Forming state recognition in deep drawing process with machine learning
In press processing, quality inspection of a product is often carried out for each lot in the post process stage. When a failure occurs, it may result in a large number of defective products due to the fast processing speed. In order to prevent this, it is ideal to immediately stop the processing ju...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Japan Society of Mechanical Engineers
2019-09-01
|
| Series: | Journal of Advanced Mechanical Design, Systems, and Manufacturing |
| Subjects: | |
| Online Access: | https://www.jstage.jst.go.jp/article/jamdsm/13/3/13_2019jamdsm0066/_pdf/-char/en |
| _version_ | 1818532157157539840 |
|---|---|
| author | Tomohiro TSURUYA Musashi DANSEKO Katsuhiko SASAKI Shinya HONDA Ryo TAKEDA |
| author_facet | Tomohiro TSURUYA Musashi DANSEKO Katsuhiko SASAKI Shinya HONDA Ryo TAKEDA |
| author_sort | Tomohiro TSURUYA |
| collection | DOAJ |
| description | In press processing, quality inspection of a product is often carried out for each lot in the post process stage. When a failure occurs, it may result in a large number of defective products due to the fast processing speed. In order to prevent this, it is ideal to immediately stop the processing just after the defect occurs. Therefore, confirming the processing state in-process is required. This study proposes a new quality inspection method for deep drawing processes by using the count rate of acoustic emission (AE) signals. To analyze the AE count, deep learning, which is a multilayered neural network, is employed to recognize defects during a deep drawing process. The material used was a ductile material of cold rolled steel plate and is relatively difficult to find cracks during the deep drawing process. Characteristics were clarified by analysis of AE counts at plastic deformation and brake of material, and performing the forming state recognition experiment by a multilayer neural network (deep learning) showed a maximum recognition rate of 97.3%. High recognition rate was obtained despite the small number of data used. |
| first_indexed | 2024-12-11T17:41:50Z |
| format | Article |
| id | doaj.art-6ab6c93382c94350bcf26bcb0a108423 |
| institution | Directory Open Access Journal |
| issn | 1881-3054 |
| language | English |
| last_indexed | 2024-12-11T17:41:50Z |
| publishDate | 2019-09-01 |
| publisher | The Japan Society of Mechanical Engineers |
| record_format | Article |
| series | Journal of Advanced Mechanical Design, Systems, and Manufacturing |
| spelling | doaj.art-6ab6c93382c94350bcf26bcb0a1084232022-12-22T00:56:30ZengThe Japan Society of Mechanical EngineersJournal of Advanced Mechanical Design, Systems, and Manufacturing1881-30542019-09-01133JAMDSM0066JAMDSM006610.1299/jamdsm.2019jamdsm0066jamdsmForming state recognition in deep drawing process with machine learningTomohiro TSURUYA0Musashi DANSEKO1Katsuhiko SASAKI2Shinya HONDA3Ryo TAKEDA4Industrial Research Institute, Hokkaido Research OrganizationGraduate School of Engineering, Hokkaido UniversityFaculty of Engineering, Hokkaido UniversityFaculty of Engineering, Hokkaido UniversityFaculty of Engineering, Hokkaido UniversityIn press processing, quality inspection of a product is often carried out for each lot in the post process stage. When a failure occurs, it may result in a large number of defective products due to the fast processing speed. In order to prevent this, it is ideal to immediately stop the processing just after the defect occurs. Therefore, confirming the processing state in-process is required. This study proposes a new quality inspection method for deep drawing processes by using the count rate of acoustic emission (AE) signals. To analyze the AE count, deep learning, which is a multilayered neural network, is employed to recognize defects during a deep drawing process. The material used was a ductile material of cold rolled steel plate and is relatively difficult to find cracks during the deep drawing process. Characteristics were clarified by analysis of AE counts at plastic deformation and brake of material, and performing the forming state recognition experiment by a multilayer neural network (deep learning) showed a maximum recognition rate of 97.3%. High recognition rate was obtained despite the small number of data used.https://www.jstage.jst.go.jp/article/jamdsm/13/3/13_2019jamdsm0066/_pdf/-char/ensheet metal formingacoustic emissiondeep learningdeep drawingdata acquisitionsensor |
| spellingShingle | Tomohiro TSURUYA Musashi DANSEKO Katsuhiko SASAKI Shinya HONDA Ryo TAKEDA Forming state recognition in deep drawing process with machine learning Journal of Advanced Mechanical Design, Systems, and Manufacturing sheet metal forming acoustic emission deep learning deep drawing data acquisition sensor |
| title | Forming state recognition in deep drawing process with machine learning |
| title_full | Forming state recognition in deep drawing process with machine learning |
| title_fullStr | Forming state recognition in deep drawing process with machine learning |
| title_full_unstemmed | Forming state recognition in deep drawing process with machine learning |
| title_short | Forming state recognition in deep drawing process with machine learning |
| title_sort | forming state recognition in deep drawing process with machine learning |
| topic | sheet metal forming acoustic emission deep learning deep drawing data acquisition sensor |
| url | https://www.jstage.jst.go.jp/article/jamdsm/13/3/13_2019jamdsm0066/_pdf/-char/en |
| work_keys_str_mv | AT tomohirotsuruya formingstaterecognitionindeepdrawingprocesswithmachinelearning AT musashidanseko formingstaterecognitionindeepdrawingprocesswithmachinelearning AT katsuhikosasaki formingstaterecognitionindeepdrawingprocesswithmachinelearning AT shinyahonda formingstaterecognitionindeepdrawingprocesswithmachinelearning AT ryotakeda formingstaterecognitionindeepdrawingprocesswithmachinelearning |