Dam Deformation Prediction Considering the Seasonal Fluctuations Using Ensemble Learning Algorithm
Abstract
:1. Introduction
- The STL algorithm is used to decompose the deformation series of the concrete dam, thereby identifying its seasonal fluctuations. The decomposition results show that this algorithm can effectively separate the seasonal and non-seasonal components in the deformation series.
- The TPE algorithm is used to optimize the parameters of the prediction model. The transparency of the optimization process is enhanced through visualizations of the parameter optimization history, parameter optimization relationships, and parameter importance.
- The XGBOOST model is applied to the prediction process of both the seasonal and non-seasonal components. Other popular machine learning models are introduced as benchmark models to validate the performance of the proposed model. The comparison results indicate that the predictive accuracy of the proposed model surpasses that of the benchmark models.
- Using feature importance measures, the contributions of the water pressure component, temperature component, and aging component in predicting the seasonal and non-seasonal fluctuations of concrete dam deformations are analyzed.
2. Methodology
2.1. Seasonal Decomposition Based on Loess
2.2. XGBoost Algorithm
2.2.1. The Basic Principles of XGBoost
2.2.2. Key Parameters of XGBoost
2.3. TPE Optimization Algorithm
3. The Modeling Framework and Performance Analysis
3.1. The Primary Steps of the Proposed Model
- (1)
- The concrete dam measured deformation series is decomposed based on STL method to obtain three components: the trend, seasonal, and residual components. The trend component and the residual component are combined as the non-seasonal component ().
- (2)
- The dataset of each component is partitioned into training and validation sets, maintaining a ratio of 4:1.
- (3)
- (4)
- For seasonal components () and non-seasonal components (), the XGBoost model is used for prediction modeling. To enhance the generalization capability of the model and reduce overfitting, the TPE optimization algorithm is introduced to obtain the most reliable parameters [52]. Multiple benchmark models are utilized for the comparative assessment of the predictive efficacy of the proposed model.
- (5)
- The prediction results for the seasonal components () and non-seasonal components () produced by XGBoost algorithm are amalgamated through summation, yielding a consolidated output that signifies the ultimate predicted deformation of the concrete dam.
3.2. Analysis of the Predictive Performance
- (1)
- RMSE:
- (2)
- MAE
- (3)
- R2
4. Empirical Analysis
4.1. Dataset Information
4.2. STL Time Series Decomposition
4.3. TPE Parameter Optimization
4.4. Proposed Model Performance Evaluation
4.5. Prediction Results Analysis
4.6. Generalization Performance of the Proposed Model
5. Conclusions and Future Work
- The STL method can effectively identify the seasonal fluctuations in a concrete dam deformation series and decompose them into seasonal and non-seasonal components. The seasonal component exhibits clear periodic features, while the non-seasonal component shows strong nonlinear features, validating the effectiveness of the STL method.
- Four well-established methods commonly utilized for forecasting a concrete dam deformation series are employed as benchmark models for comparison. Based on qualitative analysis (linear regression analysis and boxplots), the proposed model demonstrates better fitting accuracy to the data and smaller prediction residuals. As for quantitative assessment (evaluation indicators), It achieved the best performance on the evaluation metrics RMSE, MAE, and , with specific values of 0.081, 0.062, and 0.998, respectively.
- Utilizing feature importance measures, the study delved into the relationship between input factors and the seasonal and non-seasonal components of the concrete dam deformation sequence. For the non-seasonal component, the contributions of water pressure, temperature, and aging components are 0.486, 0.359, and 0.155, respectively. For the seasonal component, the contributions of water pressure, temperature, and aging components are 0.328, 0.436, and 0.236, respectively.
