[1]郑东健,赵　宇,冉　成,等.基于TSNE-NGO-RF算法的混凝土坝变形预测模型[J].郑州大学学报(工学版),2026,47(02):122-127(135).[doi:10.13705/j.issn.1671-6833.2025.05.023]
　ZHENG Dongjian,ZHAO Yu,RAN Cheng,et al.Concrete Dam Deformation Prediction Model Based on TSNE-NGO-RF Algorithm[J].Journal of Zhengzhou University (Engineering Science),2026,47(02):122-127(135).[doi:10.13705/j.issn.1671-6833.2025.05.023]
点击复制

基于TSNE-NGO-RF算法的混凝土坝变形预测模型()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
47
期数:
2026年02期
页码:
122-127(135)
栏目:
出版日期:
2026-02-13

文章信息/Info

Title:
Concrete Dam Deformation Prediction Model Based on TSNE-NGO-RF Algorithm
文章编号:
1671-6833(2026)02-0122-06
作者:
郑东健1;  赵　宇1;  冉　成1;  林英浩1;  陈林泽2
1.河海大学 水利水电学院,江苏 南京 210098;2.河海大学 河海里尔学院,江苏 南京 210098
Author(s):
ZHENG Dongjian1;  ZHAO Yu1;  RAN Cheng1;  LIN Yinghao1;  CHEN Linze2
1.School of Water Conservancy and Hydropower Engineering, Hohai University, Nanjing 210098, China; 2. Institute Hohai-Lille, Hohai University, Nanjing 210098, China
关键词:
混凝土坝;  变形预测;  降维;  北方苍鹰优化算法;  随机森林算法
Keywords:
concrete dam;  deformation prediction;  dimensionality reduction;  northern eagle optimization algorithm;  random forest algorithm
分类号:
TV698 TU528
DOI:
10.13705/j.issn.1671-6833.2025.05.023
文献标志码:
A
摘要:
对混凝土坝变形监测资料进行合理的数据分析和准确的预测是确保大坝安全长效运行的关键手段,针对影响大坝变形的环境量具有周期性和非线性的特点,以及传统随机森林模型参数寻优方法适用性差和计算效率低等问题,提出了一种新型的大坝变形预测模型。该模型采用t-分布式随机邻域嵌入对特征值进行降维,提高模型的分类性能,并运用北方苍鹰优化算法对传统随机森林模型进行了改进,提高了随机森林模型参数的择优选取效率。运用北方苍鹰优化算法在第80次迭代时即可确定随机森林模型的参数,且适应度函数为0.249 3,相较麻雀搜索算法和粒子群优化算法取得了较好的结果。选取某混凝土坝第18#坝段和第26#坝段进行实例分析,结果表明:所提融合模型预测结果的平均绝对误差分别为0.501 93和0.173 02 mm,均方误差分别为0.359 71和0.043 87 mm2,平均绝对百分比误差分别为0.819 59%,0.113 62%,决定系数分别为0.914 56和0.892 74,相较于其他模型,该模型在预测准确性和模型稳定性方面表现最优,为混凝土坝变形的精准预测开辟了新的可能性。
Abstract:
Reasonable data analysis and accurate prediction of deformation monitoring data for concrete dams are key means to ensure the safe and long-term operation of dams. In response to the periodic and nonlinear characteristics of environmental variables that could affect dam deformation, as well as the shortcomings of traditional random forest model parameter optimization methods such as poor applicability and low computational efficiency, a new type of dam deformation prediction model was proposed. The model uses t-distributed random neighborhood embedding to reduce the dimensionality of eigenvalues and improve the classification performance of the model. The traditional random forest model was improved using the northern eagle optimization algorithm, which enhanced the efficiency of selecting optimal parameters for the random forest model. The parameters of the random forest model could be determined using the northern eagle optimization algorithm in the 80th iteration, and the fitness function was 0.249 3, which achieves better results compared to the Sparrow Search Algorithm and Particle Swarm Optimization Algorithm. The analysis of the 18#th and 26#th sections of a concrete dam showed that the fusion model proposed in this study had average absolute errors of 0.501 93 and 0.173 02 mm, mean square errors of 0.359 71 and 0.043 87 mm2, average absolute percentage errors of 0.819 59% and 0.113 62%, and determination coefficients of 0.914 56 and 0.892 74, respectively. Compared with other models, this model performed better in prediction accuracy and model stability, opening up new possibilities for accurate prediction of concrete dam deformation.

参考文献/References:

[1]PRAKASH G, DUGALAM R, BARBOSH M, et al. Recent advancement of concrete dam health monitoring technology: a systematic literature review[J]. Structures, 2022, 44: 766-784.

