小波分析在测斜监测中的应用

Wavelet Analysis for Inclination Monitoring

测斜方法广泛应用于岩质高边坡内部变形监测。但因测斜监测过程中的波动性误差,普通的分析手段难以从采集的大量数据中提取有用信息。通过对原有算法的分析,在其基础上,利用小波变换具有的在时频两域表征信号局部特征的性能,得到一个比较单一直接的评价整体位移变化的标准。结合某岩质高边坡测斜监测,将测斜所得到的数据重构为信号形式,再利用小波分析滤除高频噪声信号,处理结果实际上建立了一个监测时间和综合位移变化的关系,这个综合位移变化集中了整体位移变化的信息,反映了边坡位移变化趋势。由这样的处理方法所获数据易于理解,而且容错性强,具有推广价值。

Deformation monitoring of steep rock slopes by inclinometers in bore holes is widely used in engineering practice. Due to non-coaxial of adjacent guide pipes, however, there are significant noise signals in the data collected by the inclinometer. This makes it difficult for the traditional method to refine useful information from the data collected. To solve this problem, traditional method of simple accumulation of displacement along the pipe length is improved by introducing wavelet transform method by which a straightforward solution to the overall displacement of the monitored slope is obtained. Applicability of this method in data process of inclination monitoring is based upon the fact that wavelet transform reflects the features of signals in the domains of both time and frequency. Application of wavelet transform method for data process of a heavily instrumented rock slope consists of two steps in which the collected data are first reconstructed as a series of signals including serviceable signals and noise. Noisy signals of high frequency are screened out later through wavelet analyses. Serviceable signals of low frequency reserved after several cycles of screen of the high frequency signals are regarded as the trend signals that contain the practical information of overall displacements of the slope. In this way, displacement development of the rock slope was predicted. The results obtained are generally in good agreement with reality.