Estimation of Elbow Wall Thinning Using Ensemble-Averaged Mel-Spectrogram with ResNet-like Architecture
An elbow wall thinning diagnosis method by highlighting the stationary characteristics of the operating loop is proposed. The accelerations of curved pipe surfaces were measured in a closed test loop operating at a constant pump rpm, combined with curved pipe specimens with artificial wall thinning....
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/11/3976 |
| _version_ | 1797491788018089984 |
|---|---|
| author | Jonghwan Kim Byunyoung Chung Junhong Park Youngchul Choi |
| author_facet | Jonghwan Kim Byunyoung Chung Junhong Park Youngchul Choi |
| author_sort | Jonghwan Kim |
| collection | DOAJ |
| description | An elbow wall thinning diagnosis method by highlighting the stationary characteristics of the operating loop is proposed. The accelerations of curved pipe surfaces were measured in a closed test loop operating at a constant pump rpm, combined with curved pipe specimens with artificial wall thinning. The vibration characteristics of wall-thinned elbows were extracted by using a mel-spectrogram in which modal characteristic variation shifting can be expressed. To reduce the deviation of the model’s prediction values, the ensemble mean value of the mel-spectrogram was used to emphasize stationary signals and reduce noise signals. A convolutional neural network (CNN) regression model with residual blocks was proposed and showed improved performance compared to the models without the residual block. The proposed regression model predicted the thinning thickness of the elbow excluded in training dataset. |
| first_indexed | 2024-03-10T00:54:16Z |
| format | Article |
| id | doaj.art-d947acf57d624c19adfce5d8f417f9eb |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T00:54:16Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-d947acf57d624c19adfce5d8f417f9eb2023-11-23T14:46:39ZengMDPI AGSensors1424-82202022-05-012211397610.3390/s22113976Estimation of Elbow Wall Thinning Using Ensemble-Averaged Mel-Spectrogram with ResNet-like ArchitectureJonghwan Kim0Byunyoung Chung1Junhong Park2Youngchul Choi3School of Mechanical Engineering, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul 04763, KoreaSmart Structural Safety and Prognosis Research Division, Korea Atomic Energy Research Institute, 111 Daedeok-daero 989 Beon-gil, Yuseong-gu, Daejeon 34057, KoreaSchool of Mechanical Engineering, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul 04763, KoreaSmart Structural Safety and Prognosis Research Division, Korea Atomic Energy Research Institute, 111 Daedeok-daero 989 Beon-gil, Yuseong-gu, Daejeon 34057, KoreaAn elbow wall thinning diagnosis method by highlighting the stationary characteristics of the operating loop is proposed. The accelerations of curved pipe surfaces were measured in a closed test loop operating at a constant pump rpm, combined with curved pipe specimens with artificial wall thinning. The vibration characteristics of wall-thinned elbows were extracted by using a mel-spectrogram in which modal characteristic variation shifting can be expressed. To reduce the deviation of the model’s prediction values, the ensemble mean value of the mel-spectrogram was used to emphasize stationary signals and reduce noise signals. A convolutional neural network (CNN) regression model with residual blocks was proposed and showed improved performance compared to the models without the residual block. The proposed regression model predicted the thinning thickness of the elbow excluded in training dataset.https://www.mdpi.com/1424-8220/22/11/3976wall thinningloop testconvolutional neural networkvibration characteristicsensemble averageresidual block |
| spellingShingle | Jonghwan Kim Byunyoung Chung Junhong Park Youngchul Choi Estimation of Elbow Wall Thinning Using Ensemble-Averaged Mel-Spectrogram with ResNet-like Architecture Sensors wall thinning loop test convolutional neural network vibration characteristics ensemble average residual block |
| title | Estimation of Elbow Wall Thinning Using Ensemble-Averaged Mel-Spectrogram with ResNet-like Architecture |
| title_full | Estimation of Elbow Wall Thinning Using Ensemble-Averaged Mel-Spectrogram with ResNet-like Architecture |
| title_fullStr | Estimation of Elbow Wall Thinning Using Ensemble-Averaged Mel-Spectrogram with ResNet-like Architecture |
| title_full_unstemmed | Estimation of Elbow Wall Thinning Using Ensemble-Averaged Mel-Spectrogram with ResNet-like Architecture |
| title_short | Estimation of Elbow Wall Thinning Using Ensemble-Averaged Mel-Spectrogram with ResNet-like Architecture |
| title_sort | estimation of elbow wall thinning using ensemble averaged mel spectrogram with resnet like architecture |
| topic | wall thinning loop test convolutional neural network vibration characteristics ensemble average residual block |
| url | https://www.mdpi.com/1424-8220/22/11/3976 |
| work_keys_str_mv | AT jonghwankim estimationofelbowwallthinningusingensembleaveragedmelspectrogramwithresnetlikearchitecture AT byunyoungchung estimationofelbowwallthinningusingensembleaveragedmelspectrogramwithresnetlikearchitecture AT junhongpark estimationofelbowwallthinningusingensembleaveragedmelspectrogramwithresnetlikearchitecture AT youngchulchoi estimationofelbowwallthinningusingensembleaveragedmelspectrogramwithresnetlikearchitecture |