed | Optimization of the Weld Pool Boundary Calculated by the LSTM-Based Measurement Method in GTAW |
| title_short | Optimization of the Weld Pool Boundary Calculated by the LSTM-Based Measurement Method in GTAW |
| title_sort | optimization of the weld pool boundary calculated by the lstm based measurement method in gtaw |
| topic | Gas Tungsten Arc Welding (GTAW) weld pool surface LSTM neural network measurement reconstruction |
| url | https://www.mdpi.com/2075-4701/12/8/1321 |
| work_keys_str_mv | AT jinpingliu optimizationoftheweldpoolboundarycalculatedbythelstmbasedmeasurementmethodingtaw AT shaojiewu optimizationoftheweldpoolboundarycalculatedbythelstmbasedmeasurementmethodingtaw AT yingchaofeng optimizationoftheweldpoolboundarycalculatedbythelstmbasedmeasurementmethodingtaw AT guoweipan optimizationoftheweldpoolboundarycalculatedbythelstmbasedmeasurementmethodingtaw AT pengchen optimizationoftheweldpoolboundarycalculatedbythelstmbasedmeasurementmethodingtaw AT xiaodongyang optimizationoftheweldpoolboundarycalculatedbythelstmbasedmeasurementmethodingtaw AT cancanyan optimizationoftheweldpoolboundarycalculatedbythelstmbasedmeasurementmethodingtaw |