大坝变形原始观测信号可视为真实信号与白噪声的叠加。为实现对大坝变形的有效预测,将小波去噪与云模型相结合,提出一种大坝变形时间序列分析的小波-云预测模型。首先利用小波多分辨分析特点,分解出大坝原始变形时间序列中的真实信号项及噪声项;其次,创建变形预测的云模型语言规则,利用最大隶属度原则,确定被预测变形所属的规则前件及相应的历史云,结合历史云与被预测变形所在的当前云生成预测云;最后,以对某实际大坝进行变形预测为例,比较了传统统计模型、云模型和小波-云模型的预测精度。结果表明:所提出的小波-云预测模型能够提供更准确的预测结果,能够为大坝的安全运行提供有效依据。
Abstract
The original observation signal of dam deformation can be regarded as the superposition of real signal and white noise. A wavelet-cloud prediction model for dam deformation time series analysis is proposed in the present paper by combining wavelet denoising and cloud model to effectively predict dam deformation. Firstly, the multi-resolution analysis of wavelet is used to decompose the original signal into the real signal item and the noise item in the original deformation time series of the dam. Secondly, the cloud model language rules for deformation prediction are created; the principle of maximum membership degree is used to determine the rule predecessor to which the predicted deformation belongs and the corresponding historical cloud which is further combined with the current cloud to generate predictive cloud. The prediction accuracy among traditional statistical model, cloud model, and the proposed wavelet-cloud model is compared with the deformation prediction of a dam as an example. Result demonstrates that the proposed wavelet-cloud prediction model provides more accurate prediction results, offering an effective basis for the safe operation of dam.
关键词
大坝变形预测 /
时间序列分析 /
小波分析 /
云模型 /
去噪
Key words
dam deformation prediction /
time series analysis /
wavelet analysis /
cloud model /
denoising
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 王 伟,徐 锴,方绪顺,等.基于改进粒子群算法的大坝监控加权统计模型[J].长江科学院院报,2017,34(8):41-46.
[2] SU Huai-zhi, WEN Zhi-ping, SUN Xiao-ran, et al. Time-varying Identification Model for Dam Behavior Considering Structural Eeinforcement[J]. Structural Safety, 2015, 57: 1-7.
[3] SU Huai-zhi, WU Zhong-ru, WEN Zhi-ping. Identification Model for Dam Behavior Based on Wavelet Network[J]. Computer-Aided Civil and Infrastructure Engineering, 2007, 22(6): 438-448.
[4] SU Huai-zhi, WEN Zhi-ping, CHEN Zhe-xin, et al. Dam Safety Prediction Model Considering Chaotic Characteristics in Prototype Monitoring Data Series[J]. Structural Health Monitoring, 2016, 15(6): 639-649.
[5] 李鹏鹏,苏怀智,郭芝韵,等.基于人工蜂群算法与Elman神经网络组合的大坝变形监控模型[J].水利水电技术,2017,48(3):104-108.
[6] 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.
[7] SU Huai-zhi, LI Xing, YANG Bei-bei, et al. Wavelet Support Vector Machine-based Prediction Model of Dam Deformation[J]. Mechanical Systems and Signal Processing, 2018, 110: 412-427.
[8] 汪 程,杨 光,祖安君,等.混凝土坝变形Wavelet-EGM-PE-ARIMA组合预测模型[J].长江科学院院报,2019,36(8):1-7.
[9] 蒋 嵘,李德毅,陈 晖.基于云模型的时间序列预测[J].解放军理工大学学报,2000,1(5):13-18.
[10]李德毅,刘常昱,刘 鹢.不确定性人工智能[J].软件学报,2004,15(11):1583-1594.
[11]邵年华.基于云理论的不确定性推理模型在径流预测中的应用[J].水利科技与经济,2018,24(9):62-66.
[12]康传利,陈 洋,张临炜,等.小波和混沌神经网络在大坝变形预测中的应用[J].人民黄河,2020(3):10-13.
[13]MALLAT S G. Zero-crossing of a Wavelet Transform[J]. IEEE Transactions on Information Theory, 1991, 37(4):1019-1033.
[14]杨贝贝.基于小波核函数和支持向量机的大坝变形预测[J].人民长江,2016,47(17):98-101.
[15]姜振翔,徐镇凯,魏博文,等.基于小波分解和支持向量机的大坝位移监控模型[J].长江科学院院报,2016,33(1):43-47.
[16]葛哲学,沙 威.小波分析理论与MATLAB R2007实现[M].北京:电子工业出版社,2007.
[17]付 斌,李道国,王慕快.云模型研究的回顾与展望[J].计算机应用研究,2011,28(2):420-426.
基金
国家自然科学基金项目(51979093);国家重点研发计划课题(2018YFC0407101,2017YFC0804607)
PDF(1303 KB)
