Email Alerts
RSS
Concrete dam deformation prediction based on CEEMDAN-PE-LSTM model
-
摘要: 由于混凝土坝变形监测数据有明显的非线性、非平稳特征，且数据序列包含一定的噪声，容易导致模型预测精度不高。针对上述问题，提出了基于自适应噪声完全集合经验模态分解（CEEMDAN）-排列熵（PE）-长短时记忆神经网络（LSTM）的混凝土坝变形预测模型。利用CEEMDAN对非线性信号的自适应分解能力，将原始变形数据分解为频率不同、复杂度差异明显的一组固有模态函数（IMF），降低序列中不同尺度信息的相互影响。基于PE算法将复杂度相近的IMF分量进行合并重组。最后，对若干重组序列分别构建LSTM模型进行预测，将预测结果相加得到最终变形预测值。以某混凝土坝水平位移监测数据进行建模分析，结果表明：CEEMDAN-PE-LSTM模型与常规模型相比预测精度显著提高，能更好地对非线性数据序列进行预测。与单一的LSTM模型相比，平均绝对误差、平均绝对百分比误差和均方根误差分别降低了76.43%、75.55%和74.73%，表明该模型通过对原始序列的分解与重组获取不同尺度特征，可以更好地把握非线性、非平稳数据的变化规律，提高预测精度，能有效运用于混凝土坝的变形预测。Abstract: As the deformation monitoring data of concrete dam has evident non-linear and non-stationary characteristics, and the data sequence contains a certain amount of noise, it is easy to lead to low accuracy predicted by the model. Aiming at the above issues, the deformation prediction model established for concrete dam, which is referred to as the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) - permutation entropy (PE) - long short-term memory (LSTM), is proposed. Using the capability of CEEMDAN to adaptively decompose non-linear signals, this model decomposes original deformation data into a set of intrinsic mode functions (IMF) with different frequencies and obvious differences in complexity, which reduces the mutual influence of distinct scale information in the sequence. Then, the IMF quantities with similar complexity are combined and reorganized. Finally, LSTM models are respectively constructed for several re-organized sequences to perform prediction, and then the predicted results are added to obtain the final prediction. This study is based on modeling and analyzing the horizontal displacement monitoring data of a concrete dam. The results demonstrate that the CEEMDAN-PE-LSTM model shows significant improvement in accuracy compared to the conventional model, and is able to better predict nonlinear data sequence. As compared to the LSTM model, the mean average error (MAE), mean average percentage error (MAPE) and relative mean square error (RMSE) are reduced by 76.43%, 75.55% and 74.73%, respectively, suggesting that the proposed model can better exploit the variability of non-linear and non-stationary data by decomposing and reorganizing the original sequence to obtain distinct scale features with improved prediction accuracy, and can be effectively applied to the deformation prediction of concrete dams.
-
Key words:
- deformation prediction /
- empirical mode /
- permutation entropy /
- time series /
- neural network
-
图 3 EX4测点水平位移实测序列过程线
Figure 3. Process line of measured sequence of horizontal displacement of EX4 measuring point
图 4 基于CEEMDAN的变形序列分解结果
Figure 4. Decomposition result of deformation sequence based on CEEMDAN
图 7 经过CEEMDAN-PE处理的变形重组序列
Figure 7. Deformed recombination sequence processed by CEEMDAN-PE
表 1 各IMF分量合并方案
Table 1. IMF components merger scheme
X1 X2 X3 X4 IMF1+IMF2 IMF3 IMF4+IMF5+IMF6 IMF7 
下载: 导出CSV
表 2 各预测模型性能指标对比
Table 2. Comparisons of prediction performance indexes for each prediction model
模型 平均绝对误差/mm 平均绝对百分比误差/% 均方根误差/mm PLSR 0.440 27.143 0.481 SVR 0.305 17.520 0.377 LSTM 0.157 9.078 0.182 CEEMDAN-PE-LSTM 0.037 2.220 0.046
下载: 导出CSV
-
[1] 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. (WU Zhongru, CHEN Bo. A review on development of dam safety monitoring models[J]. Modern Surveying and Mapping, 2016, 39(5): 1-3, 8. (in Chinese) [2] 顾冲时, 苏怀智, 王少伟. 高混凝土坝长期变形特性计算模型及监控方法研究进展[J]. 水力发电学报,2016,35(5):1-14. (GU Chongshi, SU Huaizhi, WANG Shaowei. Advances in calculation models and monitoring methods for long-term deformation behavior of concrete dams[J]. Journal of Hydroelectric Engineering, 2016, 35(5): 1-14. (in Chinese) [3] 郑旭东, 陈天伟, 王雷, 等. 基于EEMD-PCA-ARIMA模型的大坝变形预测[J]. 