| 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。本文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，能更好的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（MAE）、平均绝对百分比误差（MAPE）和均方根误差（RMSE）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。 |
| 关键词: 变形预测 完全集合经验模态分解 排列熵 时间序列 长短时记忆神经网络 |
| DOI： |
| 分类号: |
| 基金项目: |
|
| Concrete Dam Deformation Prediction Based on CEEMDAN-PE-LSTM Model |
|
songyang, yangjie, songjintao, chenglin
|
|
Xi’an University of Technology
|
| 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. Aimed 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 hori-zontal displacement monitoring data of a concrete dam. The results demonstrated 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 de-composing and reorganizing the original sequence to obtain distinct scale features, which improves the prediction accuracy, and can be effectively applied to the deformation prediction of concrete dam. |
| Key words: deformation prediction complete ensemble empirical mode decomposition with adaptive noise permutation entropy time series long short-term memory |
