Pearson K-Mean Multi-Head Attention Model for Deformation Prediction of Super-High Dams in First Impoundments
The first impoundment of a super-high dam is a crucial period from dam construction to operation, in which the prediction of the dam deformation is vital for the continued safety of the dam. Therefore, a multi-head attention model based on Pearson K-means clustering is proposed, which is shortened t...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/15/9/1734 |
| _version_ | 1797601599200165888 |
|---|---|
| author | Yilun Wei Chang Liu Hang Duan Yajun Wang Yu Hu Xuezhou Zhu Yaosheng Tan Lei Pei |
| author_facet | Yilun Wei Chang Liu Hang Duan Yajun Wang Yu Hu Xuezhou Zhu Yaosheng Tan Lei Pei |
| author_sort | Yilun Wei |
| collection | DOAJ |
| description | The first impoundment of a super-high dam is a crucial period from dam construction to operation, in which the prediction of the dam deformation is vital for the continued safety of the dam. Therefore, a multi-head attention model based on Pearson K-means clustering is proposed, which is shortened to PKMA. The inputs of the PKMA include measurements of the displacements of plumb lines, water levels, air temperatures, dam body temperatures, water temperatures, and foundation temperatures. Among these inputs, variables related to displacements are regarded as the dominant explanatory factors. Hence, the K-means clustering based on the Pearson index is utilised to increase the weights of displacements in the PKMA. To involve the interactions between inputs, the MA mechanism of neural networks is used to simulate the relationship between inputs and deformation targets. The PKMA model had a maximum MSE of 1.2518 and a maximum MAE of 0.9017 for the model performance metrics at the study measurement points. Compared to the comparison models MA, HST, and LSTM, the performance metrics of the PKMA model are an improvement of an average of 87.02%, 72.42%, and 69.24%. |
| first_indexed | 2024-03-11T04:03:35Z |
| format | Article |
| id | doaj.art-5bbb5259e10f43ddab38ec15bd150460 |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-11T04:03:35Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-5bbb5259e10f43ddab38ec15bd1504602023-11-17T23:57:48ZengMDPI AGWater2073-44412023-04-01159173410.3390/w15091734Pearson K-Mean Multi-Head Attention Model for Deformation Prediction of Super-High Dams in First ImpoundmentsYilun Wei0Chang Liu1Hang Duan2Yajun Wang3Yu Hu4Xuezhou Zhu5Yaosheng Tan6Lei Pei7College of Ocean Engineering Equipment, Zhejiang Ocean University, Zhoushan 316000, ChinaHydraulic Department, Tsinghua University, Beijing 100084, ChinaChina Three Gorges Group Corporation, Beijing 100038, ChinaCollege of Ocean Engineering Equipment, Zhejiang Ocean University, Zhoushan 316000, ChinaHydraulic Department, Tsinghua University, Beijing 100084, ChinaHydraulic Department, Tsinghua University, Beijing 100084, ChinaChina Three Gorges Group Corporation, Beijing 100038, ChinaChina Three Gorges Group Corporation, Beijing 100038, ChinaThe first impoundment of a super-high dam is a crucial period from dam construction to operation, in which the prediction of the dam deformation is vital for the continued safety of the dam. Therefore, a multi-head attention model based on Pearson K-means clustering is proposed, which is shortened to PKMA. The inputs of the PKMA include measurements of the displacements of plumb lines, water levels, air temperatures, dam body temperatures, water temperatures, and foundation temperatures. Among these inputs, variables related to displacements are regarded as the dominant explanatory factors. Hence, the K-means clustering based on the Pearson index is utilised to increase the weights of displacements in the PKMA. To involve the interactions between inputs, the MA mechanism of neural networks is used to simulate the relationship between inputs and deformation targets. The PKMA model had a maximum MSE of 1.2518 and a maximum MAE of 0.9017 for the model performance metrics at the study measurement points. Compared to the comparison models MA, HST, and LSTM, the performance metrics of the PKMA model are an improvement of an average of 87.02%, 72.42%, and 69.24%.https://www.mdpi.com/2073-4441/15/9/1734PKMAfirst impoundmentsuper-high arch damsdeformation predictionPearsonK-means |
| spellingShingle | Yilun Wei Chang Liu Hang Duan Yajun Wang Yu Hu Xuezhou Zhu Yaosheng Tan Lei Pei Pearson K-Mean Multi-Head Attention Model for Deformation Prediction of Super-High Dams in First Impoundments Water PKMA first impoundment super-high arch dams deformation prediction Pearson K-means |
| title | Pearson K-Mean Multi-Head Attention Model for Deformation Prediction of Super-High Dams in First Impoundments |
| title_full | Pearson K-Mean Multi-Head Attention Model for Deformation Prediction of Super-High Dams in First Impoundments |
| title_fullStr | Pearson K-Mean Multi-Head Attention Model for Deformation Prediction of Super-High Dams in First Impoundments |
| title_full_unstemmed | Pearson K-Mean Multi-Head Attention Model for Deformation Prediction of Super-High Dams in First Impoundments |
| title_short | Pearson K-Mean Multi-Head Attention Model for Deformation Prediction of Super-High Dams in First Impoundments |
| title_sort | pearson k mean multi head attention model for deformation prediction of super high dams in first impoundments |
| topic | PKMA first impoundment super-high arch dams deformation prediction Pearson K-means |
| url | https://www.mdpi.com/2073-4441/15/9/1734 |
| work_keys_str_mv | AT yilunwei pearsonkmeanmultiheadattentionmodelfordeformationpredictionofsuperhighdamsinfirstimpoundments AT changliu pearsonkmeanmultiheadattentionmodelfordeformationpredictionofsuperhighdamsinfirstimpoundments AT hangduan pearsonkmeanmultiheadattentionmodelfordeformationpredictionofsuperhighdamsinfirstimpoundments AT yajunwang pearsonkmeanmultiheadattentionmodelfordeformationpredictionofsuperhighdamsinfirstimpoundments AT yuhu pearsonkmeanmultiheadattentionmodelfordeformationpredictionofsuperhighdamsinfirstimpoundments AT xuezhouzhu pearsonkmeanmultiheadattentionmodelfordeformationpredictionofsuperhighdamsinfirstimpoundments AT yaoshengtan pearsonkmeanmultiheadattentionmodelfordeformationpredictionofsuperhighdamsinfirstimpoundments AT leipei pearsonkmeanmultiheadattentionmodelfordeformationpredictionofsuperhighdamsinfirstimpoundments |