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Li, Y.; Li, Y.; He, J. Strategic countermeasures for China’s water resources security in the new development stage. J. Hydraul. Eng. 2021, 52, 1340–1346+1354. [Google Scholar] [CrossRef]
- Liu, N.; Jia, J.; Liu, Z.; Jia, F. Ministry of water resources of the people’s republic of China. In SL 678–2014 Technical Guideline for Cemented Granular Material Dams; China Water & Power Press: Beijing, China, 2014. [Google Scholar]
- Huang, M.; Zhang, J.; Hu, J.; Ye, Z.; Deng, Z.; Wan, N. Nonlinear modeling of temperature-induced bearing displacement of long-span single-pier rigid frame bridge based on DCNN-LSTM. Case Stud. Therm. Eng. 2024, 53, 103897. [Google Scholar] [CrossRef]
- Zhang, J.; Huang, M.; Wan, N.; Deng, Z.; He, Z.; Luo, J. Missing measurement data recovery methods in structural health Monitoring: The State, challenges and case study. Measurement 2024, 231, 114528. [Google Scholar] [CrossRef]
- Zhao, E.; Gu, C. Review on health diagnosis of long-term service behaviors for concrete dams. J. Hydroelectr. Eng. 2021, 40, 22–34. [Google Scholar] [CrossRef]
- Beiranvand, B.; Rajaee, T. Application of artificial intelligence-based single and hybrid models in predicting seepage and pore water pressure of dams: A state-of-the-art review. Adv. Eng. Softw. 2022, 173, 103268. [Google Scholar] [CrossRef]
- Li, Y.; Bao, T. A real-time multi-defect automatic identification framework for concrete dams via improved YOLOv5 and knowledge distillation. J. Civ. Struct. Health Monit. 2023, 13, 1333–1349. [Google Scholar] [CrossRef]
- Cao, W.; Wen, Z.; Su, H. Spatiotemporal clustering analysis and zonal prediction model for deformation behavior of super-high arch dams. Expert Syst. Appl. 2023, 216, 119439. [Google Scholar] [CrossRef]
- Su, H.; Li, J.; Wen, Z.; Guo, Z.; Zhou, R. Integrated certainty and uncertainty evaluation approach for seepage control effectiveness of a gravity dam. Appl. Math. Model. 2019, 65, 1–22. [Google Scholar] [CrossRef]
- Liu, B.; Wei, B.; Li, H.; Mao, Y. Multipoint hybrid model for RCC arch dam displacement health monitoring considering construction interface and its seepage. Appl. Math. Model. 2022, 110, 674–697. [Google Scholar] [CrossRef]
- Wang, S.; Sui, X.; Liu, Y.; Gu, H.; Xu, B.; Xia, Q. Prediction and interpretation of the deformation behaviour of high arch dams based on a measured temperature field. J. Civ. Struct. Health Monit. 2023, 13, 661–675. [Google Scholar] [CrossRef]
- Deng, Z.; Huang, M.; Wan, N.; Zhang, J. The Current Development of Structural Health Monitoring for Bridges: A Review. Buildings 2023, 13, 1360. [Google Scholar] [CrossRef]
- Huang, M.; Ling, Z.; Sun, C.; Lei, Y.; Xiang, C.; Wan, Z.; Gu, J. Two-stage damage identification for bridge bearings based on sailfish optimization and element relative modal strain energy. Struct. Eng. Mech. 2023, 86, 715–730. [Google Scholar]
- Yang, S.; Han, X.; Kuang, C.; Fang, W.; Zhang, J.; Yu, T. Comparative Study on Deformation Prediction Models of Wuqiangxi Concrete Gravity Dam Based onMonitoring Data. CMES-Comput. Model. Eng. Sci. 2022, 131. [Google Scholar] [CrossRef]
- Wen, L.; Li, Y.; Chai, J. Multiple nonlinear regression models for predicting deformation behavior of concrete-face rockfill dams. Int. J. Geomech. 2021, 21, 04020253. [Google Scholar] [CrossRef]
