A Multi-model Coupled Dam Deformation Prediction Method Based on Interpretable Factor Selection
Received date: 2024-09-27
Revised date: 2024-11-27
Online published: 2025-01-23
At present, it is difficult for traditional models and single models to fully capture the complexity and diversity of dam deformation data, resulting in limited predictive performance and interpretation ability. In order to solve the above problems, an efficient and interpretable dam deformation prediction method was proposed by combining and optimizing various prediction models. First, the Least Absolute Shrinkage and Selection Operation (LASSO) was used for efficient screening among environmental variables, both simplifying model input and explaining the reliability of factor selection. Then, Long Short-Term Memory (LSTM) network was employed to predict dam deformation, and Attention Mechanism was introduced to enhance the extraction of important information. Finally, Bagging (bootstrap aggregating) algorithm was used to integrate multiple model prediction results to further improve the accuracy, stability and generalization ability of the overall prediction. Taking a roller-compacted concrete gravity dam as an example, the model built has a high prediction accuracy, and the average MAE, MSE and RMSE at each measuring point are 0.042mm, 0.004mm and 0.053mm respectively. The comparative analysis with various commonly used models shows that the coupled model can capture the dynamic change of dam deformation more accurately, which provides a simple and efficient method for the study of prediction models.
LIU Cong-cong , ZHANG Feng , HU Chao , ZHANG Qi-ling , GUO Yong-cheng . A Multi-model Coupled Dam Deformation Prediction Method Based on Interpretable Factor Selection[J]. Journal of Changjiang River Scientific Research Institute, 0 . DOI: 10.11988/ckyyb.20241019
| [1] |
李明超, 任秋兵, 孔锐, 等. 多维复杂关联因素下的大坝变形动态建模与预测分析[J]. 水利学报, 2019, 50(6): 687-698.
|
| [2] |
王瑞婕, 包腾飞, 李扬涛, 等. 基于多因子融合和Stacking集成学习的大坝变形组合预测模型[J]. 水利学报, 2023, 54(4): 497-506.
|
| [3] |
龙江, 左生龙, 徐朗, 等. 基于影响因子筛选和GWO-KELM的大坝变形预测模型[J]. 中国农村水利水电2024, (8): 194-199,207.
(
|
| [4] |
张孟昕, 陈波, 刘伟琪, 等. SSA-XGBoost与时空特征选取的大坝变形预测模型[J]. 水力发电学报, 2024, 43(1): 84-98.
|
| [5] |
罗璐, 李志, 张启灵. 大坝变形预测的最优因子长短期记忆网络模型[J]. 水力发电学报, 2023, 42(2): 24-35.
|
| [6] |
黄海燕, 艾星星, 刘兴阳, 等. 基于可解释性分析的大坝变形监控模型对比研究[J]. 人民长江, 2024, 55(9): 203-209.
|
| [7] |
陈斯煜, 顾冲时, 盛金保, 等. SBL驱动的可解释性大坝变形区间预测模型[J/OL]. 水力发电学报, 1-11[2024-11-22]. 2024-11-22]. http: //kns. cnki.net/kcms/detail/11.2241.TV.20241016.0900.006.html. ) (in Chinese)
|
| [8] |
姜振翔, 徐镇凯, 魏博文. 基于小波分解和支持向量机的大坝位移监控模型[J]. 长江科学院院报, 2016, 33(1): 43-47.
|
| [9] |
朱小韦, 袁占良, 李宏超. 基于BP-PCA-WCA-SVM的混凝土大坝变形预测方法[J]. 长江科学院院报, 2024, 41(9): 138-145.
|
| [10] |
崔婷婷, 安雪莲, 孙德亮, 等. 基于SHAP的可解释机器学习的滑坡易发性评价模型[J/OL]. 成都理工大学学报(自然科学版), 1-29[2024-11-22]. 2024-11-22]. http: //kns. cnki. net/kcms/detail/51. 1634. N. 20240819. 1531. 004. html. ) (in Chinese)
|
| [11] |
李端有, 周元春, 甘孝清. 混凝土拱坝多测点确定性位移监控模型研究[J]. 水利学报, 2011, 42(8): 981-985,994.
(
|
| [12] |
何裕坤, 晁阳, 李同春, 等. 基于SBO-LSTM的大坝变形预测模型[J]. 水利水电技术(中英文), 2024, 55(S1): 78-86.
(
|
| [13] |
翁鸣昊, 项兴华, 陈俊涛, 等. 基于LSTM与Transformer的大坝变形预测研究[J]. 中国农村水利水电, 2024, (4): 250-257.
(
|
| [14] |
姜建国, 陈鹏, 郭晓丽, 等. 基于双注意力机制的Seq2Seq短期负荷预测[J]. 吉林大学学报(信息科学版), 2023, 41(2): 251-258.
|
| [15] |
向镇洋, 包腾飞, 白妍丽, 等. 基于混合注意力机制和深度学习的大坝变形预测模型[J]. 水利水电科技进展, 2023, 43(2): 96-101.
|
| [16] |
王晓玲, 梁羽翎, 王佳俊, 等. 耦合注意力机制大坝变形改进LSTM序列到序列预测模型[J]. 天津大学学报(自然科学与工程技术版), 2023, 56(7): 702-712.
|
| [17] |
|
| [18] |
郭张军, 黄华东, 屈旭东. 基于深度学习的大坝变形预测模型[J]. 水电能源科学, 2020, 38(3): 83-86,185.
(
|
| [19] |
施彦彤, 郑东健, 赵汉, 等. 基于CNN-Attention-LSTM的大坝变形预测模型[J]. 水利水电技术(中英文), 2024, 55(9): 121-132.
|
| [20] |
邓思源, 周兰庭, 王飞, 等. 大坝变形的XGBoost-LSTM变权组合预测模型及应用[J]. 长江科学院院报, 2022, 39(10): 72-79.
|
| [21] |
刘丹, 吕倩, 胡少华, 等. 大坝变形GA-LSTM组合预测模型研究[J]. 安全与环境学报, 2023, 23(7): 2246-2253.
|
| [22] |
王悦, 曹颖, 许方党, 等. 考虑非滑坡样本选取和集成机器学习方法的水库滑坡易发性预测[J]. 地球科学, 2024, 49(5): 1619-1635.
|
| [23] |
|
| [24] |
王晓玲, 谢怀宇, 王佳俊, 等. 基于Bootstrap和ICS-MKELM算法的大坝变形预测[J]. 水力发电学报, 2020, 39(3): 106-120.
|
/
| 〈 |
|
〉 |