[2]樊小永, 刘嘉. 水库大坝运行期安全监测分析[J]. 工程技术研究, 2025, 10(9): 223-225.
FAN X Y, LIU J. Analysis of safety monitoring of reservoir dam during operation period[J]. Engineering and Technological Research, 2025, 10(9): 223-225.
[3]王健, 王士军. 全国水库大坝安全监测现状调研与对策思考[J]. 中国水利, 2018(20): 15-19.
WANG J, WANG S J. Investigations on reservoir dam safety monitoring in China and measure study[J]. China Water Resources, 2018(20): 15-19.
[4]龙耿文, 袁树才, 罗家良, 等. 水利工程大坝安全监测技术与发展研究[J]. 水上安全, 2025(20): 148-150.
LONG G W, YUAN S C, LUO J L, et al. Research on dam safety monitoring technology and development of water conservancy projects[J]. Maritime Safety, 2025(20): 148-150.
[5]吴中如, 吉肇泰. 坝前水库水温的变化规律和预测研究[J]. 水力发电, 1984, 10(4): 33-41.
WU Z R, JI Z T. Research on the changes and prediction of water temperature in reservoir [J]. Water Power, 1984, 10(4): 33-41.
[6]刘健, 王继敏, 杨强, 等. 混凝土大坝变形监测异常值识别方法及应用[J]. 水利水电科技进展, 2025, 45(6): 77-84.
LIU J, WANG J M, YANG Q, et al. Method for identification of outliers in concrete dam deformation monitoring and its application[J]. Advances in Science and Technology of Water Resources, 2025, 45(6): 77-84.
[7]MAATEN L V D, HINTON G. Visualizing data using t-SNE[J]. Journal of Machine Learning Research, 2008,9: 2579-2605.
[8]BREIMAN L. Random forests[J]. Machine Learning,2001,45:5-32.
[9]SU H Y, SHEN W J, WANG J R, et al. Machine learning and geostatistical approaches for estimating aboveground biomass in Chinese subtropical forests[J]. Forest Ecosystems, 2020, 7(1): 64.
[10]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.
HUANG H Y, AI X X, LIU X Y, et al. Comparison of monitoring model for dam deformation based on interpretability analysis[J]. Yangtze River, 2024, 55(9): 203-209.
[11]潘宇, 李登华, 丁勇. 基于改进随机森林的大坝监测数据质量评价算法[J]. 人民长江, 2024, 55(2): 231-237.
PAN Y, LI D H, DING Y. Data quality evaluation algorithm on dam monitoring based on improved random forest[J]. Yangtze River, 2024, 55(2): 231-237.
[12]曾永军, 张俊文, 曹登刚, 等. RS-RF模型在混凝土坝变形预测中的应用[J]. 水利水电技术, 2021, 52(5): 82-88.
ZENG Y J, ZHANG J W, CAO D G, et al. Application of RS-RF model in deformation prediction of concrete dam[J]. Water Resources and Hydropower Engineering, 2021, 52(5): 82-88.
[13]仝晓哲, 赵黎晨, 王佳明. 随机森林回归在大坝变形预测中的应用研究[C]∥2019年江苏省测绘地理信息学会学术年会论文集. 南京:江苏省测绘地理信息学会, 2019: 49-51.
TONG X Z, ZHAO L C, WANG J M. Research on the application of random forest regression in dam deformation prediction[C]∥Proceedings of the 2019 Academic Annual Conference of the Jiangsu Society for Geodesy Photogrammetry and Cartography. Nanjing: Jiangsu Society for Geodesy Photogrammetry and Cartography, 2019: 49-51.
[14]宋宝钢, 包腾飞, 向镇洋, 等. 基于小波的SSA-ELM大坝变形时空预测模型[J]. 长江科学院院报, 2023, 40(8): 145-151.
SONG B G, BAO T F, XIANG Z Y, et al. Waveletbased SSA-ELM spatio-temporal prediction model for dam deformation[J]. Journal of Changjiang River Scientific Research Institute, 2023, 40(8): 145-151.
[15]张文煜, 马可可, 郭振海, 等. 基于灰狼算法和极限学习机的风速多步预测[J]. 郑州大学学报(工学版), 2024, 45(2): 89-96.
ZHANG W Y, MA K K, GUO Z H, et al. Multistep prediction of wind speed based on grey wolf algorithm and extreme learning machine[J]. Journal of Zhengzhou University (Engineering Science), 2024, 45(2): 89-96.
[16] DEHGHANI M, HUBÁLOVSKY Š, TROJOVSKY P. Northern goshawk optimization: a new swarm-based algorithm for solving optimization problems[J]. IEEE Access, 2021, 9: 162059-162080.
[17]谭建所, 吴兴华, 徐文光, 等. 基于tSNE-LSTM算法的工业预测模型[J]. 现代电子技术, 2024, 47(12): 81-85.
TAN J S, WU X H, XU W G, et al. Industrial prediction model based on tSNE-LSTM algorithm[J]. Modern Electronics Technique, 2024, 47(12): 81-85.
[18] BARAL P, HAQ M A. Spatial prediction of permafrost occurrence in Sikkim Himalayas using logistic regression, random forests, support vector machines and neural networks[J]. Geomorphology, 2020, 371: 107331.
[19] SHANNON C E. A mathematical theory of communication[J]. Bell System Technical Journal, 1948, 27(3): 379-423.
[20]詹明强, 陈波, 袁志颖. 基于KPCA-NGO-LSSVM的混凝土坝变形预测模型[J]. 水电能源科学, 2024, 42(8): 127-131.
ZHAN M Q, CHEN B, YUAN Z Y. Deformation prediction method of concrete dam based on KPCA-NGO-LSSVM[J]. Water Resources and Power, 2024, 42(8): 127-131.
[21]秦俊德. 陈村大坝坝基渗压问题的探讨[J]. 大坝与安全, 1991(4): 28-33.
QIN J D. Discussion on the seepage pressure problem of Chencun Dam foundation [J]. Large Dam and Safety, 1991(4): 28-33.
[22]吴中如. 水工建筑物安全监控理论及其应用[M]. 北京: 高等教育出版社, 2003: 157-170.
WU Z R. Safety monitoring theory & its application of hydraulic structures[M]. Beijing: Higher Education Press, 2003: 157-170.
[23]张石, 郑东健, 陈卓研. 基于改进PSO-RF算法的大坝变形预测模型[J]. 水利水电科技进展, 2022, 42(6): 39-44.
ZHANG S, ZHENG D J, CHEN Z Y. Dam deformation prediction model based on improved PSO-RF algorithm[J]. Advances in Science and Technology of Water Resources, 2022, 42(6): 39-44.

更新日期/Last Update: 2026-03-04