- Li, B.; Han, X.; Yao, M.; Tian, J.; Zheng, Q. Quantitative analysis method for the importance of stress influencing factors of a high arch dam during the operation period using SPA–OSC–PLS. Struct. Control Health Monit. 2022, 29, e3087. [Google Scholar] [CrossRef]
- Dai, B.; Gu, H.; Zhu, Y.; Chen, S.; Rodriguez, E.F. On the Use of an Improved Artificial Fish Swarm Algorithm-Backpropagation Neural Network for Predicting Dam Deformation Behavior. Complexity 2020, 2020, 5463893. [Google Scholar] [CrossRef]
- Li, X.; Wen, Z.; Su, H. An approach using random forest intelligent algorithm to construct a monitoring model for dam safety. Eng. Comput. 2021, 37, 39–56. [Google Scholar] [CrossRef]
- Zhang, Y.; Zhang, W.; Li, Y.; Wen, L.; Sun, X. AF-OS-ELM-MVE: A new online sequential extreme learning machine of dam safety monitoring model for structure deformation estimation. Adv. Eng. Inform. 2024, 60, 102345. [Google Scholar] [CrossRef]
- Wang, S.; Xu, C.; Liu, Y.; Wu, B. A spatial association-coupled double objective support vector machine prediction model for diagnosing the deformation behaviour of high arch dams. Struct. Health Monit. 2022, 21, 945–964. [Google Scholar] [CrossRef]
- Li, B.; Yang, J.; Hu, D. Dam monitoring data analysis methods: A literature review. Struct. Control Health Monit. 2020, 27, e2501. [Google Scholar] [CrossRef]
- Flah, M.; Nunez, I.; Ben Chaabene, W.; Nehdi, M.L. Machine learning algorithms in civil structural health monitoring: A systematic review. Arch. Comput. Methods Eng. 2021, 28, 2621–2643. [Google Scholar] [CrossRef]
- Salazar, F.; Morán, R.; Toledo, M.Á.; Oñate, E. Data-based models for the prediction of dam behaviour: A review and some methodological considerations. Arch. Comput. Methods Eng. 2017, 24, 1–21. [Google Scholar] [CrossRef]
- Narwaria, M. Does explainable machine learning uncover the black box in vision applications? Image Vis. Comput. 2022, 118, 104353. [Google Scholar] [CrossRef]
- Molnar, C.; Casalicchio, G.; Bischl, B. Interpretable machine learning–a brief history, state-of-the-art and challenges. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases; Springer International Publishing: Cham, Switzerland, 2020; pp. 417–431. [Google Scholar]
- Murdoch, W.J.; Singh, C.; Kumbier, K.; Abbasi-Asl, R.; Yu, B. Definitions, methods, and applications in interpretable machine learning. Proc. Natl. Acad. Sci. USA 2019, 116, 22071–22080. [Google Scholar] [CrossRef] [PubMed]
- Chen, T.; Guestrin, C. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August 2016; pp. 785–794. [Google Scholar]
- Mazumder, R.K.; Salman, A.M.; Li, Y. Failure risk analysis of pipelines using data-driven machine learning algorithms. Struct. Saf. 2021, 89, 102047. [Google Scholar] [CrossRef]
- Ma, M.; Zhao, G.; He, B.; Li, Q.; Dong, H.; Wang, S.; Wang, Z. XGBoost-based method for flash flood risk assessment. J. Hydrol. 2021, 598, 126382. [Google Scholar] [CrossRef]
- Duan, J.; Asteris, P.G.; Nguyen, H.; Bui, X.-N.; Moayedi, H. A novel artificial intelligence technique to predict compressive strength of recycled aggregate concrete using ICA-XGBoost model. Eng. Comput. 2021, 37, 3329–3346. [Google Scholar] [CrossRef]
- Jabeur, S.B.; Mefteh-Wali, S.; Viviani, J.-L. Forecasting gold price with the XGBoost algorithm and SHAP interaction values. Ann. Oper. Res. 2024, 334, 679–699. [Google Scholar] [CrossRef]
