小波降噪组合模型在基坑沉降预测中的应用

发布时间：2018-07-12 07:50

本文选题：基坑沉降监测 + 灰色系统模型　；参考：《安徽理工大学》2017年硕士论文

【摘要】：按照设计的要求以一定的时间周期对基坑沉降进行监测,根据对这些监测数据的处理及分析,准确预测基坑沉降的趋势,以便能够及时采取措施,防止灾害事故的发生,确保基坑及周边建筑物和人员的安全。本文利用小波降噪的方法,来处理基坑沉降监测数据并对观测数据的变化趋势进行预测研究。以某市一处招待所基坑沉降观测为例,选取有代表性的监测点用来分析研究。首先,根据实际观测数据利用灰色系统和时间序列预测模型分别计算,根据不同模型的预测结果,分析比较其各自的优缺点;其次,应用软阈值小波降噪的方法,对实例中原始监测数据进行预处理;最后,分别采用经典的灰色系统和时间序列模型、时间序列—灰色系统组合模型对小波降噪后得到的数据进行预测,对其预测的结果进行分析比较。对比结果表明,利用经典灰色系统模型预测得到的结果优于时间序列模型,利用时间序列—灰色系统组合模型预测得到的结果均优于经典的灰色系统和时间序列模型;小波降噪灰色系统模型预测得到的结果优于未经降噪时间序列—灰色系统组合模型,且优于小波降噪时间序列模型。最后发现小波降噪时间序列—灰色系统组合模型预测效果最优。该文研究内容对基坑工程施工设计及监测方案设计具有指导作用。
[Abstract]:According to the design requirements, the foundation pit settlement is monitored in a certain period of time. According to the processing and analysis of these monitoring data, the trend of foundation pit settlement can be accurately predicted, so that timely measures can be taken to prevent the occurrence of disasters and accidents. Ensure the safety of the foundation pit and surrounding buildings and personnel. In this paper, wavelet denoising method is used to deal with foundation pit settlement monitoring data and forecast the trend of observation data. Taking the settlement observation of foundation pit of a guesthouse in a city as an example, representative monitoring points are selected for analysis and research. Firstly, according to the actual observation data, the grey system and time series prediction model are used to calculate respectively, and the advantages and disadvantages of different models are analyzed and compared according to the prediction results of different models. Secondly, the soft threshold wavelet denoising method is applied. The pre-processing of the original monitoring data is carried out. Finally, the data obtained by wavelet denoising are predicted by using the classical grey system and time series model, and the combination model of time series and grey system respectively. The predicted results are analyzed and compared. The results show that the results obtained by using the classical grey system model are superior to those of the time series model, and the results obtained by using the combined time series-grey system model are superior to those of the classical grey system model and the time series model. The prediction result of wavelet denoising grey system model is better than that of unnoised time series grey system combined model and wavelet denoising time series model. Finally, it is found that the prediction effect of wavelet denoising time series-grey system combined model is optimal. The research contents of this paper can be used to guide the design of foundation pit construction and the design of monitoring scheme.
【学位授予单位】：安徽理工大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TU433

【相似文献】