Concrete Dam Displacement Prediction and Engineering Application Based on Multiscale Autoregressive Model System

CHEN Liang-jie; WEI Bo-wen; YU Jun-hao; LUO Shao-yang; MAO Ying

doi:10.11988/ckyyb.20200811

PDF(2177 KB)

Journal of Changjiang River Scientific Research Institute ›› 2021, Vol. 38 ›› Issue (12) : 82-90. DOI: 10.11988/ckyyb.20200811

ENGINEERING SAFETY AND DISASTER PREVENTION

Concrete Dam Displacement Prediction and Engineering Application Based on Multiscale Autoregressive Model System

CHEN Liang-jie¹, WEI Bo-wen^1,2, YU Jun-hao¹, LUO Shao-yang¹, MAO Ying¹

Author information +

History +

Abstract

The accuracy of numerical model prediction for concrete dam displacement is severely affected by the time-frequency nonlinearity of the displacement monitoring data. In view of this, the wavelet technology is employed to analyze the effect of multiple cross environment driving in the prototype data, and then the nonlinear autoregressive model with exogenous input (NARX) and autoregressive integrated moving average model (ARIMA) are integrated to established an autoregressive model system under multiscale combination mechanism to overcome the difficulty of information mining for monitoring sequences with complex chaotic characteristics. Engineering examples manifest that the present model has better fitting accuracy and predictive ability, as well as noise resistance and robustness than traditional models. In addition, being optimized and extended, the model can also be applied to the prediction of other hydraulic structures.

Key words

concrete dam / displacement forecast / multiscale combination mechanism / autoregressive model system / NARX / ARIMA

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

CHEN Liang-jie, WEI Bo-wen, YU Jun-hao, LUO Shao-yang, MAO Ying. Concrete Dam Displacement Prediction and Engineering Application Based on Multiscale Autoregressive Model System[J]. Journal of Changjiang River Scientific Research Institute. 2021, 38(12): 82-90 https://doi.org/10.11988/ckyyb.20200811

References

[1] 吴中如, 顾冲时, 沈振中, 等. 大坝安全综合分析和评价的理论、方法及其应用[J]. 水利水电科技进展, 1998, 18(3): 3-5.
[2] 陈维江, 马震岳, 董毓新. 建立大坝安全监控数学模型的一种新方法[J]. 水利学报, 2002(8): 91-96.
[3] 顾冲时,苏怀智.混凝土坝工程长效服役与风险评定研究述评[J].水利水电科技进展, 2015,35(5):1-12.
[4] 周元春, 甘孝清, 李端有. 大坝安全监测数据粗差识别技术研究[J]. 长江科学院院报, 2011, 28(2): 16-20.
[5] 杨杰, 胡德秀, 吴中如. 大坝安全监控模型因子相关性及不确定性研究[J]. 水利学报, 2004(12): 99-105.
[6] 徐洪钟. 大坝动力系统的安全监控非线性分析模型研究[D]. 南京:河海大学, 2001.
[7] 李占超, 张慧莉, 刘兴阳, 等. 混凝土坝小样本安全监控模型研究[J]. 中国科学:技术科学, 2014, 44(10): 1043-1051.
[8] SU H Z, CHEN Z X, WEN Z P. Performance Improvement Method of Support Vector Machine-Based Model Monitoring Dam Safety[J]. Structural Control & Health Monitoring, 2016, 23(2): 252-266.
[9] 徐晖, 李钢. 基于MatLab的BP神经网络在大坝观测数据处理中的应用[J]. 武汉大学学报(工学版), 2005,38(3): 50-53.
[10] KANG F, LIU J, LI J J, et al. Concrete Dam Deformation Prediction Model for Health Monitoring Based on Extreme Learning Machine[J]. Structural Control & Health Monitoring, 2017, 24(10): 1-11.
[11] 齐长鑫, 汪树玉. 灰色系统模型在坝基位移预测中的应用[J]. 水利学报, 1996(9): 49-52,67.
[12] 苏怀智, 吴中如, 温志萍, 等. 遗传算法在大坝安全监控神经网络预报模型建立中的应用[J]. 水利学报, 2001(8): 44-48.
[13] WEI B W, CHEN L J, LI H K,et al. Optimized Prediction Model for Concrete Dam Displacement Based on Signal Residual Amendment[J]. Applied Mathematical Modelling, 2020, 78: 20-36.
[14] 杨文采, 施志群, 侯遵泽, 等. 离散小波变换与重力异常多重分解[J]. 地球物理学报, 2001(4): 534-541,582.
[15] 师洪涛, 杨静玲, 丁茂生, 等. 基于小波—BP神经网络的短期风电功率预测方法[J]. 电力系统自动化, 2011, 35(16): 44-48.
[16] 文鸿雁. 基于小波理论的变形分析模型研究[D]. 武汉:武汉大学, 2004.
[17] 张进平, 庄万康. 大坝安全监测的位移分布数学模型[J]. 水利学报, 1991(5): 28-35.
[18] 樊琨. 基于人工神经网络的大坝位移预测[J]. 长江科学院院报, 1998, 15(5): 3-5.
[19] 刘亚秋, 马广富, 石忠. NARX网络在自适应逆控制动态系统辨识中的应用[J]. 哈尔滨工业大学学报, 2005(2): 173-176.
[20] 赵晨. 动态神经网络在量化投资预测中的应用[D]. 上海:复旦大学, 2014.
[21] ZEMOURI R, GOURIVEAU R, ZERHOUNI N. Defining and Applying Prediction Performance Metrics on a Recurrent NARX Time Series Model[J]. Neurocomputing, 2010, 73(13/14/15): 2506-2521.
[22] CHATTERJEE S, NIGAM S, SINGH J B,et al. Software Fault Prediction Using Nonlinear Autoregressive with Exogenous Inputs (NARX) Network[J]. Applied Intelligence, 2012, 37(1): 121-129.
[23] 蔡磊, 马淑英, 蔡红涛, 等. 利用NARX神经网络由IMF与太阳风预测暴时SYM-H指数[J]. 中国科学(技术科学), 2010, 40(1): 77-84.
[24] 罗忠, 刘昊鹏, 朱云鹏, 等. 基于REFOR算法的多输出非线性系统动态参数化建模方法研究[J]. 机械工程学报, 2018, 54(23): 73-81.
[25] MOTAMAD H B, RUPP C, DAVID S K. Short-term Water Demand Forecasting Using Nonlinear Autoregressive Artificial Neural Networks[J]. Journal of Water Resources Planning and Management, 2020, 146(3), doi: 10.1061/(ASCE)WR.1943-5452.0001165.
[26] FEDERICO B,MARIA P,LUIGI P.A Randomized Two-stage Iterative Method for Switched Nonlinear Systems Identification[J]. Nonlinear Analysis: Hybrid Systems, 2020, 35: 100818.
[27] 向华琦. 基于时间序列分析法的大坝变形监测数据分析研究[D]. 杨凌:西北农林科技大学, 2012.
[28] WEI B W, YUAN D Y, LI H K,et al. Combination Forecast Model for Concrete Dam Displacement Considering Residual Correction[J]. Structural Health Monitoring, 2019, 18(1): 232-244.
[29] 王锋, 苏怀智, 荆凯. 基于ARIMA-ANN的大坝安全监控模型[J]. 武汉大学学报(工学版), 2010, 43(5): 585-588.
[30] 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.