- Yun, K.; Yoon, S.; Won, D. Prediction of stock price direction using a hybrid GA-XGBoost algorithm with a three-stage feature engineering process. Expert Syst. Appl. 2021, 186, 115716. [Google Scholar] [CrossRef]
- Shi, R.; Xu, X.; Li, J.; Li, Y. Prediction and analysis of train arrival delay based on XGBoost and Bayesian optimization. Appl. Soft Comput. 2021, 109, 107538. [Google Scholar] [CrossRef]
- Wen, Z.; Zhou, R.; Su, H. MR and stacked GRUs neural network combined model and its application for deformation prediction of concrete dam. Expert Syst. Appl. 2022, 201, 117272. [Google Scholar] [CrossRef]
- Lin, C.; Li, T.; Chen, S.; Lin, C.; Liu, X.; Gao, L.; Sheng, T. Structural identification in long-term deformation characteristic of dam foundation using meta-heuristic optimization techniques. Adv. Eng. Softw. 2020, 148, 102870. [Google Scholar] [CrossRef]
- Qiu, Y.; Zhou, J.; Khandelwal, M.; Yang, H.; Yang, P.; Li, C. Performance evaluation of hybrid WOA-XGBoost, GWO-XGBoost and BO-XGBoost models to predict blast-induced ground vibration. Eng. Comput. 2022, 38 (Suppl. 5), 4145–4162. [Google Scholar] [CrossRef]
- Masum, M.; Shahriar, H.; Haddad, H.; Faruk, M.J.H.; Valero, M.; Khan, M.A.; Rahman, M.A.; Adnan, M.I.; Cuzzocrea, A.; Wu, F. Bayesian hyperparameter optimization for deep neural network-based network intrusion detection. In Proceedings of the IEEE International Conference on Big Data (Big Data), Orlando, FL, USA, 15–18 December 2021; pp. 5413–5419. [Google Scholar]
- Erwianda, M.S.F.; Kusumawardani, S.S.; Santosa, P.I.; Rimadana, M.R. Improving confusion-state classifier model using xgboost and tree-structured parzen estimator. In Proceedings of the International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), Yogyakarta, Indonesia, 5–6 December 2019; pp. 309–313. [Google Scholar]
- Yang, Y. Market Forecast using XGboost and Hyperparameters Optimized by TPE. In Proceedings of the IEEE International Conference on Artificial Intelligence and Industrial Design (AIID), Guangzhou, China, 28–30 May 2021; pp. 7–10. [Google Scholar]
- Liu, Y.; Teza, G.; Nava, L.; Chang, Z.; Shang, M.; Xiong, D.; Cola, S. Deformation evaluation and displacement forecasting of baishuihe landslide after stabilization based on continuous wavelet transform and deep learning. Nat. Hazards 2024, 1–25. [Google Scholar] [CrossRef]
- Zhu, Y.; Gao, Y.; Wang, Z.; Cao, G.; Wang, R.; Lu, S.; Li, W.; Nie, W.; Zhang, Z. A Tailings Dam Long-Term Deformation Prediction Method Based on Empirical Mode Decomposition and LSTM Model Combined with Attention Mechanism. Water 2022, 14, 1229. [Google Scholar] [CrossRef]
- Yang, J.; Lv, Z. Research on dam foundation deformation prediction based on VMD optimized temporal convolutional network. In Proceedings of the 7th International Conference on Hydraulic and Civil Engineering & Smart Water Conservancy and Intelligent Disaster Reduction Forum (ICHCE & SWIDR), Nanjing, China, 6–8 November 2021; pp. 232–238. [Google Scholar]
- Yan, T.; Chen, B. Dam Deformation Prediction Based on EEMD-ELM Model. In Proceedings of the EGU General Assembly Conference Abstracts; p. 1220. [CrossRef]
- Zhang, G.P.; Qi, M. Neural network forecasting for seasonal and trend time series. Eur. J. Oper. Res. 2005, 160, 501–514. [Google Scholar] [CrossRef]
- Cleveland, R.B.; Cleveland, W.S.; McRae, J.E.; Terpenning, I. STL: A seasonal-trend decomposition. J. Off. Stat. 1990, 6, 3–73. [Google Scholar]
