小波分析和神经网络在超声波检测中的应用

疲劳断裂是港口起重机最常见,也是最危险的故障。超声波检测是一种重要的日常检测裂纹故障的方法。小波分析和人工神经网络的引入,让检测得到了从定性到定量的提高。运用小波分析从超声波检测装置提取的信号,得到的特征值可作为神经网络的输入参数,用于训练和识别。实践表明,通过这种智能诊断系统可以得到令人满意的定量的诊断结果。

Application of Wavelet Analysis and ANN in Ultrasonic Quantitative Testing

Fatigue and fracture is the most frequent and danger failure to the steel structure of harbor crane,ultrasonic testing is an important routine way to evaluate the crack defects.In order to enhance the qualitative evaluation to the quantitative evaluation,wavelet analysis and artificial neural networks(ANN) were applied.Eigenvalues were obtained by wavelet analysis signal derived from ultrasonic instrument,which can be used as the input matrix for the ANN for learning,training and diagnosing.Carrying out the combined diagnosing system into practical testing,the approving quantitative results gained.