基于Sym小波和BP神经网络的基桩缺陷智能化识别

为提高基桩低应变动测信号的分析水平,采用一种新的时频域分析方法——小波分析。利用Sym小波对基桩速度响应时程曲线进行小波分解,对指定频带上的信号分量进行特征值提取,提取的特征值为反映各频带范围内体现能量分布的功率谱均值,提取的特征值可构成反映信号特征的特征向量,同时利用BP人工神经网络的非线性映射特性建立特征向量和基桩缺陷类别之间的一种对应关系。通过数值模拟的方法可以得到大量不同缺陷类型的基桩的桩顶速度响应时程曲线,对这些数值模拟信号进行小波分解得到的特征向量为神经网络的学习提供大量训练样本。最后,利用实测信号小波分解后得到的特征向量对训练过的神经网络进行检验,其识别结果表明,训练后的神经网络能根据实测信号的特征向量对基桩缺陷进行智能化的识别。

INTELLIGENT IDENTIFICATION OF PILE DEFECT BASED ON SYM WAVELET AND BP NEURAL NETWORK

To improve the accuracy of the analysis of pile low strain testing signal,the wavelet analysis method which is a new time-frequency analysis method is adopted.The time-history velocity response signal of pile can be decomposed by Sym wavelet.The power spectrum value can be extracted from some specified spectrum range.These values from one signal makes up the characteristic vector representing this signal.The relationship between characteristic vector of pile and pile defect type can be established by using BP artificial neural network.Abundant time-history velocity response signals of pile can be acquired by numerical simulation method.The characteristic vectors of these numerical simulation signals can be used to train the BP artificial neural network as the input patterns.In order to validate this new analysis method,some characteristic vectors which are extracted from field test signals is used.The in-situ test signals are in good agreement with pile defect type.The conclusion drawn from this study on the signal analysis of pile low strain testing has practical significances for the pile integrity evaluation.