- Salazar, F.; Toledo, M.A.; Oñate, E.; Morán, R. An empirical comparison of machine learning techniques for dam behaviour modelling. Struct. Saf. 2015, 56, 9–17. [Google Scholar] [CrossRef]
- Zhou, J.; Qiu, Y.; Zhu, S.; Armaghani, D.J.; Khandelwal, M.; Mohamad, E.T. Estimation of the TBM advance rate under hard rock conditions using XGBoost and Bayesian optimization. Undergr. Space 2021, 6, 506–515. [Google Scholar] [CrossRef]
- Shi, X.; Wong, Y.D.; Li, M.Z.-F.; Palanisamy, C.; Chai, C. A feature learning approach based on XGBoost for driving assessment and risk prediction. Accid. Anal. Prev. 2019, 129, 170–179. [Google Scholar] [CrossRef]
- Bergstra, J.; Bardenet, R.; Bengio, Y.; Kégl, B. Algorithms for hyper-parameter optimization. In Proceedings of the 24th International Conference on Neural Information Processing System, Granada, Spain, 12–15 December 2011; pp. 2546–2554. [Google Scholar]
- Léger, P.; Leclerc, M. Hydrostatic, temperature, time-displacement model for concrete dams. J. Eng. Mech. 2007, 133, 267–277. [Google Scholar] [CrossRef]
- Liu, X.; Li, Z.; Sun, L.; Khailah, E.Y.; Wang, J.; Lu, W. A critical review of statistical model of dam monitoring data. J. Build. Eng. 2023, 80, 108106. [Google Scholar] [CrossRef]
- Akiba, T.; Sano, S.; Yanase, T.; Ohta, T.; Koyama, M. Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA, 4–8 August 2019; pp. 2623–2631. [Google Scholar]
Parameter | Explain |
---|---|
Gamma | Minimum loss reduction required to make a further partition on a leaf node of the tree |
Alpha | L1 regularization term on weights |
Eta | Step size shrinkage used in update to prevent overfitting |
Max_depth | Maximum depth of tree |
Min_child_weight | Minimum sum of instance weight needed in a child |
Lambda | L2 regularization term on weights |
Colsample_bytree | The subsample ratio of columns when constructing each tree |
Subsample | Subsample ratio of the training instances |
Booster Parameter | Search Space | Optimal Value |
---|---|---|
Gamma | (0.01, 10) | 0.012 |
Eta | (0.005, 0.5) | 0.015 |
Alpha | (0.01, 10) | 0.031 |
Subsample | (0.1, 0.9) | 0.459 |
Lambda | (0.01, 10) | 0.018 |
Max_depth | (4, 20) | 10 |
Min_child_weight | (0, 10) | 4 |
Colsample_bytree | (0.1, 0.9) | 0.128 |
Comparison Model | Parameters | Optimal Value |
---|---|---|
SVR | C | 0.1 |
Gamma | 1 | |
RF | N_estimators | 100 |
Max_depth | 14 | |
Min_samples_split | 20 | |
Min_samples_leaf | 10 | |
ANN | Hidden_layer_sizes | (1000, 500, 200, 100, 50) |
Models | Evaluation Indicators | ||
---|---|---|---|
RMSE | MAE | R2 | |
XGBoost | 0.081 | 0.062 | 0.998 |
RF | 0.198 | 0.133 | 0.989 |
SVR | 0.228 | 0.181 | 0.985 |
ANN | 0.253 | 0.197 | 0.983 |
MLR | 0.448 | 0.298 | 0.946 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Liu, M.; Feng, Y.; Yang, S.; Su, H. Dam Deformation Prediction Considering the Seasonal Fluctuations Using Ensemble Learning Algorithm. Buildings 2024, 14, 2163. https://doi.org/10.3390/buildings14072163
Liu M, Feng Y, Yang S, Su H. Dam Deformation Prediction Considering the Seasonal Fluctuations Using Ensemble Learning Algorithm. Buildings. 2024; 14(7):2163. https://doi.org/10.3390/buildings14072163
Chicago/Turabian StyleLiu, Mingkai, Yanming Feng, Shanshan Yang, and Huaizhi Su. 2024. "Dam Deformation Prediction Considering the Seasonal Fluctuations Using Ensemble Learning Algorithm" Buildings 14, no. 7: 2163. https://doi.org/10.3390/buildings14072163