许小荣,朱明远,石佳晨

• 1:宝鸡市凤翔区水利建设工程工作队
• 2:新疆水利水电科学研究院
• 3:新疆农业大学水利与土木工程学院

摘要(Abstract)：

大坝变形是评估大坝安全的重要指标，准确预测变形趋势对于保障大坝安全至关重要。然而，由于变形数据的非线性特征和复杂的影响因素，提升预测精度面临较大挑战。为此基于“分解-重构-预测”的思想提出了一种结合群智能优化算法的变分模态分解（VMD）-双向长短期神经网络（BiLSTM）的大坝变形预测模型。该模型首先使用经遗传算法（GA）优化的VMD把原始数据分解为若干个本征模态分量（IMF），并通过计算样本熵将其分为4类。随后使用经改进灰狼算法（IGWO）优化的BiLSTM分别对这4类分量加入环境因素进行预测，最后将4类分量的预测结果叠加获得大坝变形的最终预测结果。工程实例表明，该模型能够准确预测大坝变形，其测试集上平均MAE、MAPE、RMSE分别为0.115、0.038、0.143，相较于传统预测方法，展示出更高的预测精度与稳健性。

关键词(KeyWords)： 群智能优化算法;变分模态分解;样本熵;双向长短期神经网络;变形预测

Abstract:

Keywords:

基金项目(Foundation): 新疆维吾尔自治区公益性科研院所基本科研业务经费项目(KY2024084)

作者(Author): 许小荣,朱明远,石佳晨

参考文献(References)：

• [1] Ren Q, Li M, Li H, et al. A robust prediction model for displacement of concrete dams subjected to irregular water-level fluctuations[J]. Computer-Aided Civil and Infrastructure Engineering,2021, 36(5):577-601.
• [2]赵文剑,黄会宝,陈建康,等.基于监测数据-变形倾度的瀑布沟大坝坝顶开裂成因分析[J].水利规划与设计, 2023(5):141-148.
• [3]吴中如,陈波.大坝变形监控模型发展回眸[J].现代测绘,2016, 39(5):1-3, 8.
• [4]任秋兵,沈扬,李明超,等.水工建筑物安全监控深度分析模型及其优化研究[J].水利学报, 2021, 52(1):71-80.
• [5] Zou J, Bui K-T T, Xiao Y, et al. Dam deformation analysis based on BPNN merging models[J]. GeoSpatial Information Science,2018, 21(2):149-157.
• [6]罗丹,李昌彩,吴长彬.基于微粒群-BP神经网络算法的堆石坝坝体变形监控模型研究[J].岩石力学与工程学报, 2012, 31(S1):2926-2931.
• [7] Cao E, Bao T, Gu C, et al. A novel hybrid decomposition-ensemble prediction model for dam deformation[J]. Applied Sciences, 2020(16):5700.
• [8] Kang F, Liu J, Li J, et al. Concrete dam deformation prediction model for health monitoring based on extreme learning machine[J].Structural Control and Health Monitoring, 2017, 24(10):e1997.
• [9]魏博文,罗绍杨,徐富刚,等.基于监测时序分解再重构的混凝土拱坝位移预测组合模型[J].工程科学与技术, 2022, 54(5):51-63.
• [10]牛景太.基于奇异谱分析与PSO优化SVM的混凝土坝变形监控模型[J].水利水电科技进展, 2020, 40(6):60-65, 77.
• [11] Xing Y, Chen Y, Huang S, et al. Research on Dam Deformation Prediction Model Based on Optimized SVM[J]. Processes, 2022(9):1842.
• [12]李明军,王均星,王亚洲.基于改进粒子群优化算法和极限学习机的混凝土坝变形预测[J].天津大学学报（自然科学与工程技术版）, 2019, 52(11):1136-1144.
• [13]袁冬阳,顾冲时,顾昊.严寒地区混凝土重力坝变形行为分析与预测模型[J].水利学报, 2022, 53(6):733-746.
• [14]陈波,陈伟楠,龚学贤,等.考虑滞后与削减效应的寒区混凝土坝变形预测预报模型[J].岩土工程学报, 2021, 43(12):2315-2322.
• [15]石佳晨,岳春芳,朱明远,等.改进小波阈值与优化BiLSTM组合的大坝变形预测方法[J].水力发电学报, 2024, 43(7):97-108.
• [16] Zhang Y, Zhong W, Li Y, et al. A deep learning prediction model of DenseNet-LSTM for concrete gravity dam deformation based on feature selection[J]. Engineering Structures, 2023, 295:116827.
• [17] Madiniyeti J, Chao Y, Li T, et al. Concrete dam deformation prediction model research based on SSA–LSTM[J]. Applied Sciences, 2023, 13(13):7375.
• [18] Su Y, Weng K, Lin C, et al. Dam deformation interpretation and prediction based on a long short-term memory model coupled with an attention mechanism[J]. Applied Sciences, 2021(14):6625.
• [19] Huang B, Kang F, Li J, et al. Displacement prediction model for high arch dams using long short-term memory based encoder-decoder with dual-stage attention considering measured dam temperature[J]. Engineering Structures, 2023, 280:115686.
• [20]周伟,马刚,安妮,等.高堆石坝变形监测和变形预测关键技术及工程应用[J].水利规划与设计, 2022(11):54-60.
• [21] Lambora A, Gupta K, Chopra K. Genetic algorithm-A literature review[C]//2019 international conference on machine learning,big data, cloud and parallel computing(COMITCon). IEEE,2019:380-384.
• [22] Nadimi-Shahraki M H, Taghian S, Mirjalili S. An improved grey wolf optimizer for solving engineering problems[J]. Expert Systems with Applications, 2021, 166:113917.
• [23] Dragomiretskiy K, Zosso D. Variational mode decomposition[J].IEEE Transactions on Signal Processing, 2014, 62(3):531–544.
• [24] Huang C G, Huang H Z, Li Y F. A bidirectional LSTM prognostics method under multiple operational conditions[J]. IEEE Transactions on Industrial Electronics, 2019, 66(11):8792-8802.
• [25]朱桂勇,侯昊华,刘昌伟.深度学习在坝体变形模型训练与预测中的应用[J].水利技术监督, 2024(12):48-53, 140.
• [26] Greff K, Srivastava R K, Koutník J, et al. LSTM:A search space odyssey[J]. IEEE transactions on neural networks and learning systems, 2016, 28(10):2222-2232.
• [27] Cui Z, Ke R, Pu Z, et al. Stacked bidirectional and unidirectional LSTM recurrent neural network for forecasting network-wide traffic state with missing values[J]. Transportation Research Part C:Emerging Technologies, 2020, 118:102674.
• [28]文井辉,伍荣森,李帅永,等.基于DRSN和优化BiLSTM的轴承剩余寿命预测方法[J/OL].计算机集成制造系统, 1-18[2022-8-26].
• [29]王卫玉,何葵东,金艳,等.基于CEEMDAN样本熵和PSO-SVM的水电机组振动信号特征提取[J].武汉大学学报（工学版）,2022, 55(11):1167-1175.