长江科学院院报,2020,37(3):57-63. (ZHENG Xudong, CHEN Tianwei, WANG Lei, et al. Dam deformation prediction using EEMD-PCA-ARIMA model[J]. Journal of Yangtze River Scientific Research Institute, 2020, 37(3): 57-63. (in Chinese) [4] 罗德河, 郑东健. 大坝变形的小波分析与ARMA预测模型[J]. 水利水运工程学报,2016(3):70-75. (LUO Dehe, ZHENG Dongjian. Wavelet analysis and ARMA prediction model for dam deformation[J]. Hydro-Science and Engineering, 2016(3): 70-75. (in Chinese) [5] HUANG N E, SHEN Z, LONG S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 1998, 454(1971): 903-995. doi: 10.1098/rspa.1998.0193 [6] WU Z H, HUANG N E. Ensemble empirical mode decomposition: a noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis, 2009, 1(1): 1-41. doi: 10.1142/S1793536909000047 [7] 魏博文, 钟紫蒙. 基于改进小波阈值-EMD算法的高拱坝结构振动响应分析[J]. 水利水运工程学报,2019(4):83-91. (WEI Bowen, ZHONG Zimeng. Flow-induced vibration response analysis of high arch dam discharge structure based on improved wavelet threshold-EMD algorithm[J]. Hydro-Science and Engineering, 2019(4): 83-91. (in Chinese) [8] COLOMINAS M A, SCHLOTTHAUER G, TORRES M E, et al. Noise-assisted EMD methods in action[J]. Advances in Adaptive Data Analysis, 2012, 4(4): 1250025. doi: 10.1142/S1793536912500252 [9] 田秀娟, 于德新, 邢雪, 等. 交叉口短时流量CEEMDAN-PE-OSELM预测模型[J]. 哈尔滨工业大学学报,2018,50(3):83-89. (TIAN Xiujuan, YU Dexin, XING Xue, et al. Prediction model of CEEMDAN-PE-OSELM for intersections short-term traffic flow[J]. Journal of Harbin Institute of Technology, 2018, 50(3): 83-89. (in Chinese) [10] CAO J, LI Z, LI J. Financial time series forecasting model based on CEEMDAN and LSTM[J]. Physica A: Statistical Mechanics and its Applications, 2019, 519: 127-139. doi: 10.1016/j.physa.2018.11.061 [11] LIN H L, SUN Q B, CHEN S Q. Reducing exchange rate risks in international trade: a hybrid forecasting approach of CEEMDAN and multilayer LSTM[J]. Sustainability, 2020, 12(6): 2451. doi: 10.3390/su12062451 [12] 韩庆阳, 王晓东, 李丙玉, 等. EEMD在同时消除脉搏血氧检测中脉搏波信号高频噪声和基线漂移中的应用[J]. 电子与信息学报,2015,37(6):1384-1388. (HAN Qingyang, WANG Xiaodong, LI Bingyu, et al. Using EEMD to eliminate high frequency noise and baseline drift in pluse blood-oximetry measurement simultaneously[J]. Journal of Electronics & Information Technology, 2015, 37(6): 1384-1388. (in Chinese) [13] 魏博文, 袁冬阳, 蔡磊, 等. 基于BP-ARIMA的混凝土坝多尺度变形组合预报模型[J]. 水利水运工程学报,2018(2):52-60. (WEI Bowen, YUAN Dongyang, CAI Lei, et al. Multi-scale deformation combination forecast model for concrete dam based on BP-ARIMA[J]. Hydro-Science and Engineering, 2018(2): 52-60. (in Chinese) [14] 陈斯煜, 戴波, 林潮宁, 等. 基于PCA-RBF神经网络的混凝土坝位移趋势性预测模型[J]. 水利水电技术,2018,49(4):45-49. (CHEN Siyu, DAI Bo, LIN Chaoning, et al. PCA-RBF neural network-based prediction model fordisplacement trend of concrete dam[J]. Water Resources and Hydropower Engineering, 2018, 49(4): 45-49. (in Chinese) [15] 杨贝贝. 基于相空间重构的大坝服役性态小波支持向量机预测模型[J]. 水利水电技术,2016,47(10):83-87. (YANG Beibei. Phase space reconstruction-based wavelet support vector machine prediction model for dam service behavior[J]. Water Resources and Hydropower Engineering, 2016, 47(10): 83-87. (in Chinese) [16] MA X L, TAO Z M, WANG Y H, et al. Long short-term memory neural network for traffic speed prediction using remote microwave sensor data[J]. Transportation Research Part C: Emerging Technologies, 2015, 54: 187-197. doi: 10.1016/j.trc.2015.03.014 [17] QU X D, YANG J, CHANG M. A deep learning model for concrete dam deformation prediction based on RS-LSTM[J]. Journal of Sensors, 2019, 2019: 4581672. [18] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780. doi: 10.1162/neco.1997.9.8.1735 [19] 杨亮, 刘春红, 郭昱辰, 等. 基于EMD-LSTM的猪舍氨气浓度预测研究[J]. 农业机械学报,2019,50(增刊1):353-360. (YANG Liang, LIU Chunhong, GUO Yuchen, et al. Prediction of ammonia concentration in fattening piggery based on EMD-LSTM[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(Suppl1): 353-360. (in Chinese) -
点击查看大图
图(8) / 表 (2)
计量
- 文章访问数: 458
- HTML全文浏览量: 244
- PDF下载量: 38
- 被引次数: 0
